DESIGNING PID CONTROLLERS WITH A MINIMUM IAE CRITERION BY A DIFFERENTIAL EVOLUTION ALGORITHM

Although the integral of absolute error (IAE) has long been used as a performance measure for controller evaluation, a systematic approach is still lacking for the design of optimal PID controller with the minimum IAE performance criterion. This may be ascribed to the nonsmoothness of the IAE objective function and the lack of closed-form expression for the IAE performance index. In this paper, we propose the use of a differential evolution algorithm (DEA) to design a minimum-IAE PID controller to overcome the nondifferentiability of the IAE objective function. To achieve also a specified least relative stability margin and least damping ratio, the D-partition technique is used to identify the allowable domain in the tuning parameter space. Three examples are provided to illustrate the effectiveness of the DEA.     

ARTIFICIAL NEURAL NETWORKS: PRINCIPLE AND APPLICATION TO MODEL BASED CONTROL OF DRYING SYSTEMS - A REVIEW

This paper reviews the developments in the model based control of drying systems using Artificial Neural Networks (ANNs). Survey of current research works reveals the growing interest in the application of ANN in modeling and control of non-linear, dynamic and time-variant systems. Over 115 articles published in this area are reviewed. All landmark papers are systematically classified in chronological order, in three distinct categories; namely, conventional feedback controllers, model based controllers using conventional methods and model based controllers using ANN for drying process. The principles of ANN are presented in detail. The problems and issues of the drying system and the features of various ANN models are dealt with upto-date. ANN based controllers lead to smoother controller outputs, which would increase actuator life. The paper concludes with suggestions for improving the existing modeling techniques as applied to predicting the performance characteristics of dryers. The hybridization techniques, namely, neural with fuzzy logic and genetic algorithms, presented, provide, directions for pursuing further research for the implementation of appropriate control strategies. The authors opine that the information presented here would be highly beneficial for pursuing research in modeling and control of drying process using ANN     

BP神经网络对快烧瓷质砖烧成工况辩识的研究

本文简述了ＢＰ神经网络结构与算法,利用ＢＰ神经网络对实验电炉焙烧瓷质砖的烧成工况进行了辩识实验,取得了较满意的辩识结果,并提出选择辩识参数时应选对烧成工况取关键作用的参数,以提高辩识模型的识别率。     

Efficient warpage optimization of thin shell plastic parts using response surface methodology and genetic algorithm

During the production of thin shell plastic parts by injection molding, warpage depending on the process conditions is often encountered. In this study, efficient minimization of warpage on thin shell plastic parts by integrating finite element (FE) analysis, statistical design of experiment method, response surface methodology (RSM), and genetic algorithm (GA) is investigated. A bus ceiling lamp base is considered as a thin shell plastic part example. To achieve the minimum warpage, optimum process condition parameters are determined. Mold temperature, melt temperature, packing pressure, packing time, and cooling time are considered as process condition parameters. FE analyses are conducted for a combination of process parameters organized using statistical three-level full factorial experimental design. The most important process parameters influencing warpage are determined using FE analysis results based on analysis of variance (ANOVA) method. A predictive response surface model for warpage data is created using RSM. The response surface (RS) model is interfaced with an effective GA to find the optimum process parameter values.     

The optimization of attribute selection in decision tree-based production control systems

This study develops a learning-based production control system (PCS) to support a manufacturing system to make on-line decisions that are robust in the face of various production requirements. Selecting essential system attributes (or features) based on various production requirements to construct PCS knowledge bases is a critical issue because of the existence of a large amount of shop floor information in a manufacturing system. However, a classical decision tree (DT) learning approach to construct dynamic dispatching knowledge bases does not consider the optimal subset of system attributes in the problem domain. To resolve this problem, this study develops a hybrid genetic algorithm/decision tree (GA/DT) approach for DT-based PCS. The hybrid GA/DT approach is used to simultaneously evolve an optimal subset of system attributes and determine learning parameters of the DT from a large set of candidate manufacturing system attributes according to various performance measures. For a given feature subset and learning parameters of a DT decoded by a GA, a DT was applied to evaluate the fitness in the GA process and to generate the PCS knowledge base. The results demonstrate that the proposed GA/DT-based PCS has, according to various performance criteria, a better long term system performance than those obtained with classical DT-based PCS and the heuristic individual dispatching rules, according to various performance criteria.     

