Advanced manufacturing with new bio-derived materials can be achieved faster and more economically with first-principle-based artificial intelligence and machine learning (AI/ML)-derived models and process optimization. Not only is this motivated by increased industry profitability, but it can also be optimized to reduce waste generation, energy consumption, and gas emissions through additive manufacturing (AM) and AI/ML-directed self-driving laboratory (SDL) process optimization. From this perspective, the benefits of using 3D printing technology to manufacture durable, sustainable materials will enable high-value reuse and promote a better circular economy. Using AI/ML workflows at different levels, it is possible to optimize the synthesis and adaptation of new bio-derived materials with self-correcting 3D printing methods, and in-situ characterization. Working with training data and hypotheses derived from Large Language Models (LLMs) and algorithms, including ML-optimized simulation, it is possible to demonstrate more field convergence. The combination of SDL and AI/ML Workflows can be the norm for improved use of biobased and renewable materials towards advanced manufacturing. This should result in faster and better structure, composition, processing, and properties (SCPP) correlation. More agentic AI tasks, as well as supervised or unsupervised learning, can be incorporated to improve optimization protocols continuously. Deep Learning (DL), Reinforcement Learning (RL), and Deep Reinforcement Learning (DRL) with Deep Neural Networks (DNNs) can be applied to more generative AI directions in both AM and SDL, with bio-based materials.
Additive manufacturing (AM) has transformed the production landscape by enabling the precision creation of complex geometries. However, AM faces limitations when applied to challenging environments, such as elevated surfaces and remote locations. Aerial additive manufacturing, facilitated by drones, presents a solution to these challenges. However, despite advances in methods for the planning, control, and localization of drones, the accuracy of these methods is insufficient to run traditional feedforward extrusion-based additive manufacturing processes (such as Fused Deposition Manufacturing). Recently, the emergence of LLMs has revolutionized various fields by introducing advanced semantic reasoning and real-time planning capabilities. This paper proposes the integration of LLMs with aerial additive manufacturing to assist with the planning and execution of construction tasks, granting greater flexibility and enabling a feed-back based design and construction system. Using the semantic understanding and adaptability of LLMs, we can overcome the limitations of drone based systems by dynamically generating and adapting building plans on site, ensuring efficient and accurate construction even in constrained environments. Our system is able to design and build structures given only a semantic prompt and has shown success in understanding the spatial environment despite tight planning constraints. Our method's feedback system enables replanning using the LLM if the manufacturing process encounters unforeseen errors, without requiring complicated heuristics or evaluation functions. Combining the semantic planning with automatic error correction, our system achieved a 90% build accuracy, converting simple text prompts to build structures.
Manufacturing processes are inherently dynamic and uncertain, with varying parameters and nonlinear behaviors, making robust control essential for maintaining quality and reliability. Traditional control methods often fail under these conditions due to their reactive nature. Model Predictive Control (MPC) has emerged as a more advanced framework, leveraging process models to predict future states and optimize control actions. However, MPC relies on simplified models that often fail to capture complex dynamics, and it struggles with accurate state estimation and handling the propagation of uncertainty in manufacturing environments. Machine learning (ML) has been introduced to enhance MPC by modeling nonlinear dynamics and learning latent representations that support predictive modeling, state estimation, and optimization. Yet existing ML-driven MPC approaches remain deterministic and correlation-focused, motivating the exploration of generative. Generative ML offers new opportunities by learning data distributions, capturing hidden patterns, and inherently managing uncertainty, thereby complementing MPC. This review highlights five representative methods and examines how each has been integrated into MPC components, including predictive modeling, state estimation, and optimization. By synthesizing these cases, we outline the common ways generative ML can systematically enhance MPC and provide a framework for understanding its potential in diverse manufacturing processes. We identify key research gaps, propose future directions, and use a representative case to illustrate how generative ML-driven MPC can extend broadly across manufacturing. Taken together, this review positions generative ML not as an incremental add-on but as a transformative approach to reshape predictive control for next-generation manufacturing systems.
Pedro F. Gil, Vitali Brack, Tristan Schuler
et al.
