Search Results (2,763)

Accurate scrap forecasting is essential for advancing green manufacturing, as reducing defective output not only lowers production costs but also prevents unnecessary resource consumption and environmental impact. Effective scrap prediction enables manufacturers to take proactive measures to minimize waste generation, thereby supporting sustainability goals and improving production efficiency. This study proposes a hybrid ensemble framework that integrates CatBoost and XGBoost, combined with Particle Swarm Optimization (PSO), to enhance prediction accuracy in industrial applications. The model exploits the complementary strengths of both algorithms by applying weighted averaging and stacked generalization, allowing it to process heterogeneous datasets containing both categorical and numerical variables. A case study in the aerospace manufacturing sector demonstrates the effectiveness of the proposed approach. Compared to standalone models, the PSO-enhanced hybrid ensemble achieved more than a 30% reduction in Root Mean Squared Error (RMSE), confirming its ability to capture complex interactions among diverse process parameters. Feature importance analysis further showed that categorical attributes, such as machine type and operator, are as influential as numerical parameters, underscoring the need for hybrid modeling. Although the model requires higher computational effort, the integration of PSO significantly improves robustness and scalability. By reducing scrap and optimizing resource utilization, the proposed framework provides a data-driven pathway toward greener, more resource-efficient, and resilient manufacturing systems. Full article

In the current economic context, organizations providing automotive repair services face significant challenges in ensuring service quality, operational efficiency, and long-term sustainability. This paper examines the importance of implementing process monitoring systems through the integration of European quality frameworks and Japanese operational principles such as Kaizen, Lean Manufacturing, and Poka-Yoke, to improve the quality of services and increase performance within automotive repair organizations. The research is grounded in Sustainable Development Goals (SDG 9—Industry, Innovation and Infrastructure, and SDG 12—Responsible Consumption and Production), demonstrating how structured quality practices contribute to reducing waste, optimizing processes, and delivering responsible services. The main objectives of the study are to identify the elements that influence the performance of service-specific processes, to improve the quality management practices related to these processes, to eliminate non-conformities, and to enhance profitability and competitive differentiation through service quality assurance. A mixed-methods research design was applied, including direct participatory observation, performance monitoring, and correlational statistical analysis over a six-month period in two Romanian automotive service centers. Key performance indicators (KPIs) such as technician efficiency, rework rate, and order throughput time were collected and analyzed before and after the implementation of selected tools. Findings demonstrate measurable improvements: rework rates decreased from 7.8% to 2.6%, technician efficiency improved from 89% to 105%, and average service completion time was reduced by 1.6 days. Correlation analysis confirmed strong relationships between visual management adoption and rework reduction (r = −0.75), as well as between Lean implementation and technician efficiency (r = +0.89). The study’s novelty lies in its integration of cross-cultural quality management practices into a replicable and sustainable operational model for post-sale service environments. The results validate that implementing monitoring systems, combined with Kaizen, Lean, and Poka-Yoke, supported by visual management and active employee engagement, can lead to superior service quality management, increased customer satisfaction, and long-term organizational success in the automotive repair industry. Full article

This research enhances and evaluates the performance of a Decentralized Nash Bargaining (DNB) adaptive traffic signal controller that operates a flexible National Electrical Manufacturers Association (NEMA) phasing and timing scheme responding dynamically to fluctuating traffic demands. The DNB controller is enhanced to (1) use traffic density estimates instead of queues to optimize signal timings; (2) to consider the eight-phase two-ring NEMA controller configuration within the game-theoretic approach; and (3) to consider dynamically adaptable control time steps. The enhanced DNB controller is benchmarked against (1) a fixed-time traffic signal control using the state-of-practice Webster’s method and an emerging Laguna-Du-Rakha (LDR) method for computing the optimum cycle length; (2) a state-of-the-practice actuated traffic signal control; and (3) a state-of-the-art reinforcement learning (RL) traffic signal controller presented in the literature. The controller is tested on two isolated signalized intersections, demonstrating enhanced overall intersection performance compared to the baseline pretimed and actuated controllers at various demand levels, and offers better performance than a previously developed RL controller. Specifically, the DNB controller results in a decrease in the average vehicle delay and queue size by up to 54% and 63%, respectively, compared to Webster’s state-of-the-practice pretimed control. Unlike the RL controller, the DNB controller requires no pre-training while adapting to fluctuating traffic conditions, thereby providing a flexible framework for reducing traffic congestion at signalized intersections. As such, this research contributes to the development of smarter and more responsive urban traffic control systems. Full article

