Combining a neural network with a genetic algorithm for process parameter optimization

A neural-network model has been developed to predict the value of a critical strength parameter (internal bond) in a particleboard manufacturing process, based on process operating parameters and conditions. A genetic algorithm was then applied to the trained neural network model to determine the process parameter values that would result in desired levels of the strength parameter for given operating conditions. The integrated NN–GA system was successful in determining the process parameter values needed under different conditions, and at various stages in the process, to provide the desired level of internal bond. The NN–GA tool allows a manufacturer to quickly determine the values of critical process parameters needed to achieve acceptable levels of board strength, based on current operating conditions and the stage of manufacturing.     

基于数据挖掘的仿真模型参数修正

针对工业仿真数学模型参数估计实践中的难点,提出了通过数据挖掘来修正模型参数的新方法。从实际生产的大量数据中挖掘样本,通过数学方法计算模型参数,针对包含噪声的工业生产数据主要采用改进了最小二乘方法来修正参数;根据工业生产数据不完全及常见分布特点,采用分段组合修正参数的方法;通过实际生产的动态过程的历史数据挖掘来估计动态特性的相关参数,模型参数修正与数据挖掘过程交互引导,来缩小海量工业数据中的挖掘范围及提高参数修正所需样本数据的充分性,并建立两者之间互相协调的网络模型。实际案例验证了方法在工程项目中的有效性和实用性,表明这种方法能大幅提高仿真精度     

基于多组件智能体技术的布局问题求解方法研究

在简要介绍组件智能体技术的基础上,提出基于多组件智能体技术的布局问题协同求解方法模型。详细描述了模型中各组件智能体的定义和功能,通过它们之间的协同工作,克服传统求解方法的缺点,使其具有较强的问题求解能力和环境适应能力。     

基于微操作的Hadoop参数自动调优方法

Hadoop作为大规模分布式数据处理框架已经在工业界得到广泛的应用，针对手动和经验调优方法中参数空间庞大和运行流程复杂的问题，提出了一种Hadoop参数自动优化的方法和分析框架。首先，对作业运行流程进行解耦，从可变参数直接影响的更细粒度的角度定义微操作，从而分析参数和单次微操作执行时间的关系；然后，利用微操作对作业运行流程进行重构，建立参数和作业运行时间关系的模型；最后，在此模型上应用各类搜索优化算法高效快速得出优化后的系统参数。在terasort和wordcount两个作业类型上进行了实验，实验结果表明，相对于默认参数情况，该方法使作业执行时间分别缩短了至少41%和30%。该方法能够有效提高Hadoop作业执行效率，缩短作业执行时间。     

基于遗传算法的选煤工艺参数优化

对选煤生产过程优化目标进行了分析,采用以经济效益为目标,建立了优化工艺参数与优化目标间的关系模型,该模型是非线性的。选煤生产过程工艺参数优化就是指在市场需求、资源配置,生产能力等条件下,选择最合适的分选密度和分选灰分,获得最大经济效益。遗传算法利用生物进化机制,在一个较大的初始解空间中,通过优胜劣汰的方法进行优化求解,和其他优化方法相比不仅寻优能力强而且计算速度快。基于遗传算法对选煤生产过程工艺参数进行了优化操作,根据具体情况,采用特定的遗传操作。仿真结果表明,优化后的工艺参数能获得最大的经济效益。     

Data reconciliation for real-time optimization of an industrial coke-oven-gas purification process

Online optimization is more and more used in the chemical industry to run a process near its optimum operating condition by providing real-time computed optimal set-points to the distributed control system. Process measurements are necessary for these applications to determine the actual state of the process and to increase the accuracy of the model with parameter estimation techniques. However, these measurements usually contain random as well as gross errors which have to be identified and eliminated before the measurements are used for online optimization. In this contribution, a data reconciliation approach was integrated into an online optimization framework for the ammonia hydrogen sulfide circulation scrubbing, a common industrial coke-oven-gas purification process. We used a rigorous rate-based model to describe this reactive absorption and desorption process. To increase the accuracy of the model, we estimated several process parameters using a sequential parameter estimation approach. Data reconciliation was performed based on simple component balances to achieve model-consistent data and to identify measurement biases. The model was then validated online on a pilot plant by connecting the estimation package through the process control system. Based on the online measured data, operating cost minimization was carried out and the computed optimal set-points realized real-time. A satisfactory agreement between measured data and optimization was achieved.     

