Optimization of high-pressure die-casting process parameters using artificial neural network

High-pressure die casting is a versatile process for producing engineered metal parts. There are many attributes involved which contribute to the complexity of the process. It is essential for the engineers to optimize the process parameters and improve the surface quality. However, the process parameters are interdependent and in conflict in a complicated way, and optimization of the combination of processes is time-consuming. In this work, an evaluation system for the surface defect of casting has been established to quantify surface defects, and artificial neural network was introduced to generalize the correlation between surface defects and die-casting parameters, such as mold temperature, pouring temperature, and injection velocity. It was found that the trained network has great forecast ability. Furthermore, the trained neural network was employed as an objective function to optimize the processes. The optimal parameters were employed, and the castings with acceptable surface quality were achieved.     

基于人工神经网络的导管数控弯曲成形工艺参数预测方法

阐述了导管数控弯曲成形过程的要素,分析主要工艺参数对导管弯曲成形质量的影响,并建立预测工艺参数的BP(Back Propagation)人工神经网络模型.选取实验数据作为样本,采用LM(Levenberg_Marquardt)贝叶斯正则化算法对该模型进行训练,确定模型的主要参数.通过实例预测并与实验数据进行比较,验证该方法的有效性.与其他BP训练算法进行比较,结果表明,该算法收敛速度快、预测精度高、稳定性好.     

Development of artificial neural network-based in-process mixed-material-caused flash monitoring (ANN-IPMFM) system in injection molding

This paper describes the development of an artificial neural network-based in-process mixed-material-caused flash monitoring system (ANN-IPMFM) in the injection molding process. This proposed system integrates two sub-systems. One is the vibration monitoring sub-system that utilizes an accelerometer sensor to collect and process vibration signals during the injection molding process. The other, a threshold prediction sub-system, predicts a control threshold based on the process parameter settings, thus allowing the system to adapt to changes in these settings. The integrated system compares the monitored vibration signals with the control threshold to predict whether or not flash will occur. The performance of the ANN-IPMFM system was determined by using varying ratios of polystyrene (PS) and low-density polyethylene (LDPE) in the injection molding process, and comparing the number of actual occurrences of flash with the number of occurrences predicted by the system. After a 180 trials, results demonstrated that the ANN-IPMFM system could predict flash with 92.7% accuracy.     

Analysis of the effect of a new process control agent technique on the mechanical milling process using a neural network model: Measurement and modeling

In this study, a new process control agent (PCA) technique called as gradual process control agent technique was developed and the new technique was compared with conventional process control agent technique. In addition, a neural network (ANN) approach was presented for the prediction of effect of gradual process control agent technique on the mechanical milling process. The structural evolution and morphology of powders were investigated using SEM and particle size analyzer techniques. The experimental results were used to train feed forward and back propagation learning algorithm with two hidden layers. The four input parameters in the proposed ANN were the milling time, the gradual PCA content, previous PCA content and gradual PCA content. The particle size was the output obtained from the proposed ANN. By comparing the predicted values with the experimental data it is demonstrated that the ANN is a useful, efficient and reliable method to determine the effect of gradual process control agent technique on the mechanical milling process.     

Optimization of injection molding process parameters using integrated artificial neural network model and expected improvement function method

In this study, an adaptive optimization method based on artificial neural network model is proposed to optimize the injection molding process. The optimization process aims at minimizing the warpage of the injection molding parts in which process parameters are design variables. Moldflow Plastic Insight software is used to analyze the warpage of the injection molding parts. The mold temperature, melt temperature, injection time, packing pressure, packing time, and cooling time are regarded as process parameters. A combination of artificial neural network and design of experiment (DOE) method is used to build an approximate function relationship between warpage and the process parameters, replacing the expensive simulation analysis in the optimization iterations. The adaptive process is implemented by expected improvement which is an infilling sampling criterion. Although the DOE size is small, this criterion can balance local and global search and tend to the global optimal solution. As examples, a cellular phone cover and a scanner are investigated. The results show that the proposed adaptive optimization method can effectively reduce the warpage of the injection molding parts.     

