Hasil untuk "Mechanical industries"

Harshavardhan Kamarthi, Shangqing Xu, Xinjie Tong et al.

Hierarchical time-series forecasting is essential for demand prediction across various industries. While machine learning models have obtained significant accuracy and scalability on such forecasting tasks, the interpretability of their predictions, informed by application, is still largely unexplored. To bridge this gap, we introduce a novel interpretability method for large hierarchical probabilistic time-series forecasting, adapting generic interpretability techniques while addressing challenges associated with hierarchical structures and uncertainty. Our approach offers valuable interpretative insights in response to real-world industrial supply chain scenarios, including 1) the significance of various time-series within the hierarchy and external variables at specific time points, 2) the impact of different variables on forecast uncertainty, and 3) explanations for forecast changes in response to modifications in the training dataset. To evaluate the explainability method, we generate semi-synthetic datasets based on real-world scenarios of explaining hierarchical demands for over ten thousand products at a large chemical company. The experiments showed that our explainability method successfully explained state-of-the-art industrial forecasting methods with significantly higher explainability accuracy. Furthermore, we provide multiple real-world case studies that show the efficacy of our approach in identifying important patterns and explanations that help stakeholders better understand the forecasts. Additionally, our method facilitates the identification of key drivers behind forecasted demand, enabling more informed decision-making and strategic planning. Our approach helps build trust and confidence among users, ultimately leading to better adoption and utilization of hierarchical forecasting models in practice.

Joel M Thomas, Abhijit Chakraborty

This study investigates the economic complexity of Indian states by constructing a state-industry bipartite network using firm-level data on registered companies and their paid-up capital. We compute the Economic Complexity Index and apply the fitness-complexity algorithm to quantify the diversity and sophistication of productive capabilities across the Indian states and two union territories. The results reveal substantial heterogeneity in regional capability structures, with states such as Maharashtra, Karnataka, and Delhi exhibiting consistently high complexity, while others remain concentrated in ubiquitous, low-value industries. The analysis also shows a strong positive relationship between complexity metrics and per-capita Gross State Domestic Product, underscoring the role of capability accumulation in shaping economic performance. Additionally, the number of active firms in India demonstrates a persistent exponential growth at an annual rate of 11.2%, reflecting ongoing formalization and industrial expansion. The ordered binary matrix displays the characteristic triangular structure observed in complexity studies, validating the applicability of complexity frameworks at the sub-national level. This work highlights the usefulness of firm-based data for assessing regional productive structures and emphasizes the importance of capability-oriented strategies for fostering balanced and sustainable development across Indian states. By demonstrating the usefulness of firm registry data in data constrained environments, this study advances the empirical application of economic complexity methods and provides a quantitative foundation for capability-oriented industrial and regional policy in India.

Bukola Peter Adedeji

Accuracy in the prediction of the performances of photovoltaic plants is indispensable in power-generating industries. This has made manufacturers of photovoltaic cells place a high premium on the precision of the forecast of the power output. Artificial neural networks have been proven to be highly effective for forecasting outputs in many technologies. In this study, a feedforward backpropagation neural network model and a radial basis network model were introduced to predict or forecast the power generated by a photovoltaic plant for industrial applications. The inputs and outputs of the models for the training were selected based on the objective of the study, correlation analysis, and analysis of variance test. The results of the simulations of the proposed feedforward backpropagation artificial neural model indicated a mean absolute error of 0.0446, a mean square error of 0.0099, and a mean square error of 0.095. The results of the simulation of the developed radial basis network model indicated a mean absolute error of 0.114, a mean square error of 0.0375, and a root mean square error of 0.196. The comparative analysis of the study shows that the accuracy of the feedforward backpropagation neural network model is 3.79 times that of the radial basis function network, in terms of mean square error. The accuracy and correlation of the proposed feedforward backpropagation neural network were 98.27% and 99.97%, respectively. The proposed feedforward backpropagation neural network model is suitable for industrial applications.

Stavros Vatikiotis, Ioannis Avgerinos, Stathis Plitsos et al.