A moving window parameter adaptive control system for the F8-DFBW aircraft

This paper describes the moving window parameter adaptive control system developed for the NASA F8-DFBW aircraft. The control system employs a parameter identification process that, iteratively, adjusts parameters of a model of the aircraft motions in a batch-processing manner so that responses generated from the model fit the outputs of sensors stored in a finite record referred to as the moving window. Tests are made on the validity of the parameter estimates before using the parameters in an on-line design process. The on-line design process is an algebraic mapping of the parameters of the model into primary control system feedback and feedforward gains. The mapping was selected to satisfy specific flying quality characteristics over the range of parameter variations expected. Results are presented from simulation studies on the identification algorithm made during the development of the system. Also, results from the F8-DFBW project simulation at the NASA langley Research Center are presented that indicate the overall performance of the control system in meeting the flying quality objectives of the design.     

Practical aspects of process identification

After the presentation of various identification and parameter estimation methods in the previous papers, some selected practical aspects of process identification are discussed. This includes, for a given identification method, the steps from the design of experiments to the verification of the final model. Therefore a general procedure of process identification, the selection of input signals, the selection of the sampling time, off-line and on-line identification, comparison of parameter estimation methods, model order testing and model verification is presented. A short discussion on program packages for process identification follows.     

酸性磷铵料浆浓缩过程中氟含量的预测模型

在磷铵生产过程中,料浆的氟含量预测对生产具有重要意义。本文将径向基函数网络(RBFN)与循环子空间回归(CSR)相结合,设计了RBFN—CSR建模方法。RBFN—CSR方法在确定隐含层结构和参数时,将隐单元数取为训练样本数,径向基函数中心矢量取相应样本值,宽度参数根据样本分布情况采用尝试方法选取,隐含层到输出层的网络权系数运用CSR求解。CSR求解过程包容了最小二乘回归(LSR)、主成分回归(PCR)、偏最小二乘回归(PLSR)以及很多中间的回归方法,它可在非常广泛的范围内根据某一准则选择最优的网络结构参数。运用RBFN—CSR方法建立了酸性磷铵料浆浓缩过程中氟含量的预测模型,交叉验证表明,该模型具有较高的预测精度和良好的稳定性能,有一定的实际应用价值。     

Design of a robust fuzzy controller for the arc stability ofCO2 welding process using the Taguchi method

CO(2) welding is a complex process. Weld quality is dependent on arc stability and minimizing the effects of disturbances or changes in the operating condition commonly occurring during the welding process. In order to minimize these effects, a controller can be used. In this study, a fuzzy controller was used in order to stabilize the arc during CO(2) welding. The input variable of the controller was the Mita index. This index estimates quantitatively the arc stability that is influenced by many welding process parameters. Because the welding process is complex, a mathematical model of the Mita index was difficult to derive. Therefore, the parameter settings of the fuzzy controller were determined by performing actual control experiments without using a mathematical model of the controlled process. The solution, the Taguchi method was used to determine the optimal control parameter settings of the fuzzy controller to make the control performance robust and insensitive to the changes in the operating conditions.     

Optimized design for anti-reflection coating process in roll-to-roll slot-die coating system

This study investigated the application of the anti-reflection (AR) coating technology by using the roll-to-roll (R2R) slot-die coating process. To simulate the coating phenomenon, we investigated governing parameters in the slot-die coating process by using a viscocapillary model. Results of using this model revealed that the coating speed and solid content are two dominant factors affecting transmittance, which is an important parameter for the AR coating process. As the design of experiment methodology, response surface design was used to observe parameter interactions and establish a meta model for obtaining optimum process conditions. Further, to enhance the accuracy of analysis of the coating performance, the light wavelength was divided into visible and IR wavelength regions. In addition, the average and standard deviation values of transmittance were determined by a statistical correlation. An improvement of approximately 5% of the transmittance was observed in comparison to that of an uncoated (bare) substrate. The optimum conditions of process parameters for the AR coating process were determined through the established meta model and guidelines for performing the AR slot-die coating process were suggested.     

基于HYSYS的催化重整流程模拟及其应用

选取催化重整18集总31反应集总动力学模型,以流程模拟软件HYSYS为工具,建立了催化重整过程稳态模型。将模型参数估计问题转化为优化问题,在MATLAB中使用ActiveX技术调用HYSYS模型,利用Marquardt算法对模型进行参数估计,并利用工业数据对模型进行了验证。基于HYSYS稳态模型对催化重整过程进行了灵敏度分析,得出操作参数、进料性质和产品指标之间的关系,仿真结果与理论分析一致,从而能够对催化重整过程的监控和优化提供指导。     