Prediction of heating-line paths in induction heating process using the artificial neural network

This paper presents the development of a back propagation neural network model for the prediction of heating-line positions in induction heating process. The vertical displacements of plate have been considered as the input parameters and the selected induction heating lines as output parameters to develop the model. The training patterns of neural network are obtained using an analytical solution that predicts plate deformations in induction heating process. The feasibility test reveals that the developed method can be used to determine the heating-line positions in line heating process.     

Development of artificial neural network models to study the effect of process parameters on burr size in drilling

Burr size at the exit of the holes in drilling is a quality index and hence it becomes essential to predict the size of the burr formed in order to cater to the demand of product quality and functionability. In this paper, artificial neural network (ANN)-based models have been developed to study the effect of process parameters such as cutting speed, feed, drill diameter, point angle, and lip clearance angle on burr height and burr thickness during drilling of AISI 316L stainless steel. A multilayer feed-forward ANN; trained using error back-propagation training algorithm (EBPTA) has been employed for this purpose. The input-output patterns required for training are obtained from drilling experimentation planned through Box-Behnken design. The simulation results demonstrate the effectiveness of ANN models to analyze the effects of drilling process parameters on burr size.     

Optimization of operating parameters and performance evaluation of forced draft cooling tower using response surface methodology (RSM) and artificial neural network (ANN)

Optimization of cold water temperature in forced draft cooling tower with various operating parameters has been considered in the present work. In this study, response surface method (RSM) and an artificial neural network (ANN) were developed to predict cold water temperature in forced draft cooling tower. In the development of predictive models, water flow, air flow, water temperature and packing height were considered as model variables. For this propose, an experiment based on statistical five-level four factorial design of experiments method was carried out in the forced draft cooling tower. Based on statistical analysis, packing height, air flow and water flow were high significant effects on cold water temperature, with very low probability values (< 0.0001). The optimum operating parameters were predicted using RSM, ANN model and confirmed through experiments. The result demonstrated that minimum cold water temperature was optioned from the ANN model compared with RSM.     

Development of RSM- and ANN-based models to predict and analyze the effects of process parameters of laser-hardened commercially pure titanium on heat input and tensile strength

Laser transformation hardening (LTH) is an innovative and advanced laser surface modification technique as compared to conventional transformation hardening processes and has been employed in aerospace, marine, chemical applications, heat exchangers, cryogenic vessels, components for chemical processing and desalination equipment, condenser tubing, airframe skin, and nonstructural components which introduces the advantageous residual stresses into the surface, improving the mechanical properties like wear, resistance to corrosion, tensile strength, and fatigue strength. In the present study, LTH of commercially pure titanium, nearer to ASTM grade 3 of chemical composition was investigated using continuous wave 2 kW, Nd: YAG laser. The effect of laser process variables such as laser power, scanning speed, and focused position was investigated using response surface methodology (RSM) and artificial neural network (ANN) keeping argon gas flow rate of 10 lpm as fixed input parameter. This paper describes the comparison of the heat input (HI) and ultimate tensile strength (σ) (simply called as tensile strength) predictive models based on ANN and RSM. The paper also presents the effect of laser process variables on the HI and ultimate σ. The research work also emphasizes on the effect of HI on σ. The experiments were conducted based on a three-factor, three-level Box–Behnken surface statistical design. Quadratic polynomial equations were developed for proper process parametric study for its optimal performance characteristics. The experimental results under optimum conditions were compared with the simulated values obtained from the RSM and ANN model. Adequacy of the developed models was tested by analysis of variance technique. A multilayer feed-forward neural network with a Levenberg–Marquardt back-propagation algorithm was adopted to develop the relationships between the laser hardening process parameters, HI, and ultimate σ. The performance of the developed ANN models were compared with the second-order RSM mathematical models of HI and σ. There was good agreement between the experimental and simulated values of RSM and ANN. The comparison clearly indicates that the ANN models provide more accurate prediction compared to the RSM models. It has been found that there is a trend of increased tensile strength with the decrease of hardening heat input and a trend of increased tensile strength with the increase of hardening cooling rate. As heat input decreases, there will be a faster cooling rate. Considering the effect of HI on ultimate σ, it was found that the lower the heat input, the faster cooling rate. The details of experimentation, model development, testing, validation of models, effect of laser process variables on heat input and ultimate σ, effect of HI on σ, and performance comparison of RSM and ANN models are presented in the paper. The results of Box–Behnken design of RSM and ANN models also indicate that the proposed models predict the responses adequately within the limits of input parameters being used. It is suggested that regression equations can be used to find optimum conditions for HI and σ of laser-hardened commercially pure titanium material.     

