Hasil untuk "Industrial electrochemistry"

M. Wollschlaeger, T. Sauter, J. Jasperneite

Zhetao Li, Jiawen Kang, Rong Yu et al.

R. McCreery

E. Horn, Brandon R. Rosen, P. Baran

While preparative electrolysis of organic molecules has been an active area of research over the past century, modern synthetic chemists have generally been reluctant to adopt this technology. In fact, electrochemical methods possess many benefits over traditional reagent-based transformations, such as high functional group tolerance, mild conditions, and innate scalability and sustainability. In this Outlook we highlight illustrative examples of electrochemical reactions in the context of the synthesis of complex molecules, showcasing the intrinsic benefits of electrochemical reactions versus traditional reagent-based approaches. Our hope is that this field will soon see widespread adoption in the synthetic community.

Beibei Li, Yuhao Wu, Jiarui Song et al.

The rapid convergence of legacy industrial infrastructures with intelligent networking and computing technologies (e.g., 5G, software-defined networking, and artificial intelligence), have dramatically increased the attack surface of industrial cyber–physical systems (CPSs). However, withstanding cyber threats to such large-scale, complex, and heterogeneous industrial CPSs has been extremely challenging, due to the insufficiency of high-quality attack examples. In this article, we propose a novel federated deep learning scheme, named DeepFed, to detect cyber threats against industrial CPSs. Specifically, we first design a new deep learning-based intrusion detection model for industrial CPSs, by making use of a convolutional neural network and a gated recurrent unit. Second, we develop a federated learning framework, allowing multiple industrial CPSs to collectively build a comprehensive intrusion detection model in a privacy-preserving way. Further, a Paillier cryptosystem-based secure communication protocol is crafted to preserve the security and privacy of model parameters through the training process. Extensive experiments on a real industrial CPS dataset demonstrate the high effectiveness of the proposed DeepFed scheme in detecting various types of cyber threats to industrial CPSs and the superiorities over state-of-the-art schemes.

P. Aghion, M. Dewatripont, L. Du et al.

This paper argues that sectoral policy aimed at targeting production activities to one particular sector, can enhance growth and efficiency if it is made competition-friendly. First, we develop a model in which two firms can operate either in the same (higher growth) sector or in different sectors. To escape competition, firms can either innovate vertically or dif-ferentiate by choosing a different sector from their competitor By forcing firms to operate in the same sector, sectoral policy induces them to innovate ”vertically” rather than differentiate in order to escape competition with the other firm. The model predicts that sectoral targeting enhances average growth and productivity more when competition is more intense within a sector and when competition is preserved by policy. In the second part of the paper, we test these predictions using a panel of medium and large Chinese enterprises for the period 1998 through 2007. Our empirical results suggest that if subsidies are allocated to competitive sectors (as measured by the Lerner index) or allocated in such a way as to preserve or increase competition, then the net impacts of subsidies, tax holidays, and tariffs on total factor productivity levels or growth become positive and significant. We address the potential endogeneity of targeting and competition by using variations in targeting across Chinese cities that are exogenous to the individual firm.

Lin He, Florian Weniger, H. Neumann et al.

S. Petrovic

Sae Young Moon, Myeongjun Erik Jang, Haoyan Luo et al.

Topic modeling has extensive applications in text mining and data analysis across various industrial sectors. Although the concept of granularity holds significant value for business applications by providing deeper insights, the capability of topic modeling methods to produce granular topics has not been thoroughly explored. In this context, this paper introduces a framework called TIDE, which primarily provides a novel granular topic modeling method based on large language models (LLMs) as a core feature, along with other useful functionalities for business applications, such as summarizing long documents, topic parenting, and distillation. Through extensive experiments on a variety of public and real-world business datasets, we demonstrate that TIDE's topic modeling approach outperforms modern topic modeling methods, and our auxiliary components provide valuable support for dealing with industrial business scenarios. The TIDE framework is currently undergoing the process of being open sourced.

