共查询到20条相似文献，搜索用时 15 毫秒
1.
Carmita Camposeco-Negrete 《先进制造进展(英文版)》2021,9(2):304-317
Wire electrical discharge machining (wire-EDM) is an energy-intensive process, and its success relies on a correct selection of cutting parameters. It is vital to optimize energy consumption, along with productivity and quality. This experimental study optimized three parameters in wire-EDM:pulse-on time, servo voltage, and voltage concerning machining time, electric power, total energy consumption, surface roughness, and material removal rate. Two different plate thicknesses (15.88 mm and 25.4 mm) were machined. An orthogonal array, signalto-noise ratio, and means graphs, and an analysis of variance (ANOVA), determine the effects and contribution of cutting parameters on responses. Pulse-on time is the most significant factor for almost all variables, with a percentage of contribution higher than 50%. Multi-objective optimization is conducted to accomplish a concurrent decrease in all variables. A case study is proposed to compute carbon dioxide (CO2) tons and electricity cost in wire-EDM, using cutting parameters from multi-objective optimization and starting values commonly employed to cut that tool steel. A sustainable manufacturing approach reduced 5.91% of the electricity cost and CO2 tons when machining the thin plate, and these responses were diminished by 14.09% for the thicker plate. Therefore, it is possible to enhance the sustainability of the process without decreasing its productivity and quality.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-021-00353-2 相似文献
2.
《Materials and Manufacturing Processes》2012,27(6):467-475
The present work reports on the development of modeling and optimization for micro-electric discharge machining (μ-EDM) process. Artificial neural network (ANN) is used for analyzing the material removal of µ-EDM to establish the parameter optimization model. A feed forward neural network with back propagation algorithm is trained to optimize the number of neurons and number of hidden layers to predict a better material removal rate. A neural network model is developed using MATLAB programming, and the trained neural network is simulated. When experimental and network model results are compared for the performance considered, it is observed that the developed model is within the limits of the agreeable error. Then, genetic algorithms (GAs) have been employed to determine optimum process parameters for any desired output value of machining characteristics. This well-trained neural network model is shown to be effective in estimating the MRR and is improved using optimized machining parameters. 相似文献
3.
The purpose of this study was to develop a closed-loop machine vision system for wire electrical discharge machining (EDM) process control. Excessive wire wear leading to wire breakage is the primary cause of wire EDM process failures. Such process interruptions are undesirable because they affect cost efficiency, surface quality, and process sustainability. The developed system monitors wire wear using an image-processing algorithm and suggests parametric changes according to the severity of the wire wear. Microscopic images of the wire electrode coming out from the machining zone are fed to the system as raw images. In the proposed method, the images are pre-processed and enhanced to obtain a binary image that is used to compute the wire wear ratio (WWR). The input parameters that are adjusted to recover from the unstable conditions that cause excessive wire wear are pulse off time, servo voltage, and wire feed rate. The algorithm successfully predicted wire breakage events. In addition, the alternative parametric settings proposed by the control algorithm were successful in reducing the wire wear to safe limits, thereby preventing wire breakage interruptions.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-021-00373-y 相似文献
4.
《Materials and Manufacturing Processes》2012,27(12):1459-1465
Wire electric discharge machining (WEDM) of polycrystalline silicon (polysilicon) involves high-temperature melting that easily produces cracks on the wafer surface. This study explored the removal of surface defects by electrolytic machining (EM) to enhance surface quality. EM of polysilicon was conducted under different voltage supply modes, namely, DC voltage (DC-V), pulse voltage (Pulse-V), and auxiliary pulse voltage (Auxiliary-P-V) to examine their effects on material removal (MR) and surface roughness (SR). Results show that poor surface quality was achieved by EM with DC-V mode due to accumulation of bubbles between electrode gaps and inefficient MR. In contrast, EM with Pulse-V supply can reduce SR by proper control of pulse voltage cycle through adjustment in pulse-on and pulse-off time to ensure good replenishment of electrolyte. Finally, adding an optimal auxiliary voltage to the pulse cycle contributes to EM stability. Hence, EM with Auxiliary-P-V supply is an effective approach to electrolytic machining of WEDMed polysilicon. Not only is high MR achieved, but good surface quality is also maintained. 相似文献
5.
