Empirical models applications

When my interest returned and we began researching the analytical applications of CD in the 70 s, I felt I had a head start. But there was so much that was new. A great deal had happened to CD over the years as it matured and expanded to include the far-UV the study of optical activity in excited state emissions, and in vibrational and Raman spectroscopy and the evolution of new empirical models applicable to the interpretation of the structural properties of macromolecules. Most important of all, perhaps, was the arrival of high tech electronics and materials which had brought CD instrumentation out of the dark ages. And now, ironically, almost 35 years after my introduction to CD, my special interest is the exploitation of chiral transition metal complexes as chirality induction reagents in chemical analysis. 

Douglas C. Montgomery is Professor of Engineering andProfessor of Statistics at Arizona State University. His research interests are in response surface methodology, empirical modeling, applications of statistics in engineering, and the physical sciences. 

In this section, the conceptual framework of molecular orbital theory is developed. Applications are presented and problems are given and solved within qualitative and semi-empirical models of electronic structure. Ab Initio approaches to these same matters, whose solutions require the use of digital computers, are treated later in Section 6. Semi-empirical methods, most of which also require access to a computer, are treated in this section and in Appendix F. 

Transfer function models are linear in nature, but chemical processes are known to exhibit nonhnear behavior. One could use the same type of optimization objective as given in Eq. (8-26) to determine parameters in nonlinear first-principle models, such as Eq. (8-3) presented earlier. Also, nonhnear empirical models, such as neural network models, have recently been proposed for process applications. The key to the use of these nonlinear empirical models is naving high-quality process data, which allows the important nonhnearities to be identified. 

A key featui-e of MPC is that a dynamic model of the pi ocess is used to pi-edict futui e values of the contmlled outputs. Thei-e is considei--able flexibihty concei-ning the choice of the dynamic model. Fof example, a physical model based on fifst principles (e.g., mass and energy balances) or an empirical model coiild be selected. Also, the empirical model could be a linear model (e.g., transfer function, step response model, or state space model) or a nonhnear model (e.g., neural net model). However, most industrial applications of MPC have relied on linear empirical models, which may include simple nonlinear transformations of process variables. 

Implementation Issues A critical factor in the successful application of any model-based technique is the availability of a suitaole dynamic model. In typical MPC applications, an empirical model is identified from data acquired during extensive plant tests. The experiments generally consist of a series of bump tests in the manipulated variables. Typically, the manipulated variables are adjusted one at a time and the plant tests require a period of one to three weeks. The step or impulse response coefficients are then calculated using linear-regression techniques such as least-sqiiares methods. However, details concerning the procedures utihzed in the plant tests and subsequent model identification are considered to be proprietary information. The scaling and conditioning of plant data for use in model identification and control calculations can be key factors in the success of the apphcation. 

Various theoretical and empirical models have been derived expressing either charge density or charging current in terms of flow characteristics such as pipe diameter d (m) and flow velocity v (m/s). Liquid dielectric and physical properties appear in more complex models. The application of theoretical models is often limited by the nonavailability or inaccuracy of parameters needed to solve the equations. Empirical models are adequate in most cases. For turbulent flow of nonconductive liquid through a given pipe under conditions where the residence time is long compared with the relaxation time, it is found that the volumetric charge density Qy attains a steady-state value which is directly proportional to flow velocity... 

On the other side, many models of a different type are currently used in the biological sciences These can be envisaged as complicated (mathematical) extensions of commonsense ways to analyze results when these results are partially hidden behind noise, noise being inescapable when dealing with biological matters. This is the area currently occupied by most statisticians Using empirical models, universally applicable, whose basic purpose is to... 

The preceding set of characteristics and properties of the estimators makes our type of mapping procedures, /, particularly appealing for the kinds of systems that we are especially interested to study, i.e., manufacturing systems where considerable amounts of data records are available, with poorly understood behavior, and for which neither accurate first-principles quantitative models exist nor adequate functional form choices for empirical models can be made a priori. In other situations and application contexts that are substantially different from the above, while much can still be gained by adopting the same problem statements, solution formats and performance criteria, other mapping and search procedures (statistical, optimization theory) may be more efficient. 

In order to verify how close to a known true optimum the final solutions found by our learning methodology happen to be, we will describe here its application to a pulp digester, for which a perfect empirical model /(x) is assumed to be available. Other applications are discussed in Saraiva and Stephanopoulos (1992c). 

An extreme case of these empirical models are black box models, predominantly polynomials, the application of which is strictly restricted to the range of operating conditions and design variables for which the models were developed. Even in this range, optimization using black box models can lead to operating conditions far from the real optimum. This is due to non-linearities of the real systems, which cannot be modelled by polynomials. Black box... 

