Data-driven systems have demonstrated significant value in real-time surface roughness evaluation and pre- diction for machining processes. This study presents a comprehensive methodology for evaluating three core elements critical to decision-making in machining monitoring: sensor-based dynamic signal selection and pro- cessing, sensory fusion scenarios, and Machine Learning (ML) models. Unlike previous research that often an- alyzes these elements in isolation, this study emphasizes their collective impact on unified datasets. The proposed methodology is validated using experimental data from machining trials on two distinct machines during the finishing process of hard turning. Hard turning is a widely employed finishing operation in manufacturing that directly affects dimensional accuracy, surface integrity, and surface finish, which are key characteristics of machined parts. Surface roughness, as an essential indicator of surface quality, plays a pivotal role in the functional performance of end products, necessitating accurate monitoring and assessment throughout the process. To optimize performance, Bayesian Optimization was employed for automatic hyperparameter tuning, facilitating efficient exploration of optimal parameters. The predictive capabilities of trained ML models were subsequently evaluated using performance metrics and quantitatively assessed for uncertainty through Predic- tion Intervals (PIs), calculated via non-parametric Kernel Density Estimation. Results indicate that the Wavelet Packet Transform method significantly enhances the predictive performance across all ML models. Among the evaluated models, Support Vector Regression and K-Nearest Neighbors demonstrated superior predictive accu- racy and minimal uncertainty across all signal processing methods. This work provides actionable guidelines for researchers and manufacturers in selecting optimal combinations of methodologies for developing accurate, reliable, and generalizable data-driven surface quality monitoring and prediction systems, particularly for hard part turning applications.

Advanced manufacturing systems demand the utilization of technologies, methods and capabilities to improve production efficiency or productivity, while ensuring environmental and societal sustainability. Digitalization emerges as an alternative solution for improving the monitoring capabilities of manufacturing systems and consequently enhance the decision-making process. However, the widespread adoption of digital solutions introduces complexities in measurement reliability, data management, and environmental concerns in terms of e-waste and data storing. Therefore, enhancing monitoring capabilities while minimizing resource consumption is crucial for ensuring system reliability in a sustainable way. This research introduces a methodology for assessing the monitoring condition of manufacturing systems. By integrating functional and dysfunctional analysis, approaches that focus on identifying critical functions and potential failure modes of a system, the proposed methodology provides a comprehensive system perspective and targeted directives for improvement. The effectiveness and versatility of the methodology are demonstrated and discussed through its application to various manufacturing systems at a component, machine, and line level.

