Soft computing (SC) is an association of computing methodologies that includes as its principal members fuzzy logic, neurocomputing, evolutionary computing and probabilistic computing. We present a collection of methods and tools that can be used to perform diagnostics, estimation, and control. These tools are a great match for real-world applications that are characterized by imprecise, uncertain data and incomplete domain knowledge. We outline the advantages of applying SC techniques and in particular the synergy derived from the use of hybrid SC systems. We illustrate some combinations of hybrid SC systems, such as fuzzy logic controllers (FLC's) tuned by neural networks (NN's) and evolutionary computing (EC), NN's tuned by EC or FLC's, and EC controlled by FLC's. We discuss three successful real-world examples of SC applications to industrial equipment diagnostics, freight train control, and residential property valuation.

This paper describes the fundamental framework of an intelligent grinding process advisory system, which has been developed to help process engineers design new grinding processes. The system incorporates both highly complex, nonlinear analytical grinding process models and knowledge-based linguistic rules, and generates unified fuzzy rules by a novel automatic rule generation procedure. Optimal design of the parameters is performed via fuzzy logic inference. Several design principles for constructing the system are discussed as well as the over-all architecture of the system. The implementation of the system shows that the system can lead to the optimal design of a grinding process very effectively even with a large number of process parameters.

No abstract

No abstract