Water scarcity and the low quality of wastewater produced in industrial applications present significant challenges, particularly in managing fresh water intake and reusing residual quantities. These issues affect various industries, compelling plant owners and managers to optimise water resources within their process networks. To address this cross-sector business requirement, we propose a Decision Support System (DSS) designed to capture key network components, such as inlet streams, processes, and outlet streams. Data provided to the DSS are exploited by an optimisation module, which supports both network design and operational decisions. This module is coupled with a generic mixed-integer nonlinear programming (MINLP) model, which is linearised into a compact mixed-integer linear programming (MILP) formulation capable of delivering fast optimal solutions across various network designs and input parameterisations. Additionally, a Constraint Programming (CP) approach is incorporated to handle nonlinear expressions through straightforward modeling. This state-of-the-art generalised framework enables broad applicability across a wide range of real-world scenarios, setting it apart from the conventional reliance on customised solutions designed for specific use cases. The proposed framework was tested on 500 synthetic data instances inspired by historical data from three case studies. The obtained results confirm the validity, computational competence and practical impact of our approach both among their operational and network design phases, demonstrating significant improvements over current practices. Notably, the proposed approach achieved a 17.6% reduction in freshwater intake in a chemical industry case and facilitated the reuse of nearly 90% of wastewater in an oil refinery case.

David J. Moore

Hierarchical multi-agent systems (HMAS) organize collections of agents into layered structures that help manage complexity and scale. These hierarchies can simplify coordination, but they also can introduce trade-offs that are not always obvious. This paper proposes a multi-dimensional taxonomy for HMAS along five axes: control hierarchy, information flow, role and task delegation, temporal layering, and communication structure. The intent is not to prescribe a single "best" design but to provide a lens for comparing different approaches. Rather than treating these dimensions in isolation, the taxonomy is connected to concrete coordination mechanisms - from the long-standing contract-net protocol for task allocation to more recent work in hierarchical reinforcement learning. Industrial contexts illustrate the framework, including power grids and oilfield operations, where agents at production, maintenance, and supply levels coordinate to diagnose well issues or balance energy demand. These cases suggest that hierarchical structures may achieve global efficiency while preserving local autonomy, though the balance is delicate. The paper closes by identifying open challenges: making hierarchical decisions explainable to human operators, scaling to very large agent populations, and assessing whether learning-based agents such as large language models can be safely integrated into layered frameworks. This paper presents what appears to be the first taxonomy that unifies structural, temporal, and communication dimensions of hierarchical MAS into a single design framework, bridging classical coordination mechanisms with modern reinforcement learning and large language model agents.

Syed Tauhid Ullah Shah, Mohammad Hussein, Ann Barcomb et al.

Artificial Intelligence (AI) tools for automating design artifact generation are increasingly used in Requirements Engineering (RE) to transform textual requirements into structured diagrams and models. While these AI tools, particularly those based on Natural Language Processing (NLP), promise to improve efficiency, their adoption remains limited in regulated industries where transparency and traceability are essential. In this paper, we investigate the explainability gap in AI-driven design artifact generation through semi-structured interviews with ten practitioners from safety-critical industries. We examine how current AI-based tools are integrated into workflows and the challenges arising from their lack of explainability. We also explore mitigation strategies, their impact on project outcomes, and features needed to improve usability. Our findings reveal that non-explainable AI outputs necessitate extensive manual validation, reduce stakeholder trust, struggle to handle domain-specific terminology, disrupt team collaboration, and introduce regulatory compliance risks, often negating the anticipated efficiency benefits. To address these issues, we identify key improvements, including source tracing, providing clear justifications for tool-generated decisions, supporting domain-specific adaptation, and enabling compliance validation. This study outlines a practical roadmap for improving the transparency, reliability, and applicability of AI tools in requirements engineering workflows, particularly in regulated and safety-critical environments where explainability is crucial for adoption and certification.

Chaoran Zhang, Chenhao Zhang, Zhaobo Xu et al.

