{"id":110045,"date":"2025-08-15T12:00:00","date_gmt":"2025-08-15T10:00:00","guid":{"rendered":"https:\/\/industry-science.com\/?post_type=article&p=110045"},"modified":"2025-08-12T13:58:56","modified_gmt":"2025-08-12T11:58:56","slug":"data-standards-battery-cel","status":"publish","type":"article","link":"https:\/\/industry-science.com\/en\/articles\/data-standards-battery-cel\/","title":{"rendered":"Developing Data Standards in Battery Cell Manufacturing"},"content":{"rendered":"\n

The global energy transition, especially the rapid rise of electric mobility, is driving an unprecedented surge in demand for battery cells. By 2030, around 200 new battery factories are expected to be built globally\u2014equivalent to nearly 2.5 new plants every month [1]. To meet this growing demand efficiently and competitively, especially in Europe, battery cell manufacturing must become more digital, flexible, and adaptive.<\/p>\n\n\n\n

Traditional battery cell plants and production lines, which rely heavily on fixed processes and turnkey solutions, are too rigid to accommodate fast innovation cycles or customized product variants. Instead, digitalization can enable future battery manufacturing that is highly automated using interconnected systems that can adapt quickly to new materials, formats, and technologies [2].<\/p>\n\n\n\n

Innovative digital solutions such as digital twins, AI\/ML-assisted optimization, and modular production architectures offer significant potential for reducing production costs and enhancing product quality. Data-driven optimization can reduce scrap rates and downtime, improve cell performance, and support traceability requirements such as those defined in the EU Battery Regulation.<\/p>\n\n\n\n

However, realizing this potential depends on reliable data exchange between machines, systems, and actors across the value chain. A major obstacle to this is the lack of standardized, interoperable interfaces. Without a shared data language, integration efforts are time-consuming, error-prone, and costly. To overcome this, formalized and semantically consistent data descriptions must be established and aligned with industrial standards [3].<\/p>\n\n\n\n

These descriptions can be based on existing domain knowledge and structured information models, which serve as the technical foundation for interoperable communication. Industrial communication standards such as OPC UA (Open Platform Communications Unified Architecture) provide a standardized framework for this, enabling the consistent and secure exchange of production data across heterogeneous systems.<\/p>\n\n\n\n

In this context, the usability and practical implementability of the interface and underlying data model are critical to ensure broad adoption. This paper presents a requirements analysis for data standards in battery cell manufacturing, with a specific focus on these aspects. Based on the findings, a development procedure for domain-specific standards is derived.<\/p>\n\n\n\n

Related work on information models and ontologies<\/h2>\n\n\n\n

A key element in achieving flexible and adaptive production is the creation of formalized data descriptions that make the semantics of data explicit and machine-readable. These descriptions provide the foundation for consistent interpretation across systems. To achieve this, semantically rich and context-aware data structures can be developed using ontologies. In the context of information science and data modeling, an ontology is a formal, explicit specification of a shared conceptualization. It defines a structured set of concepts, entities, and relationships relevant to a particular domain.<\/p>\n\n\n\n

Ontologies can therefore help in making it possible to model production knowledge in a structured and meaningful way. These ontological models can then be translated into or embedded within formal information models, which define how data is organized, accessed, and communicated within and across systems. The information model complements the data model by adding contextual information, enabling consistent interpretation and use of the data.<\/p>\n\n\n\n

In the domain of battery cell production, the development of ontologies has been part of numerous research projects. Many of these ontologies refer to authorities such as the IEC: IEC 60050, for example, defines terminology for batteries. However, they have an electrochemical or product-specific focus and lack definitions for production processes and systems. Moreover, these ontologies typically operate at a high level of abstraction and are not readily applicable for direct implementation in production environments. <\/p>\n\n\n\n

Relevant previous work is listed below. The Battery Value Chain Ontology (BVCO) seeks to model processes along the entire battery value chain [4], while the Battery Interface Ontology (BattINFO) aims to provide a semantic basis for describing battery-related knowledge and for generating linked data [5]. The DigiBatMat project presents an ontology for structured data handling in lithium-ion battery cell production based on BVCO, BattINFO and others [6].<\/p>\n\n\n\n

