In the manufacturing industry, automated optical inspection aims to improve the detection and classification of anomalies by utilizing artificial intelligence and computer vision techniques to enhance quality control processes and minimize production defects. However, this automated system faces significant challenges, particularly regarding the detection of anomalies due to predominance of normal instances over defected ones. Addressing this imbalance is crucial for effective real-time anomaly detection particularly in images captured by Airbag Sensors among other automotive parts. Earlier contributions in domain-specific fields commonly relied on traditional computer vision methods, while recent systems are increasingly using deep learning techniques. Utilizing various data augmentation techniques ensures a more balanced representation of anomalies in the dataset, thereby enhancing the accuracy of the detection process. Moreover, it also enhances the robustness and generalization of the anomaly detection model by exposing it to a more diverse range of instances during training. Such work has not been carried out to augment Airbag Sensor images for analysis through a deep learner. Accordingly, this paper introduces a framework that employs data augmentation techniques for Convolutional Neural Networks (CNNs). The proposed system, based on data augmentation and CNN, significantly improves the performance for anomaly detection in Airbag Sensor images with a classification accuracy on the unaugmented dataset being 53 % which improves to 90% with augmentation.

Reusing and managing existing knowledge from available documents is crucial for success in the factory planning domain. By leveraging Artificial Intelligence (AI) and Question Answering (QA) systems, users can query a document corpus through a chat-based application and receive precise answers. The recent advancements in Large Language Models (LLMs) and their linguistic capabilities present new opportunities for such applications. Utilizing the methodology of Retrieval Augmented Generation (RAG), document sections are provided to the LLM based on user queries. However, existing RAG implementations that use vector databases as document repositories face limitations when answering questions that extend beyond the text content of the documents. To address this issue, this paper proposes a concept to enhance RAG systems by integrating a Knowledge Graph (KG) constructed from the document structures.

This paper introduces a novel methodological approach to transform a traditional model-centric machine learning pipeline into a morphological box. Utilizing a taxonomy development method, we iteratively refine a morphological box to address the complexity inherent in selecting and adjusting components within machine learning pipelines. Our method leverages a generic active learning process tailored for quality control in manufacturing, serving as a practical example. We demonstrate that decomposing the machine learning pipeline into distinct morphological box dimensions with meta char-acteristics significantly enhances decision-making clarity by reducing option complexity. This transformation is further supported by defining universal attributes-Cost, Time, Avail-ability, and Complexity-that cater to users with varying machine learning expertise. Future work will focus on empirical validation and the development of software tools to facilitate the practical application of morphological boxes in diverse machine learning pipeline contexts.

The presence of class imbalance, denoting a dis-proportionate distribution of class instances in a dataset, has emerged as a significant challenge in the era of Deep Learning (DL) where models crave abundance in data. This issue is pervasive in various real-world applications, where certain classes exhibit limited data representation. This problem is frequently encountered when dealing with image data, which exhibits an imbalanced distribution, with one class significantly outnumbering the others. Failing to address class imbalance introduces bias in machine learning and deep learning models, favoring the majority classes and leading to subpar performance for the minority classes. This research specifically delves into the recurrent problem in the context of image data, that is “class imbalance”. The research comprehensively explores the existing challenges based on data pre-processing, algorithmic techniques, hybrid methodologies, and state-of-the-art solutions.

After an initial push to outsource every single computation to remote data centers, the edge compute paradigm can now provide the necessary balance of scalability and timeliness for successful manufacturing deployments. By consolidating compute resources that were previously distributed across the shop floor, a major emphasis is being placed on the manufacturing network, which has adapted to its new role by converging the IT and OT domains into a scalable, timely, highly available, and secure network. This work centers around security mechanisms to secure virtualization-based manufacturing. Our proposed concept uses only measures in the network layer, where we see the greatest benefits, while providing the possibility to deploy it in brownfield environments today. Validation is performed by challenging it with known and emerging security threats, the cyber kill chain, and IEC 62443-3-3, improving the security level in most metrics in contrast to perimeter-based legacy architectures. In future work, the validated concept can be extended to the physical, host and application layers, providing holistic IT/OT security and enabling secure edge cloud-enabled manufacturing.

The virtualization of real-time critical workloads on edge clouds is rapidly gaining attention, placing a greater emphasis on communication between the physical and virtualized worlds. However, traditional IP-based networks lack the mechanisms to provide sufficient failover time for a variety of time-critical applications found in manufacturing, such as virtualized Programmable Logic Controllers (vPLCs). So far, only packet duplication mechanisms have been considered to meet the stringent High Availability (HA) requirements of real-time applications. In this work we propose the novel approach half&half which is characterized by sending packets alternately over two disjoint paths without duplicating them. The validation conducted confirms the applicability of half&half for the two most widely used Industrial Ethernet protocols, PROFINET and EtherNet/IP. The approach offers a comparable level of resilience to packet duplication, while requiring the same throughput as single-path communication and eliminating complexity on the receiver side, facilitating edge-cloud enabled manufacturing.

