Nonlinear modelling is empirical or semi-empirical modelling which takes at least some nonlinearities into account.
There are many ways of doing that, including linear regression with nonlinear terms, polynomial regression, nonlinear regression, splines, etc. Some of the new techniques based on artificial neural networks and series of basis functions have advantages over the traditional methods.
Good nonlinear models will take into account quantitative or heuristic knowledge of the process and materials, or parts of physical models, or knowledge of some of the nonlinearities in the relations. Nonlinear Solutions Oy has good know-how, experience and tools for this purpose.
There is plenty of literature on neural networks, including several books. At least one book covers neural networks applications in chemical engineering. There is at least one series of conferences which focuses on engineering applications of neural networks. Some of the work of Nonlinear Solutions Oy (real world applications of nonlinear modelling) also appears in articles in magazines and conferences.