Zanotto et al. discuss data specifications for the digitalization of battery manufacturing and propose a data-driven modeling approach for cell production, based in part on the BattINFO ontology [7]. The DataBatt project has developed an ontology to enable semantic linking for the storage and evaluation of data and information [8<\/a>]. In addition, the KIProBatt Ontology introduces a unified framework for the integration of a data space in battery production environments [9]. Haghi et al. propose a tailored digitalization approach based on the significance of specific process parameters [10].<\/p>\n\n\n\n

While these approaches exist, definitions for production machines and processes are lacking. It thus remains obscure how to transfer these ontologies into a framework for interoperable data exchange within production environments.<\/p>\n\n\n\n

The architecture of interoperable interfaces<\/h2>\n\n\n\n

While the content of a new standard is important, its acceptance and adoption also depend on the implementability and usability of the underlying technology. Interoperable interfaces that go beyond mere communication protocols serve as the technological foundation for standardized data exchange. In this context, a communication protocol defines the rules and formats for data exchange between devices or systems at various layers of a network. In contrast, an interoperable interface builds on lower-level protocols and provides a higher-level, structured framework.<\/p>\n\n\n\n

A study by the VDMA involving over 600 companies found that, among those for whom interoperable interfaces are relevant, more than half consider such interfaces to be of high or very high importance. Of these, 90% have either already implemented the communication standard OPC UA (Open Platform Communications Unified Architecture) or plan to do so in the future [11].<\/p>\n\n\n\n

OPC UA is a common industrial interoperable interface that enables secure and platform-independent data exchange [12]. <\/p>\n\n\n\n

This framework not only defines how data is transmitted but also how it is semantically described, enabling the meaningful interpretation of data across heterogeneous systems. Its architecture supports features such as encryption, scalability across device levels, and domain-specific data representation.<\/p>\n\n\n\n

Based on a service-oriented architecture, OPC UA comprises logical layers, including a transport layer for protocol handling, a data model layer for publishing structured information, and basic services for client-server communication. Its information modeling framework not only allows the integration of existing and already defined standards\u2014called OPC UA companion specifications\u2014but also offers the possibility to model individual information models.<\/p>\n\n\n\n

Methodology and requirements analysis<\/h2>\n\n\n\n

To derive an approach for developing implementable data standards for battery cell manufacturing, we conducted a systematic requirements analysis<\/a>. In a first step, experts from industry\u2014including machine manufacturers, automation engineers, and software developers\u2014as well as from battery cell research, collected requirements for the standards. The collected requirements address various topics, including those necessary to realize the potential benefits of standardization, as well as challenges related to implementability.<\/p>\n\n\n\n

Accordingly, they cover areas such as data acquisition and processing, requirements for the content of the information model, the modeling procedure and specific use cases relevant to battery cell manufacturing.\u00a0<\/p>\n\n\n\n

Following this, the requirements were systematically classified into three categories\u2014data, process representation and use cases\u2014as shown in Figure 1<\/strong>. Within each of these categories, the individual requirements were then refined and specified, and their priorities ranked by experts in the subject. This way, it is ensured that all important criteria are evaluated by experts from the field. A selection of requirements with highest priority is listed below.<\/p>\n\n\n\n

\"Figure
Figure 1: Classification of requirements into categories.<\/em><\/figcaption><\/figure>\n\n\n\n

In the first category, \u201cData\u201d, the clear definition and future viability of the data format is defined as very important. It is also recognized that both raw data, for example at sensor level, and result data, including from proprietary system software, must be captured to ensure comprehensive data collection. The aggregation of the recorded data should be carried out via the standard to be developed and not in advance by other systems. This will ensure that the format of the data conforms to the standard. Data visualization was identified as being less directly affected by the standard and was therefore assigned a lower priority. In terms of implementability, OPC UA was identified as the most relevant existing communication standard.<\/p>\n\n\n\n

OPC UA is also addressed in the category of \u201cProcess Representation\u201d. One requirement is to enable interoperability with existing standards such as OPC UA Machinery, for example for the handling of process values. In general, creating a consistent structure for the information model is found to be of high priority. For each data point, the relevant metadata (for example time and location), the SI unit, and a serial number must be considered in the information model. The modeling must be based on the typical process chain of battery cell production.<\/p>\n\n\n\n

