Assisted Machining Research Articles

Effect of ultrasonic vibration on fatigue life of Inconel 718 machined by high-speed milling: Physics-enhanced machine learning approach

Ultrasonic assisted high-speed machining (UAHSM) can be served as a thermomechanical surface sever plastic deformation (SSPD), because of the high-frequency impact load exerting to the sample together with thermomechanical loads due to shearing and plowing. Despite existing of few works which studied the impact of ultrasonic vibration on fatigue life assessment of difficult-to-cut material by experimental approach, they couldn’t provide an in-depth analysis to identify the underlying mechanisms of fatigue due time-consuming and costly fatigue life tests. Hence, elucidating the role of ultrasonic vibration in UAHSM on variation of fatigue life needs further studies. In order to do so, in the present work, a hybrid predictive approach based using ANFIS-based machine learning model and micromechanical Navaro-Rios (NR) fatigue crack propagation model has been introduced to directly correlates the UAHSM’s parameters to fatigue life. Here the former correlates feed rate, cutting velocity and vibration amplitude as process inputs, to surface integrity aspects (SIA) viz residual stress, roughness and grain size as output. Then, the modeled SIA are correlated to fatigue life using the former. The introduced hybrid model was then verified through series of UAHSM by examining the fatigue lives of milled Inconel 718 using four-point bending fatigue tests. Upon confirmation of the developed model, a comprehensive study was carried out to find how the process factors impact variation of SIA and subsequently fatigue. It was found from the results of developed models and confirmatory experiments that the role of ultrasonic vibration on improved fatigue life is mainly due to inducing compressive residual stress and more refined microstructure than the roughness.

Rotary ultrasonic assisted machining of aramid fiber–reinforced polymer composite: a numerical and experimental investigation using various cutting tools

Rotary ultrasonic assisted machining of aramid fiber–reinforced polymer composite: a numerical and experimental investigation using various cutting tools

Pelabelan Sentimen Berbasis Semi-Supervised Learning menggunakan Algoritma LSTM dan GRU

In the sentiment analysis research process, there are problems when still using manual labeling methods by humans (expert annotation), which are related to subjectivity, long time, and expensive costs. Another way is to use computer assistance (machine annotator). However, the use of machine annotators also has the research problem of not being able to detect sarcastic sentences. Thus, the researcher proposed a sentiment labeling method using Semi-Supervised Learning. Semi-supervised learning is a labeling method that combines human labeling techniques (expert annotation) and machine labeling (machine annotation). This research uses machine annotators in the form of Deep Learning algorithms, namely the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms. The word weighting method used in this research is Word2Vec Continuous Bag of Word (CBoW). The results showed that the GRU algorithm tends to have a better accuracy rate than the LSTM algorithm. The average accuracy of the training results of the LSTM and GRU algorithm models is 0.904 and 0.913. In contrast, the average accuracy of labeling by LSTM and GRU is 0.569 and 0.592, respectively.

Magnetic and ultrasonic vibration dual-field assisted ultra-precision diamond cutting of high-entropy alloys

Despite the remarkable achievements in single-energy field-assisted diamond cutting technology, its performance remains unsatisfactory for processing high-entropy alloys (HEAs), targeted for next-generation large-scale industrial applications due to their exceptional properties. The challenge lies in overcoming the limitations of current single-energy field-assisted processing to achieve ultra-precision manufacturing of these advanced materials. This study proposes a multi-energy field-assisted ultra-precision machining technology, the magnetic and ultrasonic vibration dual-field assisted diamond cutting (MUVFDC), to address the current challenges. The phenomenological aspects of the dual-field coupling effect on HEAs are explored and investigated through comprehensive characterization of the workpiece material, ranging from macroscopic surface morphology to microscopic structural features. These analyses are performed based on experimental results from four different processing technologies: non-energy field, magnetic field, ultrasonic vibration field, and dual-field assisted machining. Research results demonstrate that MUVFDC technology effectively combines the advantages of a vibration field, which enhances cutting stability, and a magnetic field, which improves the machinability of materials. Additionally, this coupling technology addresses the challenges associated with single-energy field machining: it mitigates the difficulty of controlling surface scratches caused by tiny hard particles in a vibration field and suppresses the rapid tool wear encountered in a magnetic field. Furthermore, the gradient evolution of the subsurface microstructure reveals that the vibration field suppresses the severe matrix deformation induced by magnetic excitation. Simultaneously, the magnetic field reduces the size inhomogeneity of recrystallized grains caused by intermittent cutting. Overall, MUVFDC technology enhances surface quality, suppresses tool wear, smooths chip morphology, and reduces subsurface damage compared to single-energy field or non-energy-assisted machining. This work breaks through the performance limitations of traditional single-energy field-assisted processing and advances the understanding of the dual-field coupling effects in HEAs machining. It also presents a promising processing technology for the future ultra-precision manufacturing of advanced materials.

