Quantum Backpropagation Neural Network Approach for Modeling of Phenol Adsorption from Aqueous Solution by Orange Peel Ash

Quantum Backpropagation Neural Network Approach for Modeling of Phenol Adsorption from Aqueous Solution by Orange Peel Ash

Siddhartha Bhattacharjee (Tata Consultancy Services, India), Siddhartha Bhattacharyya (RCC Institute of Information Technology, India) and Naba Kumar Mondal (The University of Burdwan, India)
DOI: 10.4018/978-1-4666-2518-1.ch025

Abstract

The chapter describes a multilayer quantum backpropagation neural network (QBPNN) architecture to predict the removal of phenol from aqueous solution by orange peel ash, guided by the application of three types of activation functions and characterized by backpropagation of errors. These activation functions are Sigmoid function, tanh function and tan1.5h function. First by a classical multilayer neural network architecture with three types of activation functions is discussed in this chapter. It takes 6000000 iterations to train the network with a learning rate of 0.01. Among these three types of activation functions tan1.5 function shows the best prediction result. Next, QBPNN is discussed in this chapter. It takes 22000 iterations to train the network with the same learning rate. Here also tan1.5h function shows the best result in prediction of removal of phenol. Thus QBPNN is much faster than the classical multilayer neural network architecture. Different graphs are also given for comparison between the experimental output and network output using different activation functions. This particular chapter basically deals with a model application by which experimental results can be comparing with the model output. Because of their reliable, robust, and salient characteristics in capturing the non-linear relationships existing between variables (multi-input/output) in complex systems, it has become apparent that numerous applications of ANNs/QBNN have been successfully conducted in various parts of environmental engineering. Fuzzy Logic is also used as alternate method to predict the removal of phenol from aqueous solution by orange peel ash, but QBPNN shows the best result.
Chapter Preview
Top

Removal Of Phenol By Varying Different Operational Factors

The different parameters which affect the adsorption of phenol from an aqueous solution are:

  • 1.

    pH,

  • 2.

    Initial Concentration,

  • 3.

    Adsorbent Dosage,

  • 4.

    Stirring Rate (rpm),

  • 5.

    Contact Time and,

  • 6.

    Temperature.

The effect of the variation of these parameters on the adsorption characteristics of phenol are discussed in the following subsections.

Effect of pH

The initial pH of adsorption medium is one of the most important parameters affecting the adsorption process. The adsorption of phenol by orange peel ash (OPA) was studied at various pH values (3.0, 5.0, and 7.0). The percentage removal of phenol by OPA was highest at pH 5.0. Then the percentage of removal was decreased with increasing pH of the medium. The pH primarily affects the degree of ionization of phenol and the surface properties of OPA. The pH primarily affects the degree of ionization of phenol and the surface properties of water hyacinth ash (Benat et al. 2000).

Key Terms in this Chapter

Single Layer Perceptron: This consists of a single neuron with multiple inputs and a single output. It has restricted information processing capability. The information processing is done through a transfer function which is either linear or non-linear.

Quantum Neural Network (QNN): A quantum neural network is a new field which integrates classical neurocomputing with quantum computation. It is argued that the study of quantum neural networks may give us both new understanding of brain function as well as unprecedented possibilities in creating new systems for information processing, including solving classically intractable problems.

Recurrent Neural Networks (RNN): RNN topology involves backward links from output to the input and hidden layers.

Multi Layer Perceptron (MLP): It has a layered architecture consisting of input, hidden and output layers. Each layer consists of a number of perceptrons.

Self-Organizing Maps (SOM): SOMs or Kohonen networks have a grid topology, with unequal grid weights. The topology of the grid provides a low dimensional visualization of the data distribution.

Artificial Neural Networks(ANNs): Artificial neural networks (ANNs) are non-linear mapping structures based on the function of the human brain. They are powerful tools for modeling, especially when the underlying data relationship is unknown.

Complete Chapter List

Search this Book:
Reset