Roping is a severe band-like surface defect that occurs in deformed aluminum alloy sheets. Accurate roping prediction and rating are essential for industrial applications. Recently, the authors introduced an artificial neural network (ANN) model to efficiently forecast roping behavior across the thickness of large regions with texture gradients. In this study, the previously proposed ANN model for roping prediction is briefly reviewed, and a few-shot learning (FSL)-based method is developed for roping grading with limited samples. To consider the directionality of the roping patterns, the roping dataset constructed from experimental observations is transformed into the frequency domain for more compact characterization. A transfer-based FSL method is further presented for grade roping with manifold mixup regularization and the Sinkhorn mapping algorithm. A new component-focused representation is also implemented for data-processing, exploiting the close correlation between roping and power distribution in the frequency domain. The ultimate FSL method achieved an optimal accuracy of 95.65% in roping classification with only five training samples per class, outperforming four typical FSL methods. This FSL approach can be applied to grade the roping morphologies predicted by the ANN model. Consequently, the combination of prediction and grading using deep learning provides a new paradigm for roping analysis and control.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-024-00499-9 相似文献
6.
A framework combining artificial neural network (ANN) modelling technique, data mining and ant colony optimisation (ACO) algorithm is proposed for determining multiple-input multiple-output (MIMO) process parameters from the initial chemical-mechanical planarisation (CMP) processes used in semiconductor manufacturing. Owing to the invisibility of the ANN in the solution procedures, the decision tree approach of data mining is adopted to provide the necessary information for a real-valued ACO. The simulation result demonstrates that the proposed method can be an efficient tool for selecting properly defined parameter combination with the CMP process. 相似文献
7.
《Materials and Manufacturing Processes》2012,27(1):10-25
Die sinking–electrochemical spark machining (DS–ECSM) is one of the hybrid machining processes, combining the features of electrochemical machining (ECM) and electro-discharge machining (EDM), used for machining of nonconducting materials. This article reports an intelligent approach for the modelling of DS–ECSM process using finite element method (FEM) and artificial neural network (ANN) in integrated manner. It primarily comprises development of two models. The first one is the development of a thermal finite element model to estimate the temperature distribution within the heat-affected zone (HAZ) of single spark on the workpiece during DS–ECSM. The estimated temperature field is further post-processed for determination of material removal rate (MRR) and average surface roughness (ASR). The second one is a back propagation neural network (BPNN)-based process model used in a simulation study to find optimal machining parameters. The BPNN model has been trained and tested using the data generated from the FEM simulations. The trained neural network system has been used in predicting MRR and ASR for different input conditions. The ANN model is found to accurately predict DS–ECSM process responses for chosen process conditions. This article also presents an effective approach for multiobjective optimization of DS–ECSM process using grey relational analysis. 相似文献
8.
Predicting of mechanical properties of Fe–Mn–(Al, Si) TRIP/TWIP steels using neural network modeling
G. Dini A. Najafizadeh S.M. Monir-Vaghefi A. Ebnonnasir 《Computational Materials Science》2009,45(4):959-965
In this work, an artificial neural network (ANN) model was established in order to predict the mechanical properties of transformation induced plasticity/twinning induced plasticity (TRIP/TWIP) steels. The model developed in this study was consider the contents of Mn (15–30 wt%), Si (2–4 wt%) and Al (2–4 wt%) as inputs, while, the total elongation, yield strength and tensile strength are presented as outputs. The optimal ANN architecture and training algorithm were determined. Comparing the predicted values by ANN with the experimental data indicates that trained neural network model provides accurate results. 相似文献
9.
