Machining Characteristics Research Articles

Flexible Job-shop Scheduling Problem with parallel operations using Reinforcement Learning: An approach based on Heterogeneous Graph Attention Networks

The Flexible Job-shop Scheduling Problem (FJSP) has received considerable scholarly attention as a classic problem. However, in practical industrial manufacturing scenarios, it is common for an operation to have multiple preceding parallel operations. This not only necessitates adhering to the sequential relationships inherent in FJSP but also requires ensuring that preceding operations are completed simultaneously whenever feasible. We term this scenario as the Flexible Job-shop Scheduling Problem with Parallel Operations (FJSP-PO), a pervasive challenge encountered across nearly every production line in real-world discrete manufacturing applications. Despite its prevalence, there is a noticeable scarcity of research on FJSP-PO in existing literature. Given the objective of synchronizing multiple preceding operations, FJSP-PO presents a broader solution space and more intricate optimization challenges compared to traditional FJSP. To address this, we propose an Attention Restart method based on Heterogeneous Graph Attention Networks (AR-HGAT). Leveraging a heterogeneous graph network structure and reinforcement learning, AR-HGAT learns the implicit features of operations and machines through node-level and semantic-level attention mechanisms. The AR mechanism is utilized to determine the optimal scheduling of operations at specific time slots. Compared to existing FJSP methods, our AR-HGAT approach demonstrates superior performance in terms of inference time and solution effectiveness. Furthermore, we conducted a comparative analysis using authentic operational data from companies and contrasted it with results obtained from an online tree search algorithm, thereby providing empirical validation of the effectiveness of the proposed AR-HGAT method.

Investigation on the machining characteristics of AZ91 magnesium alloy using uncoated and CVD-diamond coated WC-Co inserts

An investigation has been performed to study the compatibility of machining AZ91 magnesium alloy in dry conditions using uncoated and CVD diamond-coated WC-Co inserts. The machining characteristics such as built-up edge (BUE) formation, surface roughness, cutting forces and chip morphology were studied at the cutting speeds, 350, 650 and 950 m/min. The results revealed severe adhesion of the AZ91 Mg alloy on the uncoated WC-Co inserts with increasing cutting speed and contributed to an increase in surface roughness and cutting forces. The CVD diamond-coated inserts have shown negligible built-up edges at various cutting speeds due to their unique properties like low coefficient of friction, low chemical affinity and high thermal conductivity. Snarled types of long continuous chips were observed while machining with CVD diamond-coated WC-Co inserts, whereas short continuous chips were observed with uncoated WC-Co inserts.

Enhancing Fire Protection in Electric Vehicle Batteries Based on Thermal Energy Storage Systems Using Machine Learning and Feature Engineering

Thermal Energy Storage (TES) plays a pivotal role in the fire protection of Li-ion batteries, especially for the high-voltage (HV) battery systems in Electrical Vehicles (EVs). This study covers the application of TES in mitigating thermal runaway risks during different battery charging/discharging conditions known as Vehicle-to-grid (V2G) and Grid-to-vehicle (G2V). Through controlled simulations in Simulink, this research models real-world scenarios to analyze the effectiveness of TES in controlling battery conditions under various environmental conditions. This study also integrates Machine Learning (ML) techniques to utilize the produced data by the simulation model and to predict any probable thermal spikes and enhance the system reliability, focusing on crucial factors like battery temperature, current, or State of charge (SoC). Feature engineering is also employed to identify the key parameters among all features that are considered for this study. For a broad comparison among different models, three different ML techniques, logistic regression, support vector machine (SVM), and Naïve Bayes, have been used alongside their hybrid combination to determine the most accurate one for the related topic. This study concludes that SoC is the most significant factor affecting thermal management while grid power consumption has the least impact. Additionally, the findings demonstrate that logistic regression outperforms other methods, with the improving feature to be used in the hybrid models as it can increase their efficiency due to its linearity capture capability.

