Explore the vast range of titles available.

Monitoring tool conditions and sub-assemblies before final integration is essential to reducing processing failures and improving production quality for manufacturing setups. This research study proposes a real-time deep learning-based framework for identifying faulty components due to malfunctioning at different manufacturing stages in the aerospace industry. It uses a convolutional neural network (CNN) to recognize and classify intermediate abnormal states in a single manufacturing process. The manufacturing process for aircraft factory products comprises different phases; analyzing the components after the integration is labor-intensive and time-consuming, which often puts the company’s stake at high risk. To overcome these challenges, the proposed AI-based system can perform inspection and defect detection and alleviate the probability of components’ needing to be re-manufacturing after being assembled. In addition, it analyses the impact value, i.e., rework delays and costs, of manufacturing processes using a statistical process control tool on real-time data for various manufactured components. Defects are detected and classified using the CNN and teachable machine in the single manufacturing process during the initial stage prior to assembling the components. The results show the significance of the proposed approach in improving operational cost management and reducing rework-induced delays. Ground tests are conducted to calculate the impact value followed by the air tests of the final assembled aircraft. The statistical results indicate a 52.88% and 34.32% reduction in time delays and total cost, respectively.

This paper advances the forward extrusion process by integrating sustainable methodologies and optimizing energy efficiency. This research investigates the impact of die geometry and elongation coefficients on energy usage and process efficiency, employing finite element method (FEM) simulations alongside empirical analysis. Artificial neural networks and experimental data were utilized to predict process energy. The experimental study utilized flat, conical, and arc-shaped dies to extrude lead profiles exhibiting different elongation coefficients. The study analyzed the dynamics of material flow, energy requirements, and maximum forces. Patterns of deformation, distribution of tension, and losses of energy were discerned, with finite element models enhancing understanding of these phenomena. The mathematical framework forecasting the peak extrusion force in relation to elongation parameters was substantiated via residual diagnostics and regression analysis. The findings indicate that conical and arc dies can conserve up to 15% of the energy in comparison to flat dies, thereby improving material flow and reducing deformation forces. This comprehensive strategy provides practical solutions to reduce energy consumption and improve metal forming processes, thereby enhancing industrial efficiency and sustainability. The results not only benefit industry but also align with environmental objectives, thereby increasing the efficiency and sustainability of extrusion operations.

The persistent issues in the Tertiary Education Trust Fund (TETFund) sponsored projects highlight a critical need for innovative approaches to improve project management and execution. This research aims to evaluate the effect of lean construction on the performance of TETFund sponsored construction projects in Nigeria. The research population and sample frame consisted of construction professionals and administrative personnel in the department of works who serves as consultants on TETFund projects in the institutions selected, and in the TETFund Unit at the various institutions). The sample size was 116, obtained using census sampling technique. Regression analysis and Analysis of Variance (ANOVA) were employed for the analysis. The study found that Lean Construction (LC) practices did not significantly impact TETFund project performance, likely due to institutional barriers such as bureaucratic delays and rigid structures. Recommendations include addressing these institutional challenges to enhance Lean practices’ effectiveness. The study is significant because it will enhance the outcomes of projects, particularly government sponsored projects.

In this research, the parameters to be optimized are the machining parameters in drilling of the woven Basalt fiber‐reinforced epoxy composites. It focuses on the modeling and optimization of the spindle speed and feed rate of different laminate thicknesses with torque and delamination factor as some of the important output responses. Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) will be used to analyze and model the effects and interaction of the control parameters on the drilling performance. In order to better predict the ANN model, the Artificial Bee Colony (ABC) algorithm is used in the training process. Also, RSM optimization technique is applied based on the desirability to prove the best combination of control parameters in the investigated range. The paper includes an elaborate discourse of the impact of process variables on the results of drilling performance. The best machining conditions identified were a feed rate of 0.1 mm/rev, a spindle speed of 1200 rpm to be used on a 2.7 mm thick laminate. RSM as well as ANN–ABC based predictive models were found to be in great agreement with the experimental results that can be used in sustainable application. This study optimizes drilling of woven basalt fiber–epoxy laminates using RSM and ANN–ABC models. Spindle speed, feed rate, and laminate thickness were analyzed for torque and delamination, identifying optimal conditions (1200 rpm, 0.1 mm/rev) for sustainable machining performance.