The combination of embodied intelligence and robots has great prospects and is becoming increasingly common. In order to work more efficiently, accurately, reliably, and safely in industrial scenarios, robots should have at least general knowledge, working-environment knowledge, and operating-object knowledge. These pose significant challenges to existing embodied intelligent robotics (EIR) techniques. Thus, this paper first briefly reviews the history of industrial robotics and analyzes the limitations of mainstream EIR frameworks. Then, a new knowledge-driven technical framework of embodied intelligent industrial robotics (EIIR) is proposed for various industrial environments. It has five modules: a world model, a high-level task planner, a low-level skill controller, a simulator, and a physical system. The development of techniques related to each module are also thoroughly reviewed, and recent progress regarding their adaption to industrial applications are discussed. A case study of real-world assembly system is given to demonstrate the newly proposed EIIR framework's applicability and potentiality. Finally, the key challenges that EIIR encounters in industrial scenarios are summarized and future research directions are suggested. The authors believe that EIIR technology is shaping the next generation of industrial robotics and EIIR-based industrial systems supply a new technological paradigm for intelligent manufacturing. It is expected that this review could serve as a valuable reference for scholars and engineers that are interested in industrial embodied intelligence. Together, scholars can use this research to drive their rapid advancement and application of EIIR techniques. The authors would continue to track and contribute new studies in the project page https://github.com/jackyzengl/EIIR

Sangjun Jeon, Seong Je Park, Seung Ki Moon et al.

The increasing adoption of short carbon fibre-reinforced plastics (sCFRP) manufactured through material extrusion (MEX) in high-value-added industries has driven the development of various post-processing methods to enhance MEX-manufactured sCFRP mechanical properties. However, conventional post-processing methods require high temperatures and extended processing times, leading to potential polymer degradation. This study presents a novel room-temperature approach using cold isostatic pressing (CIP) to enhance mechanical properties with reduced anisotropy in MEX-manufactured sCFRP components. The effects of various CIP pressures (250-1000 bar) on the mechanical properties were evaluated through tensile, flexural and interlaminar shear strength (ILSS) tests. Additionally, mechanical anisotropy was assessed using tensile tests at different raster angles (0°, 90°) before and after CIP treatment. The mechanical properties significantly improved after CIP treatment, with the optimal pressure of 500 bar, resulting in a 103% increase in tensile strength for 0° raster angle specimens and a 143.3% increase for 90° specimens, effectively reducing the anisotropy from 77.3% to 42.1%. Microstructural analysis revealed reduced voids and enhanced layer adhesion with increased crystallinity. CIP-treated sCFRP maintained excellent dimensional stability within a 3% variation. This study demonstrates the potential of room-temperature CIP as a post-processing method for improving the mechanical properties of MEX-manufactured composites.

Moriamo O. John, Chukwuemeka Isanbor, Taofeek B. Ogunbayo et al.

In this study, the natural dye was extracted from Lonchocarpus cyanescens (LC), and both the crude and semi-pure extracts were used as sensitizers for dye-sensitized solar cells (DSSCs). Characterization of the prepared dye was carried out using UV-vis absorption spectroscopy. Different DSSCs based on the extracted dye were fabricated. The light conversion efficiency of the DSSC from the purified extract was found to be 0.057%. This value is lower than the performance of the DSSC from the crude extract of Lonchocarpus cyanescens with 0.116% efficiency. An electrochemical study of the cells was carried out to validate the results using cyclic voltammetry and electrochemical impedance spectroscopy (EIS) for the first time. The difference in the performances of the 2 samples is attributed to the loss of co-absorbers that acted in synergy with absorbing species of crude extract during the process of purification. These absorbing species also act as adsorbing species to the TiO2 surface. In this study, we have established the relationship between the photovoltaic performance of semi-pure and crude extracts of Lonchocarpus cyanescens DSSCs and their charge transport properties.

Poom Narongdej, Daniel Tseng, Riley Gomez et al.