Impact of device variability and protocol differences on kidney function during normothermic machine perfusion: A comparative study using porcine and human kidneys.

A growing interest in renal normothermic machine perfusion (NMP) has resulted in more clinically available perfusion devices. While all perfusion systems have the same aim, there are significant differences in their circuits, pumps, sensors, and software. Therefore, our objective was to assess the impact of different perfusion protocols and devices on kidney function and perfusion parameters during NMP. Porcine kidneys were subjected to 30 min of warm ischemia, 24 h of static cold storage, and subsequently perfused for 6 h using (1) the Kidney Assist (KA) machine with a pressure of 75 mm Hg, (2) the KA device incorporating several adjustments and a pressure of 85 mm Hg (modified KA), or (3) the Perlife (PL) perfusion device (n = 4). Consecutively, discarded human kidneys were perfused using the KA or modified KA (n = 3) protocol. The PL group quickly reached the device's upper flow limit and consequently received a significantly lower pressure compared to the KA groups. The arterial pO2 was significantly lower in the PL group. Yet, hemoglobin concentration increased over time, and oxygen consumption was significantly higher compared to the KA groups. Fractional sodium excretion was significantly lower in the PL group. Tissue ATP levels, urine production, and creatinine clearance rates did not differ between groups. In human kidneys, the modified KA group showed significantly lower vascular resistance, higher oxygen delivery, and lower levels of lactate in the perfusate compared to the KA group. This study shows that perfusion characteristics and kidney function are significantly influenced by the perfusion protocol and the device and its settings during normothermic machine perfusion and therefore should be interpreted with caution.

Artificial intelligence and assisted reproductive technology: Applying a reproductive justice lens

In recent years, health-data-driven artificial intelligence and machine learning applications have been introduced to many areas of medicine. In the field of assisted reproduction, artificial intelligence and machine learning applications and related technologies have been hailed as (potentially) significant and ground-breaking, not least because they promise standardisation and automation in in-vitro fertilisation clinics – a precondition for scaling up and branching out in the fertility bioindustry. Artificial intelligence data-driven algorithms promise time- and cost-effective selection of ‘high-quality’ reproductive cells and successful personalised treatments. In this essay, we aim to critically discuss artificial intelligence as a technological clinical practice, which is currently moving from bench to bedside internationally. Through an analytic framework of reproductive justice, we propose that introducing artificial intelligence into this already stratified context threatens to black-box health disparities and to generate what we refer to as ‘hyper-stratifications’ of reproduction in the context of rising health and social disparities in the European context. As feminist, social science and bioethics scholars, we are all too aware of how reproductive technologies reinforce normativities rather than unravel them. We cannot presume that artificial intelligence is an ethical technological agent or user of health data but, instead, need to keep a critical eye on the moral ambivalence of emerging and evolving artificial intelligence-assisted reproduction technologies practices and their gendered consequences. Given the current hype around artificial intelligence, but also with concerns around the fast development and deployment of artificial intelligence generally and in artificial intelligence-assisted reproduction technologies particularly in mind, there is an urgent need to engage in critical feminist discussion of such developments.

