A distributed scheduling and shop floor control method

We suggest a market-like framework for scheduling and shop floor control in computer-controlled manufacturing systems where each resource agent and part agent acts like an independent profit maker. A part-resource negotiation procedure is suggested including price-based bid construction and price revising mechanism. Alternative routings for each production order are considered in scheduling and shop floor control. A simulation-based scheduling method is suggested to estimate the start time and the completion time of each task. We develop a prototype soffivare which utilizes the object-oriented concept.     

A framework for artificial intelligence applications software development

Despite the promise and prominence of artificial intelligence, successful widely-based applications have been rare. Much of previous artificial intelligence work has concentrated on the demonstration of techniques rather than the development of tools that can be used in systems design, analysis and operation. A systematic program of knowledge compilation in artificial intelligence is proposed where extensible function libraries can be used by professionals in various fields and non-programming specialists in developing artificial intelligence applications.     

Recent trends in flexible automated manufacturing

In recent years, an important change in developing and implementing manufacturing systems can be observed in all industrialized countries. Due to intense international competition and the growth of personnel costs, companies are forced to use systems with a higher level of automation. At the same time, an increasing number of product variation—caused by adapting the products to customer requirements—demand more flexibility of machine tools and manufacturing systems.Basic types of computer-controlled flexible automated manufacturing systems will be shown and characterized by their special ranges of application. A planning procedure is presented which includes selecting a suitable systems structure such as; transfer line or flexible manufacturing system or automated manufacturing cell, and for determinating every single machine tool within the system. Examples of several new computer-controlled manufacturing systems which have been planned by the above planning procedure are presented with special regard to the evaluation of the system's economic performance.Finally, some rules are given for measuring the economic performance of automated manufacturing or assembly systems including automation of the handling functions.     

Shop floor control using the tactical ratio and monitoring system

In the fall of 1979, a decision was made by a manufacturing group steering committee to develop a system of shop floor control that recognized the reality of doing business in a practical rather than a theoretical way.A system was required that was capable of handling the management of work-in-process lots—as one group executive vice-president put it—“in the trenches”.Typical problems had to be dealt with in the system, such as additions, cancellations, pull ups, push outs, customer emergencies, delivery dates, short lead times, etc.The initial approach was to investigate the many software packages available on the market. A team of three manufacturing and data processing representatives was formed to undertake the search. After months of analysis and reviews, the conclusion was reached that a commercial system was not available to deal with the myriad of problems encountered everyday in shop floor control. As a result, the decision was made to develop an in-house system.     

Petri网与优化算法结合求解FMS调度研究综述

Petri网是基于图形的强有力的建模工具,被用于柔性制造系统调度问题的研究,然而,搜索整个可达树寻找最优调度方案是一个指数倍复杂的问题,由此人们想到利用人工智能算法搜索可达树的一部分获得近优解。该方法被认为是求解调度问题的极具前途的解决方案。从上世纪90年代初期以来,人们对此作了一些卓有成效的研究,对这些研究进行归纳总结,为采用该方法求解调度优化问题的研究提供参考。     

Benchmarking flexible job-shop scheduling and control systems

Benchmarking is comparing the output of different systems for a given set of input data in order to improve the system’s performance. Faced with the lack of realistic and operational benchmarks that can be used for testing optimization methods and control systems in flexible systems, this paper proposes a benchmark system based on a real production cell. A three-step method is presented: data preparation, experimentation, and reporting. This benchmark allows the evaluation of static optimization performances using traditional operation research tools and the evaluation of control system's robustness faced with unexpected events.     

Using mega-trend-diffusion and artificial samples in small data set learning for early flexible manufacturing system scheduling knowledge

Neural networks are widely utilized to extract management knowledge from acquired data, but having enough real data is not always possible. In the early stages of dynamic flexible manufacturing system (FMS) environments, only a litter data is obtained, and this means that the scheduling knowledge is often unreliable. The purpose of this research is to utilize data expansion techniques for an obtained small data set to improve the accuracy of machine learning for FMS scheduling. This research proposes a mega-trend-diffusion technique to estimate the domain range of a small data set and produce artificial samples for training the modified backpropagation neural network (BPNN). The tool used is the Pythia software. The results of the FMS simulation model indicate that learning accuracy can be significantly improved when the proposed method is applied to a very small data set.     

