Artificial neural networks worked example

Intended Use The intended use of the model sets the sophistication required. Relational models are adequate for control within narrow bands of setpoints. Physical models are reqiiired for fault detection and design. Even when relational models are used, they are frequently developed bv repeated simulations using physical models. Further, artificial neural-network models used in analysis of plant performance including gross error detection are in their infancy. Readers are referred to the work of Himmelblau for these developments. [For example, see Terry and Himmelblau (1993) cited in the reference list.] Process simulators are in wide use and readily available to engineers. Consequently, the emphasis of this section is to develop a pre-liminaiy physical model representing the unit. 

Artificial neural networks are now widely used in science. Not only are they able to learn by inspection of data rather than having to be told what to do, but they can construct a suitable relationship between input data and the target responses without any need for a theoretical model with which to work. For example, they are able to assess absorption spectra without knowing about the underlying line shape of a spectral feature, unlike many conventional methods. 

There has been a notable change in the way that the GA has been used as it has become more popular in science. Some of the earliest applications of the GA in chemistry (for example, the work of Hugh Cartwright and Robert Long, and Andrew Tuson and Hugh Cartwright on chemical flowshops) used the GA as the sole optimization tool many more recent applications combine the GA with a second technique, such as an artificial neural network. 

These various chemometrics methods are used in those works, according to the aim of the studies. Generally speaking, the chemometrics methods can be divided into two types unsupervised and supervised methods(Mariey et al., 2001). The objective of unsupervised methods is to extrapolate the odor fingerprinting data without a prior knowledge about the bacteria studied. Principal component analysis (PCA) and Hierarchical cluster analysis (HCA) are major examples of unsupervised methods. Supervised methods, on the other hand, require prior knowledge of the sample identity. With a set of well-characterized samples, a model can be trained so that it can predict the identity of unknown samples. Discriminant analysis (DA) and artificial neural network (ANN) analysis are major examples of supervised methods. 

A separate class of experimental evaluation methods uses biological mechanisms. An artificial neural net (ANN) copies the process in the brain, especially its layered structure and its network of synapses. On a very basic level such a network can learn rules, for example, the relations between activity and component ratio or process parameters. An evolutionary strategy has been proposed by Miro-datos et al. [97] (see also Chapter 10 for related work). They combined a genetic algorithm with a knowledge-based system and added descriptors such as the catalyst pore size, the atomic or crystal ionic radius and electronegativity. This strategy enabled a reduction of the number of materials necessary for a study. 

---