In material science studies, it is often desired to know in advance the fracture toughness of a material which is related to the released energy during its compact tension (CT ) test to prevent catastrophic failure. In this paper, two frameworks are proposed for automatic model elicitation from experimental data to predict the fracture energy released during the CT test of X100 pipeline steel. The is integrated in the model validation stage. This can help isolate the error distribution pattern and to establish the correlations with the predictions from the deterministic models. This is the first time a data-driven approach has been used in this fashion on an application that has conventionally been handled using finite element methods or physical models.

A new optimal strategy based on symbiotic modelling is proposed. The system combines Linear Regression Model (LR), Non-Linear Iterative Partial Adaptive Least Square Model (NIPALS), Neural Network Model with double loop procedures (NNDLP), Adaptive Numeric Modelling (Neural-Fuzzy modeling NF) and metallurgical knowledge in order to provide effective modelling solutions and achieve an optimal prediction performance. As a final step a fusion procedure is used to perform a routine decision making based on aggregation algorithm and clustering method that allow to systematically select the final best prediction outcome from a set of competing solutions. The proposed methodology is then applied to the challenging environment of a multi-dimensional, non-linear and sparse data space consisting of mechanical properties of 'Mild' Steel in particular Tensile Strength (TS) and Yield Strength (YS) in hot-rolling industrial processes. Using a data set containing critical information on the mechanical properties obtained from a hot strip mill, it is concluded that the developed new systematic modelling approach is capable of providing better prediction than each individual model even in data distribution areas which are reckoned to be sparse.

Highlights •We model mechanical properties of heat treated alloy steel using interpretable fuzzy models.• We demonstrate how to locate the 'best' processing parameters and chemical compositions.• We demonstrate how to achieve certain mechanical properties.• We demonstrated a holistic systems approach to achieve 'right-first-time' production.• We unravel the power of multi-objective optimisation and interpretable fuzzy modelling. AbstractThe primary objective of this paper is to introduce a new holistic approach to the design of alloy steels based on a biologically inspired multi-objective immune optimisation algorithm. To this aim, a modified population adaptive based immune algorithm (PAIA2) and a multi-stage optimisation procedure are introduced, which facilitate a systematic and integrated fuzzy knowledge extraction process. The extracted (interpretable) fuzzy models are able to fully describe the mechanical properties of the investigated alloy steels. With such knowledge in hand, locating the 'best' processing parameters and the corresponding chemical compositions to achieve certain pre-defined mechanical properties of steels is possible. The research has also enabled to unravel the power of multi-objective optimisation (MOP) for automating and simplifying the design of the heat treated alloy steels and hence to achieve

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

No abstract