基于GA-BP神经网络的注塑质量与能耗的工艺参数优化

以插线板上盖为例，提出了一种注塑质量与能耗的工艺参数优化分析方式。选择6个工艺参数为因素变量，产品翘曲总量与注射阶段能耗值为优化指标，利用变异系数法确定二者权重，结合综合评分法将指标拟合为综合评分值。首先建立Taguchi试验，经过极差分析得出初始优化参数，随后基于Matlab平台建立BP神经网络模型，将其作为适应度函数，通过遗传算法(GA)进行全局寻优，得到最优工艺参数为模具温度50℃、熔体温度230℃、注射时间1.465 s、保压时间10.37 s、保压压力100 MPa、冷却时间15 s，经Moldflow分析，所得指标均优于Taguchi试验提供的优化结果，实现了注塑质量与能耗值的同时优化，证明了基于GA-BP神经网络的注塑工艺参数优化方法的有效性。     

基于RBF神经网络和遗传算法的注塑成型质量控制与预测

针对注塑产品容易产生翘曲和缩痕的问题,以某检测仪外壳为研究对象,运用RBF神经网络模型和遗传算法,对注塑成型质量进行控制与预测。基于正交试验方案,运用Moldflow有限元分析软件获得试验结果;利用样本数据建立试验因素与响应值之间的RBF神经网络模型,并用最优拉丁超立方抽样技术,获得样本点对模型精度进行检验;运用带精英策略的非支配排序遗传算法(NSGA-Ⅱ)对注塑成型工艺参数进行多目标优化,达到有效控制和预测翘曲变形、体积收缩率和缩痕指数的目的,并经模拟和试模验证误差较小。结果表明,运用RBF神经网络模型和遗传算法对注塑成型质量进行控制与预测,生产出检测仪外壳最大翘曲变形量为0.394 mm,外观无缩痕。     

基于径向基函数神经网络和多岛遗传算法的注射成型质量控制与预测

针对现有多参数、多目标注塑工艺优化应用的遗传算法、粒子群算法等寻优算法存在的实施难度大、求解时间长等缺点,提出基于最优拉丁超立方试验设计方法并结合径向基函数(RBF)神经网络模型和多岛遗传算法(MIGA)对注射成型质量进行控制与预测。以充电宝下盖塑件的体积收缩率和缩痕指数为优化控制目标,以模具温度、熔体温度、保压时间、保压压力、冷却时间为试验因素,应用最优拉丁超立方试验设计方法获得试验样本,基于模流分析获得试验结果,构建试验因素与优化控制目标之间的RBF神经网络模型,基于MIGA在试验因素给定的水平范围内获得了一组最优注塑工艺参数组合并给出了优化控制目标的预测值。模拟试验结果证明,预测值与模拟试验结果基本吻合,提出的方法能实现注塑成型质量的控制与预测,减少了寻找最优工艺参数组合的时间,提高了塑件的生产效率。     

基于Kriging模型的某汽车后保险杠注塑成型优化分析

为了提高注塑成型产品的质量与效率,以某车型后保险杠为研究对象,在三维软件中建立模型,导入Moldflow软件中建立浇注系统进行模流分析。以熔体温度、模具温度、保压时间、保压压力为变量,翘曲变形量为目标量,进行最优拉丁超立方试验设计并构建Kriging近似模型,结合多岛遗传算法进行参数优化。将优化的参数代入Moldflow软件中进行模拟,得到的翘曲变形量降低了34.90%,优化结果良好,改善了产品的生产效率与质量。     

基于代理模型和遗传算法的顺序注塑成型工艺优化

提出了一种综合考虑常规注塑工艺参数与时序阀浇口参数,并集成响应面代理模型和遗传算法的优化策略,对顺序注塑成型工艺参数优化进行了研究。该策略以改善SIM制品综合品质为目标,基于中心复合试验和数值模拟结果,利用响应面代理模型构建SIM制品综合品质指标与工艺变量间的关系模型;采用遗传算法对模型进行优化以获取最优解。结果表明:基于时序阀控制的顺序注塑成型技术能有效地消除成形零件的熔接痕缺陷,构建的响应面代理模型能有效地描述SIM工艺变量对品质的影响关系。最后,对遗传算法得出的最优解进行模模拟分析验证,验证所提出优化策略的有效性。     

