The optimization of mechanical properties in acrylonitrile butadiene styrene-like (ABS-like) photopolymer utilizing neural network techniques presents a promising methodology for enhancing the performance and strength of components fabricated through stereolithography (SLA) 3D printing. This approach uses machine learning algorithms to analyze and predict the relationships between various printing parameters and the resulting mechanical properties, thereby allowing the engineering of better materials specifically designed for targeted applications. Artificial neural networks (ANNs) can model complex, nonlinear relationships between process parameters and material properties better than traditional methods. This research constructed four ANN models to predict critical mechanical properties, such as tensile strength, yield strength, shore D hardness, and surface roughness, based on SLA 3D printer parameters. The parameters used were orientation, lifting speed, lifting distance, and exposure time. The constructed models showed good predictive capabilities, with correlation coefficients of 0.98798 for tensile strength, 0.9879 for yield strength, 0.9823 for Shore D hardness, and 0.98689 for surface roughness. These high correlation values revealed the effectiveness of ANNs in capturing the intricate dependencies within the SLA process. Also, multi-objective optimization was conducted using these models to find the SLA printer’s optimum parameter combination to achieve optimal mechanical properties. The optimization results showed that the best combination is Edge orientation, lifting speed of 90.6962 mm/min, lifting distance of 4.8483 mm, and exposure time of 4.8152 s, resulting in a tensile strength of 40.4479 MPa, yield strength of 32.2998 MPa, Shore D hardness of 66.4146, and Ra roughness of 0.8994. This study highlights the scientific novelty of applying ANN to SLA 3D printing, offering a robust framework for enhancing mechanical strength and dimensional accuracy, thus marking a significant benefit of using ANN tools rather than traditional methods.

The technology of additive manufacturing (AM) has transformed the fields of machinery, aerospace, and electronics. Adopting cost-effective, precise, and rapid procedures in AM is one of the major concerns of today’s industry. Stereolithography is a promising AM technique that is thought to meet these requirements. However, the fact that materials printed with stereolithography do not have good mechanical properties limits their application, such as in biomedicine and aerospace. Previous studies have shown the shortcomings of stereolithography printers. This research focuses on enhancing the mechanical characteristics of the polymer resin used in stereolithography (SLA)-like liquid crystal display (LCD) 3D printers by fabricating a new AM composite material with carbon fibers. For this reason, chopped carbon fibers (0.1 mm size) at amounts of 0.25 wt% and 0.5 wt% have been used with Acrylonitrile butadiene styrene (ABS)-like photopolymer transparent resin during the printing process, and three different print layer thicknesses were tested. For the design of the experiment (DoE), Q-DAS software was used to analyze the resulting data. A tensile-testing machine was utilized to determine the ultimate strength using the ASTM D638 standard. The results show an increase in the ultimate strength by adding carbon fiber to some extent, but after a certain percentage of carbon fiber added, the strength drops off.

Materials and parameters for conventional arc welding with the welding torch in vertical (PA) position are well known and investigated. However, apart from the ideal PA-position, not much is known about a deposition in so called ‘forced’ positions. This is becoming increasingly important in the case of particularly large components, as these can efficiently neither be clamped nor moved on a rotating and tilting table. More flexibility is achieved when the welding gun is moved as a tool on curvilinear paths to build up complex parts without necessary part movement. This link to the component surface means to leave the ideal vertical position. To make that possible, optimal parameters must be found for each angular position to enable high-quality and reliable build-up welding. In this work, a fuzzy logic-based system is designed based on set of experiments in single and double-layer weld beads structure using mild steel wire to predict the bead widths and heights for three different positions (Horizontal, Rising, and Falling torch movement). A comparison between the fuzzy and experimental values is studied. The averages of width mean error between experimental and fuzzy logic model values for the three positions were (1.3%) and (0.85%) for the single and double-layer weld beads, respectively. Averages of width mean error for the bead heights were (0.97%) and (0.73%) for the two structures. The current proposed study demonstrates a good agreement between the predicted fuzzy values and the experimental outcomes for the bead width and height.

This study aims to detect the impact of preexfoliation corrosion on the efficiency of 2mm thick 2024-T3 aluminum alloy friction stir spot welded (FSSW) joints. Five specimens of FSSW joints, welded with 620rmin⁻¹ rotational speed and a dwell time of 10seconds, were immersed in an exfoliation corrosion solution for five different times: 10h, 20h, 30h, 40h, and 50h. The tensile shear load for the noncorroded joint was 3.5kN. The results showed that the degradation of mechanical properties increased with increasing exposure time, and the joint efficiency drop reached 62 for specimens exposed for 50h to the corroded solution. As welded FSSW 2024-T3 AA joints exhibited a nugget debonding failure mode and a mixed-mode tensile-shear fracture, in the corroded specimens, only a shear fracture could be seen. The results were attributed to a reduction in the bonding area between the upper and lower sheets due to corrosion.

Additive manufacturing is driving a significant change in industry, extending beyond prototyping to the inclusion of printed parts in final designs. Stereolithography (SLA) is a polymerization technique valued for producing highly detailed parts with smooth surface finishes. This study presents a hybrid intelligent framework for modeling and optimizing the SLA 3D printer process’s parameters for Acrylonitrile Butadiene Styrene (ABS) photopolymer parts. The nonlinear relationships between the process’s parameters (Orientation, Lifting Speed, Lifting Distance, Exposure Time) and multiple performance characteristics (ultimate tensile strength, yield strength, modulus of elasticity, Shore D hardness, and surface roughness), which represent complex relationships, were investigated. A Taguchi design of the experiment with an L18 orthogonal array was employed as an efficient experimental design. A novel hybrid fuzzy logic–Particle Swarm Optimization (PSO) algorithm, ARGOS (Adaptive Rule Generation with Optimized Structure), was developed to automatically generate high-accuracy Mamdani-type fuzzy inference systems (FISs) from experimental data. The algorithm starts by customizing Modified Learn From Example (MLFE) to create an initial FIS. Subsequently, the generated FIS is tuned using PSO to develop and enhance predictive accuracy. The ARGOS models provided excellent performances, achieving correlation coefficients (R²) exceeding 0.9999 for all five output responses. Once the FISs were tuned, a multi-objective optimization was carried out based on the weighted sum method. This step helped to identify a well-balanced set of parameters that optimizes the key qualities of the printed parts, ensuring that the results are not just mathematically ideal, but also genuinely helpful for real-world manufacturing. The results showed that the proposed hybrid approach is a robust and highly accurate method for the modeling and multi-objective optimization of the SLA 3D process.

In this work, an attempt has been made to improve the sand casting process by reducing the percentage of casting defects. The enhancement of the sand casting process is based on producing green sand castings with good pattern profiles and no failures at any complex ‎points during the separation process, handling and transportation. This work ‎introduces modified, non-destructive, direct tests for measuring sand mould ‎properties using sensor readings. ‎A new flowability sensor has been used to measure the time-dependent density, ‎distance-dependent mould hardness, and distance-dependent mould strength. The ‎sensor is able to detect sand motion at the desired points during the mould-making process. The live characterisation of the green sand mould is used to determine the optimum ‎parameters for the compaction process, reduction of the moulding time, and spent ‎energy, so that the cost of the moulding and casting process will be reduced.‎ It has been found that there is a linear relationship between the properties of the green sand samples and the sensor signals. The new method facilitates the measurement of sand properties and determines the most effective moulding parameters based on the flowability sensor readings. The resultant increases in both compactibility and compaction pressure improve mould hardness and mould strength.