Optimising the manufacturing of a ß-Ti alloy produced via direct energy deposition using small dataset machine learning.

Successful additive manufacturing involves the optimisation of numerous process parameters that significantly influence product quality and manufacturing success. One commonly used criteria based on a collection of parameters is the global energy distribution (GED). This parameter encapsulates the energy input onto the surface of a build, and is a function of the laser power, laser scanning speed and laser spot size. This study uses machine learning to develop a model for predicting manufacturing layer height and grain size based on GED constituent process parameters. For both layer height and grain size, an artificial neural network (ANN) reduced error over the data set compared with multi linear regression. Layer height predictions using ANN achieved an R2 of 0.97 and a root mean square error (RMSE) of 0.03 mm, while grain size predictions resulted in an R2 of 0.85 and an RMSE of 9.68 µm. Grain refinement was observed when reducing laser power and increasing laser scanning speed. This observation was successfully replicated in another α + ß Ti alloy. The findings and developed models show why reproducibility is difficult when solely considering GED, as each of the constituent parameters influence these individual responses to varying magnitudes.

A complementary approach of response surface methodology and an artificial neural network for the optimization and prediction of low salinity reverse osmosis performance.

The treatment of saline water sources by reverse osmosis (RO) is being utilized increasingly to address water shortages around the world. The application of RO is energy-intensive; therefore, plant and process optimization are crucial. The desalination of low salinity water sources with total dissolved solids (TDS) of <5000 mg/L is less energy intensive than the desalination of highly saline seawater and brackish water. A gap exists in optimization studies on lower salinity water (TDS = 500-5000 mg/L). The novelty of the study is the development of a complementary approach using response surface methodology (RSM) and an artificial neural network (ANN) for performance modelling, optimization, and prediction of RO desalination of low salinity water. Feed water salinity, pressure, and temperature were controlled variables to model the performance of the RO system. A performance index incorporating salt rejection efficiency and permeate flux was used as the response target of the system. The optimal parameter combination within their modelled range for the best performance index occurred near the highest pressure input of 150.57 psi, at the temperature of 38.8 °C, and at the lowest feed salt concentration of 577 mg/L. Both the RSM and ANN models demonstrated high validity. The RSM and ANN showed R2 values of 0.99 each and with a root mean square error of 2.41 and 5.85 respectively. The RSM showed a small benefit in model accuracy over the ANN, but the ANN has the benefit of not requiring the central composite design before experimentation and being a continuously improving prediction method as more data becomes available. Further applications of the optimization and modelling approach can be applied to RO system optimization considering membrane types and additional feedwater characteristics.