Attribute Selection for Neural Network-Based Adaptive Scheduling Systems in Flexible Manufacturing Systems

System attribute selection is an integral part of adaptive scheduling systems. Owing to the existence of irrelevant and redundant attributes in manufacturing systems, by selecting the important attributes, better performance or accuracy in prediction can be expected in scheduling knowledge bases. In this study, we first propose an attribute selection algorithm based on the weights of neural networks to measure the importance of system attributes in a neural network-based adaptive scheduling (NNAS) system. Next, the NNAS system is combined with the attribute selection algorithm to build scheduling knowledge bases. This hybrid approach is called an attribute selection neural network-based adaptive scheduling (ASNNAS) system. The experimental results show that the proposed ASNNAS system works very well, when measured by a variety of performance criteria, as opposed to the traditional NNAS system and a single dispatching strategy. Furthermore, the scheduling knowledge bases in the ASNNAS system can provide a stronger generalisation ability compared with NNAS systems under various performance criteria. ID="A1" Correspondence and offprint requests to: Dr C.-T. Su, Department of Industrial Engineering and Management, National Chiao Tung University, 1001 Ta Hsueh Road, Hsin-Chu, Taiwan. E-mail: ctsu@cc.nctu.edu.tw     

Hybrid evolutionary algorithm with marriage of genetic algorithm and extremal optimization for production scheduling

This paper presents a hybrid evolutionary algorithm with marriage of genetic algorithm (GA) and extremal optimization (EO) for solving a class of production scheduling problems in manufacturing. The scheduling problem, which is derived from hot rolling production in steel industry, is characterized by two major requirements: (i) selecting a subset of orders from manufacturing orders to be processed; (ii) determining the optimal production sequence under multiple constraints, such as sequence-dependant transition costs, non-execution penalties, earliness/tardiness (E/T) penalties, etc. A combinatorial optimization model is proposed to formulate it mathematically. For its NP-hard complexity, an effective hybrid evolutionary algorithm is developed to solve the scheduling problem through combining the population-based search capacity of GA and the fine-grained local search efficacy of EO. The experimental results with production scale data demonstrate that the proposed hybrid evolutionary algorithm can provide superior performances in scheduling quality and computation efficiency.     

SIMATIC PCS7系统在热电厂循环硫化床锅炉中的应用

SIMATIC PCS 7是一种面向所有工业领域的集成且质量一致的自动化解决方案,无论过程、生产或混合型工业以及制造或过程控制生产均涵盖在内。SIEMENS公司的SIMATIC PCS7作为一种优秀的全集成自动化过程控制系统,广泛地用在钢铁、化工、电站行业,本文重点介绍了西门子公司的SIMATIC PCS7系统在热电厂循环硫化床锅炉中的应用,论述了该系统的组成及其特点,并通过实际的运行情况说明该系统确实具有相当高的可靠性和安全性。     

Dispatching of overhead hoist vehicles in a fab intrabay using a multimission-oriented controller

The semiconductor manufacturing system has become one of the most important manufacturing systems in recent years. Intrabay automation for wafer transport is in high demand in a 300 mm foundry fab. The control of the transport system plays an important roles in manufacturing efficiency and the satisfaction of production strategy. In general, efficiency is the most important issue that has appeared in most research of automated transport systems. However, how to dynamically adjust the transport policy to meet the production strategy and to increase the transport efficiency as well seems to be more crucial to modern semiconductor manufacturing systems. In this paper, a fuzzy-logic-based multimission-oriented overhead vehicle dispatcher is developed. The vehicle dispatching rule is assigned in real-time according to the statistics of the manufacturing performance. In this manner, the dispatching rules can be adjusted according to possible high-risk lots so that most of the production strategies can be satisfied. If all of the lots meet the prescribed production strategies, then the nearest-job-first rule can be used to offer higher transport efficiency. In addition, the proposed vehicle dispatcher is also capable of deadlock-free operation, collision avoidance, and blockage prevention. Finally, this paper uses AutoMod simulation software to construct and evaluate the manufacturing models. By evaluating the simulation results, the proposed intelligent multimission-oriented vehicle dispatcher performs better performance than the others, and all of the production strategies are satisfied .     