A hierarchical structure is needed in which processes can be divided into sub-processes. The individual sub-processes, but also entire processes, if possible, must have a modular structure so that they can be linked and exchanged. This will also ensure that the standard is open to future process technologies replacing outdated ones in the process chain.<\/p>\n\n\n\n

The third category deals with three specific \u201cUse Cases\u201d and considers which requirements are particularly important for them in particular. The selection of these particular use cases\u2014traceability, the battery passport and process optimization\u2014was driven by their relevance in the battery cell production domain. They encompass a broad spectrum of applications, ranging from upstream and shopfloor-near use cases such as process optimization through downstream data usage in the case of the battery passport to overall data aggregation and linking for traceability purposes.<\/p>\n\n\n\n

The first use case addresses traceability, which refers to the tracking and tracing of data across the process chain and its assignment to materials and intermediate products. For the standard to be suitable for traceability, the relationships between production data and their influencing variables must be defined and subsequent changes to the models must be possible. In addition, meta-information about the individual parts used must be assigned to the finished intermediate and final products. This meta-information includes, for example, serial and batch numbers or tools used.<\/p>\n\n\n\n

The second use case deals with the creation of a battery passport based on upcoming EU regulations that define which information must be stored for a produced battery. For this, traceability is an enabler. It is required to collect and include all the data needed to implement the passport in accordance with the standard. In addition, the ability to query process data from external systems is identified as very important for the battery passport.<\/p>\n\n\n\n

The third use case considered is process optimization. In this use case, real-time and historical data are utilized to improve the performance and efficiency of production equipment. For this to be successful, the data relevant for deriving recommendations for process improvement must be available in alignment with the standard. It must also be possible to generate timestamped data records. In this way, recommendations for adjustments to current process parameters can be made based on existing data.<\/p>\n\n\n\n

Derived procedure for developing a standard\u00a0<\/h2>\n\n\n\n

The result of the analysis is a categorized list of prioritized requirements which forms the basis for deriving a procedure for developing standards. A schematic visualization of the desired standardized data exchange is shown in Figure 2<\/strong>. Machines on the shop floor are connected via standardized interfaces, enabling the use of semantically rich information models. This structured approach to data acquisition and interpretation\u2014based on conventions from standards\u2014forms the basis for interoperability and supports the aforementioned key use cases. <\/p>\n\n\n\n

\"Figure
Figure 2: Schematic representation of standardized data exchange.<\/em><\/figcaption><\/figure>\n\n\n\n

The following procedure for the creation of standards was derived based on the aforementioned requirements analysis, the prior and related work and the basic characteristics of interoperable interfaces such as OPC UA. The initial step is a systematic analysis of the battery cell production process chain, which enables the clear definition of all process steps and associated machinery. For this purpose, we recommend the use of ISA-88 or similar standardized procedures [13].<\/p>\n\n\n\n

The analysis is then used to determine the number of distinct information models to be developed. Dividing the system into further subcomponents will support the integration of existing information models from related domains. Subsequent to this, a parameter list must be created for each process step.<\/p>\n\n\n\n

As demonstrated by the requirements analysis, the selection of relevant parameters must be based on expert assessments, such as those from cell manufacturers and production machinery manufacturers, as well as existing literature and research and should be supported by relevant use cases (like those outlined above).<\/p>\n\n\n\n

After identification, a clear and structured way of naming the parameters is crucial. The naming must consider prior work on ontologies and additional expert assessments to establish unambiguous designations. Combined with explanatory descriptions, the parameters must be assigned to machines and their subcomponents within structured system descriptions. These parameter definitions must be formulated in terms concrete enough to enable process experts to perform data mapping for their respective systems.<\/p>\n\n\n\n

Altogether, this forms the basis for the development of the information model. In the case of OPC UA, types and subtypes are first to be defined, after which it will be checked whether existing variants of these (sub)-types can be integrated in order to build on existing standards. This implies that only the essential components of the model must be developed from the ground up. <\/p>\n\n\n\n

