This study comprises two main parts. The first part analyzes vibration data from turning operations performed at three different depths of cut to identify the most effective features for distinguishing between the resulting signals. Using a machine and deep learning-based classification approach, a thorough feature importance analysis was conducted to identify the most influential signal characteristics. Building on these findings, the second part of the study focuses on utilizing the most important feature identified in the first phase for near real-time tool wear monitoring. By tracking changes in this specific feature during machining, the system can detect wear progression through vibration signals, enabling more accurate and timely intervention. This two-step approach not only enhances the understanding of how vibrational features vary with cutting conditions but also offers a practical method for near real-time tool condition monitoring. It is important to note that the most influential feature is initially identified based on its sensitivity to controlled changes in cutting conditions and is subsequently tested as a tool wear indicator in the second part. Furthermore, this study demonstrates an offline trend analysis on recorded data rather than a deployed online monitoring system.

In manufacturing industries, monitoring the assembly operation performed in an assembly workstation is essential to improve product quality. Assembly monitoring enables meticulous measurement of step and cycle time and facilitates the identification of anomalies such as sequence breaks and missed steps. In this work, we propose an approach to model the actions performed by an operator in an assembly workstation, captured using vision cameras, as graphs. The spatial and temporal information from the video data was captured by modeling the interaction between objects within a video frame and between video frames, respectively. By classifying the graphs constructed through these interactions, we discern different action types, enabling a comprehensive understanding of assembly physics. Our approach was evaluated using two assembly operation datasets collected from industries, demonstrating its ability to identify assembly steps with a macro-average F1 score of 0.70 and 0.9052, respectively. This work aims to develop a real-time monitoring system capable of accurately detecting and localizing actions with an assembly cycle in an assembly workstation while maintaining computational efficiency and precision in the assembly physics modeling process.

Sapphire's high hardness and low fracture toughness make stable ductile cutting highly challenging. This study proposes oblique cutting as a simple and effective approach to improve sapphire's ductile removal capability. To elucidate the brittle-to-ductile transition (BDT) behavior and the mechanisms of crack initiation during oblique cutting, a model based on stress intensity factor theory and incorporating tool geometric parameters is established. The model reveals that the minimum stress intensity in the cutting zone occurs at 45 degrees tool inclination, corresponding to the lowest probability of crack initiation. Experiments demonstrate that introducing tool inclination markedly increases the BDT depth. Oblique 30 degrees cutting along the 180 degrees orientation achieves nearmicrometer BDT depths, while a 45 degrees inclination yields the most pronounced overall enhancement across four crystallographic orientations. Combined experimental observations and simulations further reveal that the plastic removal behavior of sapphire is governed by its crystallographic anisotropy, primarily manifested through variations in prismatic dislocation slip. When the tool-induced shear stress is collinear with the Burgers vector of prismatic dislocations, coplanar slip is activated, leading to stable and continuous plastic removal, a significant increase in BDT depth, and outward propagation of radial cracks without disruption of the plastically deformed region. In contrast, misalignment between the shear stress direction and the Burgers vector promotes cross-slip, destabilizes plastic flow, and leads to localized tearing, thereby deteriorating surface quality. Overall, oblique cutting, by adjusting the tool inclination and leveraging sapphire's crystallographic anisotropy, provides a simple and effective approach to enhance BDT depth and achieve high quality SPDT.

Hard X-ray nanoprobe diffraction microscopy is employed to investigate machining-induced residual lattice strain in single-crystal sapphire following ultra-precision orthogonal plunge cutting. In this study, tilt-series and single-angle acquisition strategies are systematically compared to evaluate their capability for resolving lattice variations associated with the machining process. An analytical framework is developed to enable the efficient and reliable extraction of strains, which serve as strain-based indicators of changes in the dominant deformation mechanism. The measured high-dimensional strain exhibits spatial heterogeneity and systematic evolution along the cutting path, consistent with deformation-regime changes from ductile response to crack-prone behavior.

