This paper proposes a methodology for leveraging convolutional neural networks (CNNs) in conjunction with advanced data preprocessing to facilitate optimal quality control decision-making in high pressure casting (HPDC) processes. The approach assists in predicting key values of the dependent variable associated with defect occurrence, enabling foundries to enhance product quality, reduce waste, and augment overall production process efficiency. The proposed study is founded on two principal pillars: the transformation of process tabular data (generated using the Conditional Tabular Generative Adversarial Network (CTGAN)), involving the mapping of features onto a fixed grid in a heatmap structure, and the configuration of the CNN algorithm to extract complex patterns in the data that are not readily apparent in the original tabular format. The study utilized a substantial dataset with a total of 61,584 images, and the most effective model attained an impressive Root Mean Square Error (RMSE) of 0.81, underscoring the model's remarkable capacity to accurately detect and predict casting quality issues. The model's efficacy was evaluated through its application to both large and small, differently distributed data sets. Utilizing a combination of statistical pre-processing, intelligent generative models, visual data transformations and deep learning, the methodology offers a comprehensive approach to enhancing production efficiency, ensuring superior process control and improving the quality of HPDC products. This development signifies a significant advancement in the field of intelligent systems for manufacturing process optimization, aligning with the principles of Industry 4.0 and Quality 4.0.
Jersson X. Leon-Medina, John Erick Fonseca Gonzalez, Nataly Yohana Callejas Rodriguez
et al.
This study presents a deep learning-based framework for forecasting energy demand in a quicklime production company, aiming to enhance operational efficiency and enable data-driven decision-making for industrial scalability. Using one year of real electricity consumption data, the methodology integrates temporal and operational variables—such as load profile, active power, shift indicators, and production-related proxies—to capture the dynamics of energy usage throughout the manufacturing process. Several neural network architectures, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Conv1D models, were trained and compared to predict short-term power demand with 10-min resolution. Among these, the GRU model achieved the highest predictive accuracy, with a best performance of RMSE = 2.18 kW, MAE = 0.49 kW, and SMAPE = 3.64% on the test set. The resulting forecasts support cost-efficient scheduling under time-of-use tariffs and provide valuable insights for infrastructure planning, capacity management, and sustainability optimization in energy-intensive industries.
This study aims to assess the mechanical tensile properties of Polyamide produced via selective laser sintering (SLS). The research focuses on the effects of post-processing, positional dependency, anisotropy, and the repeatability of SLS print jobs on material properties. Understanding this anisotropy is crucial for reliable component simulation. A design-appropriate simulation method is developed. A total of 27 identical specimens were fabricated in various orientations and positions within the build chamber, repeated across three print jobs, alongside standard specimens for different post-processing treatments and tempering durations. The mechanical tensile properties were evaluated through tensile tests and compared with simulation outcomes. A new material modeling concept was formulated in the finite element (FE) program ANSYS, employing an orthotropic approach based on linear elastic initial deformation. The Hill Yield Criterion was utilized to model the transition to the plastic region, characterized by a nonlinear strain hardening curve. The print direction was integrated into the FE simulation mesh via a local material coordinate system. Surface treatment via glass bead blasting resulted in slight increases in mechanical response, while tempering had a minor influence. Significant anisotropy was observed, with only the z-position in the build chamber affecting mechanical properties. Successful mapping of anisotropy in structural simulations was achieved. This research did not address optimization of the printing process, recyclate effects, powder aging, or fatigue. The findings provide a comprehensive analysis of the mechanical behavior of SLS-printed specimens, serving as a foundation for treatment methodologies and simulation strategy development.
Any agents we can possibly build are subject to capacity constraints, as memory and compute resources are inherently finite. However, comparatively little attention has been dedicated to understanding how agents with limited capacity should allocate their resources for optimal performance. The goal of this paper is to shed some light on this question by studying a simple yet relevant continual learning problem: the capacity-constrained linear-quadratic-Gaussian (LQG) sequential prediction problem. We derive a solution to this problem under appropriate technical conditions. Moreover, for problems that can be decomposed into a set of sub-problems, we also demonstrate how to optimally allocate capacity across these sub-problems in the steady state. We view the results of this paper as a first step in the systematic theoretical study of learning under capacity constraints.
