Modeling/simulation neural network models

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. 

Hypercubes and other new computer architectures (e.g., systems based on simulations of neural networks) represent exciting new tools for chemical engineers. A wide variety of applications central to the concerns of chemical engineers (e.g., fluid dynamics and heat flow) have already been converted to run on these architectures. The new computer designs promise to move the field of chemical engineering substantially away from its dependence on simplified models toward computer simulations and calculations that more closely represent the incredible complexity of the real world. 

The 2D model was built from a wide array of descriptors, including also E-state indices, by Simulations Plus [89], The model is based on the associative neural network ensembles [86, 87] constructed from n=9658 compounds selected from the BioByte StarList [10] of ion-corrected experimental logP values. The model produced MAE = 0.24, r = 0.96 (R. Fraczkiewicz, personal communication). 

Lopez-Rodriguez, M.L., Morcillo, M.J., Fernandez, E., Rosado, M.L., Pardo, L. and Schaper, K.-f. (2001) Synthesis and structure-activity relationships of a new model of arylpiperazines. 6. Study of the 5-HTiA/ai-adrenergic receptor affinity by classical Hansch analysis, artificial neural networks, and computational simulation of ligand recognition. Journal of Medicinal Chemistry, 44, 198-207. 

A neural-network-based simulator can overcome the above complications because the network does not rely on exact deterministic models (i.e., based on the physics and chemistry of the system) to describe a process. Rather, artificia] neural networks assimilate operating data from an industrial process and learn about the complex relationships existing within the process, even when the input-output information is noisy and imprecise. This ability makes the neural-network concept well suited for modeling complex refinery operations. For a detailed review and introductory material on artificial neural networks, we refer readers to Himmelblau (2008), Kay and Titterington (2000), Baughman and Liu (1995), and Bulsari (1995). We will consider in this section the modeling of the FCC process to illustrate the modeling of refinery operations via artificial neural networks. 

As can be seen from the tables, the ANN model consistently gives better predictions. Themainreasonis that the simulator required a lot of input information which had to be estimated while the neural network model required only four feed properties. 

Once a good fit between experimental and calculated data has been obtained, the model function given by the neural network may be tested and, if adequate, used for simulation and prediction purposes. 

Developed several decades ago, ANNs are being increasingly applied to the development and application of quantitative prediction models.43 15 ANNs simulate the parallel processing capabilities of the human brain, where a series of processing rmits (aptly called neurons ) are used to convert input variable responses into a concentration (or property) output. Neural networks cover a very wide range of techniques that are used for a wide range of applications. 

Control based on neural network. Similar to fuzzy logic modeling, neural network analysis uses a series of previous data to execute simulations of the process, with a high degree of success, without however using formal mathematical models (Chen and Rollins, 2000). To this goal, it is necessary to define inputs, outputs, and how many layers of neurons will be used, which depends on the number of variables and the available data. 

Greaves, M. A., Hybrid Modelling, Simulation and Optimisation of Batch Distillation Using Neural Network Techniques. Ph.D. Thesis, (University of Bradford, Bradford, UK, 2003). 

The four experiments done previously with Rnp (= 0.5, 1, 3, 4) were used to train the neural network and the experiment with / exp = 2 was used to validate the system. Dynamic models of process-model mismatches for three state variables (i.e. X) of the system are considered here. They are the instant distillate composition (xD), accumulated distillate composition (xa) and the amount of distillate (Ha). The inputs and outputs of the network are as in Figure 12.2. A multilayered feed forward network, which is trained with the back propagation method using a momentum term as well as an adaptive learning rate to speed up the rate of convergence, is used in this work. The error between the actual mismatch (obtained from simulation and experiments) and that predicted by the network is used as the error signal to train the network as described earlier. 

---