Pengfei Yue, Xiaokang Jiang, Yilin Lu et al.

Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manual thresholds, while supervised methods overfit due to scarce, imbalanced data. Both suffer from the "One Anomaly Class, One Model" limitation. To address this, we propose Referring Industrial Anomaly Segmentation (RIAS), a paradigm leveraging language to guide detection. RIAS generates precise masks from text descriptions without manual thresholds and uses universal prompts to detect diverse anomalies with a single model. We introduce the MVTec-Ref dataset to support this, designed with diverse referring expressions and focusing on anomaly patterns, notably with 95% small anomalies. We also propose the Dual Query Token with Mask Group Transformer (DQFormer) benchmark, enhanced by Language-Gated Multi-Level Aggregation (LMA) to improve multi-scale segmentation. Unlike traditional methods using redundant queries, DQFormer employs only "Anomaly" and "Background" tokens for efficient visual-textual integration. Experiments demonstrate RIAS's effectiveness in advancing IAD toward open-set capabilities. Code: https://github.com/swagger-coder/RIAS-MVTec-Ref.

Mari Ashiga, Vardan Voskanyan, Fateme Dinmohammadi et al.

Recent advancements in Large Language Models (LLMs) for code optimization have enabled industrial platforms to automate software performance engineering at unprecedented scale and speed. Yet, organizations in regulated industries face strict constraints on which LLMs they can use - many cannot utilize commercial models due to data privacy regulations and compliance requirements, creating a significant challenge for achieving high-quality code optimization while maintaining cost-effectiveness. We address this by implementing a Mixture-of-Agents (MoA) approach that directly synthesizes code from multiple specialized LLMs, comparing it against TurinTech AI's vanilla Genetic Algorithm (GA)-based ensemble system and individual LLM optimizers using real-world industrial codebases. Our key contributions include: (1) First MoA application to industrial code optimization using real-world codebases; (2) Empirical evidence that MoA excels with open-source models, achieving 14.3% to 22.2% cost savings and 28.6% to 32.2% faster optimization times for regulated environments; (3) Deployment guidelines demonstrating GA's advantage with commercial models while both ensembles outperform individual LLMs; and (4) Real-world validation across 50 code snippets and seven LLM combinations, generating over 8,700 variants, addresses gaps in industrial LLM ensemble evaluation. This provides actionable guidance for organizations balancing regulatory compliance with optimization performance in production environments.

Paul Koch, Marian Schlüter, Jörg Krüger

We present MVIP, a novel dataset for multi-modal and multi-view application-oriented industrial part recognition. Here we are the first to combine a calibrated RGBD multi-view dataset with additional object context such as physical properties, natural language, and super-classes. The current portfolio of available datasets offers a wide range of representations to design and benchmark related methods. In contrast to existing classification challenges, industrial recognition applications offer controlled multi-modal environments but at the same time have different problems than traditional 2D/3D classification challenges. Frequently, industrial applications must deal with a small amount or increased number of training data, visually similar parts, and varying object sizes, while requiring a robust near 100% top 5 accuracy under cost and time constraints. Current methods tackle such challenges individually, but direct adoption of these methods within industrial applications is complex and requires further research. Our main goal with MVIP is to study and push transferability of various state-of-the-art methods within related downstream tasks towards an efficient deployment of industrial classifiers. Additionally, we intend to push with MVIP research regarding several modality fusion topics, (automated) synthetic data generation, and complex data sampling -- combined in a single application-oriented benchmark.

Tianle Yang, Luyao Chang, Jiadong Yan et al.