Although sapphire is regarded as a remarkable engineering material for micro- and optical application fields owing to its exceptional mechanical, chemical, and optical properties, it has long been considered difficult to fabricate because of its pronounced anisotropy, particularly in ultra-precision machining. This study employed a two-step approach to predict the critical depth of cut (CDC), the threshold at which cracks appear on the machined surface, in ultra-precision orthogonal cutting of single crystal sapphire with respect to various cutting directions. The first step involved modeling the relationship between cutting forces and process parameters, whereas the second step focused on predicting the critical depth of cut based on the modeled forces. In the first step, machine learning algorithms were employed to predict cutting forces through data pre-processing. To develop an AI-driven model predicting anisotropic cutting-force behavior, both machining process parameters and crystallographic properties of sapphire were used as input variables for training. This model successfully captured the intricate and non-linear relationships governing force variations across distinct crystallographic orientations. In the second step, the predicted cutting forces were used as inputs for a regression model to estimate the CDC. The proposed framework was experimentally verified through orthogonal plunge-cut tests conducted on an ultra-precision CNC machining center with a 1 nm command resolution. This study demonstrated improved predictive accuracy compared with conventional approaches, offering a practical and efficient solution for optimizing ultra-precision machining processes of single crystal sapphire.

High-resolution energy data is increasingly central to Industry 4.0, where electrical signals such as three-phase voltage and current carry rich information about machine condition, tool wear, and process dynamics. Capturing this information in practice remains difficult: commercial power analysis are largely proprietary, offer limited or no access to high-sampling rate data for transient analysis, restrict access to raw waveform data, and offer no customization, while general-purpose open hardware lacks the front-end accuracy, isolation, and robustness required for industrial measurement. This paper presents Autonomous Energy Monitoring System (AEMS), an open-source, low-cost, and modular platform supported by a host, edge-gateway, and optional cloud software stack that enables autonomous, long-duration acquisition independent of a continuously connected host and thereby closes this gap by combining research-grade fidelity with industrial deployability. The system acquires three-phase voltage and current through an isolated front-end and a 24-bit, simultaneously sampling analog-to-digital converter, managed by a dual-core architecture that separates deterministic acquisition and on-board logging from host communication and control. Industrial interfaces (Ethernet, RS-485/Modbus, and BLE) together with hardware-level synchronization enable scalable, time-aligned acquisition across multiple machines, supported by a complete host, edge-gateway, and optional cloud software stack. We validate the platform on a three-axis CNC machining center, where it resolves spindle, feed-drive, rapid-traverse, and material-removal energy states and detects feed-rate changes as small as 50 mm/min. By releasing the full hardware and firmware openly, this work aims to democratize access to high-fidelity energy monitoring for both researchers and small and medium-sized manufacturers.

CuSn10–IN718 multi-material structures were fabricated by laser-directed energy deposition (L-DED) to evaluate interfacial bonding mechanisms and the resulting thermal, electrical, and mechanical responses. The CuSn10–IN718 interface exhibited metallurgical continuity without continuous interfacial delamination, although localized microcracks and CuSn10 infiltration were observed near the IN718-side fusion region. SEM–EDS analysis revealed elemental redistribution across the transition zone, with Mo and Nb enrichment and substantial Cu–Ni–Fe–Cr intermixing. TEM–EDS analysis identified compositionally distinct Cu-rich, Ni-rich, Ni–Cu–Sn-rich, and Cr-enriched regions, which were attributed to Marangoni-driven melt-pool convection, solute partitioning, heterogeneous nucleation, and non-equilibrium solidification. EBSD analysis showed predominantly equiaxed α-Cu(Sn) grains in the CuSn10 region, columnar γ-FCC grains in the IN718 region, and mixed refined grains within the transition zone. The interface also exhibited the highest average GND density, approximately 2.53 × 1013 m−2, which contributed to dislocation strengthening. Nanoindentation identified the presence of a heterogeneous strengthening zone at the interface, where nano-hardness and elastic modulus increased by 31.23

Ultra-precision machining requires a fundamentally different level of technical capability compared to conventional machining, as it must achieve nanometer-scale dimensional accuracy and surface finish. In this process, setting the workpiece coordinate is of particular importance because even minute setup errors can critically impact the final machining results. This paper provides a comprehensive review of various techniques for setting work coordinates in ultra-precision machining. First, these techniques are broadly categorized into indirect methods, which measure the tool position indirectly using sensors or probes, and direct methods, where the cutting tool itself serves as a sensor to detect the moment of contact or directly measure the gap between the tool and the workpiece. Although indirect methods are relatively straightforward to automate and enhance process stability, additional errors may occur when replacing probes. Meanwhile, direct methods allow for precise detection of contact moments or extremely small gaps; however, in the case of contact-based approaches, there is a substantial risk of surface damage or breakage of ultra-precision tools, whereas non-contact methods can be both expensive and highly sensitive to environmental factors. This paper examines a variety of contact detection techniques, including acoustic emission (AE), accelerometers, force sensors, electrical phenomena, and disturbance observers as well as non-contact detection methods using lasers, optical sensors, and electrical phenomena. In addition, it explores how uncertainty analysis and compensation strategies based on standards such as ISO 15530 can minimize the impact of setup errors on overall machining accuracy. Ultimately, the paper emphasizes that, in order to maximize the performance of ultra-precision equipment, peripheral technologies capable of achieving nanometer-scale precision in the workpiece coordinate setting process must continue to advance and be integrated.

