Genetic Algorithms with Neural Networks

In addition, the GUI also provides the possibility to visualize the component types hierarchy and the selection hierarchy defined so far (Fig. 6.5). 

The overall schema of the metasystem under development at ACA is given in Fig. 6.6. 

Integrating Genetic Algorithms with Neural Networks 

This strategy of integrating neural networks with genetic algorithms has been used to search for the optimal composition of a catalyst for the ammoxidation of propane [62]. In that case, no experiments were performed the network was trained with data published earlier by other authors [63]. However, those data were for only 26 catalysts, thus forming a quite small training set. Even more importantly, the predicted performance of the optimal catalyst, expressed by means of acrylonitrile yield, was not experimentally verified. 

The same integration strategy has also been used [64] to find the optimal Cu Zn Al ratio in mixed oxide catalysts for methanol synthesis from Syngas. 

---

Integrating Genetic Algorithms with Neural Networks I 165... 

The high degree of complexity of typical real problems implies that the final method used to solve a problem is more often a combination of several methods, such as soft computing techniques (namely, fuzzy logic, genetic algorithms, and neural networks) with more classic ones (such as algebraic, analytical, numerical, and stochastic methods). 

Westphal, H. and Bornholdt, S. (1997) Lithofacies Prediction from Wireline Logs with Genetic Algorithms and Neural Networks, Z. dt. geol. Ges. 147 465-474. 

Pigmented film coating formulations have recently been modeled and optimized to enhance opacity and reduce film cracking with neural networks combined with genetic algorithms [46, 47] as well as being studied with neurofuzzy [48]. In the latter study the rules discovered were consistent with known theory. 

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. 

Fig. 6.7 Comparison of the maximum of the neural network approximation of the ODHE ethylene yield obtained in 10 runs of the genetic algorithm with a population size 60, and the global maximum obtained with a sequential quadratic programming method run for 15 different starting points.

Fig. 4 Genetic algorithms integrated with neural network modeling in optimization system.

Thus, we have shown that the feature selection procedure which combines the genetic algorithm with fitness evaluation by a computational neural network is an effective way to... 

Concomitantly with the increase in hardware capabilities, better software techniques will have to be developed. It will pay us to continue to learn how nature tackles problems. Artificial neural networks are a far cry away from the capabilities of the human brain. There is a lot of room left from the information processing of the human brain in order to develop more powerful artificial neural networks. Nature has developed over millions of years efficient optimization methods for adapting to changes in the environment. The development of evolutionary and genetic algorithms will continue. 

Huang and Tang49 trained a neural network with data relating to several qualities of polymer yarn and ten process parameters. They then combined this ANN with a genetic algorithm to find parameter values that optimize quality. Because the relationships between processing conditions and polymer properties are poorly understood, this combination of AI techniques is a potentially productive way to proceed. 

Cartwright, Sztandera and Chu50 have also used the combination of a neural network with a GA to study polymers, using the neural network to infer relationships between the structure of a polymer and polymer properties and the genetic algorithm to predict new promising polymer structures whose properties can be predicted by the network. 

---