The amount of necessary information and knowledge to fulfill the tasks within the factory planning domain is rapidly growing. Currently, data and documents containing relevant information are stored as single artifacts in various established systems which makes information gathering time-consuming. Therefore it would be helpful to connect the existing artifacts so that it is possible to get all information of different origins at a glance. As Semantic Web technologies are recently evolving from academic research to industry applications, Knowledge Graphs (KG) as one of their specific implementations seem to be a suitable option to manage and connect these information artifacts in a sustainable matter. This can effectively support knowledge management in factory planning and provides machine-readable access to domain information that can be used by currently emerging Artificial Intelligence (AI) applications. This paper focuses on the conceptual challenges related to the creation of a knowledge graph within the factory planning domain and proposes a concept for a platform to collect and access existing information and experiences from domain experts.

Cloud computing is becoming more popular in domains where previously hardware-based bare metal implementations dominated the field of computation workloads such as the automation and process industry. A variety of stateful applications exist that will require high availability on cloud infrastructures while also meeting the hard real-time requirements in the millisecond area of their superimposed processes, e.g., virtualized programmable logic controllers (vPLCs) and artificial intelligence inference services. This paper presents an approach for stateful applications on distributed systems to meet the application’s requirements in failover scenarios through state synchronization by means of Remote Direct Memory Access (RDMA). Experimental results with a software PLC confirm the effectiveness of the described approach in comparison to UDP-based synchronization, reducing the average synchronization time by up to 99.39%. The concept is suitable for applications on virtual machines and containers and might be an enabler for virtualization of real-time critical applications such as control functions in the automation and process industry.

The introduction of edge computing, big data analytics and virtualization technology offers a variety of benefits for manufacturing environments. With the advent of Industry 4.0, Operational Technology (OT) was supposed to converge with the IT domain to create a unified network that satisfies all requirements for these novel technologies. However, the OT environment only adopts new technologies once a real benefit and their resilience are confirmed. Hence, most factory networks and its computational infrastructure have not adapted to the new data-based paradigm and virtualization is still in its infancy for shop floor applications. In this work we propose a new architecture for shop floor infrastructure and conduct a first experimental validation. The designed architecture is applicable for brownfield and greenfield environments and creates new possibilities in terms of scalability, optimization potential and security.

Virtual commissioning is evolving to become an indispensable part included in modern planning processes. New challenges related to recent technologies like the usage of information models in Industry 4.0 implementations make it necessary to test the behaviour in production-related communication beforehand. Different data aquisition methods have to be evaluated concerning their benefits, risks and the environment it has to be implemented in. Information model management and aggregation can help to fulfill these tasks. This concept paper focuses on architectural challenges related to the implementation of information models in brown- as well as green-field approaches and the overall management system behind.

Information models are defined as a comprehensive semantic description of data within a production system. These systems underlay a constant change. Therefore, the corresponding information models are also subject to continuous evolution. This paper shows approaches for the versioning compliant design of information models and their implementation as well as support strategies to assist such changes.

The objective of this paper is to present a hybrid methodology of analysing acoustic signals arising in industrial processes through comparisons of known numerical techniques such as clustering. Apart from data acquisition and pre-processing, the other essential component of using acoustics is to design an analysis methodology, that can culminate in practical applications. This paper applies Gaussian Mixture Models and Self-Organising Maps to cluster pre-processed AE hits obtained from acoustic sensors in the form of tensile, shear and mixed modes of compression on a material. For an in-depth analysis, custom features such as high peak regions, low peak regions, strongly hit and weakly hit signals are introduced to compare with the clusters formed. The results show that for small AE signals that are obtained or extracted after events detection, a time-domain based clustering can be applied and used for isolating similarities and distinctions among the signals belonging to the same group.

In this paper, we classify Kaizen (production process related best practices) from Volkswagen internal knowledge database into their adaptability status over other Volkswagen production plants with help of supervised machine learning. Different criteria's like Return on Investment, implementation time-frame, impact on various other key performance indicators, plant-specific technical details, etc. are used to evaluate Kaizens and eventually cluster them into two categories. Empirical results show that the Decision tree model can predict the degree of adaptability (Success/Denied) with 85% accuracy.

Information exchange across different departments in factories must be structured and verified for effective production processes. However, any such exchange across networks to clients must be compliant to company standards so that uniformity and security in data dispensation is maintained. Open Platform Communications Unified Architecture (OPC UA) solutions provide users with the flexibility of discharging information through network based protocols. This paper aims to build a compliance testing methodology for external vendors of an organisation who are interconnected with the OPC UA Server-Client Protocols. The structure is built on a host of UA clients that test UA specifications and information models from these vendors. This enables an organisational entity, for example, a manufacturer, to provide its clients, in this case external vendors such as suppliers, with the flexibility of conforming to prescribed standards in a testing phase on an automated digital platform rather than with older methods such as data transfer though databases or documents. An implementation of this approach is presented using example servers created for this purpose. It follows that external vendors can perform compliance testing and possibly improve their standards to match the company standards through remote testing after proper authentication measures provided by OPC UA.