Glass fiber-reinforced polymer (GFRP) composites are widely utilized across industries, particularly in structural components exposed to hygrothermal environments characterized by elevated temperature and moisture. Such conditions can significantly degrade the mechanical properties and structural integrity of GFRP composites. Therefore, it is essential to utilize effective methods for assessing their hygrothermal aging. Traditional approaches to hygrothermal aging evaluation are hindered by several limitations, including time intensity, high costs, labor demands, and constraints on specimen size due to laboratory space. This study addresses these challenges by introducing a facile and efficient alternative that evaluates GFRP degradation under hygrothermal conditions through surface wettability analysis. Herein, a glass fiber-reinforced benzoxazine (BZ) composite was fabricated using the vacuum-assisted resin transfer molding (VARTM) method and was aged in a controlled humidity and temperature chamber for up to 5 weeks. When analyzing the wettability characteristics of the composite, notable changes in the contact angle (CA) and contact angle hysteresis (CAH) were 21.77% and 90.90%, respectively. Impact droplet dynamics further demonstrated reduced wetting length and faster droplet equilibrium times with the prolonged aging duration, indicating a progressive decline in surface characteristics. These changes correlated with reductions in flexural strength, highlighting the surface’s heightened sensitivity to environmental degradation compared with internal structural integrity. This study emphasizes the critical role of surface characterization in predicting the overall integrity of GFRP composites.

T. Sathish, Jayant Giri, Saravanan R. et al.

Natural fiber composites are often sought after in industries, such as automotive and aerospace, due to their low density compared to traditional synthetic composites. Sisal and jute are renewable and biodegradable resources, making them attractive from a sustainability standpoint. The effect of carbon nanotube (CNT) insertion of a composed sisal and jute fiber composite material on the thermal and mechanical characteristics is investigated in this study. The primary objective of this research is to determine the exceptional mechanical strength and heat resistance that allows the composite-filled filling CNT to perform better than others. The methodical experimental approach was used to evaluate the effect of sisal and jute matrix and different amounts of CNTs’ mechanical and thermal properties. Thermal behavior is found by thermogravimetric analysis, and mechanical performance is used to qualify tensile strength, flexural strength, and impact resistance. The result suggests that CNTs may have reinforcing properties and significant tensile and flexural strength improvement. Impact resistance improved and increased the toughness of the composite material. The 7% CNT composite exhibited improvements in tensile strength of 63.9% and flexural strength of 46.6%, suggesting the synergistic reinforcing effect of CNTs. The high temperature from the use of need resistance shows promise for the composite material based on the tests of its capability for heat absorption and thermal stability. Various technical contexts are potentially useful in focusing on environmentally friendly material creation that exhibits exceptional thermal and mechanical properties.

Lei Liu, Menghe Zhu, Jiabing Feng et al.

Abstract High‐performance polymers have proliferated in modern society across a variety of industries because of their low density, good chemical stability, and superior mechanical properties. However, while polymers are widely applied, frequent fire disasters induced by their intrinsic flammability have caused massive impacts on human beings, the economy, and the environment. Supramolecular chemistry has recently been intensively researched to provide fire retardancy for polymers via the physical barrier and char‐catalyzing effects of supramolecular aggregates. In parallel, the noncovalent interactions between supramolecular and polymer chains, such as hydrogen bonding, π–π interactions, metal–ligand coordination, and synergistic interactions, can endow the matrix with enhanced mechanical strength. This makes it possible to integrate physical–chemical properties and noncovalent interactions into one supramolecular aggregate‐based high‐performance polymeric system on demand. However, fulfilling these promises needs more research. Here, we provide an overview of the latest research advances of fire‐retardant and high‐strength polymer materials based on supramolecular structures and interactions of aggregates. This work reviews their conceptual design, characterization, modification principles, performances, applications, and mechanisms. Finally, development challenges and perspectives on future research are also discussed.

Sanjay Kumar Awasthi, Kamal Sharma, Aayush Gupta

Understanding how to manage the hydrophilicity and hydrophobicity of a surface has been the focus of a lot of research in recent years. The surface's energy often controls its hydrophobic state. There are numerous techniques to realize a change in the surface energy. Smart nano-based materials are being used to create super hydrophobic coatings that will serve as layers of defence against mechanical abrasion, corrosion, and fouling agents on the surface of metallic components. These coatings, which have recently gained popularity, have shown to be excellent choices for protecting steel pipelines. The recently created super hydrophobic coatings for glass surfaces, papers, cotton, steel pipes, etc., are examined in-depth and critically in this review study, emphasizing their use in different industries. It explains how to create super hydrophobic coatings on glass substrates using various techniques and the most recent research results on various coating production techniques. An in-depth discussion is also given to the recent applications of these created super hydrophobic coatings for treatments, including anti-bio fouling, dicing, and corrosion prevention over the past five years. According to the literature, spraying is the most adaptable and popular technique for creating super hydrophobic coatings for any substrate.

