<Emphasis Type="Bold">Optimisation of Plastic Injection Moulding Process with Soft Computing</Emphasis>

The paper presents a hybrid strategy in a soft computing paradigm for the optimisation of the plastic injection moulding process. Various plastic injection molding process parameters, such as mold temperature, melt temperature, injection time and injection pressure are considered. The hybrid strategy combines numerical simulation software, a genetic algorithm and a multilayer neural network to optimise the process parameters. An approximate analysis model is developed using a Back-propagation neural network in order to avoid the expensive computation resulting from the numerical simulation software. According to the characteristic of the optimisation problem, a nonbinary genetic algorithm is applied to solve the optimisation model. The effectiveness of the improved strategy is shown by an example.     

A study of optimization of injection molding process parameters for SGF and PTFE reinforced PC composites using neural network and response surface methodology

This study analyzed variations of mechanical characteristics that depend on the injection molding techniques during the blending of short glass fiber and polytetrafluoroethylene reinforced polycarbonate composites. A hybrid method including back-propagation neural network (BPNN), genetic algorithm (GA), and response surface methodology (RSM) are proposed to determine an optimal parameter setting of the injection molding process. The specimens are prepared under different injection molding processing conditions based on a Taguchi orthogonal array table. The results of 18 experimental runs were utilized to train the BPNN predicting ultimate strength, flexural strength, and impact resistance. Simultaneously, the RSM and GA approaches were individually applied to search for an optimal setting. In addition, the analysis of variance was implemented to identify significant factors for the injection molding process parameters and the result of BPNN integrating GA was also compared with RSM approach. The results show that the RSM and BPNN/GA methods are both effective tools for the optimization of injection molding process parameters.     

A computational system for process design of injection moulding: Combining blackboard-based expert system and case-based reasoning approach

The process design of injection moulding involves the selection of the injection moulding machine, mould design, production scheduling, cost estimation, and determination of injection moulding parameters. Expert system approaches have been attempted to derive the process solution for injection moulding in the past few years. However, this approach has been found to be incapable of determining the injection moulding parameters owing to the difficulty in setting the moulding parameters. In addition, the existing expert systems for process design lack the proper architecture for organising a heterogeneous knowledge source. In this paper, the combination of a blackboard-based expert system and case-based reasoning approach is introduced to make up the deficiencies of the existing expert-system approach to the process design, from which a computational system for process design of injection moulding, named CSPD, was developed and described. CSPD first derives the process solution including the selection of injection moulding machine and mould base, tooling cost, and processing cost estimation, and production scheduling based on the blackboard-based expert-system approach. It is then followed by the determination of the injection moulding parameters based on the case-based reasoning approach and the previously derived partial solution.     

A computational system for process design of injection moulding: Combining a blackboard-based expert system and a case-based reasoning approach

Process design of injection moulding involves the selection of the injection moulding machine, mould design, production scheduling, cost estimation, and determination of injection moulding parameters. An expert system approach has been used to derive the process solution for injection moulding over the past few years. However, this approach is found to be incapable of determining the injection moulding parameters owing to the fragile nature of the knowledge for setting the moulding parameters. In addition, the existing expert systems for process design lack proper architecture for organising heterogeneous knowledge sources. In this paper, the combination of a blackboard-based expert system and a case-based reasoning approach is introduced to eliminate the deficiency of the existing expert-system approach to process design, from which a computational system for the process design of injection moulding, named CSPD, has been developed. CSPD first derives the process solution including the selection of the injection moulding machine and the mould base, tooling cost, processing cost estimation, and production scheduling based on the blackboard-based expert-system approach. It is then followed by the determination of the injection moulding parameters based on the case-based reasoning approach and the previously derived partial solution.     

Digitized die forming system for sheet metal and springback minimizing technique

The design of the runner and gating systems is of great importance to achieving a successful injection moulding process. The subjects of this study are the finite element and abductive neural network methods applied to the analysis of a multi-cavity injection mould. In order to select the optimal runner system parameters to minimize the warp of an injection mould, FEM, Taguchi’s method and an abductive network are used. These methods are applied to train the abductive neural network. Once the runner and gate system parameters are developed, this network can be used to accurately predict the warp of the multi-injection mould. A simulated annealing (SA) optimization algorithm with a performance index is then applied to the neural network in order to search the gate and runner system parameters. This method obtains a satisfactory result as compared with the corresponding finite element verification.     

大量程柔性铰六维力传感器静态解耦的研究

为提高大量程六维力传感器的测量精度,提出了一种新型的六维力传感器非线性静态解耦方法,该方法结合混合递阶遗传算法和小波神经网络的优点,采用递阶遗传算法与最小二乘法分别对小波神经网络隐层结构参数以及输出层权值进行优化,再将优化后的小波神经网络模型用于六维力传感器非线性解耦.建立了基于混合递阶遗传算法和优化小波神经网络的六维力传感器非线性解耦模型,设计了基于混合递阶遗传算法的小波神经网络结构及参数优化算法,给出了六维力传感器非线性解耦的具体实现流程.以最新研制的6-UPUR大量程柔性铰六维力传感器为对象进行实验,结果表明,采用该方法六维力传感器的Ⅰ类误差和Ⅱ类误差分别为1.25％和2.59％,比采用BP和RBF神经网络方法的测量精度高.     