Numerous studies are available regarding the effect of PVD and CVD coatings on cutting tools (inserts), cutting parameter optimization, and the application of the minimum quantity lubrication on the reduction of cutting tool wear and the improvement in surface quality of the machined parts. However, there still exists the deficiency of the comprehensive analysis of improving machining performance by suppressing high frequency vibration (micro-vibration) at the cutting edge due to the random nature of cutting force. The present study aims to mitigate this challenge of suppressing micro-vibration by applying the high dynamic stiffness multilayered Cu: CuCN<inf>x</inf> nanocomposite coating at the close proximity of cutting edge (in between the cutting insert and shim) by synthesizing the Cu:CuCN<inf>x</inf> coating on conventional cemented carbide (WC-Co) square shims. The primary objective of this study was to experimentally investigate the effect of Cu:CuCN<inf>x</inf> coating's morphology on machining performance. Coating morphology was characterized by the total coating thickness and total number of alternative Cu and CuCN<inf>x</inf> layers in a certain coating thickness. Machining performance was evaluated based on the criteria of cutting tool life and machined part's surface quality. External longitudinal turning operations of SS2541-03 alloy steel (34CrNiMoS6) material with rough cutting parameters and wet condition (using cutting fluid) were adopted for evaluating machining performance. Three different Cu:CuCN<inf>x</inf> coating series- A, B and C were synthesized by means of a double cathode Reactive High-Power Impulse Magnetron Sputtering (R-HiPIMS) deposition system. Coatings of series-A were deposited on steel disc substrates, and were used to evaluate the Cu:CuCN<inf>x</inf> nanocomposite coating's mechanical properties as a function of total number of Cu and CuCN<inf>x</inf> layers in a fixed coating thickness. Mechanical properties of the coatings were investigated by Vickers micro-indentation, and the damping loss factor of the coating was evaluated on the basis of indentation creep measurements under room temperature. Results from the analysis with coating series A demonstrated that the maximum elastic modulus, loss factor and loss modulus values of the coating was obtained when the ratio of total number Cu and CuCN<inf>x</inf> layers to coating thickness (n/h) is 0.6. However, the hardness, H/E and H³/E² values were observed to be increasing with increasing number of total layers. The coating with optimum mechanical properties exhibited the highest loss modulus of 2.85 ± 0.03 GPa confirming the high dynamic stiffness of Cu:CuCN<inf>x</inf> nanocomposite. Coated shims prepared with coating series- B and C were used to evaluate the effect of total number of Cu and CuCN<inf>x</inf> layers and the effect of total coating thickness on the machining performance, respectively. From the turning tests with conventional shim and coated shims it was evident that the coated shim with 200 μm Cu:CuCN<inf>x</inf> coating (sample C3) increased the cutting tool life by at least 50 % and reduced the machined workpiece's surface roughness by 15 %. For all turning tests, the thicknesses of coated shims and corresponding conventional uncoated shim were kept constant. The maximum error between the experimental and predicted values of the mechanical properties of coating series-B was found to be less than 10 %Moreover, in case of 200 μm Cu:CuCN<inf>x</inf> coating containing 150 layers of Cu and CuCN<inf>x</inf> phases, the coated shim (sample B3) was able to increase the cutting tool life by at least 167 %, and the machined workpiece's average surface roughness was reduced by 10 %. Analysis of the acquired vibration signals during turning tests, indicated that the cutting tool life was prominently affected by the higher frequency vibration (>7000 Hz) at the tool's cutting-edges. It was observed that with the application of 200 μm Cu:CuCN<inf>x</inf> coating in coated shim, the root mean squared (RMS) vibration energy in overall frequency range (0 to 30,000 Hz) was reduced by 40 %. From material and mechanical characterization, it was postulated that the primary vibration energy dissipation mechanisms of the multilayered nanocomposite coating are the interface frictional energy loss between the alternative Cu and CuCN<inf>x</inf> layers and the intrinsic damping due to grain boundary sliding in CuCN<inf>x</inf> layers.

This paper presents a novel design approach to soft robotic fingers based on the Fin Ray effect, which mimics the flexible yet adaptive behavior of fish fins. These soft, versatile grippers are ideal for applications requiring gentle manipulation and environmental adaptability. The study focuses on integrating multi-stage stiffening mechanisms into 3D-printed thermoplastic polyurethane (TPU) fingers. These mechanisms, featuring sequentially engageable inner structures, allow a multi-stage grasping load via increased deformation. By combining experiments with simulations, this work demonstrates how these inner structures improve the gripper's functionality and extend its application potential in soft robotics.

The integration of Artificial Intelligence into industrial maintenance remains challenging due to the scarcity of high-quality data representing faulty conditions. Machine Learning models trained on laboratory testbed data often fail to generalize effectively in real workshop environments. This study evaluated the effectiveness of Transfer Learning models in handling this domain shift challenge compared with Machine Learning models. Their potential to address the generalization gap was assessed by analyzing the model adaptability from lab-recorded data to data from emulated workshop conditions, where real-world variability was replicated by embedding synthetic noise into the lab-recorded data. The case study focuses on detecting rotor unbalance through bearing vibration signals at varying speeds. A Support Vector Classifier was trained on the transformed features for both models for binary classification. Model performance was assessed under varying data availability and noise conditions to evaluate the impact of these factors on classification accuracy, sensitivity, and specificity. The results show that Transfer Learning outperforms Machine Learning, achieving up to 30% higher accuracy under high-noise conditions. Although the Machine Learning model exhibits greater sensitivity, it misclassifies balanced cases and reduces specificity. In contrast, the Transfer Learning model maintains high specificity but has difficulty detecting mild unbalance levels, particularly when data availability is limited.

Surface roughness is an essential attribute of surface quality in the machining process to ensure the mechanical functionality of machined parts. Effective in-process monitoring of surface roughness is indispensable, which can be achieved through intelligent monitoring and prediction systems, utilizing data-driven models and dynamic process signatures. Notably, the performance of these systems, particularly in terms of prediction accuracy and robustness, is hindered by the limited application of data-driven models, especially deep learning models, which are intensive data-demanding. The inaccessibility of ample surface roughness data and corresponding process signatures leveraged for model building poses a significant challenge. In response to this challenge, as an emerging generative modelling approach, a classifier guidance diffusion model renowned for process stability and image generation with high fidelity and sufficient diversity is introduced to surmount data scarcity. The pre- trained diffusion is applied to synthesize audible sound signals collected from a machining process with the guidance of gradients from a classifier. After that, ground truth signal data mixed with synthesized ones in different proportions are leveraged to train and test the pre-trained model – VGG16, for surface roughness prediction in a transfer learning process. The results demonstrate that the proposed model can effectively generate synthesized 2D Mel-spectrogram images of audible sound signals with superior quality, further boosting the prediction performance of VGG16 in terms of its prediction accuracy and generalization under an enriched dataset. 

