Computational Intelligence In Time Series Forecasting

Foresight can be crucial in process and production control, production-and-resources planning and in management decision making generally. Although forecasting the future from accumulated historical data has become a standard and reliable method in production and financial engineering, as well as in business and management, the use of time series analysis in the on-line milieu of most industrial plants has been more problematic because of the time and computational effort required.

The advent of intelligent computational technologies such as the neural network and the genetic algorithm promotes the efficient solution of on-line forecasting problems. Their most outstanding successes include:

• prediction of nonlinear time series and the nonlinear combination of forecasts using neural networks;
• prediction of chaotic time series and of output data for second-order nonlinear plant using fuzzy logic.

The power of intelligent technologies applied individually and in combination, has created advanced forecasting methodologies, exemplified in Computational Intellingence in Time Series Forecasting by particular systems and processes. The authors give a comprehensive exposition of the improvements on offer in quality, model building and predictive control, and the selection of appropriate tools from the plethora available using such examples as:

• forecasting of electrical load and of output data for nonlinear plant with neuro-fuzzy networks;
• temperature prediction and correction in pyrometer reading, tool-wear monitoring and materials property prediction using hybrid intelligent technologies;
• evolutionary training of neuro-fuzzynetworks by the use of genetic algorithms and prediction of chaotic time series;
• isolated use of neural networks and fuzzy logic in the nonlinear combination of traditional forecasts of temperature series obtained from a pilot-scale chemical reactor with temporarily disconnected controller.

Application-oriented engineers in process control, manufacturing, the production industries and research centres will find much to interest them in Computational Intelligence in Time Series Forecasting and the book is suitable for industrial training purposes. It will also serve as valuable reference material for experimental researchers.