The purpose of this work was to develop a steel tempering model that is useful to the commercial heat treater. Most of the tempering models reported address isothermal conditions which are not typical of most heating methods used to perform the tempering heat treatment. In this work, a non-isothermal tempering model was developed based on the tempering response of four steel alloys. This tempering model employs the quantity resulting from the numerical integration of the time-temperature profiles of both the heating and cooling portions of the tempering cycle. The model provided a very good agreement between experimental and predicted hardness when secondary hardening did not occur. The developed tempering model was then used as the basis for a process simulation model of a large indirect gas-fired furnace. Unlike the small-scale laboratory experiments performed in the development stage of this work, the temperature variation in this furnace was significant. Recording the temperature with time at 29 locations within the furnace allowed for suitable characterization of the temperature variation. The thermal data was used as inputs in a finite element method model and the time – temperature profiles of three production heavy truck side rails were then simulated. The tempering model provided a good prediction of the tempered hardness compared to experimental measurements. Finally, conclusions are drawn and suggestions are made for future work. / Ph. D.

The hardness of steel is an important quality parameter for several industrial applications. Conventional mechanical testing is used in quality testing for material hardness and the method is time-consuming, can cause material mix-ups, and results in material waste. To address this issue, a possible on-line method for non-destructive testing (NDT) techniques such as laser ultrasonic (LUS) measurements has been explored to replace mechanical testing. In this thesis, machine learning models are trained to predict steel hardness using LUS measurements and data from the production process. LUS data is collected from steel samples with a measured hardness using the Brinell protocol. Measured hardness values between 250 and 700 Brinell are used as the target values for the models. The production process data includes the chemical composition and tempering temperature. The models used in this thesis are Extreme Gradient Boosting (XGBoost), Multilayered Perceptron (MLP), and Convolutional Neural Network (CNN). The first two mentioned models use feature-engineered data from LUS measurements. These features include the time-of-flight for ultrasonic waves. CNN uses the raw LUS data as a univariate time series as input. Each of the models is trained solely on data from LUS measurements and both LUS and production process data to determine the effect of adding production process data. The models are optimized and tuned based on their loss on a validation set. The models are evaluated against each other based on their root mean squared error (RMSE) on a test set to determine the best performing model. The best performing model is an XGBoost model using LUS and production process data. The results indicate that models using solely LUS data can not replace or partially replace mechanical testing. The best performing model using only LUS data has a RMSE of 69.9 Brinell, which is above the required performance of a RMSE below 50 Brinell. The results also indicate a large boost in performance if including data from the production process. However, implementing this solution in the industry without losing accuracy in measurements is a hard task. While the models are not ready for direct implementation in industry, the results demonstrate potential for further research in this area.