Integration architecture of expert systems, neural networks, hypertext, and multimedia can provide competitive opportunities for industrial applications

This paper promotes the idea of integration of computer software technologies; such as, expert systems, neural networks, hypertext, multimedia, and graphics user interface (GUI), to an unique hybrid system that increase market opportunities and competitiveness. The goal is to present ingredients of a business strategy that can ensure the capability to provide long-term competitiveness for industrial applications. Concepts for development integration and flexibility, prototype system transferring, teaming, and other consideration for winning, evolving at The University of Tennessee Space Institute (UTSI) and the Center for Space and Applied Research (CSTAR), are presented to amplify on salient aspects of competitiveness.     

PC-based hierarchical manufacturing cell control

Robots in the industrial factory plant build the backbone for CIM, which is outlined to be the factory automation strategy of the future. In this paper a hierarchical manufacturing cell control system for robotic work cells is described. This approach is based on low-cost personal computer hardware and consists of two different control systems, one for the robot control tasks and another for the work cell control tasks. The underlying concept is based on a strategic architectural model for hierarchical manufacturing control, where it focuses on the process sequence coordination and the process control in the bottom hierarchical layers.     

A scheduling decision aid in glass fiber manufacturing

A decision aid for scheduling production in glass fiber manufacturing industry is described. The methodology combines a linear programming (LP) optimization model with a heuristic model. The LP model determines production goals; the heuristic model then uses the LP output to incorporate system-specific constraints in developing processing sequences.     

智能控制与常规控制

智能控制是在常规控制理论与技术基础上的进一步发展与提高,目的是在非结构化、不确定性与控制对象有强相互作用的环境中实现过程任务(追求目标)的闭环自动控制.虽然传统人工智能方法应用于实际控制问题有很大困难,但是把对复杂环境建模的严格数学方法研究同人工智能中新兴学派思想的研究紧密结合起来,有可能导致新的智能控制体系结构的产生和发展.这种研究将会在"自上而下"和"自下而上"两个方向的交汇处取得重大突破.     

The evolving factory of the future: Integrating manufacturing and information systems

In recent years there have been rapid developments in both manufacturing and information technologies and their systems. Advances have occured so rapidly that often the results has been “islands” of automation and information subsystems, such as CAD/CAM, robotics, group technology, and office automation. Some recent developments, however, provide capabilities for integrating these “islands” into systems which both improve manufacturing productivity and produce more meaningful management information. Integrated systems seem imminent. Suggestions that could help ensure a smooth evolution toward these systems are made and some conclusions are drawn.     

The use of simulation for gross planning, scheduling, standards, and tracking

Simulation can be much more than just a tool for testing a proposed facility or examining new operating methods. Using the ideas and methods presented herein, simulation becomes an integral part of effective day-to-day operations.     

Forming processes control by means of artificial intelligence techniques

Forming processes are manufacturing processes that use force and pressure in order to modify the shape of a material part until obtaining the final product. The wide range of non-linear factors that drive this sort of processes make them very complex and extremely difficult to be controlled. Traditional control techniques, like PID controllers, have not offered a reliable solution when global control has been pursued and the figure of the operator still remains present in most of the forming facilities. On the other hand, although operators have demonstrated to be a very successful strategy when controlling this type of processes, the actual market evolution towards the fabrication of more complex parts, made of lower formability materials at higher production rates, is decreasing their capacity of reaction when solving the daily problems. Thus, the development of new global control systems based not on traditional control techniques and mathematical models but on the control strategy that has been used successfully for many years, the control through the experience and knowledge is now even more necessary. In the present work, an intelligent control system based on one of the main techniques within the artificial intelligence, expert systems, has been developed. The main purpose of this intelligent control system is to emulate the decisions that expert operators take but in a quicker and more reliable way. The developed intelligent control system has been installed in a blanking facility and very good results have been achieved.     

