Dynamic system neural networks

Ghiassi, M., Skinner, J. and Zimbra, D. (2013) Twitter brand sentiment analysis A hybrid system using n-gram analysis and dynamic artificial neural network Expert Syst Appl, 40, 6266-6282. DOI 10.1016/j.eswa.2013.05.057. 

Model based control schemes such as model predictive control are highly related to the accuracy of the process model. A regional-knowledge index is proposed in this study and applied in the analysis of dynamic artificial neural network models in process control. To tackle the extrapolation problem and assure stability of the control system, we propose to run a neural adaptive controller in parallel with a model predictive control. A coordinator weights the outputs of these two controllers to make the final control decision. The proposed analysis method and the modified model predictive control architecture have been applied to a neutralization process and excellent control performance is observed in this highly nonlinear system. 

Jemei et al. (2005) reported a Dynamic Recurrent Neural Network (DRNN) model of a PEMFC for a 500 W fuel cell. The proposed black box model can easily be extrapolated to more powerful fuel cell systems. For black-box models, simulation results are strongly dependant on the choice of input parameters. Thus, a sensitivity analysis is performed to assess the influences or relative importance of each input parameter on the output variable. Many different ways to perform sensitivity analysis are possible. A Multi Parameter Sensitivity Analysis (MPSA) is proposed to evaluate the relative importance of each input parameter independently on the fuel cell voltage. 

The local dynamics of tire systems considered tluis far has been eitlier steady or oscillatory. However, we may consider reaction-diffusion media where tire local reaction rates give rise to chaotic temporal behaviour of tire sort discussed earlier. Diffusional coupling of such local chaotic elements can lead to new types of spatio-temporal periodic and chaotic states. It is possible to find phase-synchronized states in such systems where tire amplitude varies chaotically from site to site in tire medium whilst a suitably defined phase is synclironized tliroughout tire medium 51. Such phase synclironization may play a role in layered neural networks and perceptive processes in mammals. Somewhat suriDrisingly, even when tire local dynamics is chaotic, tire system may support spiral waves... 

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. 

Narendra, K. S., and Parthasarathy, K., Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks 1, (1990). 

Robert Hecht-Nielsen, the inventor of one of the first commercial neurocomputers, defined [17] a neural network as a computing system made up of a number of simple, highly interconnected processing elements, which process information by its dynamic state response to external inputs. ... 

Kosko B 1992 Neural Networks and Fuzzy Systems A Dynamical Systems Approach to Machine Intelligence. Prentice-Hall, A Simon Schuster Company, Englewood Cliffs, New Jersey. 

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. 

This behavior reminds us of chaotic itinerancy found in dynamical systems with many degrees of freedom [18,19,21,38]. Chaotic itinerancy is the behavior where orbits repetitively approach and leave invariant structures of the phase space. Such behavior has been found in coupled maps [19], turbulence [18], neural networks [38], and Hamilton systems [21]. The mechanism of chaotic itinerancy is not yet fully understood. The study of NHIMs and how their stable and unstable manifolds intersect could offer some clues in revealing its mechanism [20]. 

State feedback control is commonly used in control systems, due to its simple structure and powerful functions. Data-driven methods such as neural networks are useful only for situations with fully measured state variables. For this system in which state variables are not measurable and measurement function is nonlinear, we are dependant on system model for state estimation. On the other hand, as shown in figure 2, in open-loop situations, system has limit cycle behavior and measurements do not give any information of system dynamics. Therefore, we use model-based approach. 

Johansen, T.A. and Foss, B.A. (1995). Semi-empirical modeling of non-linear dynamic systems through identification of operating regimes and locals models. In Neural Network Engineering in Control Systems, K Hunt, G Irwin and K Warwick, Eds., pp. 105-126, Springer-Verlag. 

Edwards R. (2001). Chaos in neural and gene networks with hard switching. Differential Equations and Dynamical Systems. 9, pp 187-220. 

Another approach has been developed for the prediction chemical shifts in H-NMR spectroscopy. In this case, special proton descriptors were applied to characterize the chemical environment of protons. It can be shown that 3D proton descriptors in combination with geometric descriptors can successfully be used for the fast and accurate prediction of H-NMR chemical shifts of organic compounds. The results indicate that a neural network can make predictions of at least the same quality as those of commercial packages, especially with rigid structures where 3D effects are strong. The performance of the method is remarkable considering a relatively small data set that is required for training. A particularly useful feature of the neural network approach is that the system can be easily dynamically trained for specific types of compounds. 

---