The result is an information model built on a communication standard like OPC UA that is technically mature and readily deployable. The integrity of the modeling is assured by the provision of clear parameter descriptions.<\/p>\n\n\n\n

The validation of the information model is to be conducted by subject experts, thereby ensuring its continuous enhancement. The actual development, integration and validation of the standard under discussion is not within the scope of this paper.<\/p>\n\n\n\n

Challenges to an established data standard<\/h2>\n\n\n\n

The presented approach to developing a battery cell manufacturing standard offers a structured method that considers both technical and organizational requirements. Nevertheless, there are still some challenges involved in developing and establishing such a standard. One major challenge is determining an appropriate level of detail for the standard. All relevant parameters and requirements must be covered, particularly with regard to interoperability, traceability, and adaptability for future developments.<\/p>\n\n\n\n

At the same time, however, the standard should not be overly complex or overdeveloped, as this would hinder its implementation and acceptance within the industry. Therefore, it is essential to achieve an optimal balance between comprehensiveness and practical feasibility.\u00a0 To achieve this, it is recommended that the standard provides users with the capability to independently extend the information model by adding specific proprietary properties, such as components or parameters, within its structure.<\/p>\n\n\n\n

Consequently, the standard must include clear guidelines and instructions on how to model these extensions to ensure that it remain accessible and user-friendly. Only by keeping the standard adaptable and flexible can it be ensured that the standard stays compact while still accommodating special cases. Nevertheless, it should also be continuously validated against industry-relevant use cases in terms of its complexity and completeness. Furthermore, additional research focused on simplifying the implementation of such standards is essential. The objective should be to facilitate the adoption and integration of these standards across both new and legacy systems.<\/p>\n\n\n\n

Such efforts will help to reduce barriers to implementation and broaden both applicability and acceptance. At this juncture, it is imperative to reiterate the necessity for the parameter descriptions and assignments to system components, as previously outlined, to be meticulously detailed and precise. This level of detail is essential to enable comprehensive data mapping. At the same time, research is being conducted into automated data mapping based on large language models, for example, in order to simplify and speed up future implementation [14].<\/p>\n\n\n\n

Another challenge during standard development lies in the incorporation of parallel developments and preliminary work. As described in this article, many attempts have already been made to establish ontologies. Leveraging existing foundational work enables the consolidation of prior knowledge, minimizes duplication, and promotes interoperability across systems. However, realizing the full benefits of this approach requires sustained interdisciplinary collaboration and continuous stakeholder engagement throughout the development process. To ensure effective collaboration, it is crucial that the organizations responsible for the underlying technologies participate in the process of translating the developed models into standards. In the case of OPC UA, this role is fulfilled by the OPC Foundation which oversees the transformation of information models into standards known as OPC UA companion specifications.<\/p>\n\n\n\n

For the standard to be successful following its technical implementation, it must be effectively disseminated and widely adopted within the industry. To engage relevant stakeholders in a unified manner, collaboration with corporate networks must be pursued. As part of the ENLARGE project, this effective collaboration with relevant industry partners is essential to advance the development of standards in battery cell manufacturing [15]. In general, platforms for collaboration, industry feedback, and ongoing development play a critical role in the path toward a standardized battery production chain.<\/p>\n