Accurate Forecasting of Global Horizontal Irradiance in Saudi Arabia: A Comparative Study of Machine Learning Predictive Models and Feature Selection Techniques

Accurate Forecasting of Global Horizontal Irradiance in Saudi Arabia: A Comparative Study of Machine Learning Predictive Models and Feature Selection Techniques

A data-driven approach for volume feature recognition based on cell graph

ABSTRACT Machining feature recognition is one of the key technologies for realizing automated process planning. The machining feature represented by volume contains more complete information due to its property of forming a closed region which facilitates subsequent process planning. The existing volume feature recognition approaches mainly rely on expert-defined rules to combine volumes into the desired feature. When dealing with some complex parts, volume feature recognition faces combinatorial explosion, and it is difficult to formulate complete combination rules manually. This research proposes a novel data-driven approach for volume machining feature recognition. The proposed approach does not require manually defined rules and can learn various complex volume combination rules from the data, which can be implicitly represented by the structure and parameters of the data-driven model. The volume machining feature recognition is first converted to machining feature subgraph (MFS) detection by creating the zone graph. MFS detection can then be achieved by graph edge cut. Finally, the edge cut is modeled as a binary classification deep learning problem, which is solved by graph neural network. Two datasets are created, and case studies are carried out on them. The results show that the proposed approach is effective for volume machining feature recognition.

Sustainable machining with LN2 in turning of super duplex steel

ABSTRACT Currently, the majority of industries rely on turning processes to manufacture mechanical products. The selection of coolant is of paramount importance in the pursuit of sustainable manufacturing. Super duplex steel’s machinability during the turning process is the subject of the present investigation. The machining characteristics, such as Flank wear (Fw) and Surface roughness (Ra), were analyzed by varying the control parameters, including cutting velocity (Vs), feed rate (f), and cutting conditions i.e. Dry, Nanofluid + MQL (NMQL), LN2 + MQL (LMQL), through a constant depth of cut (d) using a Taguchi L27 orthogonal array. The results demonstrated that the LMQL approach is more efficient as it reduces the Ra by 77%, 54%, and Fw by 83%, and 93%, respectively, in comparison to the dry and NMQL conditions. Additional research on microstructure revealed that the character of the grains is improved when the surface is machined with LMQL in comparison to other cutting conditions.

ТЕХНОЛОГИЧЕСКИЕ МЕТОДЫ ФОРМООБРАЗОВАНИЯ КАЧЕСТВЕННОЙ ПОВЕРХНОСТИ ДЕТАЛЕЙ ИЗ АЛЮМИНИЕВЫХ И МЕДНЫХ СПЛАВОВ

The surface quality of aluminum and copper alloy parts is studied when they are formed, which is important for transport engineering. The main task is to determine the conditions conducive to the formation of specified criteria for surface quality and to find out the dependencies of various factors when applying edge cutting machining and electrochemical processes. The research includes experimental and analytical parts, which are presented as conclusions, including the most optimal modes and conditions in terms of quality formation. The research methods are of an experimental and practical nature with the comparison and evaluation of the results obtained, in which the features of porous metal ceramics machining and methods for improving the efficiency of surface forming while maintaining the functional physical parameters of the part surfaces are considered. The novelty of the study is in finding dependencies of the obtained quality on the machining conditions and the comparative characteristics of the obtained surfaces not only in terms of changes in roughness, but also in surface porosity. As a result, recommendations are made for machining such materials, which minimize the effect of pore tightening and reduce deformation phenomena in the material.

Enhancing solar power forecasting with machine learning using principal component analysis and diverse statistical indicators

