Hasil untuk "Industrial electrochemistry"

Tom Maus, Stephan Frank, Tobias Glasmachers

Reinforcement learning (RL) is still rarely applied in industrial control, partly due to the difficulty of training reliable agents for real-world conditions. This work investigates how evolution strategies can support RL in such settings by introducing a continuous-control adaptation of an industrial sorting benchmark. The CMA-ES algorithm is used to generate high-quality demonstrations that warm-start RL agents. Results show that CMA-ES-guided initialization significantly improves stability and performance. Furthermore, the demonstration trajectories generated with the CMA-ES provide a strong oracle reference performance level, which is of interest in its own right. The study delivers a focused proof of concept for hybrid evolutionary-RL approaches and a basis for future, more complex industrial applications.

Guanqi Huang, Carlota Bozal-Ginesta, Alán Aspuru-Guzik

To accelerate the screening of electrocatalyst materials, it is necessary to enhance the efficiency of their performance evaluation and optimization under dynamic conditions. The activity and stability of electrocatalyst materials are two crucial metrics that are typically correlated, and thus need to be evaluated in parallel. However. assessing both activity and stability in a time-efficient, reliable and comparable manner remains a challenge. Given the rising interest in evaluating electrocatalysts under realistic fluctuating conditions, we propose an electrochemical approach that uses random sampling and Bayesian optimization to explore pulsed amperometry conditions in hydrous iridium oxides for the oxygen evolution reaction. This method provides activity and stability proxies independent of sample loading which are validated against literature data.

Yipei Wang, Jun-Hyeong Kwon, Seong-Cheol Choi et al.

In this paper, a modular cell balancing circuit based on a bidirectional flyback converter (BFC) is designed, which is equipped with a symmetrical BFC for each cell. The primary side of all BFCs is in parallel with the battery pack, and the secondary side is connected to the individual cells. Such an input-parallel output-series structure allows for bidirectional and controllable energy transfer among the cells. The control of the charging/discharging for a specific cell can be realized by adjusting the PWM signal on the primary or secondary side of the corresponding BFC. Based on this, three cell balancing strategies are proposed: maximum voltage discharge (MXVD), minimum voltage charge (MNVC), and maximum and minimum voltage balancing (MX&MNB). For MX&MNB, which is essentially a combination of MXVD and MNVC, it controls the maximum voltage cell discharging and minimum voltage cell charging simultaneously, where the energy is transferred directly between the two cells with the largest voltage difference. A cell balancing prototype is built and tested to verify the feasibility and stability of the proposed strategy. All three proposed methods can implement cell balancing simply and effectively, while the MX&MNB provides a faster speed.

Raiyaan Abdullah, Yogesh Singh Rawat, Shruti Vyas

Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabilities in high-stakes industrial domains-where recognizing both routine operations and safety-critical anomalies is essential-remain largely underexplored. To address this gap, we introduce iSafetyBench, a new video-language benchmark specifically designed to evaluate model performance in industrial environments across both normal and hazardous scenarios. iSafetyBench comprises 1,100 video clips sourced from real-world industrial settings, annotated with open-vocabulary, multi-label action tags spanning 98 routine and 67 hazardous action categories. Each clip is paired with multiple-choice questions for both single-label and multi-label evaluation, enabling fine-grained assessment of VLMs in both standard and safety-critical contexts. We evaluate eight state-of-the-art video-language models under zero-shot conditions. Despite their strong performance on existing video benchmarks, these models struggle with iSafetyBench-particularly in recognizing hazardous activities and in multi-label scenarios. Our results reveal significant performance gaps, underscoring the need for more robust, safety-aware multimodal models for industrial applications. iSafetyBench provides a first-of-its-kind testbed to drive progress in this direction. The dataset is available at: https://github.com/iSafetyBench/data.

Ali Mohammad-Djafari

Digital Twins (DTs) are virtual representations of physical systems synchronized in real time through Internet of Things (IoT) sensors and computational models. In industrial applications, DTs enable predictive maintenance, fault diagnosis, and process optimization. This paper explores the mathematical foundations of DTs, hybrid modeling techniques, including Physics Informed Neural Networks (PINNs), and their implementation in industrial scenarios. We present key applications, computational tools, and future research directions.

