薄壳注塑制品多指标工艺参数优化

高压、高速和高料温的成型工艺使得薄壳注射成型过程更易形成缺陷,因此有必要对薄壁技术进行研究并控制其缺陷。本文综合运用人工智能、模糊理论等对薄壳注射成型缺陷进行研究,开发出了参数优化模糊专家系统,给出了知识推理的技术,建立了缺陷及工艺参数的隶属度函数及模糊规则表。采用隶属函数来反映对象特征的模糊性和模糊关系,实现了基于规则的模糊推理,并对缺陷优化模块进行了实例验证。     

A real‐time process optimization system for injection molding

The proposed real‐time intelligent model for the injection molding process control consists of the initial parameters setting and online defects correction. First, preliminary optimization based on a simplified simulation model is used for the initial setting. This simplified model adopts a geometric approximation of the original part by a rectangular edge‐gated plate. Then, the molding trial will be run on the molding machine by using the initial process parameters. And a fuzzy inference model based on expert knowledge is developed for correcting defects during the molding trial. This defects correction procedure will be repeated until the part quality is found satisfactory. A corresponding intelligent system has been developed that is integrated with the injection machine by communicating with the controller. The system can be used to optimize process parameters real time. Experimental studies have been carried out for verification. POLYM. ENG. SCI., 2009. © 2009 Society of Plastics Engineers.     

Injection Molding Optimization for Minimizing the Defects of Weld Lines

Weld lines are one of the critical defects in injection molding production. They affect the strength of the plastic parts and are visually unpleasant. To address this problem, this paper proposes some strategies and methods for the formulation and implementation of an optimization procedure to minimize the defects of weld lines by minimizing their total length and by positioning them as further away as possible from, or restricting them from occurring at, the specified critical regions on the part surface. Several concepts are defined, such as the weld line relevant part qualities, types of critical regions, and constraints on the occurrence of the weld lines. Based on these, the optimization problem is modeled and a genetic algorithm (GA) based optimization procedure is proposed. The methodology can provide useful guidelines for injection molding designers in achieving the optimal part quality relevant to the weld lines. A case study is also conducted to demonstrate the effectiveness of the methodology.     

Performance analysis and fuzzy optimization of a two-stage fermentation process with cell recycling including an extractor for lactic acid production

In this study, we consider a two-stage fermenter with cell recycling including an extractor to produce lactic acid. When the extractor was omitted, the proposed process was simplified to two special processes. Under the same operating conditions, we compared the overall lactic acid productivity and glucose conversion for the three processes. The proposed fermentation process was more efficient than the other processes. To simultaneously obtain the maximum productivity and conversion, the problem is formulated as a fuzzy multiobjective optimization problem. The fuzzy decision is introduced to convert the multiobjective fuzzy optimization problem into the fuzzy goal attainment problem. Hybrid differential evolution is applied to solve the fuzzy goal attainment problem to obtain a global Pareto solution.     

Impact of Fuel Cell Power Plants on Multi‐objective Optimal Operation Management of Distribution Network

This paper presents an interactive fuzzy satisfying method based on hybrid modified honey bee mating optimization and differential evolution (MHBMO‐DE) to solve the multi‐objective optimal operation management (MOOM) problem, which can be affected by fuel cell power plants (FCPPs). The objective functions are to minimize total electrical energy losses, total electrical energy cost, total pollutant emission produced by sources, and deviation of bus voltages. A new interactive fuzzy satisfying method is presented to solve the multi‐objective problem by assuming that the decision‐maker (DM) has fuzzy goals for each of the objective functions. Through the interaction with the DM, the fuzzy goals of the DM are quantified by eliciting the corresponding membership functions. Then, by considering the current solution, the DM acts on this solution by updating the reference membership values until the satisfying solution for the DM can be obtained. The MOOM problem is modeled as a mixed integer nonlinear programming problem. Evolutionary methods are used to solve this problem because of their independence from type of the objective function and constraints. Recently researchers have presented a new evolutionary method called honey bee mating optimization (HBMO) algorithm. Original HBMO often converges to local optima, in order to overcome this shortcoming, we propose a new method that improves the mating process and also, combines the modified HBMO with DE algorithm. Numerical results for a distribution test system have been presented to illustrate the performance and applicability of the proposed method.     

采用RFR-GA算法的薄壁注塑件质量多目标优化

汽车内饰件可由注塑加工获得,但成型过程中塑件产生的翘曲、体积收缩较大,针对该问题,以某汽车薄壁注塑件为例,研究了其注塑工艺参数的优化方法.通过以注塑过程中的最小翘曲和最小体积收缩率为目标函数,以注塑温度、模具温度、注射压力、保压压力、保压时间以及冷却时间等参数作为设计变量,构建了多目标全局优化模型.利用Moldflow...     