Mathematical models based on physical and chemical laws (e.g., mass and energy balances, thermodynamics, chemical reaction kinetics) are frequently employed in optimization applications (refer to the examples in Chapters 11 through 16). These models are conceptually attractive because a general model for any system size can be developed even before the system is constructed. A detailed exposition of fundamental mathematical models in chemical engineering is beyond our scope here, although we present numerous examples of physiochemical models throughout the book, especially in Chapters 11 to 16. Empirical models, on the other hand, are attractive when a physical model cannot be developed due to limited time or resources. Input-output data are necessary in order to fit unknown coefficients in either type of the model. 

The electrostatic precipitator in Example 2.2 is typical of industrial processes the operation of most process equipment is so complicated that application of fundamental physical laws may not produce a suitable model. For example, thermodynamic or chemical kinetics data may be required in such a model but may not be available. On the other hand, although the development of black box models may require less effort and the resulting models may be simpler in form, empirical models are usually only relevant for restricted ranges of operation and scale-up. Thus, a model such as ESP model 1 might need to be completely reformulated for a different size range of particulate matter or for a different type of coal. You might have to use a series of black box models to achieve suitable accuracy for different operating conditions. 

If there is so much difficulty in distinguishing electrostatic and chemical components of energy, one could raise the question, does it make any difference In particular, for application to surface chemical reactions occurring in geochemistry, would not an empirical model be as good as a mechanistic one To answer these questions one must consider the types of data to be interpreted and the purpose for which the model is to be used. 

The concept of the reaction-rate model should be considered to be more flexible than any mechanistically oriented view will allow. In particular, for any reacting system an entire spectrum of models is possible, each of which fits certain overlapping ranges of the experimental variables. This spectrum includes the purely empirical models, models accurately describing every detail of the reaction mechanism, and many models between these extremes. In most applications, we should proceed as far toward the theoretical extreme as is permitted by optimum use of our resources of time and money. For certain industrial applications, for example, the closer the model approaches... 

One important application of analysis of variance is in the fitting of empirical models to reaction-rate data (cf. Section VI). For the model below, the analysis of variance for data on the vapor-phase isomerization of normal to isopentane over a supported metal catalyst (Cl)... 

Most of the models in this book are empirical models that provide an approximate description of the true behavior of a system. However, the techniques presented for use with empirical models are applicable to many mechanistic models as well. 

Such applications of NN as a predictive method make the artificial neural networks another technique of data treatment, comparable to parametric empirical modeling by, for example, numerical regression methods [e.g., 10,11] briefly mentioned in section 16.1. The main advantage of NN is that the network needs not be programmed because it learns from sets of experimental data, which results in the possibility of representing even the most complex implicit functions, and also in better modeling without prescribing a functional form of the actual relationship. Another field of... 

With this in mind, I ask the reader to accept my humble definition of chemometrics the application of multivariate, empirical modeling methods to chemical data [2]. 

Second, the emphasis on empirical modeling leads to chemometrics being a highly interfacial discipline, in that specific tools are often developed with specihc applications already in mind. For example, specific chemometric tools have been developed to align retention time axes in chromatograms [20] and to preprocess diffuse reflectance data [21]. In contrast, other disciplines, such as statistics, are associated with well-defined stand-alone tools (ANOVA, f-test, etc.) that can be applied to a wide array of different applications. One consequence of this interfacial property of chemometrics is that one must often sift through a very large toolbox of application-specific tools in order to find one that suits a particular application. 

Chapter S examines various models used to describe solution and compmmd phases, including those based on random substitution, the sub-lattice model, stoichiometric and non-stoichiometric compounds and models applicable to ionic liquids and aqueous solutions. Tbermodynamic models are a central issue to CALPHAD, but it should be emphasised that their success depends on the input of suitable coefficients which are usually derived empirically. An important question is, therefore, how far it is possible to eliminate the empirical element of phase diagram calculations by substituting a treatment based on first principles, using only wave-mecbanics and atomic properties. This becomes especially important when there is an absence of experimental data, which is frequently the case for the metastable phases that have also to be considered within the framework of CALPHAD methods. 

Mechanistic models can describe pharmacological and physiological events in a more refined fashion and with greater utility than empirical models. Such models make more advanced and more realistic assumptions about drug distribution and effects. Mechanistic models may be used to find optimal sampling times during clinical trial design and to model clinical trial outcomes. The application... 

None of the semi-empirical models perform as well as Hartree-Fock models (except STO-3G), local density models, density functional models or MP2 models. PM3 provides the best overall description, although on the basis of mean absolute errors alone, all three models perform to an acceptable standard. Given the large difference in cost of application, semi-empirical models clearly have a role to play in structure determination. 

There are a variety of mathematical models used to describe the relationship between the precursors and the secondary pollutants they form upon reaction. In addition, there are some simple, often empirical, models that have been developed for application in particular areas. An example of these is also discussed in the following section. 

Hartmann. Infrared collision-induced absorption by N2 near 4.3 pm for atmospheric applications measurements and empirical modeling. Appl. Opt., 35 5911, 1996. 

---