A hybrid model using genetic algorithm and neural network for process parameters optimization in NC camshaft grinding

Camshaft grinding is more complex comparing with the ordinary cylindrical grinding. Since its quality is mostly influenced by more factors, how to select process parameters quickly and accurately becomes the key to improve its quality and processing efficiency. In this paper, a hybrid artificial neural network (ANN) and genetic algorithm (GA) model is proposed to optimize the process parameters. In this method, a BP neural network model is developed to map the complex nonlinear relationship between process parameters and processing requirements, and a GA is used in order to improve the accuracy and speed based on the ANN model. The results show that the hybrid ANN/GA model is an effective tool for the process parameters optimization in NC camshaft grinding.     

基于神经网络和遗传算法的薄壳件注塑成型工艺参数优化

建立基于神经网络和遗传算法并结合正交试验的薄壳件注塑成型工艺参数优化系统.正交试验法用来设计神经网络的训练样本,人工神经网络有效创建翘曲预测模型;遗传算法完成对影响薄壳塑件翘曲变形的工艺参数(模具温度、注射温度、注射压力、保压时间、保压压力和冷却时间等)的优化,并计算出其优化值.按该参数进行试验,效果良好,可以有效地减小薄壳塑件翘曲变形,其试验数值与计算数值基本相符,说明所提出的方法是可行的.     

Conceptual design support system in a collaborative environment for injection moulding

The shortened time-to-market of new products requires experts from multiple disciplines to cooperate in product development. In this collaborative product development environment, an Internet-based conceptual design support system for Injection moulding is developed. It can help designers to put forward feasible design solutions quickly and provide strong support for collaborative design. The architecture, implementation and evaluation of this system are discussed in this paper. The proposed system makes fully use of component-based web technology and has a flexible distributed architecture. A hybrid neural network and genetic algorithm approach is also adopted for more accurate and efficient retrieval. Experiment results indicate it is superior to conventional systems in accuracy and time.     

基于遗传算法和神经网络的冷挤压工艺参数模糊优化设计

将模糊优化思想引入冷挤压工艺参数优化设计,以冷挤压模具的四个关键工艺参数为设计变量,以最终挤压件的各处材料的损伤值为目标函数,建立了冷挤压工艺参数模糊优化模型。提出了利用神经网络进行材料损伤近似计算的策略,从而形成了基于遗传算法和神经网络的冷挤压工艺参数模糊优化方法。对冷挤压工艺参数模糊优化模型进行了求解,优化结果表明模糊优化思想能提高冷挤压工艺设计质量。     

A computer-aided system for an optimal moulding conditions design using a simulation-based approach

Moulding conditions design refers to parameter settings of moulding conditions such as melt temperature, mould temperature and injection time. They are important factors in plastic injection moulding design. The determination of these parameters is a highly skilled job and has largely been dependent on injection moulding engineers' experience and intuitiveness. In this paper, the authors present a flexible computer-aided system to assist the designers by using simulation-based technology. One of the most prominent characteristics of the system is that it allows the designers to specify their intended quality measuring criteria such as minimum cavity pressure and shear stress, a uniform distribution of cooling time, end-of-fill temperature and volumetric shrinkage. The system uses weighted criteria as an objective function to determine optimal moulding conditions when multiple criteria are specified. Moldflow simulation results are used to compare different designs. A two-step exhaustive search strategy (from coarse to refined) is used to search for a near-optimal design.     

HIGH-ACCURACY SYNCHRONIZATION CONTROL WITH HYBRID NEURAL NETWORKS

A novel nonlinear control algorithm based on hybrid neural networks is presented to cope with the high-accuracy synchronization control problem for a dual-actuator electrohydraulic drive system which plays an important role for the development of elastomeric launchers. A new objective function for better synchronization performance is introduced and a learning algorithm to adjust the weights of the neural network, based on the gradient descent algorithm, is also derived. The hybrid neural network control algorithm guarantees high-accuracy synchronization performance of two motion cylinders and fast dynamic response as well as good stability of the control system. Prototype test results on the dual-actuator electrohydraulic drive system verifys the effectiveness of the proposed approach.     