The current study investigates the behavior of wire electric discharge machining (WEDM) of the super alloy Udimet-L605 by employing sophisticated machine learning approaches.The experimental work was designed on the basis of the Taguchi orthogonal L27 array,considering six explanatory variables and evaluating their influences on the cutting speed,wire wear ratio (WWR),and dimensional deviation (DD).A support vector machine (SVM) algorithm using a normalized poly-kernel and a radial-basis flow kernel is recommended for modeling the wire electric discharge machining process.The grey relational analysis (GRA) approach was utilized to obtain the optimal combination of process variables simultaneously, providing the desirable outcome for the cutting speed, WWR,and DD.Scanning electron microscope and energy dispersive X-ray analyses of the samples were performed for the confirmation of the results.An SVM based on the radial-basis kernel model dominated the normalized polykernel model.The optimal combination of process variables for a mutually desirable outcome for the cutting speed,WWR,and DD was determined as Ton1,Toff2,IP1, WT3,SV1,and WF3.The pulse-on time is the significant variable influencing the cutting speed,WWR,and DD.The largest percentage of copper (8.66%) was observed at the highest cutting speed setting of the machine compared to 7.05% of copper at the low cutting speed setting of the machine.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-017-0192-7 相似文献
10.
《Materials and Manufacturing Processes》2012,27(12):1443-1450
This study examines the use of wire electrical discharge machining (WEDM) in machining polycrystalline silicon with resistivity of 2–3 Ωcm. The effects of different WEDM parameters on cutting speed, machining groove width, and surface roughness are explored. Experimental results indicate that open voltage is the critical parameter in breaking the insulation of polycrystalline silicon, and that pulse-on time has the greatest influence on cutting speed. Other machining factors, such as flushing rate, have no significant effect on cutting speed but do nonetheless improve machining groove width and surface roughness. In addition, strengthening wire tension reduces vibration of the wire electrode, which also helps improve machining groove width. The experimental results show that WEDM can be practically applied to machining polycrystalline silicon. Hence, applications of WEDM to manufacturing of solar cell can lead to significant enhancement in production efficiency. 相似文献
11.
Lars Bodsberg 《Quality and Reliability Engineering International》1993,9(6):501-518
Various models which may be used for quantitative assessment of hardware, software and human reliability are compared in this paper. Important comparison criteria are the system life cycle phase in which the model is intended to be used, the failure category and reliability means considered in the model, model purpose, and model characteristic such as model construction approach, model output and model input. The main objective is to present limitations in the use of current models for reliability assessment of computer-based safety shutdown systems in the process industry and to provide recommendations on further model development. Main attention is given to presenting the overall concept of various models from a user's point of view rather than technical details of specific models. A new failure classification scheme is proposed which shows how hardware and software failures may be modelled in a common framework. 相似文献
12.
It is especially significant for a manufacturing company to select a proper maintenance policy because maintenance impacts not only on economy,reliability and availability but also on personnel safety.This article reports on research in the backlash error data interpretation and compensation for intelligent predictive maintenance in machine centers based on artificial neural networks(ANNs).The backlash error,measurement system and prediction methods are analyzed in detail.The result indicates that it is possible to predict and compensate for the backlash error in both forward and backward directions in machine centers. 相似文献
13.
The present article describes an attempt made to study the possibility of beneficiating low-grade iron ore fines of Barbil Area of Orissa state, India, using multi-gravity separator (MGS) after grinding the ?10 mm fines to < 75 micron size and prepare a pellet feed of 65% Fe content. For the performance analysis, an artificial neural network (ANN) mathematical modeling approach was attempted. A three-layer feedforward neural network with a backpropagation method has been adopted, considering the three significant parameters of MGS, mainly drum inclination, drum speed, and shake amplitude, were varied and the results were evaluated for grade, recovery, and separation efficiency. The results of beneficiation studies showed that good recovery of hematite is possible with simultaneous increase in Fe(T) grade from 50.74% to 65.26% with 71.25% recovery. The predicted value obtained by ANN shows good agreement with the experimental values. 相似文献
14.
15.