Today, around the world, there is huge demand for natural materials that are biodegradable and possess suitable properties. Natural fibers reveal distinct aspects like the combination of good mechanical and thermal properties that allow these types of materials to be used for different applications. However, fibers alone cannot meet the required expectations; design modifications and a wide variety of combinations must be synthesized and evaluated. It is of great importance to research and develop materials that are bio-degradable and widely available. The combination of PLA+, a bio-based polymer, with natural fillers like sawdust and soybean oil offers a novel way to create sustainable composites. It reduces the reliance on petrochemical-based plastics while enhancing the material’s properties using renewable resources. This study explores the creation of continuous hexagonal-shaped 3D-printed PLA+ samples and the application of post-print fillers, specifically sawdust and soybean oil. PLA+ is recognized for its eco-friendliness and low carbon footprint, and incorporating a hexagonal pattern into the 3D-printed PLA+ enhances its structural strength while maintaining its density. The addition of fillers is crucial for reducing shrinkage and improving binding capabilities, addressing some of PLA+’s inherent challenges and enhancing its load-bearing capacity and performance at elevated temperatures. Additionally, this study examines the impact of varying filler percentages and pattern orientations on the mechanical properties of the samples, which were printed with an infill design.
Keita Marumoto, Akira Fujinaga, Takeshi Takahashi
et al.
This study presents a new gas metal arc welding (GMAW) technique that achieves both high efficiency and low heat input using a hybridization of the hot-wire method. The optimal combination of welding speed and welding current conditions was investigated using a fixed hot-wire feeding speed of 10 m/min on a butt joint with a V-shaped groove using 19 mm thick steel plates. Molten pool stability and defect formation were observed using high-speed imaging and cross-sectional observations. The power consumption and heat input were predicted prior to welding and measured in the experiments. The results indicate that a combination of a welding current of 350–500 A and welding speed of 0.3–0.7 m/min is optimal to avoid defect formation and molten metal precedence using three or four passes. The higher efficiency and lower heat input achieved by hot-wire GMAW results in a weld metal of adequate hardness, narrower heat-affected zone, smaller grain size at the fusion boundary, and lower power consumption than those obtained using tandem GMAW and high-current GMAW. Based on the experimental results, a single bevel groove, which is widely used in construction machinery welding joints, was welded using hot-wire GMAW, and we confirmed that the welding part could be welded in six passes, whereas eight passes were required with GMAW only.
Obi Peter Adigwe, Godspower Onavbavba, Olajide Joseph Adebola
et al.
ABSTRACT Background Vaccination protects the population against infectious diseases and reduces their transmissibility. Potentials exist for local production of vaccines in Nigeria, as a means of addressing public health needs. However, challenges exist in certain critical aspects which limit development in this area. This study aimed at evaluating the challenges of local vaccines’ manufacturing in Nigeria from the perspectives of relevant stakeholders. Methods This was a cross‐sectional study. A structured questionnaire was used for data collection. The data obtained from the study were analysed descriptively. Results More than half of the study participants (55.5%) agreed that significant gaps exist with respect to access to vaccines in Nigeria. Only about one‐quarter of the respondents (25.8%) were of the view that relevant legislative frameworks exist to support government funding in the area of vaccine production. One‐third of the participants (32.3%) expressed confidence in the availability of trained human resources for vaccine production. Close to two‐thirds of the respondents (61.7%) expressed dissatisfaction regarding the current funding for vaccine research and development, and a similar proportion (65.2%) were of the opinion that a lack of local manufacturing capacity contributed to the sub‐optimal access to vaccines. Moreover, two‐thirds (62.3%) disagreed that Nigeria was prepared for future pandemics. Conclusion Ill‐suited policies, sub‐optimal infrastructure, and inadequate research and development funding, are some factors which the study identified as contributory to the lack of access to vaccines in Nigeria. There is a need to improve incentives, infrastructural development and build human resource capacity for vaccine research and development to enhance local production in Nigeria.
