Machining Properties Research Articles

Analysis of the Application of Artificial Intelligence in Mahjong

Over the past few years, AI-based models for Mahjong have received a substantial amount of contribution due to the advancements in machine learning and game theory. In this review, these state-of-the-art AI models are considered, including Tjong, Kanachan, Suphx, and Zhejiang University’s developed model. The deployed approaches are disparately represented by reinforcement learning, Monte Carlo tree search (MCTS), and deep neural networks, all of which aim at solving the issues that come with the game’s structure, such as incomplete and overburdening information. The Tjong model complements the power of the transformer architecture with hierarchical decision-making and in turn, brings strategic depth to the gameplay. Kanachan employs Q-learning and MCTS to optimize decision-making, while Suphx combines these methods with the novel ideas of Double Q-learning and Thompson Sampling to achieve higher performance than seen before. The integration of reinforcement learning and a new evaluation model imbues the model with the unique properties of both learning machines and human expertise, namely depth and intelligence. As a result of all these exploits, obstacles still exist, the most notable among them are the management of completely unknown information, handling long-distance games, and the strategic balance between offense and defense. In the future, determinants of probabilistic reasoning, the improvement of deep learning systems, and the prowess of reward shaping will result in AI improvement in Mahjong.

A methodology for evaluating feature selection and clustering methods with project-specific requirements

This paper describes a methodology for ranking feature selection and clustering methods with user-specific preferences and taking data properties into account. For a better understanding of this paper, the developed methodology is referred to as the Two Machine Learning Procedures, Preferences and Properties (2ML3P) methodology. The 2ML3P methodology aims to support users from multiple domains, such as engineers, who have little expertise in machine learning (ML). It is also independent from the disciplinary core competencies of the manufacturer, with a strong focus on employability in small and mid-sized enterprises (SME). The foundation of the methodology to evaluate the combination of the two machine learning classes is described. It focuses on a range of feature selection and clustering methods, their limitations, and their challenges. The paper covers the concept phase by defining the inputs, such as the specific characteristics of machine learning classes or the properties of the production data and the user preferences. With applied methodologies such as the analytic hierarchy process (AHP) and the technique for order preference by similarity to ideal solution (TOPSIS), the preferences of the user as valid input are integrated. The scientific contribution of this methodology is the approach to include user preferences and specific data properties in the selection process of two ML methods. As digitalisation progresses, making data-driven decisions in the domains of production and logistics is a goal for many SMEs. This methodology can support a data-driven decision-aid model by providing a guided method, which requires relatively little ML knowledge on the part of the engineer. It allows the user(s) to select the best suited combination of ML methods for a clustering use case.

Comparing coherent and incoherent models for quantum homogenization

Here we investigate the role of quantum interference in the quantum homogenizer, whose convergence properties model a thermalization process. In the original quantum homogenizer protocol, a system qubit converges to the state of identical reservoir qubits through partial-swap interactions, that allow interference between reservoir qubits. We design an alternative, incoherent quantum homogenizer, where each system-reservoir interaction is moderated by a control qubit using a controlled-swap interaction. We show that our incoherent homogenizer satisfies the essential conditions for homogenization, being able to transform a qubit from any state to any other state to arbitrary accuracy, with negligible impact on the reservoir qubits' states. Our results show that the convergence properties of homogenization machines that are important for modeling thermalization are not dependent on coherence between qubits in the homogenization protocol. We then derive bounds on the resources required to re-use the homogenizers for performing state transformations. This demonstrates that both homogenizers are universal for any number of homogenizations, for an increased resource cost. Published by the American Physical Society 2024

Gaussian Distributions in Machine Learning

To help teaching and learning of machine learning courses, properties and application examples of Gaussian distributions in machine learning are presented, including classification, regression, and approximation. In each typical cases, emphasis is placed on the assumptions and the conclusions related to Gaussian distributions, so that students can make clear that it is the Gaussian distribution that make the somewhat abstract Bayes’ theorem more concrete and yields closed-form analytical predictive distributions.

