Integrated Dynamic Process Planning and Scheduling in Flexible Manufacturing Systems via Autonomous Agents

In this study, a new and simple alternate routing heuristics, which would be superior to the conventional routing strategies in terms of various system performance measures and easier to apply practically, was presented. Because of the high investment costs of FMSs, it is also definitely worth choosing the best operating policy and system configuration by analyzing the system model, and adapting to changes over time. In future research, the heuristic rule base will be extended to include other supplementary constraints such as dynamic tool allocation and sequence dependent setup times. For practical implementation of the proposed decision support system, additional research in the area of human interfaces could be useful to develop more user friendly system which automatically constructs simulation model of the system from the knowledge base of a production system.

Improved random selection strategy, self-adaptive crossover and mutation operators, population co-evolution algorithm are adopted in this paper to set up a new genetic algorithm(GA), guaranteeing the universality of population, the thoroughness of solution and the execution efficiency of algorithm in solving multi-process, process crossover, work-piece flow and other condition based scheduling problem of flexible manufacturing system(FMS). The problem of GA in solving FMS scheduling is summarized in this paper, reasons and countermeasures for GA's pre-maturing are studied, longitudinal and transverse comprehensive state-based correlative self-adaptive crossover and mutation operators are raised according to the analysis on GA to avoid local optimization and pre-maturity, the co-evolutionary GA is designed to solve the scheduling model for FMS, and the algorithm is validated for the scheduling of box-type parts for precise machine tools.

With the surging energy cost and environmental impacts, strategies to achieve energy-efficient production have attracted increasing concerns of the manufacturing enterprises. For the fact that most manufacturing systems operate in a dynamic and nondeterministic environment, rescheduling strategies may be beneficial as it serves for adaption of initial schedule to dynamic events. Besides that, the development of modern information technology in manufacturing practice enables the flexibility of production toward alternative process plans. However, very little research has focused on the rescheduling problem integrated with process planning for energy saving. Hence, this work undertakes this challenge by proposing rescheduling decision mechanisms in response to two typical dynamic events with alternative process plans for energy-efficient flexible job shops. More specifically, by modeling the energy consumption of the flexible manufacturing system, the problem is first formulated as a mixed-integer programming optimization model. Rescheduling mechanisms for both new job arrivals and machine tool breakdowns are then designed, based on which a rescheduling algorithm is proposed in the form of a heuristic framework. The significance of the proposed algorithm is exemplified by a comparative case study under various scenarios. Note to Practitioners—The complex process plan selection and dynamic events in flexible job shops make the energy-aware schedule decision a challenging problem. Rescheduling addresses this issue, however, most existing rescheduling algorithms assume that only one process plan is given with a predetermined process route and machine tool allocation. This reduces the effectiveness of energy-saving for such a dynamic and flexible manufacturing system. This article, for the first time, to the best of our knowledge, proposes rescheduling decision mechanisms to generate schedules that can adapt to dynamic events and are energy-efficient with process plan flexibility. It may assist decision-makers to provide more practical and applicable energy-efficient schedules for flexible job shops, particularly when dynamic variations of the production environment occurred frequently.

In this paper, existing flexible manufacturing system (FMS) scheduling procedures are classified and reviewed. First, a classification scheme is provided that is based on key factors such as the FMS type, the mode of system operation, the nature of the demands placed on the system, the scheduling environment, and the responsiveness of the system to disturbances. The choice of appropriate scheduling criteria is discussed. Differences between conventional job shops and FMSs, and the eiVects of these differences on potential scheduling procedures are provided. The classification, comparisons, and FMS scheduling reviews aim to be useful to vendors, users, and researchers. We point out specific areas which appear to have been overlooked. Future research directions are also indicated.

This paper reports on a development of feature-focused dynamic routing policy and its evaluation in a flexible manufacturing systems (FMS) simulation framework. The dynamic policy is based on an integrative methodology in which process planning system IMPlanner is integrated with FMS simulation module. IMPlanner’s rule-based system process selection system performs knowledge-intensive task of generating alternative processing options for each feature for parts in production plan. Generated alternative routings (process plan network) for each part are utilized in the FMS simulation module such that routing decision in FMS are made on periodic intervals by considering alternative processes for each feature and making decision based on the current system status and performance. The proposed framework has been evaluated in an experimental FMS simulation module, implemented in Arena, in which two performance criteria, machine utilization and WIP, were used to make routing decisions. The feature-focused approach is compared with traditional static decision-making, and its improved performance is demonstrated.

The problem of decreasing production costs through an appropriate management of available resources is fundamental in the field of industrial production. The performance of a flexible manufacturing system (FMS), not properly supported by an efficient resource management strategy, may be drastically limited, & the advantages derived from its flexibility in terms of production costs may suffer a sharp reduction. Furthermore, an FMS is composed of a large number of components, thus making the identification of a correct strategy for the management more difficult. In this paper a heuristic based genetic algorithm is proposed for generating optimized production plans in flexible manufacturing systems. The ability of the system to generate alternative plans following part-flow changes & unforeseen situations is particularly stressed (dynamic scheduling). The Key-point objective is the reduction of machine idle time obtained by an optimized evolutionary strategy needed to reach the optimal schedule in complex manufacturing systems.

A Novel Optimal Online Scheduling Scheme for Flexible Manufacturing Systems

This paper presents a knowledge-based scheduling approach based on the problem-solving techniques developed in artificial intelligence. The approach is based on three key techniques. The first is the pattern-directed inference technique to capture the dynamic nature of the scheduling environment. The second is the non-linear planning technique to coordinate manufacturing processes and resource assignments. The third technique is the A∗ search algorithm to expedite the searching procedure. It models the scheduling process by state-space transitions; the job routing is obtained through selecting a sequence of scheduling operators guided by heuristics. Keeping track of the manufacturing system by a symbolic world model, this approach is adaptive to such environmental changes as new job arrivals and machine breakdowns, suitable for making real-time scheduling decisions.

