A solid-state recycling route for processing aluminium alloy 7075 chips is proposed. This process involves pulverizing the chips using an industrial scale comminution line to produce a broad particle size distribution of granulated products and powders. Upon sieving, the −140 mesh fraction of the pulverised material was consolidated by spark plasma sintering into fully dense compacts, i.e. >99%. The properties of the pulverised powders and compacts were compared to commercially available aluminium alloy 7075 powder used in industrial press-sinter applications. The comminution line produced powder particles which possessed a 7·9 ± 0·6-nm thick native oxide layer with adhering exogenous contaminants, and aluminium oxide particles dispersed throughout the powder. The presence of the oxide layer and exogenous contaminants was found to be deleterious to the powder consolidation and mechanical properties. A flexural strength and strain and hardness of 94·7 ± 7·2 MPa, 2·1 ± 0·3% and 69·3 ± 5·2 HV were obtained, respectively.

In this study, a comprehensive machine learning (ML) model was developed to predict and optimize boride coating thickness on steel surfaces based on boriding parameters such as temperature, time, boriding media, method, and alloy composition. In a dataset of 375 published experimental results, 19 features were applied as inputs to predict the boride layer thickness in various steel alloys. ML algorithms were evaluated using performance metrics like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R². Among the ML algorithms tested, XGBoost exhibited the highest accuracy. XGBoost achieved an R² of 0.9152, RMSE of 29.57, and MAE of 18.44. Incorporating feature selection and categorical variables enhanced model precision. Additionally, a deep neural network (DNN) architecture demonstrated robust predictive performance, achieving an R² of 0.93. Experimental validation was conducted using 316L stainless steel (SS), borided at 900 °C and 950 °C for 2 h and 4 h. The DNN model effectively predicted the boride thickness under these conditions, aligning closely with the observed values and confirming the models’ reliability. The findings underscore the potential of ML to optimize boriding processes, offering valuable insights into the relationships between boriding parameters and coating outcomes, thereby advancing surface modification technologies.