Process Parameter Effects on Powder Mixed EDM Machining Characteristics Using Biocompatible Ti-6Al-4V Alloy

This study examines how various process parameters affect the machining properties of a bio-compatible Ti-6Al-4V alloy using PMEDM with silicon carbide (SiC) powder. The parameters investigated include peak current, pulse on/off time, powder concentration, and voltage gap. The study analyzed their effects on material removal rate (MRR), tool wear rate (TWR), surface roughness (SR), and surface morphology. A central composite design was used in the tests to make empirical models that use response surface methods to link the process parameters to the machining results. It is found that the Pulse current and Ton influence the material removal rate and the surface roughness significantly. The powder concentration also impacts PMEDM's machining performance. The Scanning electron microscopic images reveal the effect of powder seen in the machined components. The crater, micro cracks and machining marks can be seen in the SEM images. The surface integrity is correlated with the output parameters of surface roughness. The developed mathematical models effectively predict and optimize the machining properties of Ti-6Al-4V alloy using PMEDM with SiC powder. This research offers valuable insights for applying PMEDM in the fabrication of biomedical implants and devices made from Ti-6Al-4V alloy.

Determination of Machinability Properties of Nimonic-60 Superalloy Under Sustainable Conditions

Determination of Machinability Properties of Nimonic-60 Superalloy Under Sustainable Conditions

EXPERIMENTAL DETERMINATION OF TORQUE FOR THE DRILLING OFAL7SIMG ALLOY

The productivity of a machining process is closely related to the value of the cutting force.For the calculation of the cutting forces, a series of models have been developed to allow the determination of these forces according to the machined material and the specific conditions in which the process is carried out. Usually, for a better approximation of the value of the cutting force, the unitary specific cutting force is used, which depends on the machined material. For common materials, the values of specific unitary cutting forces are presented in the specialized literature, but for less frequently used materials, for example, those with reduced machining properties, the respective values are difficult, sometimes impossible to find. In this paper, determining the unitary specific cutting force for an aluminum alloy with a high silicon content is intended, recognized as difficult to machine. The determination of the value of this force is done starting from the measured values ofthe torsional moment at the drills.

Enhancement of machinability and surface tribological property of hardened bearing steel by electric pulse-assisted hard turning

Electric pulse-assisted cutting (EPAC) can reduce the hardness of the workpiece, improve the tribological state of the tool-workpiece/chip interfaces, and enhance the machinability of the workpiece material. Hardened bearing steel has a hardness higher than 60 HRC, so the hardened bearing steel has an extremely bad machinability. This paper carried out an experimental study on electric pulse assisted hard turning (EPAHT) of hardened bearing steel, and the tribological property of the turned hardened bearing steel was also explored. Results shown that compared to conventional hard turning, the EPAHT reduced the surface roughness of hardened bearing steel by 44.2 %. The workpiece surface work-hardening rate was reduced by 3.6 %, the thickness of the workpiece surface metamorphic layer was increased by 91.4 %, the friction coefficient of the workpiece surface was reduced by 20 %, the wear mark depth was decreased by 91 %, a uniform and clean wear morphology of the workpiece surface wear appeared. The surface friction and wear performance of hard-turning of hardened bearing steel were significantly enhanced by the EPAHT.

System Study Review of Electrical Machines under Specific Operating Conditions of Power Installations

The problem of life cycle vulnerability, predetermined by the development stages, operation and modernization of electrical machines due tosize and weight restrictions, dynamic electromagnetic and thermal overloads, possible flooding and changes in ventilation and cooling conditionsis considered. Reducing the weight and size of electric machines implies eliminating passive sections of magnetic circuits and optimizing the ratio of copper and steel. The desire to reduce weight and size indicators and increase energy density entails increased heat generation and temperature loads of structural elements. The increase in operatingtemperatures of modern machines indicates the need to develop mathematical models that account the response of electrical materials and structural elements to the combined thermal and magnetic fieldeffects. Such models are in demand to study the temperature dependence of insulating, magnetic and operating properties of electrical machines when establishing the requiredoperating moderestrictions in order to preserve and extend the life cycle. The criterion for making management decisions aimed at changing operating modes during operation can be maximum loads that limit exceeding the maximum permissible temperatures of the electrical insulationclass used, as well as critical values of induction determined by the temperature dependence of ferromagnetproperties that affect the performance characteristics of electrical machines. Further solution to the problem lies in the creation of digital twins containing complete mathematical and computer simulation models that describe processes in electrical machines, taking into account the temperature dependence of materialphysical properties of structural elements being subjected to thermal, magnetic and electric fields.