基于模糊理论、遗传算法和神经网络的切削参数混合智能优化

提出一种基于模糊理论、遗传算法和神经网络的混合智能优化技术,给出优化目标的优化数学模型,详细叙述了遗传算法的寻优过程,模糊理论的应用及神经网络的训练和学习获取优化切削参数的技术,并给出各种优化目标下的切削参数混合智能优化与普通搜索方法的对比实例。     

再制造机床可修复零部件精度分配研究

研究可修复零部件精度参数的分配是关系到再制造机床性能和再制造成本的重要问题。本文提出了用BP+GA的混合算法优化分配可修复零部件精度参数的方法。首先利用BP神经网络建立零部件精度参数与再制造机床空间几何误差之间的正向映射模型,然后用正交设计法得到训练样本数据并训练网络,最后再用BP+GA的混合算法逆向确定零部件的精度参数。仿真结果表明了混合算法是解决复杂精度分配问题的一种理想方法,优化结果可用于指导零部件精度的修复。     

遗传算法改进的BP神经网络在协同创新评价中的应用

为了解决客户协同创新中协同工作效率难于评价的问题,提出了一种用遗传算法优化的神经网络对客户协同产品创新进行评价的评价模型：在评价指标方面,设计了一套包括效益、效率和过程的18个指标的评价体系;在评价算法方面,将遗传算法与BP神经网络结合起来,设计了遗传算法改进的BP神经网络算法。该模型充分利用遗传算法的全局搜索能力强与神经网络的局部搜索能力强的特点,克服了遗传算法局部收敛与神经网络收敛速度较慢的问题,是一种非常适用于评价协同工作的模型。最后通过实例训练,证明了该模型的有效性与可行性。     

基于遗传小波神经网络的多传感器信息融合技术的研究

依据小波函数的非线性逼近能力和神经网络的自学习特性,提出一种小波神经网络。为使小波神经网络具有更高的学习精度和更快的收敛速度。利用遗传算法对小波神经网络权阈值的优化,设计了遗传小波神经网络。将该网络用于多传感器信息融合设计了遗传小波神经网络多传感器信息融合系统。压力传感器数据融合系统的仿真表明该方法能有效的提高传感器的输出准确度,消除非目标参量对传感器输出结果的影响,此系统还可用于其他多传感器信息融合系统,具有实际应用价值。系统设计实现简单,适合工程应用。     

基于改进粒子群算法的神经网络PID控制研究

BP神经网络PID控制是利用BP神经网络的自学习和逼近任意非线性函数功能,对PID控制器的三个参数进行在线整定,但网络初始权值的选取困难.采用改进的PSO算法优化BP神经网络的初始权值,并对基于PAO算法的BP神经网络PID控制进行仿真实验.仿真结果表明,PSO算法使得网络初始权值的选取比较快速,系统的性能有所提高.     

Multi-response design of Nd:YAG laser drilling of Ni-based superalloy sheets using Taguchi��s quality loss function, multivariate statistical methods and artificial intelligence

This paper presents a hybrid design strategy for the determination of the optimum laser drilling parameters which simultaneously meets the requirements for seven quality characteristics (responses) of the holes produced during pulsed Nd:YAG laser drilling of a thin sheet of nickel-based superalloy Nimonic 263. The process was designed using two approaches based on the experimental data. In the first approach, the quality losses of seven correlated responses were uncorrelated into a set of components using the principal component analysis; then the grey relational analysis was applied to synthesise components into a synthetic performance measure. Since this approach considered only parameter values used in the experiment, the second approach was developed to find the global optimal parameters solution using an artificial neural network to model the relation between parameters and a synthetic performance measure, and a genetic algorithm to perform a search for the global optimum in a continual multidimensional space. The analysis of the application indicated that the proposed approaches gave a better result, in terms of the optimal parameter settings that yield the maximal synthetic performance measure, than several commonly used methods for multi-response process parameters design. The results demonstrated that the robust Nd:YAG laser drilling of Ni-based superalloy sheets was designed with respect to the requirements for seven quality characteristics of the drilled holes, by using the proposed strategy.     

基于遗传神经网络的加速度传感器动态建模方法

提出了利用遗传神经网络实现加速度传感器动态建模的新方法，介绍动态建模原理以及算法，给出用遗传神经网络建立的加速度传感器动态数学模型。该方法利用加速度传感器的动态标定数据，采用遗传神经网络搜索和优化动态模型参数。这样，既保留遗传算法的全局搜索能力，克服神经网络容易陷入局部极小的缺陷，又具有神经网络局部搜索能力强的特点。结果表明：以上提出的动态建模方法具有建模精度高、鲁棒性好等优点。     

Multi-objective optimization of material removal rate and surface roughness in wire electrical discharge turning

Wire electrical discharge turning (WEDT) is an emerging area, and it can be used to generate cylindrical forms on difficult to machine materials by adding a rotary axes to WEDM. The selection of optimum cutting parameters in WEDT is an important step to achieve high productivity while making sure that there is no wire breakage. In the present work, the WEDT process is modelled using an artificial neural network with feed-forward back-propagation algorithm and using adaptive neuro-fuzzy inference system. The experiments were designed based on Taguchi design of experiments to train the neural network and to test its performance. The process is optimized considering the two output process parameters, material removal rate, and surface roughness, which are important for increasing the productivity and quality of the products. Since the output parameters are conflicting in nature, a multi-objective optimization method based on non-dominated sorting genetic algorithm-II is used to optimize the process. A pareto-optimal front leading to the set of optimal solutions for material removal rate and surface roughness is obtained using the proposed algorithms. The results are verified with experiments, and it is found to improve the performance of WEDT process. Using this set of solutions, required input parameters can be selected to achieve higher material removal rate and good surface finish.