Bibliography <\/h2>[1]\tGrandl, G.; Duffner, F.; Baum, M.; M\u00f6hrke, M.; Wu, X.; et al.: Battery Manufacturing 2030: Collaborating at Warp Speed: What it takes for equipment manufacturers to ride the coming wave of breakneck growth, 2024. URL: https:\/\/www.porsche-consulting.com\/sites\/default\/files\/2024-02\/battery_manufacturing_2030_porsche_consulting_2024.pdf, accessed 07.05.2025.\r
[2]\tMichaelis, S.; Sch\u00fctrumpf, J.; Kampker, A.; et al.: Roadmap Batterie-Produktionsmittel 2030: Update 2023, Frankfurt, 2023. URL: https:\/\/vdma.org\/documents\/34570\/35405938\/VDMA+Batterieproduktion_Roadmap_2023.pdf\/ee2452cd-ed44-93bf-4762-6a09ce29b4b7?t=1683038844317, accessed 14.05.2025.\r
[3]\tAyerbe, E.; Berecibar, M.; Clark; et al.: Digitalization of battery manufacturing: current status, challenges, and opportunities.\u00a0In Advanced Energy Materials (2022),\u00a012(17), 2102696.\r
[4]\tStier, S.; Gold, L.; Fraunhofer ISC: Battery Value Chain Ontology. URL: https:\/\/github.com\/Battery-Value-Chain-Ontology\/ontology, accessed 13.05.2025.\r
[5]\tClark, S.; Friis, J.; Bleken, F. L.; et al.: Battery Interface Ontology. URL: https:\/\/github.com\/BIG-MAP\/BattINFO, accessed 10.05.2025.\r
[6]\tMutz, M.; Perovic, M.; G\u00fcmbel, P.; et al.: Toward a Li-Ion Battery Ontology Covering Production and Material Structure. In Energy Technology 11 (2023) 5.\r
[7]\tZanotto, F. M.; Dominguez, D. Z.; Ayerbe, E.; et al.: Data specifications for battery manufacturing digitalization: current status, challenges, and opportunities. In Batteries & Supercaps 5 (2022) 9, e202200224.\r
[8]\tStier, S.; Gannouni, A.: DataBatt 4.0 Ontology. URL: https:\/\/github.com\/DataBatt-4-0\/ontology, accessed 13.05.2025.\r
[9]\tStier, S. P.; Xu, X.; Gold, L.; M\u00f6ckel, M.: Ontology-Based Battery Production Dataspace and Its Interweaving with Artificial Intelligence-Empowered Data Analytics. In Energy Technology 12 (2024) 4: 2301305.\r
[10]\tHaghi, S.; Summer, A.; Bauerschmidt, P.; Daub, R.: Tailored digitalization in electrode manufacturing: the backbone of smart lithium\u2010ion battery cell production. In Energy Technology 10 (2022) 10, 2200657.\r
[11]\tVDMA: Studie zur Interoperabilit\u00e4t im Maschinen- und Anlagenbau, 2021. URL: www.vdma.org\/documents\/34570\/0\/Studie%20\u201eInteroperabilit\u00e4t%20im%20Maschinen-%20und%20Anlagenbau\u201c_Expertenseite%20OPC%20UA.pdf\/0083b153-a3c0-501f-08ce-e93c82627eb0, accessed 14.05.2025.\r
[12]\tOPC Foundation: Unified Architecture. URL: https:\/\/opcfoundation.org\/about\/opc-technologies\/opc-ua\/, accessed 14.05.2025.\r
[13]\tInternational Society of Automation. ANSI\/ISA-88.00.01-2010 Batch Control Part 1: Models and Terminology, 2010 (88.00.01-2010). URL: https:\/\/www.isa.org\/products\/ansi-isa-88-00-01-2010-batch-control-part-1-models, accessed 04.07.2025.\r
[14]\tJaspers, W.; Schmetz, A.; Roth, D.; Becker, B.; Kampker, A.: Identification of machine parameters in battery cell production: A comparison of different methods and approaches for mapping parameters. In Procedia CIRP 134 (2025).\r
[15]\tENLARGE consortium: SynBatt Batteriezellproduktion ENLARGE. URL: www.enlarge-projekt.de, accessed 14.05.2025.<\/div>
Potentials: Globalization<\/a><\/span>
Solutions: Safety<\/a><\/span>
Tags: Interoperabilit\u00e4t<\/a><\/span>
Industries: Information Security<\/a><\/span> Manufacturing<\/a><\/span> <\/div>
<\/i><\/a><\/i><\/a><\/i><\/a><\/i><\/a><\/i><\/a><\/div><\/div><\/div>
\n

You might also be interested in<\/h2>\n\n
\n
\n \n
\n \n \n \n \"Developing\n <\/picture>\n <\/div>\n
\n \t \n
\t\t