The real-time monitoring of assembly operations in manufacturing industries can be used for manufacturing process optimization, which is crucial to manufacturers. It helps to improve productivity by automatically identifying the bottleneck and enhancing product quality by detecting errors and providing feedback to rectify them in real-time. However, developing a robust and reliable assembly monitoring system is not trivial due to the varying length of fine-grained assembly steps and anthropometric variations associated with assembly workers. To tackle the challenge, conventionally, wireless body-worn sensors have been used, leading to operator discomfort, and raising safety concerns. In this work, we propose a novel technique to automatically recognize and localize the assembly steps in real time called the State Machine Integrated Recognition and Localization (SMIRL). SMIRL is comprised of an inference machine and a state machine. They are responsible for detecting and localizing the actions, respectively. SMIRL can measure the duration of individual assembly steps and the entire cycle. Additionally, SMIRL can also detect the mistakes that may occur in an assembly and raise an alert to notify the operators in real time. The mistakes here can be breaking the predefined assembly sequence (Sequence Break) or missing any of the assembly steps (Missed steps). The effectiveness of SMIRL was evaluated against two datasets, with one being from an assembly workstation in industry and the other from a laboratory. The result shows that SMIRL can detect and localize the actions with an Intersection over Union (IoU) score of 87.53%, and identify Sequence Breaks and Missed Steps with F1-Scores of 86.64% and 87.45%, respectively. Through this study, we aim to contribute towards real-time monitoring of human-centric assembly operations to facilitate smart manufacturing.

With the growing demand for the fabrication of microminiaturized components, a comprehensive understanding of material removal behavior during ultra-precision cutting has become increasingly significant. Single-crystal sapphire stands out as a promising material for microelectronic components, ultra-precision lenses, and semiconductor structures owing to its exceptional characteristics, such as high hardness, chemical stability, and optical properties. This paper focuses on understanding the mechanism responsible for generating anisotropic crack morphologies along various cutting orientations on four crystal planes (C-, R-, A-, and M-planes) of sapphire during ultra-precision orthogonal cutting. By employing a scanning electric microscope to examine the machined surfaces, the crack morphologies can be categorized into three distinct types on the basis of their distinctive features: layered, sculptured, and lateral. To understand the mechanism determining crack morphology, visualized parameters related to the plastic deformation and cleavage fracture parameters are utilized. These parameters provide insight into both the likelihood and direction of plastic deformation and fracture system activations. Analysis of the results shows that the formation of crack morphology is predominantly influenced by the directionality of crystallographic fracture system activation and by the interplay between fracture and plastic deformation system activations.

As the most promising and advanced technology, ultra-precision machining (UPM) has dramatically increased its production volume for wide-range applications in various high-tech fields such as chips, optics, microcircuits, biotechnology, etc. The concomitantly negative environmental impact resulting from huge-volume UPM has attracted unprecedented attention from both academia and industry. Accurate energy prediction of ultra-precision machine tools (UPMTs) can provide significant insight into energy planning, machining strategy, and energy conservation. Data-driven models for predicting energy have become increasingly popular due to their high accuracy and low modeling difficulty. However, existing data-driven models only focus on ordinary precision machine tools, and their applications on UPMTs are hardly studied. To fill the gap, this paper proposed a data-driven model constructed with 1DCNN-LSTM-Attention layers for predicting the instantaneous power profile of a five-axes UPMT. In the data-preparation phase, an advanced G-code interpreter was developed to generate the working status dataset from the G-code command and accurately match them with the power data collected. Random hyperparameters searching method was adopted to tune the 1DCNN-LSTM-Attention structure for better accuracy in the model creation phase. Finally, the sensitivity of these hyperparameters on the model performance was analyzed. Results demonstrate that the learning rate, 1DCNN, LSTM and dense layer numbers are identified as critical parameters affecting the model performance. The optimized 1DCNN-LSTM-Attention model outperforms other models, achieving an R 2 value of 0.93. This work first validate the feasibility of utilizing advanced machine learning techniques for predicting energy consumption in UPM field, which can further promoting energy-efficient and sustainable UPM practices by digitalizing the energy consumption process.