Anwar Ahmed Khan, Shama Siddiqui, Indrakshi Dey

Managing delay is one of the core requirements of industrial automation applications due to the high risk associated for equipment and human lives. Using efficient Media Access Control (MAC) schemes guarantees the timely transmission of critical data, particularly in the industrial environments where heterogeneous data is inherently expected. This paper compares the performance of Fragmentation based MAC (FROG-MAC) against Fuzzy Priority Scheduling based MAC (FPS-MAC), both of which have been designed to optimize the performance of heterogenous wireless networks. Contiki has been used as a simulation platform and a single hop star topology has been assumed to resemble the industrial environment. It has been shown that FROG-MAC has the potential to outperform FPS-MAC in terms of energy efficiency and delay both, due to its inherent feature of interrupting ongoing lower priority transmission on the channel.

Di Wen, Kunyu Peng, Junwei Zheng et al.

Industrial workflows demand adaptive and trustworthy assistance that can operate under limited computing, connectivity, and strict privacy constraints. In this work, we present MICA (Multi-Agent Industrial Coordination Assistant), a perception-grounded and speech-interactive system that delivers real-time guidance for assembly, troubleshooting, part queries, and maintenance. MICA coordinates five role-specialized language agents, audited by a safety checker, to ensure accurate and compliant support. To achieve robust step understanding, we introduce Adaptive Step Fusion (ASF), which dynamically blends expert reasoning with online adaptation from natural speech feedback. Furthermore, we establish a new multi-agent coordination benchmark across representative task categories and propose evaluation metrics tailored to industrial assistance, enabling systematic comparison of different coordination topologies. Our experiments demonstrate that MICA consistently improves task success, reliability, and responsiveness over baseline structures, while remaining deployable on practical offline hardware. Together, these contributions highlight MICA as a step toward deployable, privacy-preserving multi-agent assistants for dynamic factory environments. The source code will be made publicly available at https://github.com/Kratos-Wen/MICA.

Dr. Darren M. C. Ould, Dr. Svetlana Menkin, Holly E. Smith et al.

Abstract Invited for this issue's Front Cover is the groups of Grey and Wright. The cover picture shows the chemical structure of sodium tetrakis(hexafluoroisopropyloxy)aluminate, with the sodium ion in the beach ball and the aluminate anion floating in a pool. The cover art uses a pool theme as the sodium aluminate salt synthesised in this work is a room‐temperature ionic liquid, thus the sodium salt in the pool represents this. The application of the salt in a sodium‐ion battery is shown in the cover design with the diving board acting as a battery, which can be seen by the positive and negative signs. Cover design by Demelza Lee. Read the full text of the Research Article at 10.1002/celc.202300381.

Muhammad Aqeel, Shakiba Sharifi, Marco Cristani et al.

This study introduces the Iterative Refinement Process (IRP), a robust anomaly detection methodology designed for high-stakes industrial quality control. The IRP enhances defect detection accuracy through a cyclic data refinement strategy, iteratively removing misleading data points to improve model performance and robustness. We validate the IRP's effectiveness using two benchmark datasets, Kolektor SDD2 (KSDD2) and MVTec AD, covering a wide range of industrial products and defect types. Our experimental results demonstrate that the IRP consistently outperforms traditional anomaly detection models, particularly in environments with high noise levels. This study highlights the IRP's potential to significantly enhance anomaly detection processes in industrial settings, effectively managing the challenges of sparse and noisy data.

Hans Aoyang Zhou, Dominik Wolfschläger, Constantinos Florides et al.

Machine vision enhances automation, quality control, and operational efficiency in industrial applications by enabling machines to interpret and act on visual data. While traditional computer vision algorithms and approaches remain widely utilized, machine learning has become pivotal in current research activities. In particular, generative AI demonstrates promising potential by improving pattern recognition capabilities, through data augmentation, increasing image resolution, and identifying anomalies for quality control. However, the application of generative AI in machine vision is still in its early stages due to challenges in data diversity, computational requirements, and the necessity for robust validation methods. A comprehensive literature review is essential to understand the current state of generative AI in industrial machine vision, focusing on recent advancements, applications, and research trends. Thus, a literature review based on the PRISMA guidelines was conducted, analyzing over 1,200 papers on generative AI in industrial machine vision. Our findings reveal various patterns in current research, with the primary use of generative AI being data augmentation, for machine vision tasks such as classification and object detection. Furthermore, we gather a collection of application challenges together with data requirements to enable a successful application of generative AI in industrial machine vision. This overview aims to provide researchers with insights into the different areas and applications within current research, highlighting significant advancements and identifying opportunities for future work.