Matías Manzano-Zavala, Fabiola S. Sosa-Rodríguez, Jorge Vazquez-Arenas et al.

The interactions arising in Electrochemical Double Layer Capacitors (EDLC) made up of commercial activated carbons (DLC 50 Norit, TF-B520 and Kuraray YP-80 F), acetylene carbon black (AB) and polytetrafluoroethylene (PTFE) are analyzed with the aim of maximizing their specific capacitances. AB is varied (0–10 wt%, 0–20 wt% only for further exploration of TF-B520) to minimize its content, while maintaining fixed the PTFE composition. The best rate capabilities are obtained at 5 wt% AB for TF-B520 and Kuraray YP-80 F, and 4 wt% AB for DLC 50 Norit on the basis of cyclic voltammetry, charge/discharge curves and electrochemical impedance spectroscopy. These results strongly depend on a minimum amount of AB in the composite determined through conductivity measurements (i.e. percolation threshold), which guarantees its electronic conductivity. According to N2 adsorption/desorption and textural studies, the critical property defining the electrode supercapacitance is its specific surface area (SSA), relying considerably on the surface area of the pristine AC (main component), regardless of its pore volume and size, or AB area. The specific capacitances present the following trend: TF-B520 (1711–1830 m2 g−1) > > (1356–1571 m2 g−1) > (1319–1504 m2 g−1). Viscoelasticity properties of the composites are less important than conductivity or SSA, since mechanical pressure alters the AC-AB interparticle network, generating better percolating media. In order to optimize specific capacitance, a balance is required between electronic conductivity (percolation in the porous media by AB) and ionic transference (specific surface area of AC) in the electrode composite.

Greig Cowan, Salvatore Mercuri, Raad Khraishi

Understanding customer lifetime value is key to nurturing long-term customer relationships, however, estimating it is far from straightforward. In the retail banking industry, commonly used approaches rely on simple heuristics and do not take advantage of the high predictive ability of modern machine learning techniques. We present a general framework for modelling customer lifetime value which may be applied to industries with long-lasting contractual and product-centric customer relationships, of which retail banking is an example. This framework is novel in facilitating CLV predictions over arbitrary time horizons and product-based propensity models. We also detail an implementation of this model which is currently in production at a large UK lender. In testing, we estimate an 43% improvement in out-of-time CLV prediction error relative to a popular baseline approach. Propensity models derived from our CLV model have been used to support customer contact marketing campaigns. In testing, we saw that the top 10% of customers ranked by their propensity to take up investment products were 3.2 times more likely to take up an investment product in the next year than a customer chosen at random.

Stein Tore Johansen, Bjørn Tore Løvfall, Tamara Rodriguez Duran et al.

A methodology for building pragmatic physics based models (Zoric et al., 2015b) is here adapted to a use-case in the steel industry. The challenge is to predict the erosion of steel ladle linings, such that the model can support operators to decide if the lade lining can be used one more time or not. If the ladle has too thin lining 140 tons of hot liquid steel may escape out of the ladle, with huge consequences for workers and plant. The development was done with a very small core team (two developers), which is typical for many industrial developments. The adopted workflow for the development, challenges that were faced, and some model results are presented. One key learning is that development of models should allow time for maturing the process understanding, and time should be given for many iterations by "questions-responses and actions" at the various levels in the model development. The good interactions between development team and industry case owner is an important success factor. In this case the results of using the PPBM (Pragmatism in physics-based modelling) were good thanks to very successful interaction between development team and industry case owner. Combining or extending the model with use of ML methods and cognition-related methods, such as knowledge graphs and self-adaptive algorithms is discussed.