Ahmed Abdalkareem, Rasha Afify, Nadia Hamzawy
et al.
Friction drilling is a non-conventional process that generates heat through the interaction between a rotating tool and a workpiece, forming a hole with a bushing. In this study, the effect of the preheating temperature, rotational speed, and feed rate on the induced temperature during the friction drilling of A356 aluminum alloy was investigated. This study aimed to analyze the influence of friction-drilling parameters on the thermal conditions in the induced bushing, where it focused on the relationship between preheating and the resulting heat generation. The analysis of variance (ANOVA) approach was carried out to optimize the friction-drilling parameters that contributed most to the induced temperature during the friction-drilling processing. Experiments were conducted at various preheating temperatures (100 °C, 150 °C, 200 °C), rotational speeds (2000 rpm, 3000 rpm, 4000 rpm), and feed rates (40 mm/min, 60 mm/min, 80 mm/min). The induced temperature during the process was recorded using an infrared camera, where the observed temperatures ranged from a minimum of 154.4 °C (at 2000 rpm, 60 mm/min, and 100 °C preheating) to a maximum of 366.8 °C (at 4000 rpm, 40 mm/min, and 200 °C preheating). The results show that preheating increased the peak temperature generated in the bushing during friction drilling, especially at lower rotational speeds. The rotational speed rise led to an increase in the induced temperature. However, the increase in the feed rate resulted in a decrease in the observed temperature. The findings provide insights into optimizing friction-drilling parameters for enhanced thermal management in A356 aluminum alloy.
An important target of the UN Sustainable Development Goals (SDGs) is the efficient use of the planet’s resources. In this study, the authors show a strong exponential relationship between the economic complexity index and the efficiency of resource use in a country. The economic complexity index is a characterization of the productive capacity of large economies. This index measures the level of knowledge accumulated by a society that enables production. Assessing the level of a country’s index also makes it possible to predict future trends in the region’s economy. The model of economic sophistication index proposed by the authors includes the service economy, retail trade and manufacturing. Thus, in the paper, the authors identify how the economic complexity index affects the product level by defining the product space for each country and identifying the main products that contribute to a high product complexity index and prospective scalability, indicating the potential to produce better products in the future. Policies focused on increasing economic complexity and investing in staple products appear to be a priority for achieving sustainable development.
The global momentum towards hydrogen has led to various initiatives aimed at harnessing hydrogen’s potential. In particular, low-carbon hydrogen is recognized for its crucial role in reducing greenhouse gas emissions across hard-to-abate sectors such as steel, cement and heavy-duty transport. This study focuses on the presentation of all hydrogen-related financing initiatives in Italy, providing a comprehensive overview of the various activities and their geographical locations. The examined funding comes from the National Recovery and Resilience Plan (PNRR), from projects directly funded through the Important Projects of Common European Interest (IPCEI) and from several initiatives supported by private companies or other funding sources (hydrogen valleys). Specific calls for proposals within the PNRR initiative outline the allocation of funds, focusing on hydrogen production in brownfield areas (52 expected hydrogen production plants by 2026), hydrogen use in hard-to-abate sectors and the establishment of hydrogen refuelling stations for both road (48 refuelling stations by 2026) and railway transport (10 hydrogen-based railway lines). A detailed description of the funded initiatives (150 in total) is presented, encompassing their geographical location, typology and size (when available), as well as the funding they have received. This overview sheds light on regions prioritising decarbonisation efforts in heavy-duty transport, especially along cross-border commercial routes, as evident in northern Italy. Conversely, some regions concentrate more on local transport, typically buses, or on the industrial sector, primarily steel and chemical industries. Additionally, the study presents initiatives aimed at strengthening the national manufacturing capacity for hydrogen-related technologies, alongside new regulatory and incentive schemes for hydrogen. The ultimate goal of this analysis is to foster connections among existing and planned projects, stimulate new initiatives along the entire hydrogen value chain, raise an awareness of hydrogen among stakeholders and promote cooperation and international competitiveness.