The future of manufacturing will increasingly depend on the autonomous operation of machining systems. Currently, most machine tools lack the capability to adjust their structural properties, such as stiffness and damping, limiting their adaptability to changing machining conditions. A lathe spindle with adjustable stiffness was therefore developed to eliminate this impediment. This design of controlled preload of a front-bearing node allowed modifications of the spindle's static and dynamic properties. This innovation aims to create a mechatronic system that facilitates autonomous machining by adjusting spindle stiffness. This would result in (i) enhanced manufacturing accuracy, (ii) compensation for workpiece deflection, and (iii) suppression of self-excited vibrations during turning. The paper details the spindle structure concept, the finite element model calculations of the bearing node with its adjustable stiffness, and the results of experimental testing of a prototype. The proof of concept demonstrated that spindle stiffness could be increased by approximate to 10% by changing the preload from low to high.

The early identification of a defect that is developing in a bearing is crucial for avoiding failures in rotating machinery. Frequency domain analysis of the vibration signals has been shown to contribute to a better understanding of the nature of a developing defect. Early signs of degradation might be more noticeable in certain frequency bands. The advantages in identifying and monitoring these bandwidths are several: prevention of serious machinery damages, reduction of the loss of investments, and improvement of the accuracy in failure predicting models. This paper presents and compares two approaches for the diagnosis of bearing faults. The first approach was knowledge-based. It relied on principles of mechanics to interpret the measured vibration signals and utilized prior knowledge of the bearing characteristics and testing parameters. The second approach was data-driven whereby data were acquired exclusively from the vibration signal. Both approaches were successfully applied for fault diagnosis by identifying the frequencies of the vibration spectra characteristic for the bearing under study. From this, bandwidths of interest for early fault detection could be determined. The diagnostic abilities of both approaches were studied to analyze and compare their individual strengths regarding the aspects of implementation time, domain knowledge, data processing associated knowledge, data requirements, diagnostic performance, and practical applicability. The advantages, apparent limitations as well as avenues for further improvement of both approaches are discussed.

The transition from conventional standalone metrology to integrated metrology has been accelerating in advanced manufacturing over the past decade. This keynote paper defines the concept of integrated metrology, which extends beyond parts inspection and encompasses processes and manufacturing equipment to enhance efficiency and productivity. The paper presents the characteristics, benefits, constraints, and future possibilities of integrated metrology for parts, processes, and equipment. It also includes a classification of the physical quantities of measurands, the corresponding measuring instruments, data and communication methods, uncertainty, and traceability. The paper also discusses future challenges and emerging trends.

The performance of a machine tool is directly influenced by the characteristics of the floor, subsoil, and their interaction with the installed machine. Installing a machine tool in its operational environment poses a distinct challenge that bridges mechanical and civil engineering disciplines. This interdisciplinary issue is often overlooked within the individual separate disciplines. However, effectively addressing this challenge requires a comprehensive understanding of mechanical and civil engineering principles. To address this problem, the present study proposes a method for improved modeling of the dynamic properties of the machine tool by considering the foundation and the subsoil on which it is installed. The method is based on finite element modeling. Linear models of the system components and the connections between them were used. These, supplemented with damping expressed by complex stiffness, made it possible to determine the natural frequencies, mode shapes, and frequency response functions (based on which the transmissibilities were obtained). Based on the experimentally verified models of vertical and horizontal lathes, the sensitivity analysis aimed at estimating the impact of changes in system parameters on vibration transmissibility for a floor-type and a block-type foundation was conducted. Thus, it was possible to identify those machine tool-support-foundation-subsoil system parameters that had the most significant impacts on the vibration's transmissibility. After analyzing the cases discussed, it became evident that the transmissibility of vibrations is primarily influenced by two key factors. First and foremost, the properties of the structural loop of the machine tool played a significant role. Additionally, the characteristics of the subsoil on which the foundation was situated emerged as a crucial determinant in the observed vibration transmissibility.