The Line Balancing Problem (LBP) is a classic optimization topic in production management, aiming to improve efficiency through task allocation. With the transformation of the manufacturing industry towards intelligence, customization, and sustainability, its research scope has been significantly expanded. This study systematically reviews the recent research progress and proposes the C|H|V|E framework to analyze the LBP in four dimensions: (i) extension of the core line problem; (ii) horizontal integration with shop-floor decision-making; (iii) vertical coordination with enterprise-level operations; and (iv) extension of the value from efficiency improvement to sustainability and resilience enhancement. The review focuses on emerging trends, including artificial intelligence and data-driven approaches, digital twin-based optimization, flexible human-machine collaboration, and system integration across the lifecycle and circular economy. This paper provides a systematic overview of the current state of LBP research and explains how it continues to expand its boundaries by incorporating knowledge from new fields. Full article

The emergence of Generative Artificial Intelligence (GenAI) is reshaping logistics and supply chain operations, offering new opportunities to improve efficiency, accuracy, and responsiveness. In the automotive manufacturing sector, where high-volume throughput and precision are critical, the integration of AI technologies into warehouse management represents a strategic advancement. This study presents a case analysis of the implementation of AI-driven reception processes at an Automotive facility in Blaj, Romania. The research focuses on the transition from manual operations to automated recognition using industrial-grade imaging systems integrated with enterprise resource planning platforms. The integrated approach used combines Value Stream Mapping, quantitative performance analysis, and statistical validation using the Wilcoxon Signed-Rank Test. The results reveal a substantial reduction in reception time up to 79% and significant cost savings across various operational scales with improved data accuracy and minimized logistics failures. To support broader industry adoption, the study proposes a Cleaner Logistics and Supply Chain Model, incorporating principles of sustainability, ethical compliance, and continuous improvement. This model serves as a strategic framework for organizations seeking to align AI adoption with long-term operational resilience and environmental responsibility. The findings validate the operational and financial advantages of AI-enabled warehousing management in achieving sustainable digital transformation in logistics. Full article

Gasification of residual biomass has emerged as an efficient thermochemical conversion process, applicable to a wide range of uses, such as electricity generation; chemical manufacturing; and the production of liquid biofuels, BioSNG (biomass-based synthetic natural gas), and hydrogen. Thus, gasification of biomass residues not only constitutes an important contribution toward decarbonizing the economy but also promotes the efficient utilization of renewable resources. Although a variety of gasification technologies are available, there are no clear guidelines for selecting the type of gasifier appropriate depending on the feedstock and the desired downstream products. Herein, we propose a gasifier classification model based on an extensive literature review, combined with a multi-criteria decision-making approach. A comprehensive and up-to-date literature review was conducted to gain a thorough understanding of the current state of knowledge in biomass gasification. The different features of the different types of gasifiers, in the context of biomass gasification, are presented and compared. The gasifiers were reviewed and evaluated considering criteria such as processing capacity, syngas quality, process performance, feedstock flexibility, operational and capital costs, environmental impact, and specific equipment features. A multi-criteria classification methodology was evaluated for assessing biomass gasifiers. A case study of such methodology was a applied to determine the best gasifiers for BioSNG inclusion in the natural gas distribution system in a small-scale scenario. Validation was conducted by comparing the matrix findings with commercially implemented gasification projects worldwide. Full article

Automotive manufacturing quality control faces persistent challenges such as limited defect samples, cross-domain variability, and the demand for interpretable decision-making. This work presents an explainable few-shot anomaly detection framework that integrates EfficientNet-based feature extraction, adaptive prototype learning, and component-specific attention mechanisms to address these requirements. The system is designed for rapid adaptation to novel defect types while maintaining interpretability through a multi-modal explainable AI module that combines visual, quantitative, and textual outputs. Evaluation on automotive datasets demonstrates promising performance on evaluated automotive components, achieving 99.4% accuracy for engine wiring inspection and 98.8% for gear inspection, with improvements of 5.2–7.6% over state-of-the-art baselines, including traditional unsupervised methods (PaDiM, PatchCore), advanced approaches (FastFlow, CFA, DRAEM), and few-shot supervised methods (ProtoNet, MatchingNet, RelationNet, FEAT), and with only 0.63% cross-domain degradation between wiring and gear inspection tasks. The architecture operates under real-time industrial constraints, with an average inference time of 18.2 ms, throughput of 60 components per minute, and memory usage below 2 GB on RTX 3080 hardware. Ablation studies confirm the importance of prototype learning (−4.52%), component analyzers (−2.79%), and attention mechanisms (−2.21%), with K = 5 few-shot configuration providing the best trade-off between accuracy and adaptability. Beyond performance, the framework produces interpretable defect localization, root-cause analysis, and severity-based recommendations designed for manufacturing integration with execution systems via standardized industrial protocols. These results demonstrate a practical and scalable approach for intelligent quality control, enabling robust, interpretable, and adaptive inspection within the evaluated automotive components. Full article