Thomas Rosenstatter, Christian Schäfer, Olaf Saßnick et al.

As Industry 4.0 and the Industrial Internet of Things continue to advance, industrial control systems are increasingly adopting IT solutions, including communication standards and protocols. As these systems become more decentralized and interconnected, a critical need for enhanced security measures arises. Threat modeling is traditionally performed in structured brainstorming sessions involving domain and security experts. Such sessions, however, often fail to provide an exhaustive identification of assets and interfaces due to the lack of a systematic approach. This is a major issue, as it leads to poor threat modeling, resulting in insufficient mitigation strategies and, lastly, a flawed security architecture. We propose a method for the analysis of assets in industrial systems, with special focus on physical threats. Inspired by the ISO/OSI reference model, a systematic approach is introduced to help identify and classify asset interfaces. This results in an enriched system model of the asset, offering a comprehensive overview visually represented as an interface tree, thereby laying the foundation for subsequent threat modeling steps. To demonstrate the proposed method, the results of its application to a programmable logic controller (PLC) are presented. In support of this, a study involving a group of 12 security experts was conducted. Additionally, the study offers valuable insights into the experts' general perspectives and workflows on threat modeling.

Sheng Tian, Xintan Zeng, Yifei Hu et al.

Graph-based patterns are extensively employed and favored by practitioners within industrial companies due to their capacity to represent the behavioral attributes and topological relationships among users, thereby offering enhanced interpretability in comparison to black-box models commonly utilized for classification and recognition tasks. For instance, within the scenario of transaction risk management, a graph pattern that is characteristic of a particular risk category can be readily employed to discern transactions fraught with risk, delineate networks of criminal activity, or investigate the methodologies employed by fraudsters. Nonetheless, graph data in industrial settings is often characterized by its massive scale, encompassing data sets with millions or even billions of nodes, making the manual extraction of graph patterns not only labor-intensive but also necessitating specialized knowledge in particular domains of risk. Moreover, existing methodologies for mining graph patterns encounter significant obstacles when tasked with analyzing large-scale attributed graphs. In this work, we introduce GraphRPM, an industry-purpose parallel and distributed risk pattern mining framework on large attributed graphs. The framework incorporates a novel edge-involved graph isomorphism network alongside optimized operations for parallel graph computation, which collectively contribute to a considerable reduction in computational complexity and resource expenditure. Moreover, the intelligent filtration of efficacious risky graph patterns is facilitated by the proposed evaluation metrics. Comprehensive experimental evaluations conducted on real-world datasets of varying sizes substantiate the capability of GraphRPM to adeptly address the challenges inherent in mining patterns from large-scale industrial attributed graphs, thereby underscoring its substantial value for industrial deployment.

Tanureza Jaya, Benjamin Michalak, Marcel Radke et al.

Cabling tasks (pulling, clipping, and plug insertion) are today mostly manual work, limiting the cost-effectiveness of electrification. Feasibility for the robotic grasping and insertion of plugs, as well as the manipulation of cables, have been shown in research settings. However, in many industrial tasks the complete process from picking, insertion, routing, and validation must be solved with one system. This often means the cable must be directly manipulated for routing, and the plug must be manipulated for insertion, often in cluttered environments with tight space constraints. Here we introduce an analysis of the complete industrial cabling tasks and demonstrate a solution from grasp, plug insertion, clipping, and final plug insertion. Industrial requirements are summarized, considering the space limitations, tolerances, and possible ways that the cabling process can be integrated into the production process. This paper proposes gripper designs and general robotic assembly methods for the widely used FASTON and a cubical industrial connector. The proposed methods cover the cable gripping, handling, routing, and inserting processes of the connector. Customized grippers are designed to ensure the reliable gripping of the plugs and the pulling and manipulation of the cable segments. A passive component to correct the cable orientation is proposed, allowing the robot to re-grip the plug before insertion. In general, the proposed method can perform cable assembly with mere position control, foregoing complex control approaches. This solution is demonstrated with an industrial product with realistic space requirements and tolerances, identifying difficult aspects of current cabling scenarios and potential to improve the automation-friendliness in the product design.