Stellarator coils are known for their complexity and departure from planarity, along with tight manufacturing tolerances in order to achieve the target magnetic field accuracy. These requirements can lead to increased costs and delays in assembly; failure to meet them can compromise the stellarator's performance. Small-scale experiments offer opportunities to develop and benchmark stellarator coil design and evaluation methods more quickly and at lower budget. In this work, we analyze precise 3D scans of the manufacturing deviations of two 3D-printed coil frames (steel, Ti alloy) and one CNC-machined coil frame (Al alloy), as part of assessing these approaches to fabricating high-temperature superconducting (HTS) coils for a tabletop stellarator. The deviations are measured along the coil length, then modeled using Gaussian processes to extract characteristic length scales. Finally a statistical study of field accuracy is performed using relevant experimental parameters. We conclude that the manufacturing perturbations along the winding path from CNC-machining are almost an order of magnitude lower than those from Additive Manufacturing. Together with high overall fabrication accuracy, this allows for higher magnetic field precision and an improved assembly process.
T. Q. D. Pham, K. D. Tran, Khanh T. P. Nguyen
et al.
As global industries transition towards Industry 5.0 predictive maintenance PM remains crucial for cost effective operations resilience and minimizing downtime in increasingly smart manufacturing environments In this chapter we explore how the integration of Federated Learning FL and blockchain BC technologies enhances the prediction of machinerys Remaining Useful Life RUL within decentralized and human centric industrial ecosystems Traditional centralized data approaches raise concerns over privacy security and scalability especially as Artificial intelligence AI driven smart manufacturing becomes more prevalent This chapter leverages FL to enable localized model training across multiple sites while utilizing BC to ensure trust transparency and data integrity across the network This BC integrated FL framework optimizes RUL predictions enhances data privacy and security establishes transparency and promotes collaboration in decentralized manufacturing It addresses key challenges such as maintaining privacy and security ensuring transparency and fairness and incentivizing participation in decentralized networks Experimental validation using the NASA CMAPSS dataset demonstrates the model effectiveness in real world scenarios and we extend our findings to the broader research community through open source code on GitHub inviting collaborative development to drive innovation in Industry 5.0
Diego Alvarado-Maldonado, Blair Johnston, Cameron J. Brown
Abundant and diverse data on medicines manufacturing and other lifecycle components has been made easily accessible in the last decades. However, a significant proportion of this information is characterised by not being tabulated and usable for machine learning purposes. Thus, natural language processing tools have been used to build databases in domains such as biomedical and chemical to address this limitation. This has allowed the development of artificial intelligence applications, which have improved drug discovery and treatments. In the pharmaceutical manufacturing context, some initiatives and datasets for primary processing can be found, but the manufacturing of drug products is an area which is still lacking, to the best of our knowledge. This works aims to explore and adapt NLP tools used in other domains to extract information on both primary and secondary manufacturing, employing patents as the main source of data. Thus, two independent, but complementary, models were developed comprising a method to select fragments of text that contain manufacturing data, and a named entity recognition system that enables extracting information on operations, materials, and conditions of a process. For the first model, the identification of relevant sections was achieved using an unsupervised approach combining Latent Dirichlet Allocation and k-Means clustering. The performance of this model measured as a Cohen's kappa between model output and manual revision was higher than 90%. NER model consisted of a deep neural network, and an f1-score micro average of 84.2% was obtained which is comparable to other works. Some considerations for these tools to be used in data extraction are discussed throughout this document.
Although Digital Twin is actively deployed in manufacturing, its human-centric counterpart - Human Digital Twin (HDT) is understudied, especially in job-shop production with high task variability and manual labor. HDT applications like ergonomic posture monitoring, fatigue prediction and health-based task assignment offer benefits to industries in emerging economies. However, poor digital maturity, lack of awareness and doubts about use-case applicability hinder adoption. This study provides a strategic prioritization framework to aid human-centric digital evolution in labor-intensive industries for guiding the selection of HDT applications delivering the highest value with the lowest implementation threshold. An integrated Fuzzy AHP-TOPSIS approach evaluates the use-cases based on criteria like implementation cost, technological maturity, scalability. These criteria and use-cases were identified based on input from a five-member expert panel and verified for consistency (CR < 0.1). Analysis shows posture monitoring and fatigue prediction as most influential and practicable, especially in semi-digital environments. Strengths include compliance with Industry 5.0 principles incorporating technology and human factors. Lack of field validation and subjective knowledge pose drawbacks. Future work should include simulation-based validation and pilot tests on real job-shop settings. Ultimately, the research offers a decision-support system helping industries balance innovativeness and practicability in early stage of HDT adoption.