The statistics on the production and development of passenger airplanes in the world is presented in this article for the first time. The methods for obtaining the results are described, uncertainties of the results are estimated. It is specified what exactly is considered to be a passenger airplane. It is shown that only 60,000 passenger airplanes were built during the entire 20th century. This is less than 3% of the total production of airplanes of all classes. Their total capacity amounts less than 5 million people, or less than a thousandth of the world’s population by the end of the last century. These 60,000 airplanes provided unprecedented mobility of the population. It was revealed that the leading role in the passenger airplane manufacturing belonged to the USA, the USSR took a steady second place. The ups-and-downs in airplane production are described, including the recessions during the Great Depression, World War II and the global economic decline (in the USSR, the USA and other countries) in the early 1960s, which was replaced by a rapid increase in output. It is indicated that the number of airplanes produced in the last third of the 20th century remained approximately constant, but their average capacity was growing rapidly, which largely ensured the explosive growth of air transportation during this period. The dynamics of the dead weight per one passenger is given. The dynamics of the number of the new passenger airplane models is presented. It is shown that for the last 30 years of the century their number was approximately constant, and almost all the models that reached the test stage were put into serial production. In the period between the world wars, however, about half of all models tested in flight remained prototypes. The change in the ratio of the number of airplanes by the number of engines is given. The renaissance of three-engine airplanes in the 1960s, the almost complete disappearance of singleengine passenger airplanes by the end of the century and the stable amount of a small proportion of four-engine airplanes for the last 30 years of the past century are noted.
Nunzio A. Letizia, Andrea M. Tonello, H. Vincent Poor
In this paper, the problem of determining the capacity of a communication channel is formulated as a cooperative game, between a generator and a discriminator, that is solved via deep learning techniques. The task of the generator is to produce channel input samples for which the discriminator ideally distinguishes conditional from unconditional channel output samples. The learning approach, referred to as cooperative channel capacity learning (CORTICAL), provides both the optimal input signal distribution and the channel capacity estimate. Numerical results demonstrate that the proposed framework learns the capacity-achieving input distribution under challenging non-Shannon settings.
Dganit Hanania, Daniella Bar-Lev, Yevgeni Nogin
et al.
DNA labeling is a powerful tool in molecular biology and biotechnology that allows for the visualization, detection, and study of DNA at the molecular level. Under this paradigm, a DNA molecule is being labeled by specific k patterns and is then imaged. Then, the resulted image is modeled as a (k + 1)- ary sequence in which any non-zero symbol indicates on the appearance of the corresponding label in the DNA molecule. The primary goal of this work is to study the labeling capacity, which is defined as the maximal information rate that can be obtained using this labeling process. The labeling capacity is computed for any single label and several results are provided for multiple labels as well. Moreover, we provide the optimal minimal number of labels of length one or two that are needed in order to gain labeling capacity of 2.
Jamal Ahmed Hama Kareem, Blesa Ibrahim Mohammed, Sameer Abduljabbar Abdulwahab
This study examined the extent of optimal materials handling equipment impact on defective product reduction skills to enhance overall production efficiency, taking steel and iron factories as a case study. To achieve this end, the study was performed by using qualitative and quantitative methods of data collection was employed which represented in the questionnaire survey and semi-structured interviews. Questionnaire instrument already has been tested. Findings of the study revealed that optimal materials handling equipment, particularly storage and handling equipment and engineered systems assist significantly in improving defective product reduction skills by facilitating a shorter operating cycle, reduces handling costs, eliminates unproductive handling of materials, reduces idle machine capacity, and eliminates factory hazards. All this, in turn, enabling optimum usage of space and maintains the quality of materials toward enhancing overall production efficiency in terms of facilitating better customer care and ensuring the production of quality products and in a timely. Based on findings, the study recommended manufacturing organizations management in order to succeed in enhancing operational and production efficiency as a whole, it should give a keen interest in optimal materials handling equipment and give them prioritize as a very vital cost center to defective products reduction.
History of scholarship and learning. The humanities, Social Sciences
Leonardos Bilalis, Vassilios Canellidis, Theodore Papatheodorou
et al.