_Predicting solar energy is essential for efficient power system planning and the successful integration of renewable energy sources. This study aims to develop a framework for evaluating various machine learning models and feature selection strategies for solar energy prediction. The research applies six machine learning models, i.e., linear regression (LR), random forest (RF), neural networks (NN), K-nearest neighbor (KNN), gradient boosting (GB), and AdaBoost, to datasets from 2019 to 2021 collected at the Abiod Sid Cheikh solar station in southern Algeria. Various statistical indicators, including R2, RMSE, MAE, and Adj-R, were analyzed to assess model performance. The analysis revealed that R2 values ranged from 0.591 to 0.996 kW/m2, RMSE from 0.510 to 1.78 kW/m2, and MAE from 0.357 to 0.856 kW/m2 across different models. KNN and NN models showed significant errors, while GB and RF models demonstrated strong accuracies (RMS = 0.9). AdaBoost and LR excelled in real-time and short-term predictions, exhibiting an RMS of 0.99. This framework offers a comprehensive evaluation method for selecting the most suitable machine learning models and feature selection strategies for solar energy prediction. The findings can assist energy planners and engineers in choosing the appropriate models for accurate solar energy prediction, thereby enhancing the efficiency of power systems. Improved solar energy prediction can contribute to more reliable integration of renewable energy into power grids, supporting the transition to cleaner energy sources and reducing environmental impacts.

Numerical simulation on the machining characteristics of titanium alloy (Ti6Al4V) with coated inserts of different geometrical features

Numerical simulation on the machining characteristics of titanium alloy (Ti6Al4V) with coated inserts of different geometrical features

Exploring the machined surface characteristics of Haynes 25 superalloy: Cost mitigation and quality enhancement perspective

The current study investigates the surface characteristics and machining cost of electrical discharge machining (EDM) of Haynes 25 superalloy using tools made by additively manufactured CuCr1Zr, pure copper and graphite. Before assessing machinability, the workpiece and tool materials were characterized using Energy Dispersive Spectroscopy (EDS), X-ray Diffraction (XRD) and evaluations of tensile strength, micro-hardness, density and thermal conductivity. The effects of current (I), voltage (V), pulse duration (Ton), duty cycle (τ) and flushing pressure (Fp) is analyzed on surface characteristics viz. surface roughness (SR), surface crack density (SCD), recast layer thickness (RCT), heat-affected zone (HAZ), micro-hardness (MH) and machining cost (MC). Post machining XRD analysis revealed the formation of cobalt oxides like (CoO and Co3O4) affecting the micro-hardness of the machined surface. Alongside, a field emission scanning electron microscopy (FESEM) is carried out which confirms, the deposition of metal carbides and oxides on the EDMed surface. Current and pulse-on-time significantly influenced performance, with optimal EDM parameters identified and validated through confirmative experiments, resulting in a mean error of ∼2.84 %. It is seen that the use of additively manufactured CuCr1Zr tools resulted in improved machined surface characteristics and a more cost-effective approach for producing intricate profiles with minimal surface defects.

Geometry accuracy control in abrasive water jet taper hole machining of ultra‐thick carbon fiber‐reinforced polymer (CFRP) laminates

AbstractThe primary factors affecting the geometric accuracy of abrasive water jet (AWJ) machining of ultra‐thick carbon fiber‐reinforced polymer (CFRP) laminates are the cutting front drag and kerf width deviation caused by energy dissipation. Firstly, this study comprehensively analyzes the influence of the coupling relationship between cutting front drag and kerf width deviation on the geometric accuracy of hole machining. Secondly, a gradient distribution theory for jet traverse speed with cutting depth is proposed for taper hole machining characteristics. Finally, a general geometric error model applicable to both straight and taper hole machining of ultra‐thick CFRP laminates using AWJ is established, along with a geometric error compensation method. A series of experiments validate the accuracy of the proposed geometric error model and compensation method. The novelty of this research lies in unifying the geometric error models for straight and taper hole machining of ultra‐thick CFRP laminates by considering the gradient distribution of jet traverse speed. The proposed error compensation method reduces the high degree of freedom required for machine tools. This study provides a general geometric error model and compensation strategy for AWJ hole machining of ultra‐thick CFRP laminates, which has significant engineering value for achieving 3D controllable AWJ machining of complex ultra‐thick CFRP components.Highlights The high geometric precision taper holes machining technique is a necessary prerequisite for achieving precise machining of complex trajectories in ultra‐thick CFRP with abrasive water jet. The influence of the coupling relationship between cutting front drag and kerf taper on the geometric accuracy of hole processing is comprehensively analyzed. A model considering the gradient distribution of traverse speed during taper holes machining was established, and a geometric error model considering this gradient distribution of traverse speed was developed. A taper holes machining geometric error compensation method with high engineering applicability was proposed. Geometric error prediction experiments and error compensation experiments were conducted, and the results proved the accuracy of the geometric error model and error compensation method.