基于响应面模型和遗传算法的注塑工艺多目标优化

结合Taguchi试验设计,利用注塑成型计算机辅助工程（CAE）模拟软件Moldflow对不同工艺参数下的注射成型进行模拟分析,对成型塑件体积收缩率、翘曲变形及缩痕指数3个目标进行综合评判;建立综合评分与工艺参数关系的代理模型——响应面模型,然后结合遗传算法进行全局多目标优化寻优,获得最优工艺组合,并进行模拟验证。结果表明,建立的响应面模型是可靠的,利用响应面模型进行注塑工艺多目标优化是一种有效的方法。     

面向能耗的3C门铃注塑成型多目标工艺优化

采用NSGA-Ⅱ及正交实验法与门铃挂架注塑成型有限元模拟技术,确定了符合产品质量特性和能效的多目标最佳工艺方案。以门铃塑件注塑工艺参数为实验变量,翘曲总变形、产品重量及能耗为响应优化指标,基于Moldflow模流分析设计多因素多水平多目标正交试验模型,并借助正交表进一步设计NSGA-Ⅱ优化模型。利用极差分析方法及Pareto前沿解分析了各因素对多目标优化指标的影响规律,并通过试模实验验证了2种优化实验模型的可行性及其优化效果。研究发现,保压压力和熔体温度是影响产品质量特性和能耗的主要因素,并获得多目标优化最佳成型工艺方案。优化后的成型工艺方案提高了PIM过程的稳定性,产品翘曲变形值、重量及能耗分别降低了16. 3%、3. 0%、18. 9%,符合企业绿色制造的要求。     

基于混合遗传算法的催化重整过程多目标优化

为实现催化重整过程生产指标的综合优化,基于已实现工业应用的催化重整17集总反应动力学模型和催化重整过程机理模型,考虑相应的多种约束条件,建立了以最大化总芳烃收率和最小化重芳烃收率为目标的多目标操作优化模型。提出了一种将遗传算法与局部优化方法相结合的多目标混合遗传算法HNAGA,并用于多目标操作优化模型的求解。现场工业数据的仿真研究表明,HNAGA在寻找Pareto最优解前沿方面比原遗传算法具有一定的优越性。将该多目标优化模型和求解方法应用于工业催化重整装置的操作优化,可以有效提高决策的准确性。     

芳烃抽提过程多目标优化

芳烃抽提是芳烃生产过程的重要环节,其生产调优对提高整个芳烃联合装置的效益具有重要意义。基于流程模拟及响应面分析方法,得到了芳烃抽提过程的产品纯度模型及能耗模型。建立了以产品纯度最大化及过程能耗最小化的多目标优化模型。提出了一种改进的自适应加权求和算法,并用于多目标优化模型的求解。求解结果表明新算法在Pareto最优解分布的均匀性上与原算法相当,但求解效率要高于原算法。给出了不同产品等级下的最佳操作参数,采用优化后的操作参数可有效地提高产品纯度并降低过程能耗。提出的多目标优化模型及求解算法用于芳烃抽提过程的操作调优,可有效地提高决策的准确性。     

考虑能耗影响的多产品间歇化工过程优化排序

提出一种用于间歇生产的多产品化工厂排序的多目标优化的混合整数非线性规划(MINLP)模型,其目标函数同时考虑了总生产时间最短和能耗最小的影响,定义了关于过程能耗的影响因子及决策因子,用以对总生产时间和能耗的影响进行权衡。采用改进的模拟退火算法(SA)对具有不同决策因子和能耗影响因子情况下的算例进行了求解,结果表明,该模型能够较好地反映能耗因素在多产品厂排序问题中的影响,使排序结果达到生产时间和能耗影响的综合最优。     

Multi-objective modeling and optimization for scheduling of cracking furnace systems

Cracking furnace is the core device for ethylene production. In practice, multiple ethylene furnaces are usual y run in parallel. The scheduling of the entire cracking furnace system has great significance when multiple feeds are simultaneously processed in multiple cracking furnaces with the changing of operating cost and yield of product. In this paper, given the requirements of both profit and energy saving in actual production process, a multi-objective optimization model contains two objectives, maximizing the average benefits and minimizing the average coking amount was proposed. The model can be abstracted as a multi-objective mixed integer non-linear programming problem. Considering the mixed integer decision variables of this multi-objective problem, an improved hybrid encoding non-dominated sorting genetic algorithm with mixed discrete variables (MDNSGA-I ) is used to solve the Pareto optimal front of this model, the algorithm adopted crossover and muta-tion strategy with multi-operators, which overcomes the deficiency that normal genetic algorithm cannot handle the optimization problem with mixed variables. Finally, using an ethylene plant with multiple cracking furnaces as an example to illustrate the effectiveness of the scheduling results by comparing the optimization results of multi-objective and single objective model.     

