Hasil untuk "Manufactures"

K. Drexler

R. Hayes, S. Wheelwright, K. Clark

Melissa A. Schilling, H. Steensma

A. Bernard, Charles I. Jones

Kunal Kothari, R. Radhakrishnan, N. Wereley

T. Melton

Jan Olhager

R. Wauthlé, J. van der Stok, S. Amin Yavari et al.

L. Camarinha-Matos, H. Afsarmanesh, N. Galeano et al.

Guoqin Tang, Qingxuan Jia, Gang Chen et al.

Vision-language model (VLM) shows promise for high-level planning in smart manufacturing, yet their deployment in dynamic workcells faces two critical challenges: (1) stateless operation, they cannot persistently track out-of-view states, causing world-state drift; and (2) opaque reasoning, failures are difficult to diagnose, leading to costly blind retries. This paper presents VLM-DEWM, a cognitive architecture that decouples VLM reasoning from world-state management through a persistent, queryable Dynamic External World Model (DEWM). Each VLM decision is structured into an Externalizable Reasoning Trace (ERT), comprising action proposal, world belief, and causal assumption, which is validated against DEWM before execution. When failures occur, discrepancy analysis between predicted and observed states enables targeted recovery instead of global replanning. We evaluate VLM-DEWM on multi-station assembly, large-scale facility exploration, and real-robot recovery under induced failures. Compared to baseline memory-augmented VLM systems, VLM DEWM improves state-tracking accuracy from 56% to 93%, increases recovery success rate from below 5% to 95%, and significantly reduces computational overhead through structured memory. These results establish VLM-DEWM as a verifiable and resilient solution for long-horizon robotic operations in dynamic manufacturing environments.

F. Castellacci

V. Naidoo

Sheng Yang, Y. Zhao

Felix Wechsler, Viola Sgarminato, Riccardo Rizzo et al.

Tomographic Volumetric Additive Manufacturing (TVAM) is a light-based 3D printing technique capable of producing centimeter-scale objects within seconds. A key challenge lies in the calculation of projection patterns under non-standard conditions, such as the presence of occlusions and materials with diverse optical properties, including varying refractive indices or scattering surfaces. This work focuses on demonstrating a wide variety of overprinting scenarios. First, utilizing a telecentric laser-based TVAM (LaserTVAM), we demonstrate the printing of a microfluidic perfusion system with biocompatible resins on existing nozzles for potential biomedical applications. In a subsequent demonstration, embedded spheres within the bio-resins are localized inside this perfusion system, optimized into specific patterns, and successfully connected to the nozzles via printed channels in less than three minutes. As a final LaserTVAM example, we print gears on a glossy metal rod, taking into account the scattered rays from the rod's surface. Using a non-telecentric LED-based TVAM (LEDTVAM), we then overprint engravings onto an existing LED placed in the resin. With an additional printed lens on this LED, we can project those engravings onto a screen. In a similar application with the same setup, we print microlenses on a glass tube filled with water, allowing us to image samples embedded within the glass tubes. Based on a differentiable physically-based ray optical approach, we are able to optimize all these scenarios within our existing open-source framework called Dr.TVAM. This framework enables the optimization of high-quality projections for both LaserTVAM and LEDTVAM setups within minutes, as well as lower-quality projections within seconds, outperforming existing solutions in terms of speed, flexibility, and quality.

Arkady V. Krasheninnikov, Yung-Chang Lin, Kazu Suenaga

Recent intensive research on two-dimensional materials (2DMs) rekindle the interest in the intercalation of various atoms and molecules into layered compounds as a tool to manufacture 2DMs and tune their optoelectronic, magnetic and catalytic properties. Intercalation into free-standing bilayer graphene (BLG) has received special attention, as graphene is stable, chemically inert and enables one to study the atomic structure of the intercalated 2DM using high-resolution transmission electron microscopy. It was also discovered that the protecting action of graphene sheets makes it possible to not only stabilize the encapsulated single sheets of marginally stable layered materials, but also synthesize completely new 2D systems inside BLG, which in comparison to the bulk graphite allows for easier intercalation and much larger increase in the inter-layer separation of the sheets. In this review, we summarize the recent progress in this area, with a special focus on new materials created inside BLG. We compare the experimental findings to the theoretical predictions, pay special attention to the discrepancies and outline the challenges in the field. Finally, we discuss unique opportunities offered by the intercalation into 2DMs beyond graphene and their heterostructures.