Virtual Commissioning is an important part of modern design engineering approaches. Early simulation models of newly developed production structures can help to elaborate and evaluate different ideas concerning new processes. The machine communication is an important part of this evaluation. Currently the focus is on different approaches like CPS, IIoT and the overall crosslinking in Industry 4.0 implementations. In many of these cases the functional static behaviour of the communication interface is checked in later phases of the development process and not in a dynamical aspect, although it is useful to understand it early to draw conclusions for the proceeding project. This paper shows an early simple approach for checking the dynamical interoperability between the different automation levels in a production environment by adapting known Virtual Commissioning methods to a broader view.

A production system consists of multiple production entities. To enable a manufacturing process, these entities have to exchange information. Information models offer the possibility to standardize the data exchange between the entities. In addition to a common communication protocol, concepts that integrate and aggregate the different entities into a common address space, have to be developed. Another important issue is the historicization of information, for example, to improve the production process or for legal reasons. Graph databases enable semantic relations between objects for representation and storage of information. Therefore, it is a promising concept to be used in the production context. This paper presents a concept for the aggregation and historicization of production entities into a graph database.

Predictive analytics is seen as one of the emerging technology in this digital age of big data. Computational processing power and speed has grown exponentially in the last few years that has made predictive analytic practical for application in different organization. Manufacturing industries has huge amount of data in different shapes and forms, and keep regular track of their performance by monitoring key performance indicators defined under business strategy. Prioritizing and predicting these key performance indicators provide organization cutting edge as compared to competitors by being proactive rather than reactive. As compared to traditional business intelligence tools where focus is on static report or dashboards about past data, predictive analysis focuses on estimating outcomes with the objective of driving better business performance. Moreover, it is also being adopted for decision-making tools. Different data mining techniques are applied in the field of performance management system as per individual or project need. Many researches has developed different ideas to understand and evaluate complex intervened key performance indicator relationships in performance measurement system. The aim of the paper is to present comprehensive version of predictive key performance indicator analysis from its background to state of the art, describing various data mining standards, methodologies as well as industrial and research application. The paper also studies various surveys regarding predictive analytic for business application to identify different best practices in this field.

Processes such as welding involve consumption of huge amounts of energy leading to generation of significant electrical data consisting of current and voltage signals. The added task is to inspect the quality of welding using such data as early as possible to identify defects in producing welded parts or equipment. From the perspective of machine learning, this paper presents a data mining approach to analyse small sampled amounts of electrical signals to identify welding inconsistencies using conventional methods such as clustering algorithms, time-series and multi-label classifiers. Using unlabelled and discrete signals, an attempt is made to build a process profile on the welding robots with the use of comparison measures such as Jaccard's metric. To monitor such a mechanism, a simulation application based on IIoT standard Open Platform Communication (OPC UA) is developed to present the analysis over secure network servers to clients. The application setup presents a basic monitoring system for welding processes using available technologies like machine learning algorithms and OPC UA.

Workshop-type manufacturing systems grow over time and therefore they have heterogeneous communication interfaces. Digitalization can be an enabler to lowering their costs and improving their performance. This can be facilitated with the introduction of common information models. But the widespread introduction of information models in such manufacturing environments is entailed with significant efforts and risks. This paper describes how existing workshop-type manufacturing environments can be documented in such a way that they can subsequently be reproduced in an OPC UA information model.

This study presents an assessment of the OPC Unified Architecture as an integration framework for heterogeneous healthcare systems enabling compliance with the Industry 4.0 paradigm. The contributions of this work are: 1) a conceptual architecture with heterogeneous networks for enabling Internet of Things healthcare applications, 2) OPC UA data models based on the HL7 Reference Information Model for information exchange and storage, and 3) an analysis of how OPC UA can enable the healthcare sector to be part of the Industry 4.0.

In industrial production scenarios, there is often a need to access heterogeneous information sources such as production units but also DBMS (Data base management system) and/or a local or shared file system to realize the necessary workflows. EDDL (Electronic Device Description Language) provides a standardized way to access and exchange information with the devices that make up the automation system. This paper discusses an approach to use the EDDL approach to describe databases and files, which is to say that in this approach the databases and files both have been modelled as ‘devices’ and can be communicated with like any other device with its own device description. For this to work, EDDL based device descriptions were formulated for databases as well as files and the communication with the same was established with the help of an OPC UA Server, containing nodes corresponding to database entries and files (of a local file system), in its address space. The OPC UA Server used the EDDL based descriptions of the file system and databases to gain connection and access related information about the same, thus establishing the communication. The results of this approach have also been discussed in the following sections, along with a proposal for some enhancements to the EDDL standard.

Devices in industrial automation systems are becoming more and more intelligent. Consequently, functions such as server services are migrating into the device level. To solve the resulting connection mesh, this paper entails the concept of aggregation of servers connected to devices in an industrial automation scenario. The first section discusses the basic requirements for aggregation and proposes an architecture for server aggregation as a solution. The following section describes the building blocks of the architecture. Finally, the paper presents a prototype based on this architecture model as a proof of concept implementation of the concept introduced in this paper. The last section discusses the results of the prototyping phase including the possible improvements of the same.