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.

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. 

Surface roughness plays an indispensable and fundamental role as a leading indicator of the surface quality of machined parts in the manufacturing process. The precise and effective monitoring and prediction of surface roughness is crucial for surface quality control. In this regard, the development of an in-process surface quality monitoring system is necessary, which has the promising potential to achieve this goal. Such a system typically comprises data-driven models for decision-making and sensing techniques for detecting associated process information. However, some challenges still exist in building such systems. Firstly, the architecture design and deployment of data-driven models, specifically deep learning (DL)-based models, demand adequate domain knowledge. Secondly, most models trained on specific tasks with limited datasets are prone to suppressing their versatility and generalization across different machining conditions. Additionally, in most cases, reliance on handcrafted features to represent dynamic information on various signals during model training necessitates extensive expertise in selecting appropriate feature types. Furthermore, due to the nature of their low dimensionality, handcrafted features have difficulty in capturing of overall process-related underlying patterns from dynamics signatures, which is time-varying and often occurs in transient events. To address these challenges, this paper proposes the regression-based pre-trained convolutional neural network (pre-trained CNN) combined with Mel-spectrogram images based on the transfer learning method for surface roughness prediction. Within the context, the architecture of the transfer model is slightly adapted from already well-trained CNNs. Initial weights in each layer of the CNN model are directly inherited and then fine-tuned through the Bayesian optimization tuning method. Besides, the audible sound signals are captured and subsequently converted into 2D Mel-spectrogram images with variant time lengths, which are separately engaged to retrain and validate four existing pre-trained CNN models (VGG16, VGG19, ResNet50V2 and InceptionResNetV2). Eventually, the effectiveness of proposed models and comparison of their predictive capabilities are further validated through a case study in the turning process. The results demonstrate that each applied pre-trained CNN model is capable of effectively predicting surface quality with satisfactory prediction results. Therefore, the proposed method can facilitate the establishment of a machining monitoring system concerning its accuracy, reliability, and robustness.

In the turning process, the surface roughness of the machined part is considered a critical indicator of quality control. Provided the conventional offline quality measurement and control is time-consuming, with slow feedback and an intensive workforce, this paper presents an online monitoring and prediction system for the effective and precise prediction of surface roughness of the machined parts during the machining process. In this system, the audible sound signal captured through the microphone is employed to extract the features related to surface roughness prediction. However, owing to the nonlinear phenomena and complex mechanism causing surface quality in the whole process, the selection of statistical features of the sound signal in both the time and frequency domains varies from one case to another. This variation may lead to false prediction results as sufficient domain knowledge is required. Therefore, the versatile and knowledge-independent features extraction method is proposed, which exploits deep transfer learning to automatically extract sound signal features in the time-frequency domain through pre-trained convolution neural networks (pre-trained CNN). The performance of prediction models based on two feature extraction methods – statistical feature extraction and automatic feature extraction was further tested and validated in the case study. The results demonstrate that the performances of the prediction model built on the automatically extracted features outperformed that developed with the statistical feature method concerning the accuracy and generalization of the prediction model. In addition, this study also provides solid theoretical and experimental support for developing a more precise and robust online surface quality monitoring system.

Rotor vibration and stationary displacement patterns observed in rotating machineries subject to local harmonic excitation are analysed for improved understanding and dynamic characterization. The analysis stresses the importance of coordinate transformation between rotating and stationary frame of reference for accurate results and estimation of dynamic properties. A generic method which can be used for various rotor applications such as machine tool spindle and turbo machinery vibration is presented. The phenomenon shares similarities with stationary waves in rotating disks though focuses on vibration in shafts. The paper further proposes a graphical tool, the displacement map, which can be used for selection of stable rotational speed for rotating machinery. The results are validated through simulation of dynamic response of a milling cutter, which is a typical example of a variable speed rotor operating under different load conditions.