ÉTUDE COMPARATIVE D'UNE MACHINE À AIMANT PERMANENT À INVERSION DE FLUX À ROTOR INTÉRIEUR ET EXTÉRIEUR POUR ÉOLIENNE À ENTRAÎNEMENT DIRECT

The topology, operation principle, and electromagnetic performance of the inner rotor flux reversal permanent magnet (IRFRPM) machine and the outer rotor flux reversal permanent magnet (ORFRPM) machine are quantitatively compared in this paper. First, the mass torque of both machines is optimized and compared using particle swarm optimization (PSO) combined with the finite element method (FEM). Second, the static properties of both machines are calculated using finite element analysis (FEA). Both machines are suitable for direct-drive wind turbines, but ORFRPM outperforms IRFRPM.

MULTI-OBJECTIVE OPTIMIZATION OF ROTARY ASSISTED ELECTROCHEMICAL ARC DRILLING (R-ECAD) PROCESS USING GRA

Electrochemical Arc Drilling (ECAD) has demonstrated its effectiveness in micro-machining a variety of materials notwithstanding the inherent properties of materials. The increased machining properties of the ECAD method are a result of the inclusion of rotational effect of the working material. Better electrolyte replenishment, effective debris flushing, thin gas layer development, and spark uniformity are all credited with this improvement. Several input factors affect the machining characteristics of ECAD, making it difficult to simultaneously optimize these factors for several objectives. In order to maximise Material Removal Rate (MRR) and minimising Hole Overcut (HOC), this paper focuses on the multi-objective optimization of rotary-assisted ECAD (R-ECAD) input factors. Taguchi's L9 experimental design is used to produce micro-holes, and then Grey Relational Analysis (GRA) is used to perform the multi-objective optimization. The chosen input factors are working material rotation (WR), tool feed rate (FR) and applied voltage (V), whereas the chosen response factors are MRR and HOC. Results indicate that the rotating effect of the working material, which aids in the replenishment of electrolyte and the creation of a stable gas layer surrounding the tool, is notably the most significant input factor. For maximising the MRR and minimising HOC, the GRA-based optimised factors were found to be AIICIIBIII (60 rpm, 40 V, 0.8 mm/min). The responses are greatly improved by 39% as compared to the original machining, as demonstrated by microscopy images obtained during the GRA-based input factor optimization.

The Impact of nanoparticles (B4C-Al2O3) on mechanical, wear, fracture behavior and machining properties of formwork grade Al7075 composites

This study explores how ageing temperature and the volume percentage of Al2O3+B4C nanoparticles influence the machinability and hardness of stir-cast Al-7075 Metal Matrix Composite (MMC). Using liquid metallurgy techniques, hybrid materials were created by reinforcing Al7075 metal matrix with varying weight percentages of nanosized B4C (1.5%, 3%, and 4.5%) and Al2O3 (1%, 1.5%, and 2%). After fabrication, the samples were subjected to five-hour ageing process at temperatures of 100, 120, and 140 degrees Celsius, followed by cooling to ambient temperature (27 degrees Celsius). Hybrid nano composites that had been heat treated were tested for wear, tensile strength, and hardness. Results shows that, the addition of nanoparticles and heat treatment considerably improves the tensile strength, hardness, and wear resistance of hybrid composites by 3%, 17%, and 10%, respectively, for samples reinforced with 4.5% B4C + 2% Al2O3. SEM analysis was used to investigate the type of wear and the tensile fracture mode of nano composite samples by analyzing the wornout surface and the surface where tensile fracture occurred. Machinability was assessed using L27 orthogonal array tests, focusing on three key process parameters: feed rate (0.1 mm/min), depth of cut (0.2 mm/min), and spindle speed (1000 rpm). Outcomes show that, increasing the wt. % of nano-Al2O3/B4C leads to higher machining force and surface roughness (Ra) of MMCs. Conversely, higher ageing temperatures result in decreased machining force and surface roughness. Optimal surface roughness and machining force were achieved with 1% Al2O3 + 1.5% B4C and an ageing temperature of 140°C. These findings offer valuable insights into the ease of machining of composite metal alloys, emphasizing the importance of parameter selection and optimization for desired machining outcomes.

Development and Validation of a 1D Dynamic Model of an Injection Moulding Process and Design of a Model-Based Nozzle Pressure Controller.