Deadlock-free scheduling for flexible manufacturing systems using Petri nets and heuristic search

Deadlock-free control and scheduling are two different problems for flexible manufacturing systems (FMSs). They are significant for improving the behaviors of the systems. Based on the Petri net models of FMSs, this paper embeds deadlock control policies into heuristic search algorithm, and proposes a deadlock-free scheduling algorithm to minimize makespan for FMSs. Scheduling is performed as heuristic search in the reachability graph of the Petri net. The searching process is guided by a heuristic function based on firing count vectors of state equation for the Petri net. By using the one-step look-ahead method in the optimal deadlock control policy, the safety of a state is checked. Experimental results are provided to show effectiveness of the proposed heuristic search approach in deadlock-free scheduling for FMSs.     

Intelligent knowledge based expert inventory control system for computer integrated manufacturing

The paper discusses the framework and development of an expert inventory management system for integrative manufacturing planning. The system developed with an artificial intelligent language provides a linkage between management and computer-integrated manufacturing(CIM), has the following major elements: data base to represent a hierarchical tree using recursive objects on different levels; knowledge base containing heuristic rules; goal oriented interaction; and backtracking interface procedures. Potential benefits of the system includes: better manufacturing planning, reduced inventory levels and production lead times, and consistent inventory control records.     

What artificial experts can and cannot do

One's model of skill determines what one expects from neural network modelling and how one proposes to go about enhancing expertise. We view skill acquisition as a progression from acting on the basis of a rough theory of a domain in terms of facts and rules to being able to respond appropriately to the current situation on the basis of neuron connections changed by the results of responses to the relevant aspects of many past situations. Viewing skill acquisition in this ways suggests how one can avoid the problem currently facing AI of how to train a network to make human-like generalizations. In training a network one must progress, as the human learner does, from rules and facts to wholistic responses. As to future work, from our perspective one should not try to enhance expertise as in traditional AI by attempting to construct improved theories of a domain, but rather by improving the learner's access to the relevant aspects of a domain so as to facilitate learning from experience.     

Search strategy for scheduling flexible manufacturing systems simultaneously using admissible heuristic functions and nonadmissible heuristic functions

To scheduling flexible manufacturing system (FMS) efficiently, we propose and evaluate an improved search strategy and its application to FMS scheduling in the P-timed Petri net framework. On the execution of Petri net, the proposed method can simultaneously use admissible heuristic functions and nonadmissible heuristic functions for A^* algorithm. We also prove that the resulting combinational heuristic function is still admissible and more informed than any of its constituents. The experimental results of an example FMS and several sets of random generated problems show that the proposed search method performs better as we expected.     

Application of a continuous supervisory fuzzy control on a discrete scheduling of manufacturing systems

This paper considers the design and the practical implementation of a stable multiple objective real-time scheduling problem for a complex production system. In this paper, a complex production system is viewed as a kind of systems producing a variety of products (multiple-part-type) under constraints and multiple production objectives often conflicting. Previously, fuzzy control theory and fuzzy intervals arithmetic have been used to develop a distributed and supervised continuous-flow control architecture. In this framework, the objective of the distributed control structure is to balance the production process by adjusting the continuous production rates of the machines on the basis of the average local behavior. The supervisory control methodology aims at maintaining the overall performances within acceptable limits. In the new proposed approach, the problem of a stable real-time scheduling of jobs is considered at the shop-floor level. In this context, as the stability of the control structure is ensured, the actual dispatching times are determined from the continuous production rates through a discretization procedure. To deal with conflicts between jobs at a shared machine, a decision is made. It concerns the actual part to be processed and uses some criterions representing a measure of the job's priority. The simulation results show the validity of the proposed approach in terms of production cost, robustness and system stability.