Dynamic characteristics of machine tools and cutting tools have gained much attention from researchers and industry as it is one of the major factors limiting productivity due to excessive vibrations such as chatter during the cutting process. Numerous factors have to be taken into consideration when selecting material of the cutter body. This paper presents a comparison between two cutter bodies with the same geometry but made out of different alloys. Pre-hardened steel and conventional tool steel were investigated in order to highlight the advantages of selecting correct material to achieve high performance tools with respect of chatter resistance. The experimental part of this paper consists of impact testing, machining tests and surface integrity measurements. Operational dynamic parameters obtained through auto-regressive moving average model estimates from machining tests under stable and unstable conditions was used to characterise the performance. The findings are in correlation with material damping research and chatter analysis, thus giving a strong coupling to material selection in tool holders for enhanced process stability. The research also shows that operational dynamic properties obtained through indirect measurements is a valuable tool for process stability characterisation.

Machine tool joints have significant influence on the dynamic characteristics of the machine tool and therefore on the response of the machining system to excitations from the cutting process. In cases of unstable response, generally described as chatter, surface quality of a machined workpiece and tool life deteriorate significantly. This paper presents a novel way of exploiting joints in order to control the dynamic response of the system, by integrating a mechatronic tool holder (Joint Interface Module - JIM) in the machine tool. This system has a purposely designed joint interface with controllable natural characteristics (stiffness and damping). These characteristics are controlled by altering the applied pre-load on the internal joint interface of the tool holder. The preload on the joint interface is controlled by pneumatic means. In doing so, a milling process during which the stability limit was exceeded became stable during the machining process, without alteration of the process parameters.

Multi-layered nanostructured Cu and Cu-CNx composites synthesized by plasma-enhanced chemical vapour deposition were applied in the clamping area of a milling tool to suppress regenerative tool chatter. Scanning electron microscopy analysis showed a multi-layered nanostructure with excellent conformality, i.e. coating is not only uniform on planar surfaces but also around corners of the substrate. Cu:CuCNx nanostructured multilayers with thicknesses of approximately 0.5:1.6 mu m were obtained. With a diameter of 20 mm, the milling tool performed slotting processes at an overhang length of 120 mm. Modal analysis showed that a coating, with a thickness of approximately 300 mu m, can add sufficient damping without losing stiffness of the tool, to increase the critical stability limit by 50% or 100% depending on cutting direction.

Machining components out of tolerances is of no use in competitiveproduction. The machining system sets the limitations of dimensionalaccuracy and surface quality of a machined component. The capabilityof the machining system describes these limits in terms of specifiedvalues. This thesis deals with machining system capability analysismainly focused on machine tool static and dynamic stiffness.The influence of stiffness and flexibility on machining systemcapability is analytically and experimentally investigated. Theexperimental work presented in the thesis complies with the theoriesand shows the relation between machine tool capability and theoutcome on the machine component.The concept of capability analysis by elastic linked system andthe currently available tools for such an evaluation is presented anddiscussed. The basis of elastic linked system analysis is the use ofmeasurements under loaded condition. The machine tool is loadedwith a known force creating a test condition closer to real machining,compared to current methods of unloaded machine tools. Twomeasurement tools for elastic linked system capability analysis areexplained in the thesis: Loaded Double Ball Bar and ContactlessExcitation and Response System.The thesis consists of an analytical base and an experimental casestudy on spiral bevel gear face milling. The experiments are discussedand compiled with the given theories.

The spindle system is a critical part of a machine tool structure and its dynamic properties are important for the performance of the whole machining system. Currently the only way to extract the dynamic properties of a given structure is via experimental modal analysis. This approach, however, can only be employed on idle systems and is performed with the assumption that the dynamics of a system are independent of rotational speed. The latter assumption cannot be applied to spindle systems. This paper introduces a novel testing system for analysing machine tool spindles dynamic properties, consisting of real-time recursive estimation of modal and operational dynamic parameters, employed alongside a contactless excitation and response system. The presented approach allows analysing the spindle system condition and dynamic properties not only at discrete rotational speed intervals but also during continuous sweep of rotational speed.