Optimisation of metal microstructure using a Population Adaptive based Immune Algorithm (PAIA)

Abstract

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 possesses 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. S.Gaffour is with the

An Integrated System Approach for Solving Multi-Objective Scheduling Problems and Advanced Control of an Experimental Hot-Rolling Mill

“…Using the above framework, one should first specify the desired mechanical properties and the initial conditions of rolling, then by using the symbiotic modelling technique which combines Non-Linear Iterative Partial Adaptive Least Square (NIPALS) model, Linear Regression Model (LR), Neural Network Model with double loop procedures (NNDLP), Neural-Fuzzy model (NF) and metallurgical knowledge, a microstructure optimisation-based Population Adaptive Immune Algorithm (PAIA) search to find near optimal quantitative microstructural parameters that will yield the above properties. For more details on this symbiotic modelling technique and PAIA algorithm refer to (Gaffour et al 2010a) and (Gaffour et al 2010b). To define the optimisation problem of this stage (Module1), it is necessary to establish an optimality criterion.…”

“…In the first stage, the optimal rolling schedule is systematically calculated according to the desired final microstructure and properties. In this stage the design methodology is separated into a microstructure optimisation problem (module1) to obtain prescribed microstructural parameters such as final grain size and volume fraction recrystallised during deformation (Gaffour et al 2010a) and a rolling schedule optimisation problem (module2) to achieve the thermomechanical conditions required in the module1. The design approach requires four basic components for defining and setting-up the optimisation problem: 1. the stock model describing the microstructure evolution of the material during hot-rolling, 2. the optimal strategy based on symbiotic modelling approach for the prediction of the mechanical properties of alloy steel (Gaffour et al 2010b), 3. the physical constraints present both in the stock and in the mill including the limitations of the forming process and the hot workability of the stock and 4. the optimality criterion.…”

Interactive multiobjective optimization for the hot rolling process

“…In addition, to calculating the setup of the mill, they consider the closed-loop control of the mill as well. The paper Gaffour et al (2010) studies another type of optimization algorithms, related to genetic algorithms, for different microstructure objectives such as ferrite grain size and the volume fraction of pearlite. The models used in the two latter references consist of a combination of data-driven and physically-based models.…”