The application of predictive and prescriptive maintenance procedures in industries is revolutionizing mainstream manufacturing by cutting down on time loss and waste of resources. Reactive maintenance and preventive strategies are some of the traditional maintenance management techniques that tend to cause inefficiency in the systems, high operational costs and some failures. This paper uses data from breakdown analysis in the development of predictive maintenance models and prescriptive decision systems. A methodology is used that incorporates predictive analytics based on individual machine learning with the knowledge of the failure patterns. The analysis of historical breakdown records allows predictive models to achieve higher accuracy in forecasting potential failures by identifying key failure trends. The prescriptive maintenance program provides information regarding the best course of action to be taken, minimizing operational disruptions and downtimes. As means of testing the efficiency of the proposed concept, experiments were conducted on real-world industrial datasets. The implications of this are lower number of unplanned maintenance interventions, increased efficiency, and reduced costs. This paper adds to the literature on predictive and prescriptive maintenance as it highlights how historical breakdown information can enhance the predictive analysis while giving suggestions concerning industrial maintenance management. Further research on deep learning algorithms and real-time integration of the sensors have potential to improve maintenance processes.
Syed Fouzan Iftekar, Abdul Aabid, Nor Aiman Sukindar
et al.
Abstract The high costs associated with metal additive manufacturing methods including expensive feedstock, energy-intensive lasers, and controlled environments have limited their widespread adoption in industries like aerospace and automotive, despite powder bed fusion success in producing intricate and high-precision components. As a cost-effective alternative, material extrusion 3D printing enables the fabrication of metal-polymer composites using simpler equipment. However, challenges remain in optimizing post-processing parameters to enhance mechanical performance and microstructural integrity. This study focuses on improving the post-processing of copper-filled PLA parts fabricated with an Artillery Sidewinder X1 material extrusion printer. A Taguchi design of experiments approach using an L8 orthogonal array was employed to investigate the effects of debinding time, sintering time, and layer thickness. Results showed that shorter debinding compromised structural integrity in 25% of samples, while optimized settings achieved a 30.59% shrinkage and a 12.5% hardness increase. These findings highlight the significance of proper thermal post-processing in controlling dimensional changes and improving part quality.
Materials of engineering and construction. Mechanics of materials
Dario Atzori, Claudia Bassano, Edoardo Rossi
et al.
The European Union promotes decarbonization in energy-intensive industries like glass manufacturing. Collaboration between industry and researchers focuses on reducing CO<sub>2</sub> emissions through hydrogen (H<sub>2</sub>) integration as a natural gas substitute. However, to the best of the authors’ knowledge, no updated real-world case studies are available in the literature that consider the on-site implementation of an electrolyzer for autonomous hydrogen production capable of meeting the needs of a glass manufacturing plant within current technological constraints. This study examines a representative hollow glass plant and develops various decarbonization scenarios through detailed process simulations in Aspen Plus. The models provide consistent mass and energy balances, enabling the quantification of energy demand and key cost drivers associated with H<sub>2</sub> integration. These results form the basis for a scenario-specific techno-economic assessment, including both on-grid and off-grid configurations. Subsequently, the analysis estimates the levelized costs of hydrogen (LCOH) for each scenario and compares them to current and projected benchmarks. The study also highlights ongoing research projects and technological advancements in the transition from natural gas to H<sub>2</sub> in the glass sector. Finally, potential barriers to large-scale implementation are discussed, along with policy and infrastructure recommendations to foster industrial adoption. These findings suggest that hybrid configurations represent the most promising path toward industrial H<sub>2</sub> adoption in glass manufacturing.
Vishwas Deep Joshi, Medha Sharma, Lenka Čepová
et al.