Experimental investigation of micro-machining of borosilicate glass using an ultrasonic assisted rotary electrochemical discharge machining (UA-RECDM) process

Electrochemical discharge machining is an advanced micro-machining process for machining of conductive as well as non-conductive hard and brittle materials, e.g. glass, ceramics, silicon wafer, etc. The present work explores the machining of glass using an in-house developed novel ultrasonic assisted rotary electrochemical discharge machining setup. The setup has specialized features, such as using ultrasonic vibrations to tool the electrode and incorporating rotary motion for manipulating the workpiece. Experiments were conducted using a one factor at a time approach by varying the tool feed rate, the amplitude of the vibrations and the rotation of the workpiece as process parameters. The quality of the machining output was evaluated by observing two key parameters: the overcut and the circularity of the hole. It was observed that as the workpiece rotation speed increased from 40 rpm to 60 rpm, the overcut in the machined samples decreased from 181.378 μm to 163.564 μm. The rotary motion of the workpiece caused a seeping action of the electrolyte in the hydrodynamic regime, leading to the formation of a thin gas film and the stabilization of the discharging process. The morphology of the machined hole exhibits better circularity, low heat-affected zones, minimum micro-cracks and smooth edges at its periphery due to stable discharge formation.

Design, Fabrication and Analysis of Battery Operated Brush Cutter

Crop harvesting involves either removing the plants after they have been torn out or cutting the crops close to the earth. It entails cutting coral crop stems, such as tuar, Jawar, Bajra, and maize, close to the ground. In our nation, a sharp sickle is typically used to cut things. Mainly, small-scale rice farmers are using conventional methods or, we could say, traditional methods in farming. The reaping process of the rice crop is very time-consuming as well as it requires more human effort. The labour required for farming is also more compared to other crops. So, the development of mechanical operated reaper is come but the reapers are costly for the use for the farmers those farms are small in size. They cannot afford harvesters and other expensive machinery. So, we have developed a small and low-cost solar assisted rice reaper machine which runs on electricity by use of batteries.

Surface integrity analysis of Si3N4 under cryogenic assisted femtosecond laser ablation

Femtosecond laser is suitable to process Si3N4, but heat effect forming during machining process could degrade the performance of specimen. To reduce heat damage, in this study, the effects of cryogenic assisted laser machining on the surface quality and micro-structures of Si3N4 was investigated. The femtosecond laser was employed to ablate Si3N4 at various low temperatures, accompanied with comprehensive analysis of the surface roughness, material removal rate and SEM topography. To further illustrate the formation mechanism of surface structure, finite element analysis was conducted. Results indicated that while low temperature exerted negligible effects in single-layer ablation, multi-layer laser machining benefits from improved surface quality. Low temperature mitigated thermal effects and reduced the recast layer area, resulting in decreased surface roughness. The lowest surface roughness was obtained during the machining of the specimen at −60 °C of 1.072 μm, representing a 54.6 % reduction compared to ambient air machining. However, further decreasing the temperature below −60 °C led to an increase in surface roughness. This was attributed to the combined effects of Gaussian beam energy distribution and low temperature, resulting in incomplete ablation of the surface region between two scanning pitches, thereby decreasing surface quality. This research provides valuable insights into the cryogenic assisted femtosecond laser machining.

Effects of dealloying surface modification on machinability improvement of NiTi alloy during micro-machining process

In this work, a novel dealloying assisted machining (DAM) method is proposed to modify the machinability of a typical high toughness NiTi alloy. The DAM method can produce nanoporous layer on workpiece surface through dealloying process. Under different cutting depths, micro-milling experiments are performed on workpieces with and without dealloying surface modification. The results indicate that the embrittlement effect of nanoporous layer induce ductile to brittle transition during material removal process leading to the fragmented chip formation. Consequently, the cutting force and temperature decrease by over 14% and 12%, respectively. Meanwhile, the tool wear is alleviated and the machined surface quality is improved. The proposed method can also provide guidance for micro machining of other difficult-to-machine materials.