Dispatching and Conflict-Free Routing of Automated Guided Vehicles: An Exact Approach

This article presents an exact solution approach for the problem of the simultaneous dispatching and conflict-free routing of automated guided vehicles. The vehicles carry out material handling tasks in a flexible manufacturing system (FMS). The objective is to minimize the costs related to the production delays. The approach is based on a set partitioning formulation. The proposed model is solved to optimality by a column generation method, which is embedded in a branch-and-cut exploration tree. The proposed model and solution methodology are tested on several scenarios with up to four vehicles in the manufacturing system. The results show that most of these scenarios can be solved to optimality in less than three minutes of computational time.     

An adaptive approach to dynamic scheduling in knowledgeable manufacturing cell

To overcome deficiency in the global capacity of a single dispatching rule, it is vital to select a dispatching rule in real time for dynamic scheduling. Among the studies addressing the method for selecting dispatching rules, few have no requirements for domain knowledge or accurate training example, which is hard to acquire from the real production system. In this paper, a new learning algorithm, along with the presentation of an adaptive scheduling control policy, is proposed to obtain the dynamic scheduling knowledge effectively, and different dispatching rules are selected to schedule the jobs in the machine buffer according to the current transient state of the system. Case studies are given to illustrate the validity of the scheduling control policy.     

Linking manufacturing strategy to the design of a customized hybrid production control system

In recent years, increasing attention has been paid to manufacturing strategy. Considerable work has been done in defining market-driven competitive priorities as part of manufacturing strategy and linking them to ‘structural’ decision areas. Linkage to ‘infrastructural’ decision areas like Production Control Systems (PCS) is found to be inadequately researched. This paper presents a three-staged approach which links manufacturing strategy to PCS. First, the PCS environment is described using three dimensions of: competitive priorities, product complexity and process complexity. The environment defined in the first stage is then used to select the appropriate level of multi-level ‘decision variables’ which fully define a PCS in Stage 2. In the third stage, the set of selected levels for each of the decision variables, which form the guidelines for detailed PCS design, are then integrated into a hybrid PCS customised to the manufacturing strategy of the firm. This approach to PCS design was then tested at several firms and was found to be useful for identifying the inconsistencies between existing PCS and the manufacturing environment and strategy.     

Knowledge-based workcell attribute oriented dynamic schedulers for flexible manufacturing systems

The economy of production in flexible manufacturing systems (FMS) depends mainly on how effectively the production is planned and how the resources are used. This requires efficient and dynamic factory scheduling and control procedures. This paper addresses two knowledge-based scheduling schemes (work cell attribute oriented dynamic schedulers WCAODSs) to control the flow of parts efficiently in real-time for FMS in which the part-mix varies continually with the planning horizon. The present work employs a hybrid optimisation approach in the generalised A1 framework. A genetic algorithm that provides an optimal combination of a set of priority dispatching rules, one for each work cell WC (WCwisepdr set), for each of the problem instances characterised by their WC attributes, is used for generating examples. The WC attributes reflect the information about the operating environment of each individual WC. Two inductive learning algorithms are employed to learn the examples, and scheduling rules are formulated as a knowledge base. The learning algorithms employed are: the Genetic CID3 (Continuous Interactive Dichotomister3 algorithm extended with genetic program for weight optimisation) and the Classification Decision Tree algorithm. The knowledge base obtained through the above learning schemes generates robust and effective schedules intelligently with respect to the part-mix changes in real-time, for makespan criteria. The comparison made with a GA-based scheduling methodology shows that WCAODSs provide solutions closer to the optimum.     

Design and analysis of a rule-based knowledge system supporting intelligent dispatching and its application in the TFT-LCD industry

As flexibility and agility become key success factors of a competitive manufacturing enterprise, the ability to support the short term decision making of manufacturing planning, scheduling, and dispatching becomes a critical issue. This research presents a rule-based knowledge system run on the Java Expert System Shell (JESS) platform to addresses how engineering knowledge can be dynamically represented and efficiently utilized in job dispatching. The knowledge system, called Intelligent Dispatching Decision Support System (IDDSS), is designed and implemented using the rule-based inference and reasoning approach. The distinctive technical contributions of IDDSS focus on three critically integrated elements: (1) a visualized rule editor, (2) a knowledge object data gateway, and (3) an embedded application component. Furthermore, a case study of the thin-film transistor liquid-crystal display (TFT-LCD) panel repair line is applied to demonstrate the rule-based knowledge system for agile TFT-LCD repair job dispatching.     