As industrial products become abundant and sophisticated, visual industrial defect detection receives much attention, including two-dimensional and three-dimensional visual feature modeling. Traditional methods use statistical analysis, abnormal data synthesis modeling, and generation-based models to separate product defect features and complete defect detection. Recently, the emergence of foundation models has brought visual and textual semantic prior knowledge. Many methods are based on foundation models (FM) to improve the accuracy of detection, but at the same time, increase model complexity and slow down inference speed. Some FM-based methods have begun to explore lightweight modeling ways, which have gradually attracted attention and deserve to be systematically analyzed. In this paper, we conduct a systematic survey with comparisons and discussions of foundation model methods from different aspects and briefly review non-foundation model (NFM) methods recently published. Furthermore, we discuss the differences between FM and NFM methods from training objectives, model structure and scale, model performance, and potential directions for future exploration. Through comparison, we find FM methods are more suitable for few-shot and zero-shot learning, which are more in line with actual industrial application scenarios and worthy of in-depth research.

Francesco Aurelio Pironti, Angelo Furfaro, Francesco Blefari et al.

The security of Industrial Control Systems (ICSs) is critical to ensuring the safety of industrial processes and personnel. The rapid adoption of Industrial Internet of Things (IIoT) technologies has expanded system functionality but also increased the attack surface, exposing ICSs to a growing range of cyber threats. Honeypots provide a means to detect and analyze such threats by emulating target systems and capturing attacker behavior. However, traditional ICS honeypots, often limited to software-based simulations of a single Programmable Logic Controller (PLC), lack the realism required to engage sophisticated adversaries. In this work, we introduce a modular honeynet framework named ICSLure. The framework has been designed to emulate realistic ICS environments. Our approach integrates physical PLCs interacting with live data sources via industrial protocols such as Modbus and Profinet RTU, along with virtualized network components including routers, switches, and Remote Terminal Units (RTUs). The system incorporates comprehensive monitoring capabilities to collect detailed logs of attacker interactions. We demonstrate that our framework enables coherent and high-fidelity emulation of real-world industrial plants. This high-interaction environment significantly enhances the quality of threat data collected and supports advanced analysis of ICS-specific attack strategies, contributing to more effective detection and mitigation techniques.

Bowen Zheng

To address the challenges of 3D modeling and structural simulation in industrial environment, such as the difficulty of equipment deployment, and the difficulty of balancing accuracy and real-time performance, this paper proposes an integrated workflow, which integrates high-fidelity 3D reconstruction based on monocular video, finite element simulation analysis, and mixed reality visual display, aiming to build an interactive digital twin system for industrial inspection, equipment maintenance and other scenes. Firstly, the Neuralangelo algorithm based on deep learning is used to reconstruct the 3D mesh model with rich details from the surround-shot video. Then, the QuadRemesh tool of Rhino is used to optimize the initial triangular mesh and generate a structured mesh suitable for finite element analysis. The optimized mesh is further discretized by HyperMesh, and the material parameter setting and stress simulation are carried out in Abaqus to obtain high-precision stress and deformation results. Finally, combined with Unity and Vuforia engine, the real-time superposition and interactive operation of simulation results in the augmented reality environment are realized, which improves users 'intuitive understanding of structural response. Experiments show that the method has good simulation efficiency and visualization effect while maintaining high geometric accuracy. It provides a practical solution for digital modeling, mechanical analysis and interactive display in complex industrial scenes, and lays a foundation for the deep integration of digital twin and mixed reality technology in industrial applications.

Jannick Stranghöner, Philipp Hartmann, Marco Braun et al.

High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and environmental uncertainty. Current robotic systems struggle to meet these demands. Manual programming is brittle and costly to adapt, while learning-based methods suffer from poor sample efficiency and unsafe exploration in contact-rich tasks. To address this, we present SHaRe-RL, a reinforcement learning framework that leverages multiple sources of prior knowledge. By (i) structuring skills into manipulation primitives, (ii) incorporating human demonstrations and online corrections, and (iii) bounding interaction forces with per-axis compliance, SHaRe-RL enables efficient and safe online learning for long-horizon, contact-rich industrial assembly tasks. Experiments on the insertion of industrial Harting connector modules with 0.2-0.4 mm clearance demonstrate that SHaRe-RL achieves reliable performance within practical time budgets. Our results show that process expertise, without requiring robotics or RL knowledge, can meaningfully contribute to learning, enabling safer, more robust, and more economically viable deployment of RL for industrial assembly.