Wen Xu, Minghui Zhang, Yanfeng Dong et al.

Aqueous zinc batteries (AZBs) show promising applications in large-scale energy storage and wearable devices mainly because of their low cost and intrinsic safety. However, zinc metal anodes suffer from dendrite issues and side reactions, seriously hindering their practical applications. Two-dimensional (2D) materials with atomic thickness and large aspect ratio possess excellent physicochemical properties, providing opportunities to rationally design and construct practically reversible zinc metal anodes. Here, we systematically summarize the recent progress of 2D materials (e.g., graphene and MXene) that can be used to enable dendrite-free zinc metal anodes for AZBs. Firstly, the construction methods and strategies of 2D materials/Zn hybrid anodes are briefly reviewed, and are classified into protecting layers on Zn foils and host materials for Zn. Secondly, various 2D material/Zn hybrid anodes are elaborately introduced, and the key roles played by 2D materials in stabilizing the Zn/Zn²⁺ redox process are specially emphasized. Finally, the challenges and perspectives of advanced 2D materials for advanced Zn anodes in next-generation AZBs are briefly discussed.

Tao Yang, Xuefeng Jiang, Wei Li et al.

Existing research on sensor data anomaly detection for industrial sensor networks still has several inherent limitations. First, most detection models usually consider centralized detection. Thus, all sensor data have to be uploaded to the control center for analysis, leading to a heavy traffic load. However, industrial sensor networks have high requirements for reliable and real-time communication. The heavy traffic load may cause communication delays or packets lost by corruption. Second, there are complex spatial and temporal features in industrial sensor data. The full extraction of such features plays a key role in improving detection performance.To solve the limitations above, this paper develops a cloud-edge collaborative data anomaly detection approach for industrial sensor networks that mainly consists of a sensor data detection model deployed at individual edges and a sensor data analysis model deployed in the cloud. The former is implemented using Gaussian and Bayesian algorithms, which effectively filter the substantial volume of sensor data generated during the normal operation of the industrial sensor network, thereby reducing traffic load. It only uploads all the sensor data to the sensor data analysis model for further analysis when the network is in an anomalous state. The latter based on GCRL is developed by inserting Long Short-Term Memory network (LSTM) into Graph Convolutional Network (GCN), which can effectively extract the spatial and temporal features of the sensor data for anomaly detection.

Aintzane Mosteiro-Sanchez, Marc Barcelo, Jasone Astorga et al.

Industry 4.0 uses a subset of the IoT, named Industrial IoT (IIoT), to achieve connectivity, interoperability, and decentralization. The deployment of industrial networks rarely considers security by design, but this becomes imperative in smart manufacturing as connectivity increases. The combination of OT and IT infrastructures in Industry 4.0 adds new security threats beyond those of traditional industrial networks. Defence-in-Depth (DiD) strategies tackle the complexity of this problem by providing multiple defense layers, each of these focusing on a particular set of threats. Additionally, the strict requirements of IIoT networks demand lightweight encryption algorithms. Nevertheless, these ciphers must provide E2E (End-to-End) security, as data passes through intermediate entities or middleboxes before reaching their destination. If compromised, middleboxes could expose vulnerable information to potential attackers if it is not encrypted throughout this path. This paper presents an analysis of the most relevant security strategies in Industry 4.0, focusing primarily on DiD. With these in mind, it proposes a combination of DiD, an encryption algorithm called Attribute-Based-Encryption (ABE), and object security (i.e., OSCORE) to get an E2E security approach. This analysis is a critical first step to developing more complex and lightweight security frameworks suitable for Industry 4.0.

Bhavya Kotak, Yash Kotak, Katja Brade et al.