Abstract This paper introduces a novel two-step generalized parametric approach for addressing Fuzzy Multi-Objective Transportation Problems (FMOTPs), commonly encountered in logistics and transportation systems when essential parameters—such as supply, demand, and transportation costs—are uncertain. Driven by the necessity for resilient and flexible decision-making amidst uncertainty, the method employs Triangular Fuzzy Numbers (TFNs) and an accuracy parameter μ ∈ [0,1] to turn fuzzy data into precise equivalents through parametric transformation. Initially, imprecise input data are methodically converted into a sequence of Crisp Multi-Objective Transportation Problems (CMOTPs). In the subsequent phase, these CMOTPs are addressed by Fuzzy Linear Programming (FLP), and the most equitable solution at each μ-level is determined by its Euclidean distance from the fuzzy ideal solution. The suggested method is tested by numerical case studies and compared with current models—such as Nomani’s approach, fuzzy DEA, and Grey Relational Analysis (GRA)—showing enhanced performance in optimality proximity, solution stability, and ranking accuracy. This research has practical applications, including improved managerial capacity to manage uncertainty, reconcile trade-offs among cost, time, and service quality, and execute robust transportation strategies in fluctuating environments. The model’s scalability and openness make it suited for integration into enterprise logistics systems across industries such as manufacturing, retail, distribution, and e-commerce. The study offers a systematic and computationally efficient framework that enhances both theoretical comprehension and practical implementation of fuzzy optimization in multi-objective transportation planning.
Shivashankar Hiremath, Kevin Amith Mathias, Tae-Won Kim
Abstract Soft gripping technologies have attracted significant attention due to their potential to advance mechatronics and human-machine interaction. Among various soft actuation methods, 3D-printed, pneumatic-based soft actuators stand out for their versatility and adaptability. This study investigates a unique semi-oval-shaped groove design, featuring a hollow 3D-printed structure made from soft material, and analyses its performance under varying pneumatic pressures. Soft actuators with different groove geometries were fabricated using material extrusion techniques. Their compliance, deformation behavior, and gripping capabilities were evaluated through experimental testing. The outcome shows that the actuator exhibits increased deflection with rising pneumatic pressure, highlighting its high sensitivity. At an applied pressure of 5 bar, a maximum deformation of 72.0 mm was recorded. Furthermore, numerical simulations closely matched the experimental results within a certain pressure range. The actuator’s ability to bend and conform to objects of various shapes and sizes demonstrates its excellent compliance and adaptability. These findings confirm that an optimal pressure level enables reliable object gripping using a Thermoplastic polyurethane-based soft actuator. As soft gripping technologies advance, such actuators are poised to play a crucial role in revolutionizing industries like manufacturing, logistics, and robotics by offering innovative solutions for diverse gripping challenges.
Abstract Three-dimensional printing (3DP) technology has gained an increased popularity in making prototypes in all types of manufacturing industries including automotive, healthcare, aerospace, sports, textile, apparel and fashion industry etc. Researchers, textile technologists, fashion designers, manufacturers and retailers have been working on adopting 3DP technology in their respective fields since the last decade. 3DP has been proved highly beneficial in reducing manufacturing time and production cost significantly regarding fiber reinforced composites fabrication. However, the application of this technology is still at niche while it comes to manufacturing everyday clothing. The purpose of this paper is to provide an integrative review of the existing literature to identify current state-of-the-art 3DP methods, materials, application in the textile and fashion industries. Further, the review considers the future of this technology with regard to sustainability, novelty, complexity in fashion related fields.
Application of lean manufacturing (LM) principles within the manufacturing industry extends back several decades to drive efficiency and reduce waste across complex production lines. The advent of the Fourth Industrial Revolution, known as “Industry 4.0” technology is transforming the LM processes to promote the manufacturing industry. Additive Manufacturing (AM) has been identified as a technology with great potential to create a longstanding impact on the manufacturing world and is a core component of the Fourth Industrial Revolution. Many successful industries have achieved outstanding performance by integrating LM principles at the core of their corporate transformation. Of recent, AM and 3D printing has been identified as a technology that is revolutionizing LM principles in the following ways: easier prototyping, easily customize products, shorter lead times, local on-demand manufacturing, and lower cost production. Despite the exceptional success of LM principles across different industries and sectors, still many companies LM journeys fail due to many obvious reasons. The emergence of Industry 4.0 digital technologies has created an enabling environment for different manufacturing industries currently using LM principles to identify the need to embrace or add digital technologies to their lean manufacturing transformation journey. The intersections between LM and digital technologies are termed as “Digital Lean” or “Lean 4.0”. There are limited studies and literature gaps on lean manufacturing within the context of AM industry. More so, there is no study that examines the application of digital lean manufacturing in an AM industry. The paper presents a review of the concept of lean manufacturing principles and how it is revolutionizing the AM industry. This paper investigates the concept of digital lean manufacturing and its future potential impact in the AM industry. Finally, this paper develops a digital lean manufacturing system or tools considered suitable for the AM industry.