This study investigates the complex relationships between process parameters and material properties in FDM-based 3D-printed biocomposites using explainable AI techniques. We examine the effects of key parameters, including biochar content (BC), layer thickness (LT), raster angle (RA), infill pattern (IP), and infill density (ID), on the tensile, flexural, and impact strengths of FDM-printed pure PLA and biochar-reinforced PLA composites. Mechanical testing was used to measure the ultimate tensile strength (UTS), flexural strength (FS), and impact strength (IS) of the 3D-printed samples. The extreme gradient boosting (XGB) algorithm was used to build a predictive model based on the data collected from mechanical testing. Shapley Additive Explanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), and Partial Dependence Plot (PDP) techniques were implemented to understand the effects of the interactions of key parameters on mechanical properties such as UTS, FS, and IS. Prediction by XGB was accurate for UTS, FS, and IS, with R-squared values of 0.96, 0.95, and 0.85, respectively. The explanation showed that infill density has the most significant influence on UTS and FS, with SHAP values of +2.75 and +5.8, respectively. BC has the most significant influence on IS, with a SHAP value of +2.69. PDP reveals that using 0.3 mm LT and 30° RA enhances mechanical properties. This study contributes to the field of the application of artificial intelligence in additive manufacturing. A novel approach is presented in which machine learning and XAI techniques such as SHAP, LIME, and PDP are combined and used not only for optimization but also to provide valuable insights about the interaction of the process parameters with mechanical properties.

Introduction. One of the most significant phenomena in every industrial sector is friction and wear, which inevitably occurs when there is relative motion between similar or dissimilar materials. A substantial portion of global energy production is estimated to be expended in overcoming friction and wear, making them critical factors in energy efficiency and sustainability. Recently, advances in materials science, lubrication technologies, and innovative design approaches have facilitated a significant reduction in friction and wear, leading to considerable energy savings and extended component lifespan. Polytetrafluoroethylene (PTFE), among other materials, has revolutionized the tribological field, emerging as a highly effective synthetic polymer. This is attributed to its exceptional properties, including a low coefficient of friction, chemical inertness, thermal stability, non-stick characteristics, and biocompatibility. These unique properties make PTFE an ideal material for various industrial applications, spanning from aerospace to biomedical sectors. The purpose of work. This study aims to conduct a comprehensive numerical and experimental investigation into the tribological properties of PTFE-based composites. The materials selected for investigation include pure PTFE, PTFE with 25% carbon (C) filler, and PTFE with 20% glass filler. Testing was performed using stainless steel (SS 304) as the counterbody. Tribological testing and subsequent evaluation were conducted under dry sliding friction conditions, considering key parameters such as load, sliding speed, and temperature. Response surface methodology (RSM) was employed to develop an empirical model, utilizing experimental data to predict the wear resistance of these materials. Empirical models were developed to understand the influence of process parameters on wear behavior and to optimize operating conditions for minimizing material loss. Method of investigation. Archard's wear model was used as the theoretical framework for predicting volume loss and specific wear rate based on numerical simulations. The wear coefficient (K) was determined through experimental testing and used as an input parameter in the numerical models. Numerical simulations were developed using the finite element analysis (FEA) software ANSYS, enabling the simulation of complex tribological interactions between the composite materials and the counterbody. A central composite rotatable design (CCRD) within the framework of RSM was used to structure the experiments. The experiments were conducted under dry sliding friction conditions using pin on disc tribometer. The input parameters for the experiments were load (ranging from 15 N to 200 N), sliding speed (ranging from 400 rpm to 1000 rpm), and temperature (ranging from 60 °C to 200 °C). Each experiment was conducted for a sliding distance of 5 km to ensure sufficient wear for analysis. A total of 20 experiments were performed for each material, providing a comprehensive dataset for statistical analysis and model validation. Result and discussion. The results of the study highlight the effectiveness of numerical simulation in predicting the wear resistance of PTFE-based composites under dry sliding friction conditions. Experimental investigations reveal that pure PTFE exhibits low mechanical strength, leading to a high wear rate, whereas PTFE with carbon and glass fillers demonstrates improved wear resistance characteristics. The addition of carbon to PTFE enhances the composite's performance by forming a stable transfer film on the counterbody, while the addition of glass promotes increased hardness and, consequently, reduced material loss. Empirical models developed using response surface methodology (RSM) confirm that the applied load on the pin is the most significant parameter affecting wear, followed by sliding speed and temperature. Numerical simulations based on Archard's wear model exhibit good agreement with experimental data, validating the accuracy of the numerical simulations. This research contributes to a deeper understanding of the application of PTFE-based composites in extending the service life and enhancing the reliability of industrial products.

The present study demonstrates the roller burnishing process of aluminum alloy 6061-T6 by using a combination of aluminum oxide and vegetable oil as a lubricant. Machining parameters were explored, varying speed (v) (range 100–300 rpm), feed (f) (range 0.1–0.3 mm), and number of passes (nop) (range 1 to 3). However, performance was measured in terms of surface roughness, microhardness, and roundness. According to the results obtained from experiments, it was found that lubrication had a significant impact on performance in terms of surface roughness, mmicrohardness and roundness. Under lubricated conditions, surface roughness ranged from 0.012 µm to 1.7 µm. However, an increase in mimicrohardnessrom 92 HV to 96 HV and an improvement in roundness from 0.07 mm up to 0.05 mm were observed. Additionally, the findings indicated that high speeds with low feed rates yielded the best results: for instance, at a feed of 0.1 mm/rev, speed (v) of 300 rpm, and number of passes of three, a surface roughness of about 0.8 µm, microhardness of approximately 94 HV, and roundness of about 0.02 mm were recorded when applying lubrication. This study demonstrates how minimal lubrication techniques can be used to improve the roller burnishing process, thereby achieving better mechanical properties and surface finishes while extending the lifespan of the burnishing tool. The study has brought about a conclusion that optimizing v and f during burnishing while including relevant lubricant helps manufacturers to realize significant product quality improvements and enhance production efficiency.

The speed control security system is best suited for the task of slowing the speed of a vehicle during rash driving as the Driver is over speeding the circuit captures the images of the lanes witch decides the speed of the road the car is currently on this input is further provided to the ESP-32 micro Prosser module in the car switch compiles this data with the data received for the RPM sensor of the car and decides whether the car is over speeding or not in case of over speeding a signal is send by the ESP to the Arduino witch actuates the dc motor used in the car to reduce the speed of the car by the use of a hydraulic brake system actuated by a DC motor.