A 1D model describing the dynamics of an injection moulding machine and the injection process is presented. The model describes an injection cylinder actuated by a dual-pump electro-hydraulic speed-variable drive and the filling, holding and cooling phases of the injection moulding process utilising amorphous polymers. The model is suggested as the foundation for the design of model-based pressure controllers of, e.g., the nozzle pressure. The focus is on using material, mould and machine properties to construct the model, making it possible to analyse and design the dynamic system prior to manufacturing hardware or conducting experiments. Both the presented model and the developed controller show good agreement with experimental results. The proposed method is general in nature and enables the design, analysis and evaluation of the machine, material and mould dynamics for controller design based solely on the physical properties of the system.

Synthesis, characterization, antibacterial efficacy, and Cytotoxicity of monoclinic KMg3(Al0.5B0.5)Si3O10F2: A novel material for anticariogenic applications

Fluorophlogopite is a well-known fluorosilicate glass-ceramic derivative known for its bioactivity, machinability and optimal mechanical properties. There is limited information regarding its antibacterial and biocompatible properties. This research paper presents the synthesis and characterization of a novel Boron-doped Fluorphlogopite [KMg3(Al0.5B0.5)Si3O10F2] aiming to improve its antibacterial properties intended for anticariogenic applications. The combustion synthesis method was employed, with oxalyl dihydrazide (ODH) (C2H6N4O2) serving as the fuel. X-ray Diffraction (XRD) analyses unveiled a monoclinic crystal system, showcasing a P21 space group, and an average crystallite size of approximately 28 nm. Morphological scrutiny divulged clustered, irregularly shaped, cluster-like structures. The energy gap was determined to be around 4.97 ± 0.0062 eV. Fourier-Transform Infrared (FTIR) spectroscopy depicted the presence of characteristic bonds. BET analysis indicated the presence of a large surface area and porous structure (mesopores), which may contribute to lower MIC and MBC values, enhancing antibacterial effectiveness. The antibacterial activity, evaluated via agar well diffusion, yielded an 8 mm zone of inhibition. Furthermore, the Minimum Inhibitory Concentration (MIC) and Minimum Bactericidal Concentration (MBC) against S mutans were determined to be 2 mg/ml and 16 mg/ml, respectively. The biocompatibility of the synthesized KMg3(Al0.5B0.5)Si3O10F2 was assessed through the MTT assay, indicating non-toxic behavior at a concentration of 12 μg/ml with 98 % cell viability, while showing moderate toxicity with 61 % viable cells at its highest concentration of 200 μg/ml.

A brief review of machine learning-assisted Mg alloy design, processing, and property predictions

Owing to the hexagonal close-packed (HCP) crystal structure inherent in Mg alloys, strong basal texture can readily be induced through the processes of rolling or extrusion. The anisotropy of the texture of Mg alloys impacts their stamping and forming capabilities, limiting their use in certain applications. Microalloying and shear deformation are currently the most common methods of weakening the texture of Mg alloys. Many shearing processes have been extensively studied, and given that they require complex equipment and make it difficult to achieve mass production, major attention has turned to studying the design of microalloys. Traditional trial-and-error approaches for developing micro-alloying confront many challenges, including longer test cycles and increasing expenses. The rapid advancement of big data and artificial intelligence opens up a new channel for the efficient advancement of metallic materials, specifically the application of machine learning to aid in the design of Mg alloys. ML modeling can be used to find correlations between features and attributes in data, allowing for the development and design of high-performance Mg alloys. The article provides an extensive overview of machine learning applications in Mg alloys. These include the discovery of high-performance alloys, the selection of coating designs, the design of Mg matrix composites, the prediction of second phases, the microstructure modification, optimization of rolling or extrusion parameters, and the prediction of mechanical and corrosion properties. In conclusion, challenges and prospects for the rational design of alloys with machine learning support were discussed.

A State of the Art on Cryogenic Cooling and Its Applications in the Machining of Difficult-to-Machine Alloys.

Cryogenic cooling has gathered significant attention in the manufacturing industry. There are inherent difficulties in machining materials that are difficult to machine because of high levels of hardness, abrasiveness, and heat conductivity. Increased tool wear, diminished surface finish, and reduced machining efficiency are the results of these problems, and traditional cooling solutions are insufficient to resolve them. The application of cryogenic cooling involves the use of extremely low temperatures, typically achieved by employing liquid nitrogen or other cryogenic fluids. This study reviews the current state of cryogenic cooling technology and its use in machining difficult-to-machine materials. In addition, this review encompasses a thorough examination of cryogenic cooling techniques, including their principles, mechanisms, and effects on machining performance. The recent literature was used to discuss difficult-to-machine materials and their machining properties. The role of cryogenic cooling in machining difficult materials was then discussed. Finally, the latest technologies and methods involved in cryogenic cooling condition were discussed in detail. The outcome demonstrated that the exploration of cryogenic cooling methods has gained prominence in the manufacturing industry due to their potential to address challenges associated with the machining of exotic alloys.