Developing Virtual Reality in Learning Contexts<\/h4>\n
Navigating efficiency, content relevance and scalability<\/div>
Stella Kanatouri<\/a> \n \"ORCID<\/a>, Oliver Sosna<\/a> \n \"ORCID<\/a>, Alexander Kulik<\/a>, Sina C. Truckenbrodt<\/a> \n \"ORCID<\/a>, Friederike Klan<\/a> \n \"ORCID<\/a>, Christian Erfurth<\/a> \n \"ORCID<\/a><\/div>\n <\/td>\n <\/tr>\n <\/table>\n
\n While virtual reality can facilitate hands-on learning, its development faces barriers, including high costs and time demands and scalability challenges. This article presents two case studies that illustrate strategies for overcoming such barriers when training the next generation of skilled workers in environmental technologies. By examining approaches for streamlining development and increasing content relevance and scalability, we highlight lessons learned for future practice. We conclude by envisioning a future in which educational institutions can flexibly and cost-effectively prototype virtual reality in learning contexts, ensuring alignment with curricular goals and learners\u2019 needs. <\/div>\n <\/div>\n
Industry 4.0 Science<\/strong> | Volume 42 | Edition 3 | Pages 26-34 | DOI 10.30844\/I4SE.26.3.3<\/a><\/div> <\/div>\n <\/div>\n <\/a>\n <\/div>\n
\n \n
\n \n \n \n \"Serious\n <\/picture>\n <\/div>\n
\n \t \n
\t\t

Serious Gaming and the Energy Transition<\/h4>\n
Collaborative knowledge generation and interactive understanding of complex interrelationships<\/div>
Janine Gondolf<\/a> \n \"ORCID<\/a>, Gert Mehlmann<\/a>, J\u00f6rn Hartung<\/a>, Bernd Schweinshaut<\/a>, Anne Bauer<\/a><\/div>\n <\/td>\n <\/tr>\n <\/table>\n
\n Conveying the complexity and multifaceted nature of the energy transition to a broad audience is a challenge. This article demonstrates how interactive serious games on a multitouch table can help make connections tangible and comprehensible. The games and the table were used in various conversational contexts. These are presented here in three case vignettes based on participant observation of the different applications, as well as situated and shared reflection. The vignettes demonstrate how interaction can trigger epistemic processes, enable shifts in perspective, and foster collective thinking, all of which are necessary for shaping the future of society as a whole. <\/div>\n <\/div>\n
Industry 4.0 Science<\/strong> | Volume 42 | 2026 | Edition 2 | Pages 62-69<\/div> <\/div>\n <\/div>\n <\/a>\n <\/div>\n
\n \n
\n \n \n \n \"Industrial\n <\/picture>\n <\/div>\n
\n \t \n
\t\t

Industrial Transformation via a Machining Learning Factory<\/h4>\n
A learning module to foster competencies for a sustainability-driven transformation<\/div>
Oskay Ozen<\/a> \n \"ORCID<\/a>, Victoria Breidling<\/a> \n \"ORCID<\/a>, Stefan Seyfried<\/a> \n \"ORCID<\/a>, Matthias Weigold<\/a> \n \"ORCID<\/a><\/div>\n <\/td>\n <\/tr>\n <\/table>\n
\n Sustainability-enhancing transformation processes are necessary in all sectors if we are to remain within planetary boundaries. This also applies to the industrial sector as a significant emitter of greenhouse gases. Employees need new competencies to master this complex task of industrial transformation. These range from CO2 equivalents accounting to the development and evaluation of transformation scenarios, including technical measures. The learning module developed here addresses these competency requirements and uses the example of the ETA factory to show how a competency-oriented learning module for industrial transformation can be structured. It essentially comprises four phases: data collection and CO2 equivalents accounting, cause analysis, development of measures and evaluation of measures. <\/div>\n <\/div>\n
Industry 4.0 Science<\/strong> | Volume 42 | Edition 2 | Pages 38-47 | DOI 10.30844\/I4SE.26.2.38<\/a><\/div> <\/div>\n <\/div>\n <\/a>\n <\/div>\n
\n \n
\n \n \n \n \"Data\n <\/picture>\n <\/div>\n
\n \t \n
\t\t

