ANNs based models

ANNs have been used to develop behavioral models to enable efficient system-level simulation of integrated microfluidic devices. Magargle et al. [8] reported a feedforward ANN-based model for an injector device that is used in... 

Under-fitting and over-fitting were discussed in some detail in Section 5.4. There, it was explained that over-fitting is much more likely to occur than under-fitting. The same can be argued for ANN-based models, although one should keep in mind that they are very much prone to over-fitting. In effect, the intrinsic behaviour of the ANNs leads them to predict the (limited number of) calibrators as closely as possible. Therefore, if any unexpected phenomenon appears in the unknown samples we want to predict (e.g. a spectral artefact or a new component), it may well happen that the net does not predict these samples properly. This is in fact also a problem with any classical (univariate) calibration, but it is exacerbated when ANNs are used." ... 

An ANN-based model of available capacity in a LAB for EV applications was developed by Chan et al. in 2000 with an ANN toolbox available in MATLAB [4], They compared their model with Peukert s equation (Equation 9.8), which describes the nonlinear relationship between the available capacity and discharge current... 

Three years later, a novel approach was developed by Yanqing using an adaptive ANN-based model and a neurocontroller for online cell SOC determination [10]. A radial basis function (RBE) NN has been adopted to simulate the battery. It is a typical two-layer feedforward NN that allows for fast training and is capable of converging to a global optimum. Its hidden layer comes with a nonlinear RBF activation function given by... 

Several various compositions were used for training and testing the ANN-based models of SOFC. 

H2 + CO SOFC is often fed by a mixture of different eompounds resulting from the processes of steam reforming of methane. Apart from diluents, the influences of other fuels at anode side on the quality of the ANN-based model were tested. 

Parameters previously tested do have their own numerical representation, but there are SOFC features that either cannot to be expressed in numerical form or can only be expressed with great difficulty, i.e. electrolyte material, anode material, cathode material, cell type (planar, tubular), etc. In those situations a hybrid model can be applied which consists of the ANN model and additional mathematical expressions (hybrid model means a combination of known relationships and an ANN-based model). For instance, there are two options for accommodating the material type of electrolyte in an ANN-based model ... 

A summary of the networks used is presented in Table 5.3. From use of ANN based models, both standard and hybrid, and based on investigations made, the following general conclusions can be drawn ... 

Table C.l The values of the weights for the ANN based model of SOFC...

Recently, a new approach called artificial neural networks (ANNs) is assisting engineers and scientists in their assessment of fuzzy information, Polymer scientists often face a situation where the rules governing the particular system are unknown or difficult to use. It also frequently becomes an arduous task to develop functional forms/empirical equations to describe a phenomena. Most of these complexities can be overcome with an ANN approach because of its ability to build an internal model based solely on the exposure in a training environment. Fault tolerance of ANNs has been found to be very advantageous in physical property predictions of polymers. This chapter presents a few such cases where the authors have successfully implemented an ANN-based approach for purpose of empirical modeling. These are not exhaustive by any means. 

The purpose of this case study was to develop a simple neural network based model with the ability to predict the solvent activity in different polymer systems. The solvent activities were predicted by an ANN as a function of the binary type and the polymer volume frac-... 

Any colony optimization (ACO) and swarm intelligence are forms of agent-based modeling inspired by colonies of social animals such as ants and bees [32]. ACO has become popular in engineering for optimal routing in water distribution systems [33, 34]. Particle swarm optimization has been successfully used to train ANNs, for instance, ANNs to predict river water levels [35], for parameter estimation, for example, in hydrology [36]. 

Since the dynamics of a batch reactor is characterized by a unitary relative order, the GMC law can be adopted [6, 14, 22, 40, 42, 65], In order to cope with model uncertainties, adaptive GMC approaches have been developed [56, 60, 62] in [27] some unknown quantities—namely, the effect of the heat released by the reaction and the heat transfer coefficient—are estimated by adopting the nonlinear adaptive observer proposed in [24] in [63], an ANN-based GMC approach is presented for semi-batch processes with relative order higher than one. 

The application of ANN for a representation of reaction kinetics can be a very promising method to solve modelling problems. Besides intrinsic kinetics also internal diffusion resistances can be included into the neural network based model. This approach significantly reduces the time required for experimental studies. Despite that neural networks do not help to understand and develop a real reaction mechanism, they make the prediction of the reactor behaviour possible. This approach can be essential in the case of complex or uncertain kinetics - e.g. for polymerization reactions. In this study the neural network approach has been tested for a batch reactor. A trained network can be successfully implemented into any type reactor model. 

The artificial neural network (ANN) based prediction model utilized in the present study is the multilayer perceptrons (MLPs). It is adopted as the benchmark to compare with the time-varying statistical models since it has been shown that the MLP architecture could approximate... 

The ANN-based dynamic modulus models using the same input variables were found to exhibit significantly better overall prediction accuracy, better local accuracy at high and low temperature extremes, less prediction bias and better balance between temperature and mixture influences than do their regression-based counterparts (Ceylan et al. 2009). 

No single paradigm of the various ML-based modelling methods, such as ANNs, SVR and GP, is capable of consistent out-performance in every modelling task. It is therefore at most important to utilize and compare the performance of all the ML methods for a particular modelling task to arrive at the best possible model. Within a class of methods such as ANNs, there exist multiple architectures (e g. MLP and RBF networks) for performing nonlinear function approximation and supervised classification tasks. Accordingly, all such alternatives within a class of ML methods also need to be tested. 

ANN based creep constitutive model for marine sediment clay in coastal zone... 

Chen Changfu, Liu Hui, Xiao Yan. ANN based creep constitutive model for marine sediment clay. Journal of Engineering Geology, 2008, 16(4) 507-511 (In Chinese). 

---