With the widespread adoption of Industry 4.0 and smart manufacturing concepts across industries, sensor development, system integration, and data analysis have become important aspects of efficient manufacturing operations. In addition to monitoring the performance of machines, significant importance is given to human condition monitoring in factories, using body-worn sensors to ensure the well-being of workers and for injury prevention. This research presents the development of a body-worn sensor system capable of sampling acceleration and rotation data up to 400 Hz and wirelessly transmitting the data over Bluetooth Low Energy (BLE). Further, the communication protocols for data acquisition, data communication within the device, Real Time Operating System (RTOS) programming, and multi-threading are described. This system is designed in such a way that multiple devices can be connected to the Data acquisition (DAQ) system simultaneously, and data is collected from the sensors in a synchronized manner. This information is valuable for the wider adoption of sensor systems for human condition monitoring in industry. Lastly, to test the system's capabilities, a case study of lifting risk assessment is presented, where data collected from the accelerometer and gyroscope are used to determine a relative estimate of the physical stress associated with a manual lifting task by using different machine learning (ML) algorithms. The case study highlights how sensor placement, feature extraction, and sensor types influence machine learning models. As the sensor system can perform computations on the edge, a framework to carry out real-time lifting risk assessment using lightweight algorithms and the most important data features is proposed.

In this study, a functional gradient material (FGM) structure composed of a nickel alloy (IN718), and a cobalt alloy (CoCrMo) was additively manufactured using a co-axial powder-fed laser-directed energy deposition (L-DED) system. The high manufacturing flexibility of L-DED enabled the seamless deposition of IN718-CoCrMo FGM structure through interfacial bonding driven by thermal gradient and cool-down mechanisms. Microscopic analysis confirmed the absence of cracks or delamination in the CoCrMo-IN718 interfacial bonding region. The SEM-EBSD microstructural analysis and micro-hardness testing were performed on the as-printed CoCrMo-IN718 FGM primarily to correlate the hardness properties-microstructural grain phase morphology between the parent alloys and their interfacial bonding region. It was observed that the average hardness of the CoCrMo-IN718 interface zone (322.83 HV1) fell between IN718 (268.67 HV1) and CoCrMo (359.75 HV1) regions. The EBSD analysis reports indicated that along the build direction of CoCrMo-IN718 FGM, the preferential grain orientation aligned in [100] with grain structure transitioning from equiaxed -> columnar -> elongated columnar dendrites -> equiaxed grain, predominantly comprised of face-centered cubic (FCC)-gamma (gamma) phase crystal structures. Relatively, coarser grain structures were observed in the interface bonding region, attributed to the analogous crystallography space groups, and prolonged localized thermal gradients. (c) 2024 The Authors. Published by ELSEVIER Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)

In this paper, material deformation during ultra-precision machining (UPM) on the C-, R-, and A-planes of sapphire was investigated using the slip/fracture activation model where the likelihood of activation of individual plastic deformation and fracture systems on different crystallographic planes was calculated. The stress data obtained from molecular dynamics (MD) simulations were utilized, and the slip/fracture activation model was developed by incorporating the principal stresses in calculating the plastic deformation and fracture cleavage parameters. The analysis methodology was applied to study material deformation along various cutting orientations in sapphire. The stress field at crack initiation during UPM on C-, R-, and A-planes of sapphire was calculated using molecular dynamics (MD) simulations. An equation describing the relationship between crack initiation and its triggering parameters was formulated considering the systems' plastic deformation and cleavage fractures. The model can qualitatively predict the crack initiations for various cutting orientations. The proposed model was verified through ultra-precision orthogonal plunge cut experiments along the same cutting orientations as in the MD simulations.

Single crystalline sapphire (alpha-Al2O3) possesses superior mechanical, thermal, chemical, and optical properties over a wide range of temperatures and pressure conditions, allowing it for a broad spectrum of industrial applications. For the past few decades, research has aimed at comprehensive understanding of its plastic deformation mechanisms under mechanical loading. In this study, we have employed molecular dynamics (MD) simulations to study rhombohedral twinning of sapphire, which is of critical importance in understanding the plastic deformation of sapphire as one of most commonly observed deformation modes. Since the critical resolved shear stress (CRSS) plays a pivotal role in describing the activation of slip systems, it is adopted in this study as the key parameter for analysis. The CRSS is calculated during the uniaxial compression test of a cubic sapphire crystal, oriented to exclusively activate rhombohedral twinning deformation, under simulation conditions such as temperature, strain rate, and system size. Furthermore, a theoretical model of CRSS is constructed based on theories of thermal activation processes, then empirically fitted to CRSS data gathered from the MD simulations. This model accurately captures the relationships between CRSS and external parameters including temperature, strain rate, and system size and shows excellent agreements with the simulation results.