Parul Khanna, Sameer Prabhu, Ramin Karim et al.

The construction industry is presently going through a transformation led by adopting digital technologies that leverage Artificial Intelligence (AI). These industrial AI solutions assist in various phases of the construction process, including planning, design, production and management. In particular, the production phase offers unique potential for the integration of such AI-based solutions. These AI-based solutions assist site managers, project engineers, coordinators and other key roles in making final decisions. To facilitate the decision-making process in the production phase of construction through a human-centric AI-based solution, it is important to understand the needs and challenges faced by the end users who interact with these AI-based solutions to enhance the effectiveness and usability of these systems. Without this understanding, the potential usage of these AI-based solutions may be limited. Hence, the purpose of this research study is to explore, identify and describe the key factors crucial for developing AI solutions in the construction industry. This study further identifies the correlation between these key factors. This was done by developing a demonstrator and collecting quantifiable feedback through a questionnaire targeting the end users, such as site managers and construction professionals. This research study will offer insights into developing and improving these industrial AI solutions, focusing on Human-System Interaction aspects to enhance decision support, usability, and overall AI solution adoption.

Deniz Dogan, Burkhard Hecker, Xue-Dan Hou et al.

Electrolysis is a dynamic research area in which both mature and new promising processes, such as alkaline water electrolysis and electrochemical CO2 reduction, are under enormous development pressure due to their high relevance for the energy sector. High‐throughput (HT) technologies are efficient screening platforms that can accelerate research activities and significantly shorten development times. Over the past 25 years, various HT platforms have found their way into electrochemical research. These typically have one or more major disadvantages: they are characterized by abstract experimental conditions, designed for a specific application or process, or generate insufficiently comparable data. In this publication, we present a newly developed HT test system that enables the parallel operation of 16 electrochemical bench‐scale flow cells under industry‐relevant test conditions. The specially developed modular flow cell can be operated variably in the fully automated system and allows research into the most common applications in electrochemistry for many different processes with a focus on all relevant variants of water electrolysis and electrochemical CO2 reduction. Both the HT system and the developed flow cell are designed to accelerate the generation of reliably reproducible data with high comparability in order to strengthen scientific exchange. The fully automated process control, online analysis and programmable feedback loops of the HT test system provide great potential for the design of experiment strategies. The implementation of Design of Experiment strategies will maximize the testing efficiency of this innovative research system.