Ruonan Liu, Quanhu Zhang, Te Han

Industrial Cyber-Physical Systems (ICPS) integrate the disciplines of computer science, communication technology, and engineering, and have emerged as integral components of contemporary manufacturing and industries. However, ICPS encounters various challenges in long-term operation, including equipment failures, performance degradation, and security threats. To achieve efficient maintenance and management, prognostics and health management (PHM) finds widespread application in ICPS for critical tasks, including failure prediction, health monitoring, and maintenance decision-making. The emergence of large-scale foundation models (LFMs) like BERT and GPT signifies a significant advancement in AI technology, and ChatGPT stands as a remarkable accomplishment within this research paradigm, harboring potential for General Artificial Intelligence. Considering the ongoing enhancement in data acquisition technology and data processing capability, LFMs are anticipated to assume a crucial role in the PHM domain of ICPS. However, at present, a consensus is lacking regarding the application of LFMs to PHM in ICPS, necessitating systematic reviews and roadmaps to elucidate future directions. To bridge this gap, this paper elucidates the key components and recent advances in the underlying model.A comprehensive examination and comprehension of the latest advances in grand modeling for PHM in ICPS can offer valuable references for decision makers and researchers in the industrial field while facilitating further enhancements in the reliability, availability, and safety of ICPS.

Jan Heine, Herbert Palm

The increasing pressure within VUCA (volatility, uncertainty, complexity and ambiguity) driven environments causes traditional, plan-driven Systems Engineering approaches to no longer suffice. Agility is then changing from a "nice-to-have" to a "must-have" capability for successful system developing organisations. The current state of the art, however, does not provide clear answers on how to map this need in terms of processes, methods, tools and competencies (PMTC) and how to successfully manage the transition within established industries. In this paper, we propose an agile Systems Engineering (SE) Framework for the automotive industry to meet the new agility demand. In addition to the methodological background, we present results of a pilot project in the chassis development department of a German automotive manufacturer and demonstrate the effectiveness of the newly proposed framework. By adopting the described agile SE Framework, companies can foster innovation and collaboration based on a learning, continuous improvement and self-reinforcing base.

Chengming Yang, Guilong Wang, Aimin Zhang et al.

Thermoplastic polyurethane (TPU) foams have exhibited promising prospect in many industries such as automobile, sportswear and packaging, due to their outstanding mechanical properties. However, the application of TPU foams prepared by microcellular foaming with CO2 as blowing agents is still limited, due to the serious shrinkage after foaming. Herein, in this study microcellular foaming with mixed CO2 and N2 as co-blowing agents was used to control the shrinking behavior of hexamethylene diisocyanate (HDI)-based TPU foams, and further, the effects of shrinkage, expansion ratio, and cell size on the mechanical properties of TPU foams were decoupled. The results show that the stretching degree of the molecular chain and the solubility of co-blowing agents play a vital role in stabilizing TPU foams. Foams with an expansion ratio of up to 16-fold can be prepared with both pure CO2 and co-blowing agents. The shrinkage ratio of TPU foams prepared with co-blowing agents is 6.3 %, while that of foams prepared with pure CO2 is 37.8 %. Moreover, it is also found that the mechanical properties of TPU foams with a smaller shrinkage ratio are much higher than those with a larger initial expansion ratio and a similar final expansion ratio.

Kamolov B S, Kurbanov A A, Sattorov L Kh

The scientific and technological progress of the 21st century is inextricably linked with the widespread use of new materials based on mineral and organic fibers. The most widespread in various industries received on the basis of basalt crystalline fibers. These fibers, in terms of their inherent indicators, for example, physical, mechanical and chemical properties, and price indicators, significantly exceed the classical ones, the production technology of which was implemented in industrial conditions at the end of the last century only in Russia and Ukraine and is a priority of these countries. Basalt fibers are well compatible with polymer, metal, ceramic, inorganic and carbon matrices and various fibers when creating hybrid and composite materials. These unique materials outperform their counterparts made of fiberglass and even steel in terms of performance. They are distinguished by durability, reliability, high corrosion resistance, are operational in a wide temperature range (from -275 to 800 °C), and are chemically inert.