The importance of mine planning is often underestimated. Nonetheless, it is essential in achieving high performance by identifying the potential value of mineral resources and providing an optimal, practical, and realistic strategy for extraction, which considers the greatest quantity of options, materials, and scenarios. Conventional mine planning is based on a mostly deterministic approach, ignoring part of the uncertainty presented in the input data, such as the mineralogical composition of the feed. This work develops a methodology to optimize the mineral recovery of the heap leaching phase by addressing the mineralogical variation of the feed, by alternating the mode of operation depending on the type of ore in the feed. The operational changes considered in the analysis include the leaching of oxide ores by adding only sulfuric acid (H2SO4) as reagent and adding chloride in the case of sulfide ores (secondary sulfides). The incorporation of uncertainty allows the creation of models that maximize the productivity, while confronting the geological uncertainty, as the extraction program progresses. The model seeks to increase the expected recovery from leaching, considering a set of equiprobable geological scenarios. The modeling and simulation of this productive phase is developed through a discrete event simulation (DES) framework. The results of the simulation indicate the potential to address the dynamics of feed variation through the implementation of alternating modes of operation.

Prosopis julifera is a non-edible feedstock found in the arid and semi-arid regions was used for the production of biodiesel. Solvent extraction technique was used for oil extraction from Prosopis julifera .The present work mainly concentrates on the three step process of biodiesel production from Prosopis julifera oil .The acid value of Prosopis julifera oil was reduced below 1% using acid catalyst 1% v/v H2SO4 followed by esterification process using alkaline catalyst (KOH).Transesterification reaction is found to be affected by the reaction variables namely methanol to oil molar ratio, amount of catalyst used, reaction time and reaction temperature. Gas chromatography was used to analyse the Fatty acid methyl esters. The methyl ester obtained from the previous step was refined to produce biodiesel. The fuel properties of Prosopis julifera methyl ester (PJME) such as viscosity, cetane number, flash point, acid value, etc were determined and compared according to the ASTM standards. The optimum reaction conditions of Methanol/oil molar ratio of 9:1v/v, reaction temperature of 550C, reaction time of 2 hrs and 0.75% w/v of KOH usage were determined. Response surface Methodology (RSM) technique was used to optimize the maximum yield of Prosopis julifera methyl ester.

This study aims to obtain raw materials with optimal characteristics for hydroxyapatite synthesis from bovine tibia bones by optimizing temperature and time in the bone extraction process using thermal decomposition. Bovine tibia bones were prepared into powder and extracted using a furnace at different temperatures and time factors. Using a factorial design, the extraction process was optimized at temperatures ranging from 600 to 1100°C and 2-6 hours of heating times. Responses to this optimization process included powder density, extraction yield, carbon (C) content, oxygen (O) content, calcium (Ca) content, and phosphorus (P) content in the extracted powder. The optimal temperature and time for the extraction process yielded the following response values: powder density of 0.926g/cm3, extraction yield of 64.9132%, C content of 3.772%, O content of 33.7829%, Ca content of 16.2654%, and P content of 5.8544%. Lack of fit results indicated non-significant values in testing for extraction yield, C content, O content, Ca content, and P content, suggesting insignificant differences between experimental data and predictions from the proposed model. The extraction process at 1100°C for 6 hours resulted in raw material with optimum characteristics for hydroxyapatite synthesis, enabling the production of high-quality biomaterials for bone tissue engineering.