Direct Digital Manufacturing (DDM) is considered by many as one of the most promising approaches towards cost- and time-efficient mass customization. Compared to conventional manufacturing systems, DDM systems are not as common and incorporate several distinctive features, such as higher flexibility in product form and structure, lower economies of scale and higher potential for decentralized production network. The initial design phase of a DDM production system, where very important in term of efficiency and quality, decisions are made, is a relatively unexplored topic in the relevant literature. In the present study, the corresponding issues are investigated through a case study involving the direct digital production of a customized reusable face mask (respirator) for medical use. Investigated system design aspects include product, process, and facility design. Based on data generated through manufacturing tests, a preliminary cost analysis is performed and several scenarios regarding production throughput and facility planning are examined. According to the results, DDM of custom-made face masks is, to a large extent, technically and economically feasible. Interestingly, considering the whole process, a large part of production cost is associated with labor and materials. Finally, evidence for a fundamental trade-off between manufacturing cost and speed/flexibility is identified, implying that different implementations of DDM systems can be realized depending on strategic operational objectives.
Wire Arc Additive Manufacturing (WAAM) has many applications in fabricating complex metal parts. However, controlling surface roughness is very challenging in WAAM processes. Typically, machining methods are applied to reduce the surface roughness after a part is fabricated, which is costly and ineffective. Therefore, controlling the WAAM process parameters to achieve better surface roughness is important. This paper proposes a machine learning method based on Gaussian Process Regression to construct a model between the WAAM process parameters and top surface roughness. In order to measure the top surface roughness of a manufactured part, a 3D laser measurement system is developed. The experimental datasets are collected and then divided into training and testing datasets. A top surface roughness model is then constructed using the training datasets and verified using the testing datasets. Experimental results demonstrate that the proposed method achieves less than 50 μm accuracy in surface roughness prediction.
Objectives : Manufacturing－based production facilities are required to install dust collection devices for air pollution prevention facilities. In particular, manufacturing-based companies need low-power hazardous gas treatment devices. However, due to the slowing economic growth, the cost of replacing new hazardous gas treatment devices is increasing, and new products in the form of parts that can be attached to scrubbers that are already installed are urgently needed.
Methods : To deal with residual gas from organic and inorganic compounds used in semiconductor manufacturing processes, the concentration of air pollutants emitted through the process of removing harmful substances from the primary scrubber and re-treatment of gases emitted from the secondary scrubber is further lowered.
Results and Discussion : In this study, a cooling block device which is a hazardous gas treatment part is developed to solve the limitation of scrubber processing capacity from overcapacity harmful gases such as strong toxicity, corrosivity, combustion, and environmental pollution in semiconductor manufacturing process.
Conclusions : In the design factors and performance survey of cooling module using thermoelectric element, it was calculated that the cooling capacity of the peltier thermoelectric element with a margin of 9,300 W was required. Based on these results, the absolute humidity decreased by 5.8 g/kg and the temperature decreased by 9.5 degrees, showing the possibility of solving the problem of the decrease in the effectiveness of hazardous gas treatment of secondary scrubber due to increased moisture.
Expensive power cost is a significant concern in today’s manufacturing world. Reduction in energy consumption is an ultimate measure towards achieving manufacturing efficiency and emissions control. In the existing literature of scheduling problems, the consumption of energy is considered uncertain under the dimensions of uncertain demand and supply. In reality, it is a random parameter that also depends on production capacity, manufacturing technology, and operational condition of the manufacturing system. As the unit production cost varies with production rate and reliability of the manufacturing system, the energy consumption of the system also varies accordingly. Therefore, this study investigated an unreliable manufacturing system under stochastic production capacities and energy consumption. A stochastic production−inventory policy is developed to optimize production quantity, production rate, and manufacturing reliability under variable energy consumption costs. As energy consumption varies in different operational states of manufacturing, we consider three specific states of power consumption, namely working, idle, and repair time, for an integrated production−maintenance model. The considered production system is subjected to stochastic failure and repair time, where productivity and manufacturing reliability is improved through additional technology investment. The robustness of the model is shown through numerical example, comparative study, and sensitivity analysis of model parameters. Several graphical illustrations are also provided to obtain meaningful managerial insights.