The methods for unsupervised visual inspection use algorithms that are developed, trained and evaluated on publicly available datasets. However, these datasets do not reflect genuine industrial conditions, and thus current methods are not ...

• Review of existing public datasets and highlight of the need for a genuine dataset.
• Introduction of AutoVI, the first genuine industrial dataset for anomaly detection.
• Benchmark study of current state-of-the-art anomaly detection ...

Data form the backbone of manufacturing sciences, initiating a revolutionary transformation in our understanding of manufacturing processes by unravelling complex scientific patterns embedded within them. Digital characteristics (DC) is defined ...

Display Omitted

• Proposed a novel methodology to unlock inherent values of manufacturing metadata.
• Developed a physics-based filter to identify naturally unattributed fragmental data.
• Developed digital characteristics of identified manufacturing ...

The cotter pin (CP) is a vital fastener for the catenary support components (CSCs) of high-speed electrified railways. Due to the vibration and excitation caused by the passing of railway vehicles, some CPs may be broken or fallen off over time, ...

• A CP detection model based on an improved Faster R-CNN is proposed.
• The proposed method achieves 99.05 % precision and 98.40 % recall rate on CP defect detection.
• The proposed method is more accurate, faster, and robust than the ...

This article presents a systematic literature review (SLR) of empirical studies concerning Artificial Intelligence (AI) in the field of Supply Chain Management (SCM). Over the past decade, technologies belonging to AI have developed rapidly, ...

• AI in SCM is subject to a potential hype: a substantiated view is provided by a review of empirical studies.
• Five main themes emerge.
• Future research should focus on framing disruptions and consistencies with established SCM theory ...

With the transformation and upgrading of the manufacturing industry, manufacturing systems have become increasingly complex in terms of the structural functionality, process flows, control systems, and performance assessment criteria. Digital ...

• New technologies concerning performance optimization and control for smart manufacturing are reviewed.
• A closed-loop performance optimization and control architecture with “cloud-edge-device” collaboration is proposed.
• Based on ...

Resistance spot welding (RSW) is a widely used welding technology in automotive manufacturing, and weld nugget quality is closely related to the quality of the vehicle body. Offline random checks are largely relied on the quality inspection of ...

• Weld nuggets are classified by learning the features of the weld spot point cloud.
• LFE module is designed to obtain the local features of the point cloud.
• A residual ratio module is developed to fuse the local and global features.

Generative Artificial Intelligence (AI) models serve as powerful tools for organizations aiming to integrate advanced data analysis and automation into their applications and services. Citizen data scientists—individuals without formal training ...

• A new model is developed to assess the impact of generative AI citizen on data scientist performance.
• A SWOT analysis is performed to develop factors in the model.
• Data from 268 retail companies is collected for model evaluation.

After two decades of research and development, process mining techniques are now recognized as essential analysis tools, as they have their own Gartner Magic Quadrant. The development of process mining techniques is rooted in process-related ...

• Process mining need to move from single cases to multiple object types and events.
• This aligns well with essential concepts from production and logistics.
• Process mining evaluation is elaborated by proposing an “evaluation ladder”.

The booming Internet economy and generative artificial intelligence have driven the rapid growth of the digital content trading industry, creating an urgent need for the fair protection of the rights of both buyers and sellers. To meet this need, ...

• Protecting the rights of both buyers and sellers throughout content transactions.
• Offering solutions for the orderly development of the content trading industry.
• Client-side embedding is implemented alongside resolving the ...

In the context of the Fourth Industrial Revolution, a large amount of heterogeneous data and information is generated during the lifecycle of complex products, which poses a considerable challenge for manufacturers and effective knowledge ...

• A well-structured domain ontology to enhance design for maintenance (DFM).
• Ontology promotes the formalization and effective reuse of DFM knowledge.
• The semantic interoperability has been validated through a case study.
• Rule-...

Accurate X-ray image defect segmentation is of paramount importance in industrial contexts, as it is the foundation for product quality control and production safety. Deep learning (DL) has demonstrated powerful image scene understanding ...

• A core-profile decomposition network is proposed for X-ray image defect segmentation.
• Core feature learning creates an effective space to extract X-ray image features.
• Elasticity profile refinement uses elasticity scores to enhance ...

Computational fluid dynamics (CFD) has been extensively used as a simulation tool for product development in various industrial fields. Engineers sequentially query the CFD simulator to evaluate their design instances, during which they improve ...

• A CFD-ML system based on stream-based active learning is proposed.
• It adaptively alternates between the CFD simulator and ML model for evaluating design queries.
• It reduces costs compared to using only the CFD simulator.
• It ...

Structural components produced through hot stamping of lightweight materials, such as aluminium alloys, play a pivotal role in mass reduction, leading to decreased CO₂ emissions and enhanced fuel efficiency, especially in applications such as ...

• Establishing a cloud-based database of manufacturing processes.
• Developing distinctive digital characteristics (DC) of hot stamping process.
• Proposing a novel methodology to unlock inherent values of manufacturing metadata.

Trade restrictions, the COVID-19 pandemic, and geopolitical conflicts have significantly exposed vulnerabilities within traditional global supply chains. These events underscore the need for organisations to establish more resilient and flexible ...

• Turbulent trade environments have highlighted the need for organisations to enhance the resilience and diversity of their supply chains.
• The model of autonomous supply chains, characterised by predictive and self-decision-making ...

Effective fault detection and diagnosis (FDD) is crucial for proactively identifying irregular states that could jeopardize operator well-being and process integrity. In the era of Industry 4.0, data-driven FDD techniques have received particular ...

• Process fault detection is difficult due to large and complex datasets.
• Domain knowledge is required to unpick relationships to give accurate predictions.
• KESA integrates engineering knowledge with deep learning for fault ...

Large numbers of maintenance Work Request Notification (WRN) records are created by industry as part of standard business work flows. These digital records hold invaluable insights crucial to best practice in asset management. Of particular ...

Display Omitted

• Free-text maintenance work request documents hold valuable causal information on asset failures.
• Work requests are multi-sentence and contain information extraneous to causal analysis so a novel sentence-level noise removal method is ...

In the new hyper connected factories, data gathering, and prediction models are key to keeping both productivity and piece quality. This paper presents a software platform that monitors and detects outliers in an industrial manufacturing process ...

• Description of a platform to collect, analyze and visualize data in real time.
• Target is to detect outliers during a manufacturing process.
• Tests with real manufacturing machine show impact of communication protocol.
• Tests ...

The current practice for creating as-built geometric Digital Twins (gDTs) of industrial facilities is both labour-intensive and error-prone. In aged industries it typically involves manually crafting a CAD or BIM model from a point cloud ...

• A workflow for creating semantic- and -instance labelled real point cloud datasets.
• A benchmark of the SoftGroup DL Network in the industrial domain.
• Indoor 3D instance segmentation networks are applicable in the industrial domain.

While the adoption of open Building Information Modeling (open BIM) standards continues to grow, the inherent complexity and multifaceted nature of the built asset lifecycle data present a critical bottleneck for effective information retrieval. ...

• We compare traditional and transformer architectures for building entity extraction.
• Our work takes into account the practical needs and constraints of the industry.
• We leverage open data standards to design an adaptable semantic ...

Structured enterprise information systems such as Enterprise Resources Planning (ERP) and Product Lifecycle Management (PLM) have reached a maturity plateau and are storing up to hundreds of millions of objects and links. Such data is crucial for ...

• Proposes a tooled-up method called Data Systemizer (D6) that defines data packages suitable for a Data Migration process.
• Proposes an analysis method optimized for PLM data able to build data packages at mesoscopic scale.
• D6 relies ...