A machine learning approach was used to perform a regression analysis of Evans’s shielded metal arc (SMA) weld metal (WM) database involving several groups of Fe-C-Mn high-strength steels. The objective of this investigation was to develop an expression for austenite-to-ferrite (Ar3) transformation temperature that also included the effects of principal and minor alloy elements (in wt-%) and weld cooling rate (in °C/s) and relate this expression with WM ultimate tensile strength (UTS). The Ar3 data from 257 records obtained from several selected sources were combined with Ar3 projections at extreme end points in Evans’s WM database. Subsequently, a cluster analysis was performed. The data in Evans’s database was filtered with the carbon equivalent number limited to 0.3 maximum, carbon content limited to 0.1 wt-% maximum, nitrogen content limited to 99 ppm (0.0099 wt-%) maximum, preassigned Ar3 values limited to 680°C minimum, and WM UTS limited to 710 MPa maximum. The results provided a good approximation to the expression for Ar3 transformation temperature in terms of elemental compositions and cooling rate. This allowed the Ar3 to correlate with WM UTS of Fe-C-Mn in at least four ways depending on the sign of correlation of the data clusters. The elemental combinations in the cluster with the highest negative correlation revealed highly predictable WM UTS. In particular, the new Ar3 expression helped to predict decreases observed in certain Ar3 experimental data on WMs with balanced Ti, B, Al, N, and O additions reported among 13 records with additional dilatometry results. This correlation between the new expression for the Ar3 temperature and UTS of Fe-C-Mn WM is expected to complement the Japan Welding Engineering Society artificial neural network model currently available to predict Charpy V-notch test temperature for 28 J absorbed energy based on WM chemical composition. It will thereby provide a pair of effective tools for efficient development and/or evaluation of high-performance welding electrodes based on an Fe-C-Mn system for demand-critical applications.

High-strength steel (HSS) welding electrode specifications offer two sets of Tables for compliance, one on Specified Electrode Chemical Composition Requirements and the other on Specified Minimum Weld Mechanical Properties Requirements. These sets of Tables may appear mutually exclusive but underlying metallurgical principles keep them inter-dependent. Suppressing austenite transformation-start (TS) temperature simultaneously increases both strength and low-temperature impact toughness of HSS weld metal (WM). Specifically, a two-step approach is useful in understanding the metallurgy of high-performance electrodes and WMs. This approach includes calculated TS temperatures such as Ar3, BS or MS, besides carbon content, carbon equivalent number (CEN) and balanced Ti (and/or Zr), B, Al, N, O additions that correlate identified WM chemical composition with desired high-performance microstructures to meet or exceed minimum WM tensile and Charpy V-notch (CVN) impact toughness property requirements. The first step uses a set of constitutive (statistical/regression) equations to control the amounts of principal alloy elements such as C, Mn, Cr, Ni, Mo, and Cu so the relevant calculated TS temperatures such as Ar3, BS, or MS and CEN stay in a desirable range relative to the base metals being joined. While doing so, one also needs to ascertain that the common progression of calculated TS temperatures wherein Ar3 > BS > MS remains valid. The second step requires balanced Ti (and/or Zr), B, Al, N, O additions to further lower the actual TS temperature compared to the calculated TS temperature. Both a lower TS temperature and a narrow start-to-finish (TS–TF) temperature range ensure exceptional CVN impact toughness. The balanced Ti (and/or Zr), B, Al, N, O content can be ascertained using an artificial neural network (ANN) model offered by the Japan Welding Engineering Society (JWES) at its website. The JWES ANN model allows one to manipulate 16 elements of the WM compositions, each within a specified range and seek a lower predictive temperature range for achieving 28 J absorbed energy (T28J/°C) during CVN impact testing.