Integration of scheduling and control with online closed-loop implementation: Fast computational strategy and large-scale global optimization algorithm

In this paper, we propose a novel integration method to solve the scheduling problem and the control problem simultaneously. The integrated problem is formulated as a mixed-integer dynamic optimization (MIDO) problem which contains discrete variables in the scheduling problem and constraints of differential equations from the control problem. Because online implementation is crucial to deal with uncertainties and disturbances in operation and control of the production system, we develop a fast computational strategy to solve the integration problem efficiently and allow its online applications. In the proposed integration framework, we first generate a set of controller candidates offline for each possible transition, and then reformulate the integration problem as a simultaneous scheduling and controller selection problem. This is a mixed-integer nonlinear fractional programming problem with a non-convex nonlinear objective function and linear constraints. To solve the resulting large-scale problem within sufficiently short computational time for online implementation, we propose a global optimization method based on the model properties and the Dinkelbach's algorithm. The advantage of the proposed method is demonstrated through four case studies on an MMA polymer manufacturing process. The results show that the proposed integration framework achieves a lower cost rate than the conventional sequential method, because the proposed framework provides a better tradeoff between the conflicting factors in scheduling and control problems. Compared with the simultaneous approach based on the full discretization and reformulation of the MIDO problem, the proposed integration framework is computationally much more efficient, especially for large-scale cases. The proposed method addresses the challenges in the online implementation of the integrated scheduling and control decisions by globally optimizing the integrated problem in an efficient way. The results also show that the online solution is crucial to deal with the various uncertainties and disturbances in the production system.     

Genetic algorithm for short-term scheduling of make-and-pack batch production process

This paper considers a scheduling problem in industrial make-and-pack batch production process. This process equips with sequence-dependent changeover time, multipurpose storage units with limited capacity, storage time, batch splitting, partial equipment connectivity and transfer time. The objective is to make a production plan to satisfy al constraints while meeting demand requirement of packed products from various product fam-ilies. This problem is NP-hard and the problem size is exponentially large for a realistic-sized problem. Therefore, we propose a genetic algorithm to handle this problem. Solutions to the problems are represented by chromo-somes of product family sequences. These sequences are decoded to assign the resource for producing packed products according to forward assignment strategy and resource selection rules. These techniques greatly reduce unnecessary search space and improve search speed. In addition, design of experiment is carefully utilized to de-termine appropriate parameter settings. Ant colony optimization and Tabu search are also implemented for com-parison. At the end of each heuristics, local search is applied for the packed product sequence to improve makespan. In an experimental analysis, al heuristics show the capability to solve large instances within reason-able computational time. In al problem instances, genetic algorithm averagely outperforms ant colony optimiza-tion and Tabu search with slightly longer computational time.     

Integrated production planning and scheduling optimization of multisite,multiproduct process industry

The current manufacturing environment for process industry has changed from a traditional single-site, single market to a more integrated global production mode where multiple sites are serving a global market. In this paper, the integrated planning and scheduling problem for the multisite, multiproduct batch plants is considered. The major challenge for addressing this problem is that the corresponding optimization problem becomes computationally intractable as the number of production sites, markets, and products increases in the supply chain network. To effectively deal with the increasing complexity, the block angular structure of the constraints matrix is exploited by relaxing the inventory constraints between adjoining time periods using the augmented Lagrangian decomposition method. To resolve the issues of non-separable cross-product terms in the augmented Lagrangian function, we apply diagonal approximation method. Several examples have been studied to demonstrate that the proposed approach yields significant computational savings compared to the full-scale integrated model.     