模糊神经网格控制的定子电阻的在线检测

在直接转矩控制中定子电阻是一个十分重要的参数，因此协调感应电机定子电阻是非常重要。在这里，提出了基于模糊神经网络理论的一种在线检测定子电阻的有效方法。在对广泛选择的样本进行学习后，优化了控制规则、各语言变量的隶属函数及每条规则的输出函数，在线估测结果与实验结果吻合良好。为进一步估算直接转矩控制或矢量控制系统中电机的磁通提供了可靠的保证，为改善系统的低速性能提供了有数的方法．     

Effect of extrusion pressure and number of finishing cycles on surface roughness in magnetorheological abrasive flow finishing (MRAFF) process

Magnetorheological abrasive flow finishing (MRAFF) was developed as a new precision finishing process for complicated geometries using smart magnetorheological polishing fluid. This process introduces determinism and in-process controllability of rheological behaviour of abrasive laden medium used for finishing intricate shapes. Magnetorheological polishing (MRP) fluid is comprised of carbonyl iron powder and silicon carbide abrasives dispersed in a viscoplastic base of grease and mineral oil and exhibits change in rheological behaviour in presence of external magnetic field. This smart behaviour of MRP fluid is utilized to precisely control finishing forces. The process performance in terms of surface roughness reduction depends on process variables like hydraulic extrusion pressure, magnetic flux density in the finishing zone, number of finishing cycles, and composition of MRP fluid. In the present work, experiments were conducted on a hydraulically powered MRAFF experimental setup to study the effect of extrusion pressure and number of finishing cycles on the change in surface roughness of stainless steel grounded workpieces. A new observation of “illusive polishing” action with the initial increase in number of finishing cycles is reported. The actual finishing action is possible only after removal of initial loosely held material remaining after grinding.     

把神经网络应用于丝杠磨削过程的建模与控制

提出了利用两个人工神经网络对丝杠的磨削过程进行建模与预测控制的思想.其中,网络1用于复映传动链、热变形和力变形等误差源与工件螺距误差的关系,即建模;网络2根据网络1的输出和工件螺距误差的仿真值而预报输出下一采样周期的综合补偿控制量.通过一系列试验研究,证明此控制策略能减少工件螺距误差80%以上,有效提高了试件丝杠的磨削精度.     

Optimization of wire electrical discharge machining (WEDM) process parameters using Taguchi method

Wire electrical discharge machining (WEDM) is extensively used in machining of conductive materials when precision is of prime importance. Rough cutting operation in WEDM is treated as a challenging one because improvement of more than one machining performance measures viz. metal removal rate (MRR), surface finish (SF) and cutting width (kerf) are sought to obtain a precision work. Using Taguchi’s parameter design, significant machining parameters affecting the performance measures are identified as discharge current, pulse duration, pulse frequency, wire speed, wire tension, and dielectric flow. It has been observed that a combination of factors for optimization of each performance measure is different. In this study, the relationship between control factors and responses like MRR, SF and kerf are established by means of nonlinear regression analysis, resulting in a valid mathematical model. Finally, genetic algorithm, a popular evolutionary approach, is employed to optimize the wire electrical discharge machining process with multiple objectives. The study demonstrates that the WEDM process parameters can be adjusted to achieve better metal removal rate, surface finish and cutting width simultaneously.     