Investigation of processing characteristics of PCD in ultrasonic-assisted graphene powder mixed EDM

Polycrystalline diamond is widely used in many fields including ultra-precise machining, optical material and semiconductor electronic devices due to its excellent physical properties. However, traditional mechanical processing methods of polycrystalline diamond leads to severe tool wear, low efficiency and high costs. Although electrical discharge machining can overcome some limitations, it usually exhibits a low material removal rate and poor surface quality. This study aims to explore the effect of graphene powder and ultrasonic vibration on polycrystalline diamond by electrical discharge machining. It was found that the synergistic effect of graphene powder and ultrasonic vibration can achieve a good surface quality. The results show that ultrasonic-assisted powder mixed electrical discharge machining can obtain the smallest surface roughness (1.98 μm) at low parameter and the biggest material removal rate (0.773 mg/min) at high parameter compared with ultrasonic assisted electrical discharge machining and powder mixed electrical discharge machining. In addition, after ultrasonic-assisted powder mixed electrical discharge machining, the minimum value (0.807) of ID/IG is obtained. For polycrystalline diamond, this study also proposes a removal mechanism that diamond converts into graphite and is peeled under tensile stress.

A novel finite element model for thermally induced machining of Ti6Al4V

Titanium alloys, including Ti6Al4V, are considered hard to cut materials due to their low thermal conductivity, low elastic modules and high chemical reactivity. This leads to high cutting forces and high surface roughness. Thermal assisted machining is used to improve the machinability of Ti6Al4V. To improve the performance of thermal assisted machining, this study investigates how are the cutting force, cutting zones temperatures, chip morphology, shear plane angle and strain rate are affected by the cutting speed and the heating element characteristics during thermally assisted machining of Ti6Al4V. A 2D numerical model simulating orthogonal cutting process was created using ABAQUS/Explicit software. In this model, Johnson Cook constitutive model was used to describe the material behavior during cutting process. Also, Johnson Cook damage model was used to simulate chip separation mechanism. After the verification of the model by comparison with results found in the literature, a number of simulations were run at different levels of four factors: cutting speed (40, 60, 80, 100, 120 and 140 m/min), heat source temperature (200, 400 and 600 °C), heating source distance from the cutting tool (0.3, 0.6 and 0.9 mm) and heating source size/diameter (0.6, 0.8 and 1 mm). Taguchi L18 orthogonal mixed level design was used to plan for simulation runs using Minitab software. ANOVA analysis was used to investigate the significance of the four factors. The response table of means and the main effect of means are used to compare between the four factors and find their ranking. Based on 95% confidence Interval (CI), the results show that cutting speed has a significant effect on cutting force, strain rate, chip compression ratio, cutting tool nose temperature, cutting tool and chip temperature in the secondary deformation zone, average chip thickness at peaks and average chip thickness at valleys and average pitch. This conclusion is based on the P-values which are << 0.05 and the contribution which reaches 99.01%. Similarly, based on P-values (< 0.05) and contributions (up to 12.16%), the heating source temperature has a significant effect on average chip thickness at valleys, chip compression ratio and strain rate. The cutting speed has Rank 1 among the four factors affecting cutting force, cutting zones temperatures, chip morphology, shear plane angel and stain rate. The effect of instantaneous heating directly before cutting process is negligible compared to the effect of plastic deformation and fracture mechanism in the cutting zone.

Industrial Application of AI-Based Assistive Magnetic Particle Inspection

Magnetic Particle Inspection (MPI) is one of the most used methods in Non-Destructive Testing (NDT), allowing precise and robust defect detection on industrial-grade manufactured parts. However, human controllers perform this task in full black environments under UV-A lighting only (with safety glasses) and use chemical products in a confined environment. Those constraints tends to lower control performance and increase stress and fatigue. As a solution, we propose an AI-based assistive machine (called “PARADES”) inside the hazardous environment, remotely manipulated by a human operator, outside of the confined area, in cleaner and safer conditions. This paper focuses on the development of a complete industrial-grade AI machine, both in terms of hardware and software. The result is a standalone assistive AI-based vision system, plug-and-play and controller-friendly, which only needs the usual power supply 230 V plug that detects defects and measures defect length. In conclusion, the PARADES machines address for the first time the problem of occupational health in MPI with an industrial standalone machine which can work on several parts and be integrated into current production lines. Providing cleaner and healthier working conditions for operators will invariably lead to increased quality of detection. These results suggest that it would be beneficial to spread this kind of AI-based assistive technology in NDT, in particular MPI, but also in Fluorescent Penetrant Testing (FPT) or in visual inspection.