Hydrogen and CO2 Management in the Refinery with Fuzzy Multiobjective Nonlinear Programming

An innovative approach for optimization of the hydrogen network in a refinery is presented. The optimization problem was formulated as a fuzzy‐based multiobjective nonlinear programming (FMONLP), aiming at simultaneous minimization of the total annual cost and CO₂ emission. This is achieved by defining an objective function with a weighted sum of the annual cost and CO₂ emission. The weighting factors are considered as fuzzy parameters which are described based on the experts' experiences. The applicability of the proposed approach is illustrated by optimization of an Iranian refinery hydrogen network.     

Control of injection velocity using a fuzzy logic rule-based controller for thermoplastics injection molding

Injection velocity to a large degree determines the melt injection rate during the injection phase, and it has critical impact on the molded part quality, such as shrinkage, warpage, and impact strength. An injection molding machine operates with different injection velocity profiles, barrel temperatures, molds, and materials. These strongly different molding conditions cause the injection velocity dynamics to very significantly and to make the control performance of the injection velocity poor with a typical PID controller. A real-time, closed-loop feedback and feedforward control system based on fuzzy logic has been designed, developed, and implemented to control the injection velocity. The fuzzy logic rules of the controller are optimized by analyzing phase plane characteristics. The controller output membership functions are optimized based on a 2^k factorial design technique. The experimental results reveal that the fuzzy logic-based controller works well with different molds, materials, barrel temperatures, and injection velocity profiles, indicating that the fuzzy logic controller has superior performance over the conventional PID controller in response speed, set-point tracking ability, noise rejection, and robustness.     

含分段线性隶属函数的模糊规划建模方法

针对具有分段线性隶属函数的模糊规划问题,提出了一种新的模糊规划建模方法。通过对二元变量的合理配置,准确地表达出了隶属函数的各分段之间的关系。这种方法可以有效地避免常规建模方法解决模糊规划时出现的系统失去约束的问题,使得优化问题能够获得满意的最优解。并且,在一些情况下可以使用比普通方法更少的二元项进行优化问题的建模,从而使得计算更为简便。详细地给出了两种相关的建模方法,并通过实例进行了验证。     

Multiobjective optimization of injection molding using a calibrated predictor based on physical and simulated data

This paper presents a method for improving injection molding processes having competing performance measures using multiobjective optimization. The procedure uses calibrated predictors that combine physical and simulated data to estimate the values of the performance measures. After the predictors are built, the values of the selected performance measures are estimated at a grid of process control variables, and a set of predicted Pareto solutions is identified using nondominance criteria. A refinement of the original Pareto solutions is obtained by predicting the performance measures at a finer grid of the process variables near the original Pareto set. Finally, as validation, a subset of these solutions is evaluated on the physical process. A case study with three performance measures is presented to show how the calibrated predictors allow the injection molding manufacturer to identify the processing conditions that optimize a process having competing objectives. POLYM. ENG. SCI., 57:248–257, 2017. © 2016 Society of Plastics Engineers     

基于多目标的模糊神经网络及在pH控制过程中的应用

设计了一种基于多目标的动态模糊递归神经网络（FRNN）建模方法,用于pH中和过程的广义预测控制。所设计的多目标优化算法以提高拟合精度和简化网络结构为原则,同时优化模糊神经网络中的模糊规则数、隶属度函数中心点及其宽度,由此得到的FRNN模型可以高精度拟合pH中和过程。依据该动态模型,在控制过程的每一个控制周期得到其局部线性模型,将广义预测控制中复杂的非线性优化问题转化为简单的二次线性规划问题。仿真对比结果验证了所提方法的有效性。     

Multiobjective Optimization of the Industrial Naphtha Catalytic Re-forming Process

1 INTRODUCTION Petroleum refining and petrochemical industries aim at maximizing one prime product while simulta-neously minimizing another accessory product to im-prove the quality of the prime product. Unfortunately, the two requirements are often conflicting or incon-sistent. It is necessary to determine the trade-off com-promises to balance the two objectives[1,2]. As the core of aromatics complex unit, catalytic reforming is a very important process for transforming naphtha into arom…     

车用CD托架CAE注塑工艺参数优化分析

以汽车CD托架注塑成型为例,结合生产实际问题,构建了产品CAE分析模型,运用Moldfl ow2015软件对产品材料推荐的注塑成型工艺参数进行了初步仿真,对注塑过程中的翘曲、熔接痕、气穴等缺陷成因进行了分析,并给出了质量改善优化目标,提出了一种结合Taguchi试验法、BP神经网络预测的注塑成型工艺寻优方法,并对寻优结果进行了CAE模流分析验证。结果表明,神经网络预测结果与CAE模流分析结果相近,产品翘曲量降低至1.192 mm,产品较佳的注塑成型工艺参数为:料温为225℃,模温为60℃,注塑压力为70 MPa,注塑时间为1.3 s,第一保压压力为80 MPa,第一保压时间为12 s,第二保压压力为30 MPa,第二保压时间为3 s,冷却时间为15 s,型腔随形水路C1,C2冷却水的温度均为30℃。提出的优化设计方法能有效降低模具试模成本,缩短模具生产周期。     

OPTIMIZATION OF PROCESS CONDITIONS IN GAS-ASSISTED INJECTION MOLDING

Gas-assisted injection molding has been widely used to provide promising solutions to problems in conventional molding. With additional process parameters introduced, optimization in gas-assisted injection molding is much more complex than in conventional injection molding. This paper proposes an automated design methodology for gas-assisted injection molding with robustness in consideration. By introducing a definition of gas penetration cost, the optimization problems dealing with multiple quality issues can be modeled as constrained optimization problems, with the gas penetration cost as main objective function and other quality quantities as constraints. A direct search-based optimization procedure, the Complex method, is used to optimize a bounded single-criterion problem. To illustrate the proposed methodology, a case study is carried out on simulation results.     

