This study addresses a significant gap in the field of time series regression modeling by highlighting the central role of data augmentation in improving model accuracy. The primary objective is to present a detailed methodology for systematic sampling of training datasets through data augmentation to improve the accuracy of time series regression models. Therefore, different augmentation techniques are compared to evaluate their impact on model accuracy across different datasets and model architectures. In addition, this research highlights the need for a standardized approach to creating training datasets using multiple augmentation methods. The lack of a clear framework hinders the easy integration of data augmentation into time series regression pipelines. Our systematic methodology promotes model accuracy while providing a robust foundation for practitioners to seamlessly integrate data augmentation into their modeling practices. The effectiveness of our approach is demonstrated using process data from two milling machines. Experiments show that the optimized training dataset improves the generalization ability of machine learning models in 86.67% of the evaluated scenarios. However, the prediction accuracy of models trained on a sufficient dataset remains largely unaffected. Based on these results, sophisticated sampling strategies such as Quadratic Weighting of multiple augmentation approaches may be beneficial.

Machine learning methods have widely been applied to detect anomalies in machine and cutting tool behavior during lathe or milling. However, detecting anomalies in the workpiece itself have not received the same attention by researchers. In this article, the authors present a publicly available multivariate time series dataset which was recorded during the milling of 16MnCr5. Due to artificially introduced, realistic anomalies in the workpiece, the dataset can be applied for anomaly detection. By using a convolutional autoencoder as a first model, good results in detecting the location of the anomalies in the workpiece were achieved. Furthermore, milling tools with two different diameters where used which led to a dataset eligible for transfer learning. The objective of this article is to provide researchers with a real-world time series dataset of the milling process which is suitable for modern machine learning research topics such as anomaly detection and transfer learning.

Continuous fiber-reinforced polymer (CoFRP) parts offer significant potential for reducing future product consumption and CO₂ emissions due to their high tensile properties and low density. Additive manufacturing enables the tool-free production of complex geometries with optimal material utilization, making it a promising approach for creating load-path-optimized CoFRP parts. Recent advancements have integrated continuous fibers into laser sintering processes, allowing for the support-free production of complex parts with improved material properties. However, additive manufacturing faces challenges such as long production times, small component dimensions, and defects like high void content. New processes, including Arburg Polymer Freeforming (APF), robotic direct extrusion (DES) and the integration of thermoplastic tapes, and laser sintering, have enabled the production of CoFRPs to address these issues. A comparison of these new processes with existing material extrusion methods is necessary to determine the most suitable approach for specific tasks. The fulfillment factor is used to compare composites with different matrix and fiber materials, representing the percentage of experimentally achieved material properties relative to the theoretical maximum according to the Voigt model. The fulfillment factor varies significantly across different processes and materials. For FFF processes, the fulfillment factor ranges from 20% to 77% for stiffness and 14% to 84% for strength, with an average of 52% and 37%, respectively. APF shows a high fulfillment factor for stiffness (94%) but is lower for strength (23%), attributed to poor fiber–matrix bonding and process-induced pores. The new DES process improves the fulfillment factor due to additional consolidation steps, achieving above-average values for strength (67%). The CoFRP produced by the novel LS process also shows a high fulfillment factor for stiffness (85%) and an average fulfillment factor for strength (39%), influenced by suboptimal process parameters and defects.

The increasing demand for personalized products and the lack of skilled workers, intensified by demographic change, are major challenges for the manufacturing industry in Europe. An important framework for addressing these issues is a digital twin that represents the dynamic behavior of machine tools to support the remaining skilled workers and optimize processes in virtual space. Existing methods for modeling the dynamic behavior of machine tools rely on the use of expert knowledge and require a significant amount of manual effort. In this paper, a concept is proposed for individualized and lifetime-adaptive modeling of the dynamic behavior of machine tools with the focus on the machine’s tool center point. Therefore, existing and proven algorithms are combined and applied to this use case. Additionally, it eliminates the need for detailed information about the machine’s kinematic structure and utilizes automated data collection, which reduces the dependence on expert knowledge. In preliminary tests, the algorithm for the initial model setup shows a fit of 99.88% on simulation data. The introduced re-fit approach for online parameter actualization is promising, as in preliminary tests, an accuracy of 95.23% could be reached.

The transition to highly customized, one-off production in modern manufacturing necessitates sophisticated process monitoring to reduce waste, minimise downtime, and alleviate operator burden. Computer Numerically Controlled (CNC) axes represent a fundamental component of automated manufacturing and offer a universal and accessible monitoring option through power supply data. By accurately predicting reference signals and comparing them with real-time measurements, deviations can be used for effective model-based process monitoring and anomaly detection. This study explores the efficacy of hybrid machine learning (ML) models in predicting reference signals for CNC axes using features derived from a physical model. Additionally, relevant but difficult-to-measure features such as process forces and the material removal rate (MMR) were made accessible through soft sensors. Various ML models were evaluated, including tree-based models (e.g. random forest (RF) and gradient boosting (GB)) and deep learning (DL) models (e.g. feed-forward neural networks (FNN), long short-term memory (LSTM), and transformers-based models (TF)). Feature importance analysis was performed, identifying velocity, acceleration, process forces, spindle torque, andMMRas crucial predictors that influence model performance. Key results indicate that tree-based models, specifically RF and GB, consistently delivered the highest accuracy, achieving R2 up to 0.98 for translatory axes and approximately 0.89 for the main spindle. These models demonstrated robustness, outperforming deep learning approaches, particularly when trained on smaller datasets. Although DL models improved with larger data volumes, their performance remained inferior compared to tree-based methods. The study underscores the potential of the integration of physical knowledge into hybrid ML models to enhance model-based process monitoring.

The development of interoperable and reusable information models is a key challenge for digitalization in manufacturing domains with heterogeneous and complex process chains. Ensuring seamless data exchange requires the standardization of both data syntax and semantics, while maintaining compatibility with existing industry standards. This paper presents a methodology for deriving standardizable and generalizable OPC UA information models tailored to domains with high process variability and interdisciplinary requirements. The methodology integrates system analysis, parameter mapping, and the development of modular submodels, supported by expert input and validation. It emphasizes the reuse and extension of existing OPC UA Companion Specifications to reduce complexity, avoid redundancy, and enable long-term standardization. The approach is exemplified by its application to battery cell production, an emerging manufacturing domain combining process and mechanical engineering with continuous and discrete processes. Its high degree of heterogeneity and lack of domain-specific standards pose significant challenges for model development. Through iterative expert workshops and structured model validation, a dedicated and transferable OPC UA framework is created. The resulting layered model structure combines a cross-industry standard with newly developed, process-aware model elements. This enables both broad applicability and the depth required for complex production environments, while supporting use cases such as traceability, regulatory reporting (e.g., EU Battery Passport), and process optimization. The resulting model improves interoperability, transparency, and data integration, offering a scalable blueprint for other complex manufacturing sectors.