Ultra-precision work coordinate system (WCS) setting by measuring the relative distance between the workpiece and the tool is a key element to further improve the accuracy of ultra-precision machine tools. Touch probe is the most widely used WCS method in conventional machining, yet it cannot be used in ultra-precision machining (UPM) applications due to the nature of contact with the workpiece, potentially resulting in surface damage or tool breakage. Furthermore, indirect methods, such as a touch probe, require the sensor to be replaced with a tool after setting the work coordinate. This induces uncertainty. In this paper, the repeatability of the newly proposed non-contact and direct WCS method using electrical breakdown (E.B.) was evaluated for the use in UPM. The standard deviation of the tool positions after performing the method 11 times was under 40 nm. Using a tungsten carbide tool and aluminum workpiece, the proposed method's repeatability and surface damage were investigated. (c) 2023 The Authors. Published by ELSEVIER Ltd.

Detection and localization of activities in a human-centric manufacturing assembly operation will help improve manufacturing process optimization. Through the human-in-loop approach, the step time and cycle time of the manufacturing assemblies can be continuously monitored thereby identifying bottlenecks and updating lead times instantaneously. Autonomous and continuous monitoring can also enable the detection of any anomalies in the assembly operation as they occur. Several studies have been conducted that aim to detect and localize human actions, but they mostly exist in the domain of healthcare, video understanding, etc. The work on detection and localization of actions in a manufacturing assembly operation is limited. Hence, in this work, we aim to review the process of human action detection and localization in the context of manufacturing assemblies. We aim to provide a holistic review that covers the current state-of-the-art approaches in human activity detection across different problem domains and explore the prospective of applying them to manufacturing assemblies. Additionally, we also aim to provide a complete review of the current state of research in human-centric assembly operation monitoring and explore prospective future research directions.

Work coordinate setup in an ultra-precision machine tool is one of the important tasks to fabricate a structure at the desired position with high accuracy. Setting up the work coordinate is very challenging because it requires high precision, direct measurement, and non-contact preferred. This paper proposes a new method to measure the relative distance between tool-work materials using the electrical breakdown where current flows through electrical insulator when an applied voltage is higher than the breakdown voltage. The applied voltage is linearly proportional to the relative distance in nanoscale. Experiment with Al6061, SS316, AISI1018 steel, and OFHC Cu work materials, and WC and CBN tools showed a successful and easy application of this method in work coordinate setup with 70 nm uncertainty at low applied voltage. Surface damages by the electrical breakdown of Al6061, SS316, AISI1018 steel, and OFHC Cu were not found at less than or equal to 1, 2, and 3 V, respectively. An automated detection test was conducted and found approaching speed of 0.1 mm/min without surface damage. Standard uncertainty analysis validated the confidence of the proposed method.

Ability to detect faults in manufacturing machines have become crucial in the era of Smart Manufacturing to enable cost savings from erratic downtimes, in an effort towards Green Manufacturing. The power consumption data provides myriad of information that would facilitate condition monitoring of manufacturing machines. In this work, we retrofit an ultra-precision CNC machine using an inexpensive power meter. The data collected from the power meter were streamed in real-time to Amazon Web Services (AWS) servers using industry standard Message Query Telemetry Transport (MQTT) protocol. The error identification study was carried out in two-folds, we first identify if the error has occurred followed by classifying the type of controller error. The study also develops anomaly detection models to identify normal operating condition of the machine from the anomalous error states. Anomaly detection was particularly favorable for manufacturing machines as it requires data only from the normal operating conditions of the machine. The developed models performed with macro F1-Score of 0.9971 ± 0.0012 and 0.9974 ± 0.0018 for binary and multiclass classification respectively. The anomaly detection models were able to identify the anomalous data instances with an average accuracy of 95

Recognition and localization of actions in manufacturing assembly operations improves productivity and product quality by identifying bottlenecks and assembly errors. In our previous work, we developed an approach that can recognize and localize the assembly standard operating procedures (SOP) steps in real-time using vision cameras. In this work, we augment the previous study with the ability to detect objects corresponding to the step being performed. Additionally, identifying non-value-added (NVA) activities in an assembly operation is challenging, hence, in this study, we propose an approach to detecting NVA activities by considering the out-of-distribution for deep learning models.