A mixed dispatching rule approach in FMS scheduling

Short-term scheduling in flexible manufacturing systems (FMSs) is a difficult problem because of the complexities and dynamic behavior of FMSs. To solve this problem, a dispatching rule approach is widely used. In this approach, however, a single dispatching rule is usually assigned for all machines in a system during a given scheduling interval. In this paper, a mixed dispatching rule which can assign a different dispatching rule for each machine is proposed. A search algorithm which selects an appropriate mixed dispatching rule using predictions based on discrete event simulation is developed for this approach. The search algorithm for the mixed dispatching rule is described in detail. The effectiveness (in meeting performance criteria) of the mixed dispatching rule and the efficiency of the search algorithm relative to exhaustive search (complete enumeration) is demonstrated on an FMS model. The mixed dispatching rule approach performs up to 15.9% better than the conventional approach, and is 4% better on average. The statistical significance of the results is dicussed.     

基于混合推理的高速切削数据库系统的建立

高速切削包含大量相互作用的参量,详细地讨论了这些参量之间的相互关系和作用,并对工程中常用的智能方法进行了分析比较。在此基础上,提出了基于规则和实例混和推理建立高速切削数据库系统。在该系统中,实例推理起主要作用,当实例库中没有积累相关数据时,采用规则推理求解。根据各属性的特点和高速切削加工知识,确定了实例属性局部相似度的计算方法和各属性整体相似度的权值。为了快速查找实例,采用全部属性值索引和单个属性值索引两种索引方式,并采用规则推理来补充和验证实例推理的结果。规则和实例混合推理的采用,使系统的数据采集和知识更新简单易行。     

物与信息混合驱动的带返修生产系统性能分析

聚焦物与信息两流混合驱动的含返修闭环异步串联生产系统,在综合考虑加工设备和信息控制设备随机故障的基础上研究了生产和信息控制参数对复杂生产系统稳态性能的影响。基于工件加工与信息的交互作用关系,采用重叠分解法将该系统拆分成多个混合驱动的装配和拆卸子系统。建立了前向和反向递归迭代算法来估计系统稳态生产率。数值实验与工业缝纫机数字化生产线案例验证了迭代算法在识别系统瓶颈和估算系统稳态性能等方面的有效性。     

Intelligent sensory decision-making for error identification in autonomous robotic systems

Successful automatic assembly of complex artefacts requires the robotic system to have the capability of detecting, identifying and recovering from various errors. Efficient error identification process is essential to ensure fast recovery and minimum loss of production time. It is not cost-effective to interrogate every sensor for every pass through the assembly process. This paper presents a machine-learning approach to identify error. The basic idea is to construct a decision tree based on some sensor and error attributes in the knowledge base.     

基于分层实例推理的混合型行业工艺设计系统研究

混合流程型生产行业的生产周期长、工艺过程复杂多变,工艺设计知识的提取和表达比较困难,若采用传统的单一大型实例推理系统表示其工艺设计方案,将造成实例库的庞大和冗余,求解效率低下。针对该问题,提出了基于分层实例推理的混合型行业的工艺设计策略。通过设计问题的逐步分解以及不同层次的多实例重用,既充分利用了实例推理方法的优点,又降低了搜索空间,提高了实例检索效率;研究了不同层次下工艺实例的知识表达、实例库的组织结构,以及实例的分层检索匹配算法,并以某钢铁产品订单的工艺设计问题为例加以说明;最后,给出了基于分层实例推理的混合型生产行业的智能工艺设计系统的总体框架,并总结了该方案的优点。     