Data Quality and Domain Expertise for Resilient AI Deployment<\/h4>\n
Integrating anomaly and label error detection in industry<\/div>
Pavlos Rath-Manakidis<\/a>, Henry Huick<\/a>, Erdi \u00dcnal<\/a>, Bj\u00f6rn Kr\u00e4mer<\/a> \n \"ORCID<\/a>, Laurenz Wiskott<\/a> \n \"ORCID<\/a><\/div>\n <\/td>\n <\/tr>\n <\/table>\n
\n AI implementation transforms work and worker-technology relationships in industrial quality control. This paper explores how approaches to data quality and model transparency support ethical AI deployment, fostering worker agency, trust, and sustainable work design in automatic surface inspection systems (ASIS). Recurring problems like data inefficiency, variable model confidence, and limited AI expertise point to key challenges of human-centered AI: user trust, agency and responsible data management. A solution co-developed with an ASIS supplier demonstrates that the challenges extend beyond the purely technical, underscoring the value of AI design that augments human capabilities. Technical solutions such as anomaly, label error, and domain drift detection are proposed to enhance data quality and model reliability. The insights emphasize the following generalizable strategies for resilient AI integration: understanding user-reported problems through a human-AI interaction lens, ... <\/div>\n <\/div>\n
Industry 4.0 Science<\/strong> | Volume 42 | Edition 1 | Pages 128-135 | DOI 10.30844\/I4SE.26.1.120<\/a><\/div> <\/div>\n <\/div>\n <\/a>\n <\/div>\n
\n \n
\n \n \n \n \"Digital\n <\/picture>\n <\/div>\n
\n \t \n
\t\t

Digital Competence Lab (DCL) for Speech Therapy<\/h4>\n
Designing a learning platform to advance digital skills<\/div>
Anika Thurmann<\/a> \n \"ORCID<\/a>, Antonia Weirich<\/a> \n \"ORCID<\/a>, Kerstin Bilda<\/a>, Fiona D\u00f6rr<\/a> \n \"ORCID<\/a>, Lars T\u00f6nges<\/a> \n \"ORCID<\/a><\/div>\n <\/td>\n <\/tr>\n <\/table>\n
\n The digital transformation of healthcare results in lasting changes in speech therapy. Smart technologies and artificial intelligence (AI) are creating new opportunities to ensure therapy quality, address care bottlenecks, and actively involve patients in exercise processes. At the same time, these developments are expanding the role of speech therapists, who increasingly use digital systems as supportive tools in addition to their core therapeutic tasks. Based on a feasibility study of the AI-supported application ISi-Speech-Sprechen in a real-world setting of complex Parkinson's therapy (PKT), this article outlines the key challenges associated with implementing smart technologies. <\/div>\n <\/div>\n
Industry 4.0 Science<\/strong> | Volume 42 | 2026 | Edition 1 | Pages 110-118 | DOI 10.30844\/I4SE.26.1.102<\/a><\/div> <\/div>\n <\/div>\n <\/a>\n <\/div>\n
\n \n
\n \n \n \n \"AI\n <\/picture>\n <\/div>\n
\n \t \n
\t\t

AI Implementation in Industrial Quality Control<\/h4>\n
A design science approach bridging technical and human factors<\/div>
Erdi \u00dcnal<\/a> \n \"ORCID<\/a>, Kathrin Nauth<\/a> \n \"ORCID<\/a>, Pavlos Rath-Manakidis<\/a>, Jens P\u00f6ppelbu\u00df<\/a> \n \"ORCID<\/a>, Felix Hoenig<\/a>, Christian Meske<\/a> \n \"ORCID<\/a><\/div>\n <\/td>\n <\/tr>\n <\/table>\n
\n Artificial intelligence (AI) offers significant potential to enhance industrial quality control, yet successful implementation requires careful consideration of ethical and human factors. This article examines how automated surface inspection systems can be deployed to augment human capabilities while ensuring ethical integration into workflows. Through design science research, twelve stakeholders from six organizations across three continents are interviewed and twelve sociotechnical design requirements are derived. These are organized into pre-implementation and implementation\/operation phases, addressing human agency, employee participation, and responsible knowledge management. Key findings include the critical importance of meaningful employee participation during pre-implementation, and maintaining human agency through experiential learning, building on existing expertise. This research contributes to ethical AI workplace implementation by providing guidelines that preserve human ... <\/div>\n <\/div>\n
Industry 4.0 Science<\/strong> | Volume 42 | 2026 | Edition 1 | Pages 120-127 | DOI 10.30844\/I4SE.26.1.112<\/a><\/div> <\/div>\n <\/div>\n <\/a>\n <\/div>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":"