Battery safety is a prominent concern for the deployment of electric vehicles (EVs). The battery powering an EV contains highly energetic active materials and flammable organic electrolytes. Usually, an EV battery catches fire due to its thermal runaway, either immediately at the time of the accident or can take a while to gain enough heat to ignite the battery chemicals. There are numerous battery abuse testing standards and regulations available globally. Therefore, battery manufacturers are always in dilemma to choose the safest one. Henceforth, to find the optimal outcome of these two major issues, six standards (SAE J2464:2009, GB/T 31485-2015:2015, FreedomCAR:2006, ISO 12405-3:2014, IEC 62660-2:2010, and SAND2017-6295:2017) and two regulations (UN/ECE-R100.02:2013 and GTR 20:2018), that are followed by more than fifty countries in the world, are investigated in terms of their abuse battery testing conditions (crush test). This research proves that there is a need for (a) augmenting these standards and regulations as they do not consider real-life vehicle crash scenarios, and (b) one harmonised framework should be developed, which can be adopted worldwide. These outcomes will solve the battery manufacturers dilemma and will also increase the safety of EV consumers.

Heba H. El-Maghrabi, Hager R. Ali, Fouad Zahran et al.

This study reports the development of 3-aminopropyltriethoxysilane (APTES) functionalized magnetic bentonite (AMB) nanocomposite by microwave assisted route to adsorb and decrease Ba(II) and Sr(II) ions, which are responsible for scale formation in the tubing of gas and oil production. Phases, function groups, morphology and magnetic properties was investigated for the prepared samples as well as porosity and surface area. Adsorption results obtained at different temperatures shows that the adsorption process of the prepared AMB is exothermic and follows Langmuir adsorption isotherm model. Kinetics of the adsorption processes at AMB surface was investigated. The process was found to follow the pseudo-second order kinetic model. pH of the system has a great influence on the adsorption of both ions. At pH 9, maximum adsorption was achieved, 124.8 mg/g and 120.0 mg/g for strontium and barium ions, respectively. While it was 107.7 mg/g and 86.7 mg/g for strontium and barium, respectively, at pH 7 similar to produced water pH. AMB showed good removal efficiency that reached 41% and 76.2% for Ba(II) and Sr(II), respectively. Based on the experimental results, AMB is a good natural low-cost material that can be used to decrease scale formation in tubing of oil/gas production.

M.M. Zareh, Kh. Elgendy, A.A. Keshk et al.

The assembly and characteristics of a copper(II) electrochemical sensor (CuES) based on β-cyclodextrin (βCD) dopped into PVC was reported in this paper. The CuES was prepared by combining Ag/AgCl reference electrode plus the polyvinyl chloride (PVC) membrane electrochemical sensor. The CuES reveals a Nernstian behavior over a wide copper ion concentration range (1.0 × 10–2 to 5.0 × 10–6 mol L–1) and a relatively low detection limit (0.32 ppm). The potentiometric response was independent of the pH of the solution above 3.9 whatever the used concentration. The CuES showed a very short response time (5 s for 10–3 and 10–2M) and (15 s for 10–4 M)) for all compositions. It exhibited very good selectivity relative to a wide variety of metal cations. The proposed CuES was used for the analysis of copper in Haematon-containing samples. This method was compared with traditional spectrophotometric techniques.

Ming La, Daohong Wu, Yanping Gao et al.

Impedimetric aptasensors without signal amplification exhibit poor sensitivity for the detection of small molecule contaminants. In this work, biotinylated nanoparticles of biotin-FNPs were readily prepared by the self-assembly of biotin-phenylalanine (biotin-Phe) monomers. The biotin-FNPs were then used for the development of competitive impedimetric aptasensors by streptavidin–biotin (SA–biotin) coupling chemistry. Specifically, capture of biotinylated DNA (biotin-DNA) by the aptamer-modified electrode allowed for the in situ formation of SA–biotin-FNPs networks on the electrode surface, hampering the electron transfer by creating an insulating layer. The target–aptamer interaction prevented the capture of biotin-DNA, thus inhibiting the formation of SA–biotin-FNPs networks on the electrode surface and allowing for the electron transfer. To demonstrate the analytical performances of the strategy, aflatoxin B1 (AFB1) was determined as the model analyte. The aptasensor exhibited a linear range of 0.05–3 pg/mL. The detectable concentration is much lower than that achieved by other impedimetric aptasensors. The strategy may provide a general way for the design of biosensors to determine various small molecules by matching sequence-specific aptamers.