Additive manufacturing (AM) or 3D printing is growing rapidly in the manufacturing industry and has gained a lot of attention from various fields owing to its ability to fabricate parts with complex features. The reliability of the 3D printed parts has been the focus of the researchers to realize AM as an end-part production tool. Machine learning (ML) has been applied in various aspects of AM to improve the whole design and manufacturing workflow especially in the era of industry 4.0. In this review article, various types of ML techniques are first introduced. It is then followed by the discussion on their use in various aspects of AM such as design for 3D printing, material tuning, process optimization, in situ monitoring, cloud service, and cybersecurity. Potential applications in the biomedical, tissue engineering and building and construction will be highlighted. The challenges faced by ML in AM such as computational cost, standards for qualification and data acquisition techniques will also be discussed. In the authors’ perspective, in situ monitoring of AM processes will significantly benefit from the object detection ability of ML. As a large data set is crucial for ML, data sharing of AM would enable faster adoption of ML in AM. Standards for the shared data are needed to facilitate easy sharing of data. The use of ML in AM will become more mature and widely adopted as better data acquisition techniques and more powerful computer chips for ML are developed.

Injection molding is a widely used manufacturing technology for the mass production of plastic parts. Despite the importance of process optimization for achieving high quality at a low cost, process conditions have often been heuristically sought by field engineers. Here, we propose two systematic data-driven optimization frameworks for the injection molding process based on a multi-objective Bayesian optimization (MBO) framework and a constrained generative inverse design network (CGIDN) framework. MBO, an extension of Bayesian optimization, uses Gaussian process regression adopting a multidimensional acquisition function based on the concepts of hypervolume and Pareto front. The CGIDN, which is an improved version of the original generative inverse design network (GIDN), uses backpropagation to calculate the analytical gradients of the objective function with respect to design variables. Both methods can be used for multi-objective optimization with trade-off relationships, for example, between the cycle time and deflection after extraction. We demonstrate the applicability of the optimization methods utilizing simulation data from Moldflow software for the manufacturing process of a door trim part. We showed that the optimal process parameters which simultaneously minimized deflection and cycle time were obtained with a relatively small dataset. We expect that in a realistic manufacturing facility, the optimal conditions found from simulations can guide the process design of the injection molding machine, or the proposed methods can be directly utilized because they do not require a very large dataset. We also note that the proposed optimization schemes are readily applicable to the optimization of other types of plastic manufacturing processes.

The tight sandstone gas reservoirs of the Xujiahe Formation are critical targets for tight gas exploration and development in the Sichuan Basin. While Class I reservoirs have been successfully developed using staged volume fracturing technology, efforts are being increasingly directed toward Class II and III matrix-type blocks. These reservoirs are characterized by a low permeability, high geo-stress differentials, strong heterogeneity, and limited fracture development. These properties result in several challenges, including ambiguous gas production sources, low reservoir utilization rates, significant variability in horizontal well performance, and rapid early-stage production decline—all of which hinder the effective development of matrix-type reservoirs. This study examines two representative fractured wells, Xin 8-5H and Xinsheng 204-1H, located in Class II and III blocks of the Xujiahe Formation gas reservoir. To identify gas production sources, we establish full-fracturing-section productivity models. Furthermore, accounting for variations in geological characteristics, we develop distinct productivity models for three key zones, the matrix area, fracture area, and fault area, to evaluate the productivity controls. The findings reveal that well Xin 8-5H primarily produces gas from the matrix and fault zones, whereas well Xinsheng 204-1H derives most of its production from the matrix and natural fractures. In matrix-dominated zones, generating complex fracture networks enhances productivity. An optimal cluster spacing of approximately 14 m ensures broad pressure sweep coverage while maintaining effective inter-cluster fracture connectivity. Additionally, natural fractures in the Xu-2 matrix reservoirs play a vital role in fluid communication. To maximize reservoir contact, well trajectories should be designed such that natural fractures are oriented either parallel or perpendicular to the wellbore, thereby improving lateral and vertical development. Near fault zones, adjusting cluster spacing to 14–25 m—while keeping the distance between faults and fracturing stages below 50 m—effectively connects faults and substantially increases production. This study introduces a systematic methodology for identifying gas sources in matrix reservoirs and optimizes key productivity-influencing parameters. The results provide both theoretical insights and practical strategies for the efficient development of Xu-2 matrix reservoirs.