基于行列式比的阶次和参数同步递推辨识算法

针对输出误差模型,结合辅助模型的思想对原有阶次辨识和参数估计的方法进行融合和扩展,推导出基于辅助模型的行列式比定阶法,同时得出模型的阶次和参数,不仅减少了辨识过程的计算量,也节约了辨识时间。考虑到原有行列式比定阶法可能存在的不准确性,提出了一种系统模型的确认方法,增强了阶次辨识能力。仿真实验也充分表明,对行列式比定阶法的扩展不仅可以准确地辨识出系统的阶次,得出的参数估计值也有较高的精度。     

Estimation technique for non-stationary parameters with application to disposal of inventories subject to obsolescence

In this paper we develop a parameter estimation procedure for a stochastic process when that process is non-stationary. Although the estimation procedure itself is very general, we derive the model for the particular case of a Poisson process with parameter µ(t) subject to exponential decay. We then illustrate the application of this particular model to a fundamental problem in the management of inventories subject to obsolescence, i.e. how to identify excess inventories in sufficient time to ensure that stocks are cleared before the end of the season.     

Implementation of regularization for separable nonlinear least squares problems

This paper considers a class of separable nonlinear least squares problems in which a model can be represented as a linear combination of nonlinear functions. A regularized nonlinear parameter optimization approach is presented for coping with the potential ill-conditioned problem of parameter divergence. Together with a regularization parameter detection technique, Tikhonov regularization and truncated singular value decomposition are utilized in the estimation of the linear parameters if the nonlinear parameters are changed during the parameter optimization process, which centers on a nonlinear parameter search using the Levenberg-Marquardt algorithm. Benefiting from the regularization in parameter optimization, the potential ill-conditioned issue can be avoided, and the multi-step-ahead forecasting accuracy of the estimated model may be largely improved. The usefulness of this approach is illustrated by means of a chaotic time-series prediction and nonlinear industrial process modeling.     

General frameworks for optimization of plastic injection molding process parameters

Plastic injection molding is widely used for manufacturing a variety of parts. Molding conditions or process parameters play a decisive role that affects the quality and productivity of plastic products. This work reviews the state-of-the-art of the process parameter optimization for plastic injection molding. The characteristics, advantages, disadvantages, and scope of application of all of the common optimization approaches such as response surface model, Kriging model, artificial neural network, genetic algorithms, and hybrid approaches are addressed. In addition, two general frameworks for simulation-based optimization of injection molding process parameter, including direct optimization and metamodeling optimization, are proposed as recommended paradigms. Two case studies are illustrated in order to demonstrate the implementation of the suggested frameworks and to compare among these optimization methods. This work is intended as a contribution to facilitate the optimization of plastic injection molding process parameter.     

一种新型的过程模型参数辨识方法

针对模型参数辨识问题,提出了一种基于菌群优化（BSFO）算法的模型参数辨识方法。通过将辨识参数设置为群体细菌在参数空闸的位置,并模拟细菌群体觅食的动态行为来实现对参数的寻优,有效地提高了参数辨识的精腰和效率。对火电厂热工过程参数辨识的仿真研究验证了本文算法的有效性,结果表明,菌群优化算法能够实现对过程模型参数的有效辨识,仿真结果令人满意。     

Multi-attribute decision making for green electrical discharge machining

This paper aims to develop a combination of Taguchi and fuzzy TOPSIS methods to solve multi-response parameter optimization problems in green manufacturing. Electrical Discharge Machining (EDM), a commonly used non-traditional manufacturing process was considered in this study. A decision making model for the selection of process parameters in order to achieve green EDM was developed. An experimental investigation was carried out based on Taguchi L9 orthogonal array to analyze the sensitivity of green manufacturing attributes to the variations in process parameters such as peak current, pulse duration, dielectric level and flushing pressure. Weighing factors for the output responses were determined using triangular fuzzy numbers and the most desirable factor level combinations were selected based on TOPSIS technique. The model developed in this study can be used as a systematic framework for parameter optimization in environmentally conscious manufacturing processes.     

Use of multiple models and qualitative knowledge for on-line moving horizon disturbance estimation and fault diagnosis

An integrated fault detection, fault isolation, and parameter estimation technique is presented in this paper. Process model parameters are treated as disturbances that dynamically affect the process outputs. A moving horizon estimation technique minimizes the error between process and model measurements over a finite horizon by calculating model parameter values across the estimation horizon. To implement qualitative process knowledge, this minimization is constrained such that only a limited number of different faults (parameters) may change during a specific horizon window. Multiple linear models are used to capture nonlinear process characteristics such as asymmetric response, variable dynamics, and changing gains. Problems of solution multiplicity and computational time are addressed. Results from a nonlinear chemical reactor simulation are presented.