基于P-graph的乙烯裂解原料调度建模与优化

乙烯工业不同的裂解装置间存在着设备、技术上的差别，每一种原料在乙烯工厂不同炉型或工艺的裂解装置的乙烯产品收率、能耗也存在着差别。随着新的乙烯工厂的投产，需要同时运行台数众多的差异化裂解装置，从而为通过优化调度乙烯裂解原料实现提高物效、降低能耗提供了空间。对于此类工厂间原料调度及能耗优化问题提出了一种基于P-graph的建模和优化方法(scheduling generation based on P-graph, SGBP算法)，该算法通过P-graph本身提取过程结构信息的能力，在加速求解的同时，保留了次优解集。之后以两个实际的乙烯厂为研究实例，采用提出的SGBP方法实现了原料调度的建模和优化，该方法与MINLP优化算法的对比分析验证了提出方法的优势：(1)可以同时提供较为丰富的最优解与次优解方案；(2)提出方法的最优结果与MINLP的优化效果相当；(3)优化后的整体能耗下降明显，为生产计划人员选择可采用灵活的原料调配方案提供了多种可选择的运行方案。     

Application of traveling salesman problem (TSP) for decision of optimal production sequence

In the present study a reliable and structural decision system for production sequence of polymeric products is developed. Minimization of the amount of off-specs is the main objective in the decision of production sequence to maximize profit. Off-specs are generated when the production sequence of polymeric products is changed. The amount of off-specs depends on changes of product grades. In the present study we applied the traveling salesman problem (TSP) to achieve optimal decision of production sequence. To solve the optimal decision problem formulated by TSP, we employed three different approaches such as Branch and Bound (B&B) method, Dynamic Programming (DP) method and Hopfield Neural Network (HNN) method. Production sequences computed based on the actual plant off-spec data were compared with the sequences employed in the actual plant operation. From the comparison the decision method proposed in the present study showed increased profits and reduced off-specs.     

Integration of production scheduling and dynamic optimization for multi-product CSTRs: Generalized Benders decomposition coupled with global mixed-integer fractional programming

Integration of production scheduling and dynamic optimization can improve the overall performance of multi-product CSTRs. However, the integration leads to a mixed-integer dynamic optimization problem, which could be challenging to solve. We propose two efficient methods based on the generalized Bender decomposition framework that take advantage of the special structures of the integrated problem. The first method is applied to a time-slot formulation. The decomposed primal problem is a set of separable dynamic optimization problems and the master problem is a mixed-integer nonlinear fractional program. The master problem is then solved to global optimality by a fractional programming algorithm, ensuring valid Benders cuts. The second decomposition method is applied to a production sequence formulation. Similar to the first method, the second method uses a fractional programming algorithm to solve the master problem. Compared with the simultaneous method, the proposed decomposition methods can reduce the computational time by over two orders of magnitudes for a polymer production process in a CSTR.     

改进的生物地理学优化算法在混合流水车间调度中的应用

调度问题是将有限的资源分配给各项不同任务的决策过程,其目的是优化一个或多个目标,它广泛存在于当今大多数的制造和生产系统中。混合流水车间调度问题是一般流水车间调度问题的推广,更接近实际的生产过程。采用一种新型的算法--生物地理学优化算法求解混合流水车间调度问题,通过引入改进策略,增强了算法的全局搜索能力和局部搜索能力,并提高了算法的收敛速度。通过10个标准调度算例的仿真研究,并与遗传算法进行对比,验证了改进后的生物地理学优化算法在求解混合流水车间调度问题方面的优越性。     

基于分片线性逼近的聚氯乙烯生产计划优化分解算法

聚氯乙烯全流程生产过程计划优化往往描述为复杂MINLP模型,求解难度非常大,为此引入分片线性技术逼近实际生产中的非线性特征,建立基于HH的MILP模型,进一步提出一种基于离线层级模型的分解算法来加速求解过程：第一层在对生产设备以最优能耗点进行层级划分得到离线层级模型的基础上优化一个等价MILP问题,确定表征设备操作状态的二值变量;第二层以HH模型为基础,在二值变量确定的情况下,代入计划优化模型调整设备的工作点,最终确定模型的最优操作决策方案。最后,以一个实际工厂规模的案例来验证模型和算法的有效性,结果表明本算法在基本不损失优化结果性能的前提下可以大大提高求解效率,缩短求解时间达99%以上。