Niklas Hensle, T. Smolinka

Industrial PEM water electrolysis stack designs can suffer from an unevenly distributed water amount over the cell area. This can lead to performance differences and thermal hot spots due to the lack of reactant supply and poor thermal management. Undersupplied spots could also degrade more quickly [1,2]. Especially in the water flow direction, gradients are expected due to the water consumption and gas evolution and accumulation along the supply channels. To face these issues, we built up a segmented along the channel (AtC) PEM electrolysis test cell in industrial scale for locally-resolved investigations. The cell has a length of 30 cm at 2 cm cell width with a straight parallel flow field. To minimize transverse currents the cell is divided into 10 equal segments along the channels. The main focus of our investigation is locally-resolved electrochemical impedance spectroscopy (EIS). With a shunt resistor approach, it is feasible to measure the impedance of each segment and the mean cell in parallel. Additionally, it is possible to measure the current density and temperature distribution of the anodic bipolar plate highly resolved using 120 sensors over the cell length. With this test cell we want to understand mass transport processes along the channel in industrial scale. Diffusion and mass transport overpotentials are usually dominant at high current densities. To be able to face extreme conditions and investigate possible future operation points the cell was designed up to 10 A∙cm-2 (600 A absolute) and successfully tested. Furthermore, an operation of 10 bar differential and equal pressure is possible. Figure 1 shows the cell design (a), the mean cell polarization curve of the AtC cell (60 cm²) in comparison with measurements of the same setup in our 4 cm² test cell (b) and locally-resolved high frequency resistance (HFR) free EIS at 7 A∙cm-2 (c). It is noticeable, that the here used commercially available materials do not show high mass transport limitations, neither in the 4 cm² ISE-reference cell nor in the 60 cm² AtC cell. An increase of the slope of the polarization curve towards higher current densities remains out, see Figure 1 (b). Instead of this the slope of the polarization curve is constantly decreasing. This can not only be explained by the temperature increase of the catalyst-coated membrane (CCM) due to higher heat dissipation. Using EIS, we here can detect an additional electrochemical process at low frequencies of inductive type which is increasing with increasing current density. In the locally-resolved EIS in Figure 1 (c) the inductive process (positive imaginary values) is detectable as the so called “inductive loop”. This phenomenon has a negative resistance magnitude and therefore a beneficial impact on the cell performance. Inductive Loops are discussed in several electrochemical applications, like batteries and fuel cells [3,4]. Despite this, in PEM electrolysis this process has not been discussed yet. We could show that this phenomenon is reproducible and has an important impact on the cell performance and impedance-based performance analyses when operating at current densities > 1 A∙cm-2 [5]. For diffusion analyses, the inductive loop is essential to be considered since both processes happen at similar frequencies. In Figure 1 (c) an increasing of the number of time constants at frequencies < 100 Hz is detectable towards the cell outlet (e.g. segment 9 and 10). These slow processes are most likely diffusion related. Our upcoming investigations will face locally-resolved measurements with varying structural parameters of porous transport layers (PTL) and CCMs with different anodic catalyst loadings to gain a better understanding of mass transport processes for future PEM electrolysis cells along the channel. Reference List: [1] IMMERZ, C., et al. Experimental characterization of inhomogeneity in current density and temperature distribution along a single-channel PEM water electrolysis cell. Electrochimica acta, 2018, 260. Jg., S. 582-588. [2] VERDIN, B., et al. Operando current mapping on PEM water electrolysis cells. Influence of mechanical stress. International Journal of Hydrogen Energy, 2017, 42. Jg., Nr. 41, S. 25848-25859. [3] KLOTZ, Dino. Negative capacitance or inductive loop?–A general assessment of a common low frequency impedance feature. Electrochemistry Communications, 2019, 98. Jg., S. 58-62. [4] GERLING, Christophe, et al. Experimental and Numerical Investigation of the Low-Frequency Inductive Features in Differential PEMFCs: Ionomer Humidification and Platinum Oxide Effects. Journal of The Electrochemical Society, 2023, 170. Jg., Nr. 1, S. 014504. [5] HENSLE, Niklas, et al. On the role of inductive loops at low frequencies in PEM electrolysis. Electrochemistry Communications, 2023, 155. Jg., S. 107585. Figure 1

Yanliang Chen, Chiwoo Park, Anuj Srivastava

This paper addresses the critical and challenging task of developing emulators for simulating human operational motions in industrial workplaces. We conceptualize human motion as a sequence of human body shapes and develop statistical generative models for sequences of (body) shapes of human workers. We model these sequences as a continuous-time stochastic process on a Riemannian shape manifold. This modeling is challenging due to the nonlinearity of the shape manifold, variability in execution rates across observations, infinite dimensionality of stochastic processes, and population variability within and across action classes. This paper proposes multiple solutions to these challenges, incorporating time warping for temporal alignment, Riemannian geometry for tackling nonlinearity, and Shape- and Functional-PCA for dimension reduction. It imposes a Gaussian model on the resulting Euclidean spaces, uses them to emulate random sequences in an industrial setting and evaluates them comprehensively.