Gas dynamics and heat exchange of stationary and pulsating air flows during cylinder filling process through different configurations of the cylinder head channel (applicable to piston engines)

Piston machines are used in distributed generation, are in demand as auxiliary energy sources in hybrid systems and are indispensable devices in compressor technology. The purpose of this article is to develop a method for improving the quality of the cylinder filling process based on an experimental study of the gas dynamics and heat transfer of stationary and pulsating flows in an intake system with profiled channels in a piston machine's cylinder head. Experiments were carried out on full-scale models of piston machines with thermal anemometry and thermal imaging. The article examines three cross-sectional shapes for the intake port in the cylinder head: circle (basic design), square and triangle. It is established that profiled channels in a piston machine's intake system have a significant impact on the gas-dynamic, flow and heat-exchange characteristics of both stationary and pulsating air flows. It is shown that the use of profiled channels leads to a more uniform distribution of air flow throughout the entire cylinder volume and a significant reduction in stagnation zones, which should lead to a reduction in specific fuel consumption. It is established that air flow through an intake system with square and triangular ducts increases up to 30 % compared to the basic system, which should lead to an increase in power. It is found that the use of square and triangular channels leads to an increase in the flow turbulence intensity by 3…30 % and an increase in the heat transfer coefficient to 25 % in a piston machine's intake system. On the practical side, the installation of a cylinder head with profiled channels should improve the technical, economic and environmental characteristics of piston machines.

Particulate matter emissions from open pit mines; measurement methodologies, instruments, and research undertaken

Particulate matter is one of the primary pollutants in open pit mining operations. Measurements must be taken to control particulate matter created during open pit mining activities and to compare them to the regulatory limits. Numerous studies have been undertaken to estimate particulate matter emissions produced by open pit mining. It was discovered that the research were largely conducted on coal mines (69.4%), with little study done in other mining types. Research studies on particulate matter estimation took into consideration mostly machine characteristics (loader bucket volume, truck capacity, number of truck wheels etc.) and atmospheric conditions (air temperature, wind speed, relative humidity etc.). This study emphasizes on particulate matter measurement methods along with other measuring parameters and equipment for particulate matter estimation (TSP, PM10, PM4, PM2.5, and PM1).

Study on the impact of large-capacity unit commissioning on the stability of the power grid using EEAC theory

Abstract In view of the fact that the commissioning of large-capacity units in areas with weak grids may reduce the transient stability of the system and lead to a decrease in the load capacity of the power grid, this paper analyzes the phenomenon. Combined with the actual situation of a certain power grid, the equal-area rule and the extended equal-area rule are applied in this paper. It is pointed out that in the planning and design of the power grid, factors such as the structure of the sending-end power system, the output of the unit, and the short-circuit capacity of the area should be fully considered, in order to avoid the drop in the transient stability of the power grid due to the structural characteristics of the large machine, large load and small network of the sending end system. Finally, through simulation analysis, it is proposed that the transient stability and splicing load capacity of the regional power grid can be improved by controlling the output of the unit, expanding the main transformer, quickly removing the fault, improving the characteristics of the generator and its excitation regulation system, increasing the terminal voltage and reactive power output of the leading group of units, and cutting the machine.

Nonequilibrium fluctuations of a quantum heat engine

The thermodynamic properties of quantum heat engines are stochastic owing to the presence of thermal and quantum fluctuations. We here experimentally investigate the efficiency and nonequilibrium entropy production statistics of a spin-1/2 quantum Otto cycle in a nuclear magnetic resonance setup. We first study the correlations between work and heat within a cycle by extracting their joint distribution for different driving times. We show that near perfect correlation, corresponding to the tight-coupling condition between work and heat, can be achieved. In this limit, the reconstructed efficiency distribution is peaked at the deterministic thermodynamic efficiency, and fluctuations are strongly suppressed. We further successfully test the second law in the form of a joint fluctuation relation for work and heat in the quantum cycle. Our results characterize the statistical features of a small-scale thermal machine in the quantum domain, and provide means to control them.

