Search

A new design methodology for an efficient implementation of Adaptive Fuzzy Predictive Control (AFPC) using a Radial Basis Function (RBF) based neural-fuzzy model and Particle Swarm Optimisation (PSO) for an experimental hot-rolling mill is proposed in this paper. A predictive model of the process based on RBF is studied. On-line adaptive neural network identification was used to adapt the model parameters. A modified PSO is used at the optimisation process in Nonlinear Model Predictive Control (NMPC) to calculate a sequence of future control actions. The performance of AFPC along with PSO was evaluated via a computing simulation platform under different operating conditions. The simulation results demonstrate the effectiveness of the proposed control scheme Robust nonlinear predictive controller design using Partial Swarm Optimisation (PSO): a case study in speed control of an experimental hot-rolling mill (PDF Download Available). Available from: http://www.researchgate.net/publication/263844370_Robust_nonlinear_predictive_controller_design_using_Partial_Swarm_Optimisation_(PSO)_a_case_study_in_speed_control_of_an_experimental_hot-rolling_mill [accessed Sep 22, 2015].

The research in this paper aims at linking the steel crack propagation process to the prediction of released flat fracture energy. In this work, an adaptive fuzzy modelling approach and a neural network model with double loop training process were developed in order to build the model for the prediction of flat fracture energy which is normally released during the compact tension (CT) test of X100 pipeline steel. Using the proposed modelling technique, a rule-based fuzzy prediction model as well as a Back-Propagation (BP) neural network model were constructed and optimized automatically from the experimental data. These two models related the load, crack mouth opening displacement (CMOD), and crack length to the released flat fracture energy. The relationship between the fracture propagation and the flat fracture energy was investigated in this paper in detail. The results showed that it is able to predict the flat fracture energy using the proposed modelling approach, and the resulting model can be a useful part of a more comprehensive modelling structure in the future.

This paper introduces a new data granulation algorithm using significance weights on the input space of the data set. This data granulation algorithm aims to provide a more reliable way of grouping data together by directing the data granulation to favor the most significant variables of the process under investigation. Such a data granulation algorithm assists in the elicitation of the initial rule-base of a fuzzy or neural-fuzzy model. A hybrid correlation index, called Significance Index, is introduced to rank the process variables based on the linear correlation coefficient and the partial correlation measure. The new algorithm is used to classify the process variables and subsequently model and predict mechanical properties of heat treated steel. The property under investigation is the Tensile Strength and the case study data set consists of chemical composition and microstructure measurements coupled with Tensile Strength measurements.

A new optimal design method and a systematic scheduling approach for a laboratory-scale Hot-Rolling Mill are presented. The proposed design is based upon 1. metallurgical principles, which sufficiently consider the behaviour of workpiece material and the mechanics of the manufacturing process and 2. a modified version for multi-objective optimization of a Population Adaptive based Immune Algorithm (PAIA), physically-based models and symbiotic modelling approach to carry-out an optimal search for the best microstructural parameters. This methodology processes adequate capabilities for finding effective and best microstructural parameters such as the ferrite grain size and the volume fraction of pearlite that satisfy the requirements for mechanical properties. Hence, the overarching aim of this research work is to integrate knowledge about both the stock and the rolling process to find optimal hot-deformation profiles that will be used as information in order to compute the most suitable rolling schedule and systemise the optimal route for processing and achieve a ‘right-first-time’ production of the desired properties.