Designing high-efficiency organic semi-conductors for organic photodetectors assisted by machine learning and property prediction

Quantum chemical calculations have been widely utilized to design and explore organic semi-conductors for various photovoltaics applications. Photovoltaic devices such as photodetectors work on the principle of photo-electric-effect and widely used for optical communications. In recent years, machine learning has become famous in many research fields. In present study, we have predicted reorganization energy of organic semi-conductors with the aid of machine learning. Statistical analysis is used to select best molecular descriptors (features). About 10 machine learning models are tested for selecting the best one. Among various tested models, gradient forest regressor and random forest regressor are the top models. By using our new designing approach, easy to synthesize building blocks are connected to design new organic semiconductors. Their reorganization energies are predicted using fast machine learning method. For this purpose, already trained and hyper parameter optimized gradient boosting regressor is used. It is generally accepted that to obtain higher charge mobility molecules should have lower reorganization energy. Ten organic semi-conductors with lower reorganization energy are selected for density functional calculations and their energy levels are calculated. The chemical similarity analysis using clustering and heatmap is also done for selected organic semi-conductors. Synthetic accessibility score is calculated and majority of semi-conductors are easy to synthesize. These molecules are potential candidates for device fabrication. The proposed python-based pipeline has ability to select the molecules for organic photodetectors in fast and cheaper way.

Online tracking of dynamically time-varying inertia using an enhanced SDFT-based estimation methodology

The overall motion performance of mechatronic machines depends heavily on proper knowledge of the machine’s characteristics, among which the inertia. Moreover, the inertia of most multi-body mechanisms, for example, reciprocating slider-crank mechanisms, varies as a function of the machine position, thereby challenging optimal control. Nevertheless, the inertia’s variation is sometimes not known accurately enough or changes over time due to, e.g. a production process or premature wear, forcing an online control/correction of the inertia profile. Therefore, earlier, the author developed a new computational-friendly online method based on a frequency-specific magnitude response to estimate the machine’s position-dependent load side inertia, assuming good knowledge of all other machine properties. Yet, to guarantee accuracy, the maximum machine speed during estimation had to be strongly reduced, resulting in an undesirable longer motion time. Therefore, in this work, the failure mechanism of the earlier proposed estimator is analysed and overcome by intelligently separating estimation and motion signals. As a result, the estimator is no longer limited by the machine’s motion speed but rather by a maximum in the inertia variation per signal excitation period and, thus, time. Moreover, given this limiting variation, a guideline was established to evaluate the new method’s estimation quality. Finally, both in simulation and on a physical machine, by taking advantage of the newly proposed method, the minimal required estimation time is reduced significantly (up to 50% on the machine) without diminishing the estimation accuracy.

An Experimental Study on Microstructural, Mechanical and Machinability Properties of As-Cast and Heat-Treated Al-7Si-Mg Alloy

An Experimental Study on Microstructural, Mechanical and Machinability Properties of As-Cast and Heat-Treated Al-7Si-Mg Alloy

General Fuzzy Switchboard Transformation Semigroup

Commutative and switching processing are central to computation. However, some problems arise when classical versions do not reflect the true needs of current computer science, whereby they cannot predict the flow of the next input information in the specified output. The Switchboard State Machine is a controller that controls the direct flow of information from one state to another and also plays the main part in communication between the subsystems. If the simple system satisfies the two properties of the switching and commutative state machines, the system is therefore a finite switchboard state machine. The general fuzzy switchboard automation (GFSA) was introduced by incorporating the switchboard into the general fuzzy automation. This paper is intended to introduce the concept of a general fuzzy switchboard transformation semigroup (GFSTS) by combining the GFSA and the transformation semigroup. Some related definitions and properties are established. The example of certain products, such as GFSTS cascade products, has also been studied. General Fuzzy Switchboard Poly-Transformation Semigroup (GFSPS) is also introduced since it fulfils the switchboard state machine properties. Some of the definitions and properties associated with the GFSPS are defined. Applications for general fuzzy switchboard automata, such as washing machines, are also provided.