Grinding force model for ultrasonic assisted grinding of γ-TiAl intermetallic compounds and experimental validation

Abstract The introduction of ultrasonic vibration in the grinding process of γ-TiAl intermetallic compounds can significantly reduce its processing difficulty. It is of great significance to understand the grinding mechanism of γ-TiAl intermetallic compounds and improve the processing efficiency by studying the mechanism of ordinary grinding of abrasive grains. Based on this, this study proposes a grinding force prediction model based on single-grain ultrasonic assisted grinding (UAG) chip formation mechanism. First, the prediction model of grinding force is established based on the chip formation mechanism of abrasive sliding ordinary grinding and the theory of ultrasonic assisted machining, considering the plastic deformation and shear effect in the process of material processing. Second, the UAG experiment of γ-TiAl intermetallic compounds was carried out by using diamond grinding wheel, and the unknown coefficient in the model was determined. Finally, the predicted values and experimental values of grinding force under different parameters were compared to verify the rationality of the model. It was found that the maximum deviation between the predicted value of tangential force and the actual value is 23%, and the maximum deviation between the predicted value of normal force and the actual value is 21.7%. In addition, by changing the relevant parameters, the model can predict the grinding force of different metal materials under different processing parameters, which is helpful for optimizing the UAG parameters and improving the processing efficiency.

Characterization, quantitative evaluation, and formation mechanism of surface damage in ultrasonic vibration assisted scratching of Cf/SiC composites

Carbon fiber reinforced silicon carbide ceramic matrix composites (Cf/SiC composites) have a wide range of applications in aerospace, nuclear energy, braking systems owing to its excellent mechanical performance. Nevertheless, the hardness, brittleness, heterogeneity, and anisotropy of Cf/SiC composites give rise to difficulties in machining them. In addition, the characterization and formation mechanism of surface damage in the grinding of Cf/SiC composites have not been fully elucidated. The purpose of this paper is to provide a characterization method for surface damage of Cf/SiC composites and an evaluation index for surface edge chipping damage (SECD) through conventional scratching (CS) / ultrasonic vibration assisted scratching (UVAS) tests with single abrasive. Towards revealing the surface damage behavior of Cf/SiC composites during scratching, as well as the impact of fiber orientation on surface damage. The findings indicate that main forms of surface damage of Cf/SiC composites in single abrasive scratching are fiber breakage, fiber fracture-shedding, fiber fracture, fiber-matrix interface debonding, interface fragmentation, matrix cracking, and matrix microcracks. Further, ultrasonic vibration could help to suppress the SECD, and the SECD factor was smallest when scratching along the perpendicular fiber. Furthermore, the fiber orientation can significantly affect the scratching force and cross-sectional area of scratches on Cf/SiC composites via single abrasive scratching. The tangential scratching force was usually smaller as compared to the normal scratching force, and the cross-sectional area of scratches in UVAS is smaller than that in CS. Based on the above findings, this study elucidates the formation and evolution of surface damage after scratching under different fiber orientations, filling the research gap in surface damage under ultrasonic assisted machining of Cf/SiC composites and providing technical guidance for the machining.

Raman spectroscopy assisted support vector machine: a steadfast tool for noninvasive classification of urinary glucose of diabetes mellitus

The currentstudy presents the application of a Raman spectroscopy-assisted Support Vector Machine (SVM) algorithm for the analysis and classification of urine samples of diabetes mellitus and healthy control subjects. Raman spectra of pathological as well as control samples were acquired in the spectral range of 600 to 1800 cm−1. Spectral differences were observed in Raman spectra of diabetic and non-diabetic urine samples based on variations in their chemical composition. Effective machine-learning techniques were utilized to highlight the spectral differences between diabetic and normal urine samples. Data classification was carried out by using SVM models with different kernel functions: radial basis function (RBF), polynomial function, linear function, and sigmoid. The algorithm classifies data sets into different classes based on even subtle variations in the spectral features. The classification performance of the model was evaluated by employing a 10-fold cross-validation method. The best performance was obtained with RBF having a diagnostic accuracy, precision, sensitivity, specificity, F-score, and AUC of approximately 94%, 100%, 90%, 100%, 0.94, and 0.99 respectively.