Shiqing Qiu

In the era of smart manufacturing, predictive maintenance (PdM) plays a pivotal role in improving equipment reliability and reducing operating costs. In this paper, we propose a novel Markov Decision Process (MDP) framework that integrates advanced soft computing techniques - Fourier Neural Operator (FNO), Denoising Autoencoder (DAE), Graph Neural Network (GNN), and Proximal Policy Optimisation (PPO) - to address the multidimensional challenges of predictive maintenance in complex manufacturing systems. Specifically, the proposed framework innovatively combines the powerful frequency-domain representation capability of FNOs to capture high-dimensional temporal patterns; DAEs to achieve robust, noise-resistant latent state embedding from complex non-Gaussian sensor data; and GNNs to accurately represent inter-device dependencies for coordinated system-wide maintenance decisions. Furthermore, by exploiting PPO, the framework ensures stable and efficient optimisation of long-term maintenance strategies to effectively handle uncertainty and non-stationary dynamics. Experimental validation demonstrates that the approach significantly outperforms multiple deep learning baseline models with up to 13% cost reduction, as well as strong convergence and inter-module synergy. The framework has considerable industrial potential to effectively reduce downtime and operating expenses through data-driven strategies.

Sakhinana Sagar Srinivas, Shivam Gupta, Venkataramana Runkana

Recent advances in generative AI have accelerated the discovery of novel chemicals and materials. However, scaling these discoveries to industrial production remains a major bottleneck due to the synthesis gap -- the need to develop entirely new manufacturing processes. This challenge requires detailed engineering blueprints: PFDs for equipment layouts and material/energy flows, and PIDs for process plant operations. Current AI systems cannot yet reliably generate these critical engineering schematics, creating a fundamental obstacle to manufacturing scale-up of novel discoveries. We present a closed-loop, physics-aware framework for automated generation of industrially viable PFDs and PIDs. The framework integrates three key components: (1) domain-specialized small language models (SLMs) trained for auto-generation of PFDs and PIDs, (2) a hierarchical knowledge graph containing process flow and instrumentation descriptions for 1,020+ chemicals for Graph Retrieval-Augmented Generation (GRAG), and (3) an open-source chemical process simulator for modeling, simulation, optimization, and analysis of novel chemical processes. The SLMs are trained through a multi-stage pipeline on synthetic datasets, with process simulator-in-the-loop validation ensuring feasibility. To enhance computational efficiency, the framework implements structural pruning (width and depth) guided by importance heuristics to reduce language model size while preserving accuracy, followed by advanced inference optimizations including FlashAttention, Lookahead Decoding, PagedAttention with KV-cache quantization, and Test-Time Inference Scaling. Experimental results demonstrate that our framework generates simulator-validated process descriptions with high fidelity.

Siddharth Singh, Tian Yu, Qing Chang et al.

Industrial robots are widely used in diverse manufacturing environments. Nonetheless, how to enable robots to automatically plan trajectories for changing tasks presents a considerable challenge. Further complexities arise when robots operate within work cells alongside machines, humans, or other robots. This paper introduces a multi-level hybrid robot motion planning method combining a task space Reinforcement Learning-based Learning from Demonstration (RL-LfD) agent and a joint-space based Deep Reinforcement Learning (DRL) based agent. A higher level agent learns to switch between the two agents to enable feasible and smooth motion. The feasibility is computed by incorporating reachability, joint limits, manipulability, and collision risks of the robot in the given environment. Therefore, the derived hybrid motion planning policy generates a feasible trajectory that adheres to task constraints. The effectiveness of the method is validated through sim ulated robotic scenarios and in a real-world setup.

Eristy Minda Utami, Gusni Gusni, Reva Yuliani et al.

The growing impact of technology has attracted a greater number of people, especially Generation Z, to financial markets. Enhancing financial literacy and attitudes is essential for promoting informed investing choices. This research analyzes the impact of financial knowledge and social influence on Generation Z's investment aspirations, while accounting for the mediating functions of financial literacy and attitude. This research seeks to elucidate the mediating role of financial literacy and attitude in the interaction among financial knowledge, social influence, and investment intentions. A survey methodology was used with a sample size of 200 students enrolled in capital market courses at Widyatama University. The results demonstrate that financial knowledge and attitudes substantially affect investing intentions among Generation Z. Furthermore, financial acumen and social influence indirectly impact investing intentions via these mediating variables. These findings emphasize the need of thorough financial education to develop superior investing strategies among young individuals. Theoretical implications indicate that augmenting financial awareness and attitudes may significantly enhance investment decision-making among Generation Z.

Daohai Zhang, Yang Lu, Haoran Li

ABSTRACT As a key transmission component, the gear failure (such as broken teeth, wear, pitting, etc.) of the gearbox can easily lead to equipment shutdown, production interruption and even cause safety accidents, which is extremely harmful. The existing fault diagnosis methods have obvious shortcomings: the traditional BP neural network has weak global optimisation ability and slow convergence; the BP model optimised by traditional particle swarm optimisation (PSO) is limited in diagnostic accuracy because PSO is easy to fall into local optimum. In this paper, the data of four working conditions of gears are collected. After preprocessing, an improved PSO algorithm combining weight index change and particle disturbance strategy is proposed to optimise the BP neural network to construct the diagnosis model. Experiments show that the accuracy of this fault diagnosis model is 29% higher than that of the traditional BP model. It provides an efficient and reliable solution for mechanical fault diagnosis, which is of great significance for reducing losses and ensuring safety.