Advanced Manufacturing with Renewable and Bio-based Materials: AI/ML workflows and Process Optimization

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.

💡 Research Summary

The paper presents a comprehensive framework that integrates renewable bio‑based polymers with advanced additive manufacturing (AM) techniques and AI/ML‑driven self‑driving laboratories (SDL) to accelerate the development of sustainable, high‑performance manufacturing processes. It begins by outlining the limitations of conventional petro‑chemical polymers—chiefly their poor recyclability and environmental impact—and argues that bio‑derived polymers such as polylactic acid (PLA), polyhydroxyalkanoates (PHAs), cellulose, chitin, and natural fiber composites offer a pathway toward a circular economy.

A detailed review of AM technologies follows, comparing fused deposition modeling (FDM), stereolithography (SLA), digital light processing (DLP), selective laser sintering (SLS), PolyJet, and direct ink writing (DIW) in terms of accuracy, material compatibility, surface finish, speed, and cost. The authors emphasize that while AM has already transformed metal and ceramic manufacturing, its application to polymers—especially bio‑based ones—requires new formulations, rheological control, and hybrid material strategies (e.g., nanocellulose, graphene oxide, or chitin nanowhiskers as fillers).

The manuscript then situates the discussion within the evolution from Industry 4.0 to Industry 5.0. Whereas Industry 4.0 focuses on digitalization, IoT, and autonomous systems, Industry 5.0 adds a human‑centric layer, ethical AI, and a net‑positive sustainability mandate. The authors argue that bio‑based AM, coupled with AI, is ideally positioned to meet these goals by enabling on‑demand, low‑waste production and by empowering human experts to guide AI‑generated hypotheses.

The core contribution is a multi‑layered AI/ML workflow that combines first‑principles modeling (DFT, molecular dynamics) with data‑driven machine learning (graph neural networks, support vector machines) and reinforcement learning (RL/DRL). The workflow is organized into three tiers:

1. Data Layer – aggregates experimental measurements, high‑throughput simulations, sensor streams, and hypotheses generated by large language models (LLMs).
2. Model Layer – builds predictive models for material properties, process windows, and defect formation; uses RL/DRL to optimize printing trajectories, laser power, temperature, and feed rates.
3. Control Layer – implements a digital twin that closes the loop with real‑time feedback, automatically adjusting machine parameters during the build.

The SDL component automates experimental design through Bayesian optimization and genetic algorithms, rapidly exploring compositional space (e.g., PLA/PHAs blends, nanocellulose‑reinforced resins) and feeding results back into the models. In‑situ characterization (optical, thermal, mechanical sensors) monitors layer‑by‑layer shrinkage, cure degree, and defect emergence, enabling on‑the‑fly correction of process parameters.

Materials‑specific insights include:

• PLA offers ease of processing but limited thermal stability; blending with high‑molecular‑weight polymers or adding nanofillers (graphene oxide, nanocellulose) can raise tensile strength and heat deflection temperature.
• PHAs provide superior biodegradability but suffer from narrow processing windows; they benefit from co‑polymerization or plasticizer addition.
• Natural fibers (hemp, bamboo, miscanthus) act as reinforcement in FDM or extrusion‑based processes, improving modulus and impact resistance, yet require moisture control and surface treatment to ensure interfacial adhesion.
• Hydrogel systems (alginate, gelatin, carrageenan) are suitable for DIW and SLA/DLP when engineered for shear‑thinning and sufficient storage modulus, opening avenues for biomedical and food‑contact applications.

Economic and environmental analyses suggest that on‑demand AM can cut inventory costs by up to 30 % and reduce waste generation by 40 % or more. Energy consumption is projected to be 20‑35 % lower than conventional injection molding or extrusion, translating into comparable reductions in CO₂ emissions.

In conclusion, the authors demonstrate that integrating AI/ML‑guided design, autonomous experimentation, and digital‑twin‑based control creates a powerful “self‑correcting” manufacturing ecosystem. This ecosystem not only overcomes the intrinsic material limitations of bio‑based polymers but also aligns with Industry 5.0’s human‑centric, sustainable vision. Future work is identified in standardizing large‑scale data sets, improving model transferability across material families, refining human‑AI collaboration interfaces, and shaping policy frameworks that support the adoption of these technologies.