MAS-based production scheduling system for manufacturing cell-based workshop

The task of production scheduling is to determine the detailed machining path, time, machine tool, etc., for every work piece, according to the production objective and constraints. It is also an important part of the manufacturing system. In this paper, the manufacturing cell-based workshop is described and its scheduling system structure is established based on MAS (multi-agent system) technology. Through the negotiation and communication of each agent, the machining path is determined and the machining sequence and start time are calculated by GA (genetics algorithm). The communication among agents uses the CORBA (common object request broker architecture) technology of the OMG (Object Management Group). The CORBA-based architecture of the communication is designed and some interfaces for the communication are listed. For the genetics algorithm, chromosome coding, fitness function, parameters selection, and the basic genetics operation including selection, crossover and aberrance, are described. The scheduling system also can deal with some abnormal conditions, such as machine tool failure and urgent tasks. Finally, two scheduling examples are given.     

Integrated and events-oriented job shop scheduling

When events such as rush orders or machine breakdown occurs during the production process in a job shop, the delivery date of order may be delayed. To solve this problem, an events-oriented job shop scheduling process is built, and a scheduling model integrated with an enterprise information system (EIS), including Enterprise Resource Planning (ERP), Product Data Management/Computer Aided Process Planning (PDM/CAPP), etc., is proposed and analyzed in detail. A genetic algorithm and a hybrid allocation-based method are used in scheduling. Lastly, an events-oriented job shop scheduling simulation system is presented.     

Hybrid approach to distribution planning reflecting a stochastic supply chain

Today’s business environment is experiencing as a period of expansion and the globalization. Therefore, a distribution plan with low cost and high customer satisfaction in supply chain management (SCM) has been widely investigated. The purpose of this study is to establish optimal distribution planning in the supply chain. In this paper, a hybrid approach involving a genetic algorithm (GA) and simulation is presented to solve this problem. The GA is employed in order to quickly generate feasible distribution sequences. Considering uncertain factors such as queuing, breakdowns and repairing time in the supply chain, the simulation is used to minimize completion time for the distribution plan. The computational results for an example of a simple supply chain are given and discussed to validate the proposed approach. We obtained a more realistic distribution plan with optimal completion time by performing the iterative hybrid GA simulation procedure which reflects the stochastic nature of supply chains.     

Determining optimal combination of genetic operators for flow shop scheduling

Genetic algorithms (GAs) have gained wide research and applications in production scheduling fields, but the efficiency and effectiveness of a GA significantly depend on its parameters and operators. In contrast to the rich research on determination of optimal and adaptive parameters, little research has been done on determining optimal combination of genetic operators. Different from the traditional way by trial and error, this paper presents a novel and systematical approach based on ordinal optimisation (OO) and optimal computing budget allocation (OCBA) technique to determine optimal combination of genetic operators for flow shop scheduling problems. Simulation results show that the proposed methodology is able to determine optimal combination of genetic operators and simultaneously to provide a good solution with reasonable performance evaluation for scheduling problem.     

Modeling of binocular vision system for 3D reconstruction with improved genetic algorithms

This paper models the binocular vision system focused on 3D reconstruction and describes an improved genetic algorithm (GA) for estimating camera system parameters. The two-camera system model that takes into account camera radial distortion includes a total of 24 parameters. The proposed improved GA is used to solve this nonlinear optimization problem with high dimension. In our improved GA, the adaptive control of camera parameter search interval and the catastrophe strategy with elitist preservation are employed. The experimental results indicate that our improved GA is effective to solve the multi-peak function optimization problem and the 3D reconstruction accuracy of the binocular vision system is promising.