Industrial engineering research has been reshaped by the integration of artificial intelligence (AI) within the framework of Industry 4.0, characterized by the interplay between cyber-physical systems (CPS), advanced automation, and the Industrial Internet of Things (IIoT). While this integration opens new opportunities, it also introduces biases that undermine the reliability and robustness of scientific and industrial outcomes. This article presents a systematic literature review (SLR), supported by natural language processing techniques, aimed at identifying and classifying biases in AI-driven research within industrial contexts. Based on this meta-research approach, a taxonomy is proposed that maps biases across the stages of the scientific method as well as the operational layers of intelligent production systems. Statistical analysis confirms that biases are unevenly distributed, with a higher incidence in hypothesis formulation and results dissemination. The study also identifies emergent AI-related biases specific to industrial applications such as predictive maintenance, quality control, and digital twin management. Practical implications include stronger reliability in predictive analytics for manufacturers, improved accuracy in monitoring and rescue operations through transparent AI pipelines, and enhanced reproducibility for researchers across stages. Mitigation strategies are then discussed to safeguard research integrity and support trustworthy, bias-aware decision-making in Industry 4.0. Full article

Logistics and warehouse operations experience an increasing pressure to adopt sustainable practices. The logistics industry generates substantial material waste, with cardboard being the primary packaging material. Adopting Circular Economy (CE) principles to control this waste is important for enhancing sustainability. However, there is a lack of studies on transforming warehouses into more sustainable operations. This paper studies the ability to transform the linear supply chain of a distribution warehouse into a circular supply chain by applying lean manufacturing principles to eliminate cardboard waste. A structured framework is presented to outline the project’s methodology and illustrate the steps taken to apply the concept of CE. The paper also tests the capability to simulate warehouse operations with engineering software using limited available data to generate various scenarios. This study contributes by showing how discrete-event simulation combined with VSM and 6R principles can provide operational insights under data-constrained conditions. Bridging the gap between theory and practice. Multiple operational scenarios were modelled and run, including peak and off-peak demand periods, as well as a sensitivity analysis for recycling durations. A comparative evaluation is shown to demonstrate the effectiveness of each alternative and determine the most feasible solution. Results indicate that introducing recycling activities created some bottlenecks in the system and reduced its efficiency. Furthermore, suggestions for future improvements are presented, ensuring that on-site actions are grounded in a simulation that reflects reality. Full article

The rapid growth of road freight has increased urban carbon emissions, but decarbonization in this sector remains slow compared to other areas. This study examines city-level road freight decarbonization, focusing on extreme values, with the goal of establishing a quantitative reference indicator for tailored policies. Using data from 342 Chinese cities, we applied K-means clustering and Extreme Value Theory (EVT) to estimate the extreme levels of freight vehicles decarbonization (FVDEL) under various economic scenarios. Results show notable differences among city types. High-Tech and Light Industry Cities (Type I) display a more substantial decarbonization potential, with a key threshold around 1.27%. Surpassing this level indicates higher readiness for zero-emission road freight, while Heavy Industry-Manufacturing Cities (Type II) tend to behave more predictably during economic ups and downs because of their close ties between industry and freight activities. The study also finds that purchase subsidies tend to have diminishing returns, whereas operational incentives like electricity price discounts and road access advantages are more effective in maintaining adoption. By proposing EVT-based thresholds as practical benchmarks, this research connects statistical modeling with policy implementation. The proposed reference indicator offers useful guidance for assessing urban decarbonization capacity and developing customized strategies to promote zero-emission freight systems. Full article

Lubricants play a crucial role in improving the reliability of internal combustion engines. The deterioration of engine oil is influenced not only by mileage and usage time but also by subjective factors. Currently, engine oil is replaced in accordance with the manufacturer’s recommendations. At the time of a scheduled oil change, two situations may arise: the degree of lubricant wear may exceed normal levels, in which case the technical systems may also be damaged, with serious consequences for the environment and, implicitly, for human health; or the degree of wear may be low, consistent with normal engine operation, in which case prolonging oil use is recommended, thereby reducing consumption. In this paper, the authors propose a method for diagnosing the engine through periodic analysis of the physico-chemical properties of used engine oil, based on which appropriate vehicle maintenance strategies are issued. Also, recommendations are made for prolonged use of the oil on the condition of its periodic evaluation. Thus, for samples taken from 43 trucks the following physico-chemical properties were analyzed: kinematic viscosity, density, flash point, fuel content, water content, and metal content and their values, for all samples, were within the recommended limits. However, for some samples, more pronounced variations in the values of some properties were found and suitable preventive maintenance recommendations were issued. Full article