Injection Molding Warpage Optimization Based on a Mode-Pursuing Sampling Method

This paper presents a new optimization approach for minimizing the warpage defect of injection-molded plastic parts. Existing methods in warpage optimization are either computationally expensive or, when inexpensive surrogate models are employed with fixed set of sample points, the accuracy of the surrogate model will only be ensured by a large number of sample points, which in turn will increase the amount of required computation. To address this problem, this paper applies a mode-pursuing sampling (MPS) method for warpage optimization, by integrating injection molding simulation with MPS, and by proposing a reinforced convergence criterion for the optimization process, in an attempt to search for the optimal process parameters of injection molding for minimizing warpage defect both effectively and efficiently. The MPS method can systematically generate more sample points in the neighborhood of the current optimal solution while statistically covering the entire search space. A case study of a scanner frame, where injection time, melt temperature and mold temperature are selected as the design variables, demonstrates that the proposed optimization method can effectively decrease the warpage deflection of an injection-molded part with significantly less computation required. Based on the optimization results, the paper also studied the influences of different process parameters on the severity of the warpage defect, providing a guideline for the setting of the proper process parameters.     

Implementation of Multimodel-Based PID and Intelligent Controller for Simulated and Real-Time Temperature Control of Injection Molding Machine

The proposed real-time multimodel for the injection molding process mainly contributes to the barrel temperature control. Good control of the plastic melt temperature is very important for injection molding in reducing the operator setup time, ensuring product quality, and preventing thermal degradation of the melt. The controllability and set points of the barrel temperature also depend on the precise monitoring and control of the plastic melt temperature. Motivated by the practical temperature control of injection molding, this article proposes a multimodel-based proportional integral derivative (PID) control scheme in real-time and the simulation studies of the PID, fuzzy, and adaptive neuro fuzzy inference system (ANFIS) control schemes. The injection molding process consists of three zones, and the mathematical model for each zone is different. The control output for each zone controller is assigned a weight, based on the computed probability of each model, and the resulting action is the weighted average of the control moves of the individual zone controller.     

注塑机工艺参数的智能设置与优化

针对工艺人员的试模思路,混合使用实例推理、代理模型和模糊推理技术,建立一种描述注塑机工艺参数设置与优化全过程的混合智能模型。首先采用实例推理技术模拟工艺人员设置初始工艺参数时的“借鉴”思维,在实例推理失败的情况下,采用代理模型模拟工艺人员的“直觉”思维设置初始工艺参数,然后将初始参数用于试模,最后利用模糊推理技术实现工艺人员不断修正缺陷、优化工艺参数的思维过程。基于上述智能模型开发出了相应的软件系统,并通过与控制器的通讯实现与注塑机的集成,实际案例验证表明该系统正确有效,可应用于实际生产。     

化工过程分离循环系统的多目标模糊优化研究

Separation-recycle system is an important part in chemical process, and its optimization is a multiobjective problem. In this paper the process optimization procedure is proposed. The fuzzy optimization algorithm with the concept of relative importance degree (RID) is utilized to transfer multi-objective optimization (MO-O) model into a single-objective optimization (SO-O) framework. The treatment of process condensate in synthesisa mmonia plant is taken as example to illustrate the optimization procedure, and the satisfactory result demonstrates feasibility and effectiveness of the suggested method.     

多目标多级串联系统优化的模糊优选动态规划技术

将模糊优选理论与动态规划技术有机地结合起来,提出多目标多级串联系统优化的模糊优选动态规划技术。为解决化工系统中的多目标多阶段优化问题提供一条新路。最后例举一多级反应器系统最优控制应用算例。     

基于模糊HSE评价的多目标反应路径综合方法

为在过程早期获取HSE综合性质优良的反应路径,提出了基于模糊HSE评价的多目标反应路径综合方法。全面考虑HSE因素,形成了HSE指标结构,通过设定指标的隶属度函数,建立模糊推理系统,应用层次分析法（analytic hierarchy process,AHP）确定指标的权重因子,形成了模糊HSE评价方法。基于模糊HSE评价体系,建立以安全、环境和健康为目标函数的多目标优化模型,求解得到优良的反应路径组合。应用于萘甲胺反应路径综合实例,定量得到了反应路径及其HSE目标函数值,为过程早期的路径优选提供定量数据。