Wavelet neural network (WNN) approach for calibration model building based on gasoline near infrared (NIR) spectra 总被引：2，自引：0，他引：2
Roman M. Balabin Ravilya Z. Safieva Ekaterina I. Lomakina 《Chemometrics and Intelligent Laboratory Systems》2008,93(1):58-62
In this paper we have compared the abilities of two types of artificial neural networks (ANN): multilayer perceptron (MLP) and wavelet neural network (WNN) — for prediction of three gasoline properties (density, benzene content and ethanol content). Three sets of near infrared (NIR) spectra (285, 285 and 375 gasoline spectra) were used for calibration models building. Cross-validation errors and structures of optimized MLP and WNN were compared for each sample set. Four different transfer functions (Morlet wavelet and Gaussian derivative – for WNN; logistic and hyperbolic tangent – for MLP) were also compared. Wavelet neural network was found to be more effective and robust than multilayer perceptron. 相似文献
16.
基于神经网络专家系统的供应商竞争力分析 总被引：9，自引：0，他引：9
供应链管理(SCM)是在IT技术广泛应用的基础上产生的一种先进、新颖的管理哲学与方法。在供应链中,合理地分析供应商的竞争力是优化选择具有敏捷性和相容性合作伙伴的关键。本文提出了供应商竞争力的分析指标体系,构建了一个基于人工智能神经网络的专家系统,较好地解决了对供应商竞争力进行分析评估的问题。 相似文献
17.
人工神经网络在玻璃配方设计中的应用研究 总被引：4，自引：0，他引：4
应用人工神经网络技术,采用Neuralworks Predict软件建立BP网络模型,通过对R2O-MO-Al2O3-SiO2系统玻璃组成与热膨胀系数关系实验数据的训练,以期能预测该系统指定组成的玻璃的热膨胀系数?研究结果表明,所建立的神经网络模型能较正确地反映玻璃氧化物组成与其热膨胀系数之间的规律性。模型对给定组成玻璃热膨胀系数的预测值与实际测试值的相对误差在6．4％以内,表明由神经网络技术建立的这一模型能正确反映R2O-MO-Al2O3-SiO2系统玻璃组成与热膨胀系数间的内在规律性。 相似文献
18.
通过影响空调负荷的参数的研究,认为空调负荷是一个动态过程;结合神经网络的内在特点和功能,对某一空调系统的冷负荷进行了预测,结果能满足计算要求.在这基础上考虑了为提高神经网络预测空调负荷准确性还应进一步开展的工作. 相似文献
19.
《Materials and Manufacturing Processes》2012,27(10):1131-1141
Stainless steel (Type 316) workpiece was heated by the mixture of Liquid Petroleum Gas (LPG) and oxygen gas, and it was machined in a lathe under different cutting conditions to study the hot machining characteristics. The orthogonal turning operations were carried out on stainless steel (Type 316) using tungsten carbide (WC) cutting tool insert. During machining the cutting speed (Vc), feed rate (fs), depth of cut (a p ), and temperature of the workpiece were varied in the range of 200°C, 400°C, and 600°C. Turning experiments were designed based on the statistical three-level full factorial experimental design techniques. An artificial neural network (ANN) and response surface model (RSM) have been developed, which can predict the surface roughness of the machined workpiece. The experimental results concur well with the results obtained from the predictive models. 相似文献
20.
《Materials and Manufacturing Processes》2012,27(2):169-173
Design and development of steel is essentially governed by the Time-Temperature-Transformation (TTT) diagram. The diagram predicts the phase evolution during isothermal transformation schedules for a given chemistry. Selection of chemistry for obtaining a desired microstructure in steel under isothermal schedule needs determination of the TTT diagrams either by extensive experimental exercise or by rigorous thermodynamic calculations. Artificial neural network (ANN) technique has recently been employed as a versatile tool to predict the CCT diagrams of steels. The present work aims to identify a favorable composition capable of yielding an ultrafine bainitic microstructure by isothermal holding of austenite at low homologous temperature. To achieve this, TTT diagrams of varying compositions have been predicted a priori to reduce the required experimental trials. The exercise has led to the development of bainitic microstructure of nanoscale dimension in steel having 0.7C-2.0Mn-1.5Si-0.3Mo-1.5Cr (wt%). Experimental trial with the predicted composition of bainitic steel resulted into attractive combination of strength and ductility. 相似文献