This research investigates the strategic interplay between pricing, delivery promises, and handling strategies for service-level returns—products returned by consumers due to operational issues like late delivery rather than product defects. In a vertical decentralized supply chain with a manufacturer and an e-tailer, a shorter promised delivery lead time (PDL) attracts more customers but also increases the risk of late delivery, making products more return-prone. Modeling the return rate as an endogenous variable dependent on the e-tailer’s PDL decision, we develop a Manufacturer-Stackelberg (MS) game-theoretic model to examine whether service-level returns should be handled by the manufacturer (Buy-Back strategy) or the e-tailer (No-Returns strategy). The results suggest that the optimal handling strategy depends on the e-tailer’s reselling ratio—a measure of its efficiency in extracting value from returns. A win-win situation is achieved when the reselling ratio is smaller than a threshold, as the manufacturer’s decision to buy back these returns also benefits the e-tailer. Surprisingly, when the manufacturer leaves the e-tailer to handle FFRs, a higher reselling ratio is not necessarily profitable for the e-tailer. Extending the analysis to a retailer-Stackelberg (RS) scenario reveals that the supply chain’s power structure is a fundamental determinant of the optimal returns handling strategy, shifting the equilibrium from a counterintuitive, power-distorted outcome in a MS system to an intuitive, profit-driven one in a RS system. Full article

This study presents a multivariate and machine learning-based approach to analyze quality alerts in an industrial manufacturing context. Based on data from recorded quality alerts, this research integrates exploratory data analysis, Multiple Correspondence Analysis (MCA), and Random Forest modeling to uncover hidden patterns among key categorical variables, including process, section, and priority. The analysis highlights structural associations and frequency distributions that differentiate alert behavior across various production units. Visualization tools such as heatmaps and bar charts are employed to provide actionable insights into the operational environment. The study has practical applications in the monitoring and continuous improvement of quality management systems in manufacturing environments. Identifying patterns in quality alerts through multivariate and machine learning techniques leads to a deeper understanding of the origin and frequency of quality issues across machines, processes, and plant sections. The findings can support preventive actions, efficient resource allocation, and targeted maintenance strategies, ultimately enhancing product consistency. Full article

The hydrogen economy stands at the forefront of the global energy transition, and additive manufacturing (AM) is increasingly recognized as a critical enabler of this transformation. AM offers unique capabilities for improving the performance and durability of hydrogen energy components through rapid prototyping, topology optimization, functional integration of cooling channels, and the fabrication of intricate, hierarchical, structured pores with precisely controlled connectivity. These features facilitate efficient heat and mass transfer, thereby improving hydrogen production, storage, and utilization efficiency. Furthermore, AM’s multi-material and functionally graded printing capability holds promise for producing components with tailored properties to mitigate hydrogen embrittlement, significantly extending operational lifespan. Collectively, these advances suggest that AM could lower manufacturing costs for hydrogen-related systems while improving performance and reliability. However, the current literature provides limited evidence on the integrated techno-economic advantages of AM in hydrogen applications, posing a significant barrier to large-scale industrial adoption. At present, the technological readiness level (TRL) of AM-based hydrogen components is estimated to be 4–5, reflecting laboratory-scale progress but underscoring the need for further development, validation and industrial-scale demonstration before commercialization can be realized. Full article

Industrial scheduling plays a central role in Industry 4.0, where efficiency, robustness, and adaptability are essential for competitiveness. This review surveys recent advances in reinforcement learning, digital twins, and hybrid artificial intelligence (AI)–operations research (OR) approaches, which are increasingly used to address the complexity of flexible job-shop and distributed scheduling problems. We focus on how these methods compare in terms of scalability, robustness under uncertainty, and integration with industrial IT systems. To move beyond an enumerative survey, the paper introduces a structured analysis in three domains: comparative strengths and limitations of different approaches, ready-made tools and integration capabilities, and representative industrial case studies. These cases, drawn from recent literature, quantify improvements such as reductions in makespan, tardiness, and cycle time variability, or increases in throughput and schedule stability. The review also discusses critical challenges, including data scarcity, computational cost, interoperability with Enterprise Resource Planning (ERP)/Manufacturing Execution System (MES) platforms, and the need for explainable and human-in-the-loop frameworks. By synthesizing methodological advances with industrial impact, the paper highlights both the potential and the limitations of current approaches and outlines key directions for future research in resilient, data-driven production scheduling. Full article