Information-Based Dynamic Manufacturing System Scheduling

Information about the state of the system is of paramount importance in determining the dynamics underlying manufacturing systems. In this paper, we present an adaptive scheduling policy for dynamic manufacturing system scheduling using information obtained from snapshots of the system at various points in time. Specifically, the framework presented allows for information-based dynamic scheduling where information collected about the system is used to (1) adjust appropriate parameters in the system and (2) search or optimize using genetic algorithms. The main feature of this policy is that it tailors the dispatching rule to be used at a given point in time to the prevailing state of the system. Experimental studies indicate the superiority of the suggested approach over the alternative approach involving the repeated application of a single dispatching rule for randomly generated test problems as well as a real system. In pa ticular, its relative performance improves further when there are frequent disruptions and when disruptions are caused by the introduction of tight due date jobs and machine breakdown—two of the most common sources of disruption in most manufacturing systems. From an operational perspective, the most important characteristics of the pattern-directed scheduling approach are its ability to incorporate the idiosyncratic characteristics of the given system into the dispatching rule selection process and its ability to refine itself incrementally on a continual basis by taking new system parameters into account.     

Impact of operation flexibility and dispatching rules on the performance of a flexible manufacturing system

Operation flexibility is one of the eight common types of flexibility that exist in flexible manufacturing systems. Dispatching rules are commonly used in loading the machines. This paper studies the effects of different levels of operation flexibility and various dispatching rules on the performance of a flexible manufacturing system. The system performance considered is mean flow time. Simulation results indicate that the mean flow time cannot be always improved by increasing the level of operation flexibility. Altering the dispatching rules seems to have a more significant effect on the mean flow time performance than changing the level of operation flexibility.     

Workflow balancing in parallel machines through genetic algorithm

Workflow balancing helps to remove the bottlenecks present in a manufacturing system. A genetic algorithm (GA) is used to solve the parallel machine scheduling problem of the manufacturing system with the objective of workflow balancing. The performance of GA is compared with three workflow balancing strategies namely random (RANDOM), shortest processing time (SPT) and longest processing time (LPT). The relative percentage of imbalance (RPI) is adopted among parallel machines for evaluating the performance of these heuristics. The GA shows better performance for the combination of various job sizes and machines. A computer program has been coded on an IBM/PC compatible system in the C++ language for experimentation to a standard manufacturing system environment in operation.     

Production engineering-oriented virtual factory: a planning cell-based approach to manufacturing systems design

In the traditional process of designing a manufacturing system, a sequential approach treats each of the design steps individually, without considering the requirements of concurrent design activities. The lack of systematic and concurrent consideration of the interactive impact of design decisions leads to repeated and excessive changes in the design and process. To resolve this problem, this research develops a production engineering-oriented virtual factory – a planning cell-based manufacturing systems design approach. The manufacturing systems design process based on a planning cell is reengineered according to the concept of concurrent engineering. The process modeling of a production engineering-oriented virtual factory is proposed at generic and particular levels. An illustrative example of an engine assembly plant demonstrates the effectiveness of the new approach.     

Production engineering-oriented virtual factory: a planning cell-based approach to manufacturing systems design

In the traditional process of designing a manufacturing system, a sequential approach treats each of the design steps individually, without considering the requirements of concurrent design activities. The lack of systematic and concurrent consideration of the interactive impact of design decisions leads to repeated and excessive changes in the design and process. To resolve this problem, this research develops a production engineering-oriented virtual factory — a planning cell-based manufacturing systems design approach. The manufacturing systems design process based on a planning cell is reengineered according to the concept of concurrent engineering. The process modeling of a production engineering-oriented virtual factory is proposed at generic and particular levels. An illustrative example of an engine assembly plant demonstrates the effectiveness of the new approach.     

Production-flow-value-based job dispatching method for semiconductor manufacturing

In a wafer manufacturing system, the value added to a particular product at a station may differ significantly from that added to a different product at the same station. If an enterprise concentrates mainly on generating profits, throughput becomes a poor performance measurement for a manufacturing system. Job dispatching rules based on maximum throughput no longer guarantee maximizing profit. Hence, profitability would be a good alternative measurement. The main purpose of this study is to develop a production-flow-value-based job dispatching rule (PFV) by the theory of constraints (TOC) for wafer fabrication. This study derives a TOC cost estimation method and a profitability estimate of a WIP-wafer lot. Jobs are then prioritized based on their profitability. Thus the PFV job dispatching rule is developed. For comparison, two job dispatching rules, MCR and MBS, are also arbitrarily selected to perform simulations. The simulation results reveal that the proposed PFV maximizes the production flow value, while MCR and MBS do not.