Range-Doppler image classification for interference detection in over-the-horizon radar

Sky-wave over-the-horizon radar (OTHR), as a useful tool for beyond-line-of-sight target detection, is inevitably affected by radio frequency interference (RFI) and transient interference (TSI). Conventional interference detection is usually based on radar signal processing. This paper proposes to detect the interference by classifying the range-Doppler (RD) image into three categories, i.e. RFI, TSI, and NoI (No Interference), according to the texture differences. Unlike the conventional way, RD image classification has direct reflection of the interference's influence on target detection. To design the RD image classifier, we develop signal models to construct the simulated database, use real data to construct the real database, and employ various classification theories, e.g. deep learning, traditional machine learning, feature fusion, and ensemble learning. Experimental results show that the RD image classifier is an effective and promising tool for interference detection. Strong interference can be accurately detected, while weak interference needs more study in the future.

Digital twin for subcritical extraction driven by data-mechanism fusion

Abstract Addressing the key issue of low automation in the production process due to the complex associations involved in sub-critical extraction, this study focuses on sub-critical extraction as the subject matter. It integrates data models with mechanism models to construct a multidimensional digital twin model and conduct systematic research. By combining simulation methods with real-time experimental data, the study establishes multilevel machine characteristics of data, behavior, and mechanisms, and identifies data patterns. From the perspectives of the physical production line, virtual production line, and data transmission, it builds an interactive mapping platform for multi-source data and carries out corresponding application research.

Recognizing Speech Emotions Using AI

Abstract: I suggest an Among the most fundamental forms of self-expression is speech, which may convey a variety of feelings, including excitement, tranquility, joy, and rage, to mention a few. It is feasible to rearrange our activities, services, and even products in order to give each person a more customized experience customer by evaluating the emotions that underlie communication. The intention of this project is to recognize and extract various human speech sound files' emotions. to use Python to accomplish something similar. Python and a number of specialist libraries, such as Librosa, Sound File, NumPy, Scikit-learn, and PyAudio, will be used to accomplish this. These initiatives provide the features required for machine learning, feature extraction, and audio processing

Network Intrusion Detection and Classification System: A Supervised Machine Learning Approach

Abstract: Intrusion detection systems (IDSs) are crucial for computer security, as they identify and counteract malicious activities within computer networks. Anomaly-based IDSs, specifically, use classification models trained on historical data to detect these harmful activities. This paper proposes an enhanced IDS based on 3-level training and testing of machine learning models, feature selection, resampling, and normalization using Decision Tree, Gaussian Naïve Bayes, K-Nearest Neighbours, Logistic Regression, Random Forest, and Support Vector Machine. In the first stage, the six models are trained and evaluated using the original datasets after pre-processing. In the second stage, the models are built and tested with a resampled version of the dataset using the Synthetic Minority Oversampling Technique (SMOTE). In the third stage, the models are trained and tested with a dataset that has been both resampled and normalized using the standard scaling method. We employ the feature importance technique using the random forest model to select the essential features from NSL-KDD and UNSW-NB15 datasets. The results of our study surpass previous related research, with the decision tree achieving an accuracy, precision, recall, and F1 score of 99.99% on the UNSW-NB15 dataset. Additionally, the decision tree recorded an accuracy of 99.98%, precision of 99.97%, recall of 99.97%, and F1 score of 99.99% on the NSL-KDD dataset.

Influence of Cryogenic Treatment of Cutting Tools on the Machinability Characteristics of Materials: A Comprehensive Review

Influence of Cryogenic Treatment of Cutting Tools on the Machinability Characteristics of Materials: A Comprehensive Review