An Integrated Process Planning and Scheduling problem solved from an adaptive multi-objective perspective

PurposeA major factor to the success of flexible manufacturing systems (FMSs) is their ability to transport work pieces between different workstations. FMS have now become more advanced and material‐handling systems have become progressively more sophisticated, it is not exceptional to have automated steering of tools to workstations as well. Such system design will improve the tool‐handling capability and the system productivity while holding tool cost to a minimum. Tool cost could represent as much as 25 percent of the operating cost. The purpose of this paper is to propose a new colored Petri net (CPN)‐based approach to the design and development of a tool sharing control system that is intended to help use of the proper and minimal number of tools for a manufacturing system.Design/methodology/approachA new black token timed PN model is first developed, to reduce the complexity of the graphical representation a new CPN model is developed. The new CPN model also allows to find the optimal sequence. The optimal sequence has no effect on the work in process (WIP) but it influences the number of tools used in the system. The main input to the PN model for a manufacturing system is the process plan. Next, all the invariants and total number of possible elementary circuits are determined using the Integrated Net Analyzer (INA) software. Output from the INA software is exported to the Excel spreadsheet. The Excel spreadsheet can be designed to calculate the total number of tokens, processing time, cycle time, etc. of each elementary circuit. Subsequently, the constraints used in Lingo will be created according to critical circuit rules. Finally, linear programming (LP) technique is used to optimize the WIP and tool inventory. Lingo software is used for the LP, the constraints from the Excel sheet will be the input data to the Lingo program, and based on those constraints the Lingo will provide the optimal values for the desired parameters. The output from Lingo will be used to recalculate the cycle time of each elementary circuit in the Excel sheet. The system is then analyzed before and after the implementation of the CPN model.FindingsA new CPN model based on tool‐sharing philosophy for an FMS with N part types and M stations is proposed.Originality/valueThe paper presents a new CPN‐based approach to the design and development of a tool sharing control system, that is, intended to help use of the proper and minimal number of tools for a manufacturing system. The new CPN model also allows to find the optimal sequence. The idea is new and pure and has not been presented before using the methodology adopted in this paper.

Process planning and scheduling used to be two very separate processes. However, owing to the recognition of the intricate relationship between them, recent work has focused on integrating the two processes. The use of flexible process plans in scheduling allows more flexibility in production and thus gives substantial cost savings. It also increases the solution space of the optimisation problem and makes it more critical to have an effective optimisation algorithm than for traditional scheduling problems. This paper describes a process-planning and scheduling system that makes use of the branch and bound approach to optimise priority weighted earliness of jobs scheduled in a mould manufacturing shop. Instead of considering a flexible manufacturing system, this paper focuses on the demands of less integrated factories, which are especially typical of mould manufacturing shops. The layout of the system, the methodology of the algorithm and effectiveness of performance measures for real industrial use are discussed in the paper.

The objective of this study is to develop a neural network based decision support system for selection of appropriate dispatching rules for a real-time manufacturing system, in order to obtain the desired performance measures given by a user, at different scheduling periods. A simulation experiment is integrated with a neural network to obtain the multi-objective scheduler, where simulation is used to provide the training data. The proposed methodology is illustrated on a flexible manufacturing system (FMS) which consists of several number of machines and jobs, loading/unloading stations and automated guided vehicles (AGVs) to transport jobs from one location to another.

A scheme for the scheduling of flexible manufacturing systems (FMSs) have been developed. It integrates neural networks, parallel Monte-Carlo simulation, genetic algorithms, and machine learning. Modular neural networks are used to generate a small set of attractive plans and schedules from a larger list of such plans and schedules. Parallel Monte-Carlo simulation predicts the impact of each on the future evolution of the manufacturing system. Genetic algorithms are utilized to combine attractive alternatives into a single best decision. Induction mechanisms are used for learning and simplify the decision process for future performance. The development of a modular neural network architecture for candidate rule selection for a FMS cell is investigated. A scheduling example illustrates the scheme capabilities including speed, adaptability, and computational efficiency. >

An effective hybrid algorithm for integrated process planning and scheduling

Currently, manufacturers seek to provide customized and sustainable products, requiring flexible manufacturing systems and advanced production management to cope with customization complexity and improve environmental performance. The reconfigurable manufacturing system (RMS) is expected to provide cost-effective customization in high responsiveness. However, reconfiguration optimization to produce sustainable mass-customized products in RMS is a complex problem requiring multi-criteria decision making. It is related to three problems, process planning, scheduling, and layout optimization, which should be integrated to optimize the RMS performance. This paper aims at integrating the above three problems and developing an effective approach to solving them concurrently. It formulates a multi-objective mathematical model simultaneously optimizing process planning, job-shop scheduling, and open-field layout problem to improve RMS sustainability. The penalty for product tardiness, the total manufacturing cost, the hazardous waste, and the greenhouse gases emissions are minimized. Economic and environmental indicators are defined to modify the Pareto efficiency when searching the Pareto-optimal solutions. Exact Pareto-optimal solutions are obtained by brute-force search and compared with those of the non-environmental indicator model. NSGA-III is adopted to obtain the approximate Pareto-optimal solutions in high effectiveness and efficiency. A small numerical example is applied to validate the mathematical model and resolution methods.