Designing an Athletic Training Assistance System under Deep Learning Guided by Kinesiology Theory

Abstract The combined application of computer artificial intelligence technology and sports promotes the positive development of the sports industry. The combined application of computer artificial intelligence technology and sports promotes the positive development of the sports industry. After completing the model construction, the structure of the external limb sports training auxiliary machinery is designed, and the system structure of the sports training auxiliary machinery is constructed by combining the needs of sports training. The optimization of external limb sports training auxiliary machinery was achieved by performing and solving mathematical modeling of a single limb. The performance of the action recognition model and the sports auxiliary machinery is examined through experiments, in which the action recognition model based on deep learning in this paper has the best effect, which is 95.75%, and the loss values of the model after convergence are all below 0.2. In the empirical testing of the performance of the sports assistive machine, the obtained target trajectory tracking error is within ±3mm and ±2mm, respectively, and the performance of the deep learning-based action recognition model and the external limb sports training assistive machine is excellent, which can effectively help the sports training. The purpose of this study is to provide design direction and practical significance for the design of a sports training assistance system.

Intelligent Assistant for Smart Factory Power Management

This article presents the development and implementation of an intelligent assistant for smart energy management in an industrial setting. The project, developed in collaboration with Bosch Termotecnologia Aveiro, aims to leverage the advancements of Industry 4.0 and address the increasing demands for efficiency, quality and sustainability in industrial processes. The intelligent assistant implements machine learning algorithms, specifically autoencoders, to predict energy consumption related variables and detect anomalies in data collected from the factory floor. In the models’ building process, an AutoML hyperparameter optimization tool is utilized to further enhance their predictive abilities. The implementation of the assistant showcases its capabilities not only regarding the predictions, but also in terms of data visualization and alarm generation. The results obtained through the use of Auto ML showcase remarkable improvements compared to traditional regression models and basic autoencoders, proving its effectiveness in terms of making accurate predictions, with improvements up to 90% in some indicators when compared to those basic models. Alsointerms of the anomaly detection task, the chosen methodology proves to be effective in detecting different kinds of anomalies. The integration of the assistant with a Grafana dashboard and the exploration of additional communication tools, such as a Telegram bot, further improve the user experience and expand the potential applications of the assistant.

Development of a numerical cutting model for understanding the chip formation in cryogenic machining

The aim of this study is to develop a finite element model of metal cutting that includes fluid structure interaction. The proposed model is used to improve the physical comprehension of the chip formation during cryogenic assisted machining. This is performed based on the coupled-Eulerian-Lagrangian formulation. An algorithm is also developed to ensure heat exchange between the fluid and the structure. It also allows decoupling the mechanical and thermal effects induced by liquid nitrogen. The titanium alloy Ti17 is used as a work material, and uncoated tungsten carbide is used as a tool under dry and cryogenic conditions with cutting speeds of 50 m/min and 70 m/min and feeds of 0.1 mm/rev and 0.2 mm/rev. Simulation is validated by comparison with the experimental results. Standard deviations of both forces and chip thickness are low; they stay under 15% and 35% of the average value, respectively. The chip formation, the cutting force and the temperature are studied. It is shown that cryogenic machining has a significant effect on the chip formation and the temperature distribution in the cutting zone. A remarkable temperature reduction by up to 500 °C is observed at the tool rake face. However, the tool tip temperature slightly decreases with the application of liquid nitrogen when compared to dry machining.

Influence of the nozzle inclination during an assisted machining based on an orthogonal cutting configuration of a titanium alloy: A CFD modeling

Influence of the nozzle inclination during an assisted machining based on an orthogonal cutting configuration of a titanium alloy: A CFD modeling