The growing demand for battery cells offers significant potential for the use of digital solutions in their manufacture, which in turn creates opportunities for added value through adaptive and flexible production systems. A key enabler is interoperable data exchange based on formalized data descriptions. Existing ontologies and information models remain too abstract for direct implementation. This paper presents a requirements analysis of data standards in battery cell manufacturing. A procedure for developing domain-specific standards based on OPC UA (Open Platform Communications Unified Architecture) is derived from the results.<\/p>\n","protected":false},"featured_media":109607,"menu_order":0,"template":"","categories":[79167,79298],"tags":[79454],"product_cat":[79304],"topic":[67617,79333],"technology":[67596],"knowhow":[],"industry":[79353,79494],"writer":[],"content-type":[83932],"potential":[67586],"solution":[68055],"glossary":[],"class_list":["post-110045","article","type-article","status-publish","has-post-thumbnail","category-design-en","category-typeset","tag-interoperabilitaet-en","product_cat-articles","topic-adaptability","topic-process-optimization","technology-software-en","industry-information-security","industry-manufacturing-en","content-type-article","potential-globalization","solution-safety","product","first","instock","downloadable","virtual","sold-individually","taxable","purchasable","product-type-article"],"uagb_featured_image_src":{"full":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie.jpeg",1400,788,false],"thumbnail":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-150x150.jpeg",150,150,true],"medium":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-666x375.jpeg",666,375,true],"medium_large":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-768x432.jpeg",768,432,true],"large":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-1024x576.jpeg",1020,574,true],"front-page-entry":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-1032x320.jpeg",1032,320,true],"post-entry":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-764x376.jpeg",764,376,true],"post-teaser":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-392x320.jpeg",392,320,true],"post-teaser-mobile":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-608x496.jpeg",608,496,true],"post-custom-size":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-640x325.jpeg",640,325,true],"whitepaper-teaser":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-274x376.jpeg",274,376,true],"card-big":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-514x292.jpeg",514,292,true],"card-portrait":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-320x440.jpeg",320,440,true],"card-big-company":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-514x289.jpeg",514,289,true],"gp-listing":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-196x180.jpeg",196,180,true],"1536x1536":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie.jpeg",1400,788,false],"2048x2048":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie.jpeg",1400,788,false],"woocommerce_thumbnail":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-510x510.jpeg",510,510,true],"woocommerce_single":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-510x287.jpeg",510,287,true],"woocommerce_gallery_thumbnail":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-100x100.jpeg",100,100,true],"dgwt-wcas-product-suggestion":["https:\/\/industry-science.com\/wp-content\/uploads\/2025\/08\/roth-AdobeStock_1385935387-copie-64x36.jpeg",64,36,true]},"uagb_author_info":{"display_name":"Florian Goldmann","author_link":"https:\/\/industry-science.com\/en\/author\/"},"uagb_comment_info":0,"uagb_excerpt":"The growing demand for battery cells offers significant potential for the use of digital solutions in their manufacture, which in turn creates opportunities for added value through adaptive and flexible production systems. A key enabler is interoperable data exchange based on formalized data descriptions. Existing ontologies and information models remain too abstract for direct implementation.…","_links":{"self":[{"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/article\/110045","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/article"}],"about":[{"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/types\/article"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/media\/109607"}],"wp:attachment":[{"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/media?parent=110045"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/categories?post=110045"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/tags?post=110045"},{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/product_cat?post=110045"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/topic?post=110045"},{"taxonomy":"technology","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/technology?post=110045"},{"taxonomy":"knowhow","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/knowhow?post=110045"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/industry?post=110045"},{"taxonomy":"writer","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/writer?post=110045"},{"taxonomy":"content-type","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/content-type?post=110045"},{"taxonomy":"potential","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/potential?post=110045"},{"taxonomy":"solution","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/solution?post=110045"},{"taxonomy":"glossary","embeddable":true,"href":"https:\/\/industry-science.com\/en\/wp-json\/wp\/v2\/glossary?post=110045"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}