Modeling and Machine Learning of Vibration Amplitude and Surface Roughness after Waterjet Cutting.

This study focused on analyzing vibrations during waterjet cutting with variable technological parameters (speed, vfi; and pressure, pi), using a three-axis accelerometer from SEQUOIA for three different materials: aluminum alloy, titanium alloy, and steel. Difficult-to-machine materials often require specialized tools and machinery for machining; however, waterjet cutting offers an alternative. Vibrations during this process can affect the quality of cutting edges and surfaces. Surface roughness was measured by contact methods after waterjet cutting. A machine learning (ML) model was developed using the obtained maximum acceleration values and surface roughness parameters (Ra, Rz, and RSm). In this study, five different models were adopted. Due to the characteristics of the data, five regression methods were selected: Random Forest Regressor, Linear Regression, Gradient Boosting Regressor, LGBM Regressor, and XGBRF Regressor. The maximum vibration amplitude reached the lowest acceleration value for aluminum alloy (not exceeding 5 m/s2), indicating its susceptibility to cutting while maintaining a high surface quality. However, significantly higher acceleration amplitudes (up to 60 m/s2) were registered for steel and titanium alloy in all process zones. The predicted roughness parameters were determined from the developed models using second-degree regression equations. The prediction of vibration parameters and surface quality estimators after waterjet cutting can be a useful tool that for allows for the selection of the optimal abrasive waterjet machining (AWJM) technological parameters.

Analysis of Vibration, Deflection Angle and Surface Roughness in Water-Jet Cutting of AZ91D Magnesium Alloy and Simulation of Selected Surface Roughness Parameters Using ANN.

The use of magnesium alloys in various industries and commerce is increasing due to their properties such as high strength and casting properties, high vibration damping capability, good shielding of electromagnetic radiation and high machinability. Conventional machining methods can, however, pose a risk of ignition. AWJM is a safe alternative to conventional machining, but the deflection and vibration of the water jet can affect surface quality. Therefore, the aim of this study was to investigate the effects of selected AWJM parameters on the surface quality and vibration of machined magnesium alloys. Jet deflection angle, surface roughness parameters and vibration during AWJM were investigated. The findings showed that higher skewness occurred at a lower abrasive flow rate, while higher average values of the Sku roughness parameter were obtained at ma = 8 g/s in the range of 60-140 mm/min. It was also observed that higher vibration values occurred at ma = 8 g/s. The input parameters for creating an artificial neural network (ANN) model used in this study were the cutting speed vf and the mass flow rate ma. The results of this study provided valuable insights into ways of ensuring a safe and efficient machining environment for magnesium alloys. The use of ANN modeling for predicting the vibration and surface roughness of AZ91D magnesium alloy after water-jet cutting could be an effective tool for optimizing AWJM parameters.

Experimental Study and Artificial Neural Network Simulation of Cutting Forces and Delamination Analysis in GFRP Drilling.

This paper reports the results of measurements of cutting forces and delamination in drilling of Glass-Fiber-Reinforced Polymer (GFRP) composites. Four different types of GFRP composites were tested, made by a different manufacturing method and had a different fiber type, weight fraction (wf) ratio, number of layers, but the same stacking sequence. GFRP samples were made using two technologies: a novel method based on the use of a specially designed pressing device and hand lay-up and vacuum bag technology process. The study was conducted with variable technological parameters: cutting speed vc and feed per tooth fz. The two-edge carbide diamond-coated drill produced by Seco Company was used in the experiments. Cutting-force components and delamination factor were measured in the experiments, and photos of the holes were taken to determine the delamination. In addition, modeling of cause-and-effect relationships between the technological drilling parameters vc and fz was simulated with the use of artificial neural network modeling. For all tested GFRP materials, an increase in fz led to an increase in the amplitude of cutting-force component Fz. The lowest values of the amplitude of cutting-force component Fz were obtained with the lowest tested feed per tooth value of 0.04 mm/tooth for all tested materials. It was observed that materials produced with the use of the specially designed pressing device were characterized by lower values of the cutting-force component Fz. It was also found that the delamination factor increased with an increase in fz for all tested GFRP materials. A comparison of the lowest and the highest values of fz revealed that the lowest delamination factor increase was archived by the B1 material and amounted to about 12.5%. The error margin of the obtained numerical modeling results does not exceed 15%, so it can be concluded that artificial neural networks are a suitable tool for modeling cutting force amplitudes as a function of vc and fz. The study has shown that the use of the special pressing device during the manufacturing of composite materials has a positive effect on delamination.