Identifying change point of a non-random pattern on control chart using artificial neural networks

An important step in root cause analysis is the identification of the time when process first changed. The time when a disturbance first manifested itself into the process is referred to as change point. Identification of the change point could help process engineer to perform root cause analysis effectively. In this paper, an estimator for the change point of a normal process mean using artificial neural network (ANN) is proposed. Five patterns of change namely single step, linear trend, systematic, cyclic, and mixture are studied. Whenever possible, results are compared numerically to the results obtained by other methods proposed by different researchers. First the type of change to be recognized by an ANN-based pattern recognizer is identified and then the change point in the process mean is estimated. Results indicate satisfactory performance for the proposed method that could be used as an effective method for root cause analysis by process engineer.     

Comparative study of modeling and identification of the pneumatic artificial muscle (PAM) manipulator using recurrent neural networks

The paper deals with the PAM manipulator modeling and identification based on autoregressive recurrent neural networks. For the first time, the most powerful types of neural-network-based nonlinear autoregressive models, namely, NNARMAX, NNOE and NNARX models, will be applied comparatively to the PAM manipulator identification. Furthermore, the evaluation of different nonlinear neural network auto-regressive models of the PAM manipulator with different number of neurons in hidden layer is completely discussed. On this basis, the merits of each identified model of the highly nonlinear PAM manipulator have been analyzed and compared. The results show that the nonlinear NNARX model yields better performance and higher accuracy than the other nonlinear NNARMAX and NNOE model schemes. These results can be applied to model and identify not only the PAM manipulator but also to control other nonlinear and time-varying industrial systems.     

Evaluation of the effects of machining parameters on MQL based surface grinding process using response surface methodology

Journal of Mechanical Science and Technology - Grinding is a precision machining process widely used for close tolerance and good surface finish. Due to aggregate of geometrically undefined cutting...     

Optimisation of the electrical discharge machining process using a GA-based neural network

In this paper, the optimisation of the EDM process parameters from the rough cutting stage to the finish cutting stage has been reported. A trained neural network was used to establish the relationship between the process parameters and machining performance. Genetic algorithms with properly defined objective functions were then adapted to the neural network to determine the optimal process parameters. Examples with specifications intentionally assigned the same values as those recorded in the database or selected arbitrarily have been fed into the developed GA-based neural network in order to verify the optimisation ability throughout the machining process. Accordingly, the optimised results indicate that the GA-based neural network can be successfully used to generate optimal process parameters from the rough cutting stage to the finish cutting stage.     

Prediction of friction coefficient of treated betelnut fibre reinforced polyester (T-BFRP) composite using artificial neural networks

The current work is an attempt of using artificial neural network configuration to predict frictional performance of treated betelnut fibre reinforced polyester (T-BFRP) composite. Experimental dataset at different applied loads (5-30 N) and sliding distances (0-6.72 km) was used to train the ANN configuration with a large volume of experimental data (492 sets) where three different fibre mat orientations were considered (anti parallel, parallel and normal orientations). Results obtained from the developed ANN model were compared with experimental results. It is found that the experimental and numerical results showed good accuracy when the developed ANN model was trained with Levenberg-Marqurdt training function.     

Sensitivity analysis on ram speed of a direct extrusion process model using a porthole die through CEL method

Prediction of machine tool chatter requires the characterization of dynamic of the machine-tool-workpiece system by means of frequency response functions (FRFs). Uncertainties of the measured FRFs result in uncertainties of the calculated stability diagrams, therefore robustness of stability prediction against parameter perturbations is of high importance. Although there exist methods to determine robust stability in terms of stability radii, these methods either give a conservative estimate of the real uncertainties or are limited to perturbations of a few modal parameters, only. In this paper, a frequency-domain approach is presented to determine robust stability boundaries using the measured FRFs directly without any modal parameter identification. The method is based on an envelope fitting around the measured FRFs combined with some considerations of the single-frequency method. The application of the method is demonstrated in case of a turning operation, where the machine tool structure is characterized by a series of FRF measurements.