Abstract This work explores the application of state-of-the-art techniques of time series forecasting to the delignification process in the pulp and paper industry, aiming to enhance sustainability and efficiency. While traditional machine learning models, such as Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM), have been widely used, recent advancements in time series architectures provide significant improvements in prediction accuracy. This study adopts cutting-edge time series architectures and integrates them with explainability techniques (Explainable Artificial Intelligence, XAI) to analyze critical features and their temporal saliency, providing insights into the most influential variables in the delignification process. For a sequence length of 96, Crossformer attains the lowest error of 0.625±0.032, while for a sequence length of 24, LMS-AutoTSF achieves the lowest error of 0.281±0.0001. Additionally, we perform simulation analyses using the identified important features to evaluate the effects of input parameter changes–such as temperature or H-factor adjustments–on correlated variables and the target Kappa number. To model these interdependencies and generate realistic input scenarios, we employ a Conditional Variational Autoencoder (CVAE), which enables the adjustment of one input feature while automatically adapting correlated features in a coherent and interpretable manner. This allows for counterfactual simulations that help operators understand the dynamic impact of process modifications on the overall system behavior. By leveraging advanced forecasting models, XAI-driven feature analysis, and CVAE-based simulation studies, we aim to improve prediction accuracy, optimize resource usage, and enhance operational efficiency. This work underscores the potential of combining modern time series forecasting, explainability techniques, and generative modeling to advance delignification processes, contributing to a more sustainable future for the pulp and paper industry. We further extend our experimental analysis to another industrial pulp dataset comprising a large number of instances, where Crossformer achieves the lowest error of 0.283 ± 0.112, followed by LMS-AutoTSF with the second-lowest error of 0.367 ± 0.136, across average prediction lengths of 12, 24, and 48.

Abstract Research and development of CNC machines dedicated to rotational metal forming processes have made it possible to form difficult non–circular geometries and even more difficult axially asymmetrical ones. New processes require not only the development of new methods for creating metal–forming trajectories but also the identification of their advantages and disadvantages. This article presents mathematical equations and algorithms for trajectory design in the rotational metal forming of axially asymmetrical parts. Simple algorithms using conditional while–loops were developed that are compatible with modern CNC machines. The algorithms were used to metal form parts with complex axially asymmetrical geometry. An analysis was conducted to evaluate the influence of selected technological parameters on the trajectory generation process. The impact of rotational symmetry was assessed by analysing the number of commands required to execute a single forming movement using mandrels with circular, elliptical, square, and asymmetrical cross–sections. The $$\alpha $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>α</mml:mi> </mml:math> angle was examined for values $$\alpha =90^{\circ }$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>α</mml:mi> <mml:mo>=</mml:mo> <mml:msup> <mml:mn>90</mml:mn> <mml:mo>∘</mml:mo> </mml:msup> </mml:mrow> </mml:math> and $$\alpha &gt;90^{\circ }$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>α</mml:mi> <mml:mo>&gt;</mml:mo> <mml:msup> <mml:mn>90</mml:mn> <mml:mo>∘</mml:mo> </mml:msup> </mml:mrow> </mml:math> , while differences in trajectory programming between absolute–G90 and incremental–G91 positioning systems were analysed. Results from FEM simulations and laboratory tests were presented, in which an axially asymmetrical mandrel was employed, and EN AW–1050A aluminium alloy was formed. Advantages and limitations of the proposed trajectory design method were discussed. A modern division for Rotational Metal Forming processes was proposed. RMF was divided into subcategories: axially symmetrical ( Shear Forming—RMF SF and Metal Spinning—RMF MS ) and asymmetrical processes ( Rotationally Symmetrical—RMF RS and Axially Asymmetrical—RMF AA ).

Abstract Vision sensors like CMOS and CCD cameras are often used for in-process monitoring of melt pools in laser-based additive and welding processes, but they require transferring large amounts of data and computational processing resources. Event-based neuromorphic imagery, on the other hand, detects only the change in pixel intensity, thus potentially reducing the data amount and latency. With an event imager, this study develops a framework for melt pool condition classification, including image construction, time scale selection, optimal pixel selection, and sparse classification, to achieve a highly memory-efficient scheme. These are based on sparse sensing techniques with singular value decomposition (SVD) and QR pivoting, the two fundamental matrix transformations for linear dimensionality reduction. The framework is then validated by classifying a controlled experiment by exciting various mode shapes of liquid gallium pools of varying depths (3, 6, and 8 mm). At 200 pixels, the classifier can reach overall accuracy of 75%, while at 2000 pixels (0.013% of the total possible pixels), the accuracy is nearly 90% (89.86%). At the same number of pixels, random selection can only achieve 46% and 67%, respectively. The memory savings of the sparsely sampled event data compared to a conventional imager is about 500 times. In addition to performance, implementation and limitations of the framework are also discussed.

Abstract The advent of Industry 4.0 has reshaped modern manufacturing, driven by breakthroughs in cutting-edge technologies. A key example is the widespread deployment of sensors, which capture and transmit large volumes of operational data. This data surge has fueled the development of advanced Artificial Intelligence (AI) applications, enhancing manufacturing intelligence and efficiency. A key enabler of such intelligence is Time-Series Forecasting (TSF), which leverages historical data to predict future trends and events, thereby providing actionable insights for proactive decision-making. In parallel, Digital Twin (DT) technology has gained significant prominence due to its capacity for bidirectional communication with physical manufacturing systems, enabling unprecedented levels of real-time monitoring, control, and optimization. Despite their benefits, the combined adoption of TSF and DT technologies presents considerable challenges, particularly in developing integrated, closed-loop systems. This study addresses this gap by proposing a novel framework that unifies TSF with DTs for the early detection of potential collisions between manufacturing assets. The framework is demonstrated using a robotic assembly line, with a detailed account of the training and deployment process of a TSF–DT pipeline. The proposed proof-of-concept is designed to be generalizable, offering applicability across diverse manufacturing systems.

Abstract Although graph neural networks (GNNs) have achieved remarkable success for fault diagnosis, the mainstream node classification paradigm suffers from low efficiency. Furthermore, intrinsic correlations within raw signals are rarely exploited to address the insufficient fault knowledge in model training. To address these issues, a time–frequency constraint-guided graph-level feature representation learning method for few-shot fault diagnosis is proposed. It overcomes the inevitable challenges of graph reconstruction and model retraining associated with node-level diagnosis models, thereby enhancing the real-time responsiveness. Specifically, a feature-enhanced chain graph (FECG) with only a few edges is introduced, which improves the interpretability and efficiency of edge construction in input graphs. Further, a time–frequency constrained graph convolutional network (TFCGCN) is developed, which can guide the gradient descent direction during model training based on the designed time–frequency constraint loss, reducing the model's reliance on labeled faulty samples. To mitigate the attenuation of time–frequency constraints during cross-layer propagation, a node feature transfer technique is proposed, and it also enhances the feature extraction capabilities of graph convolution layers. Through ablation experiments and comparisons with various existing models, the effectiveness and superiority of the proposed FECG-TFCGCN were validated, with several extremely unbalanced training sets on axial flow pumps and machine tool spindles.