Iman Badr

An agent-based approach for automating the disturbance handling for flexible manufacturing systems

In this paper, an agent-based approach for automating the disturbance handling in flexible manufacturing systems is proposed. This approach builds on a model that captures the environmental context of disturbances to derive their expected impact. Distributed hierarchical optimization is employed to update the generated schedule under consideration of efficiency and stability. The proposed approach has been realized and tested on a model of a real flexible manufacturing system. Test results have shown a very good potential for the proposed approach in automating disturbance handling by keeping small deviations from the original schedule and achieving high efficiency measures with good reactivity.

An agent-based approach for scheduling under consideration of the influencing factors in FMS

Production scheduling classically regards the processing units as the only constraining factor. However, scheduling for flexible manufacturing systems (FMS) involves a set of other allocation decisions like allocating jobs to transportation units. Ignoring the relevant allocation decisions has led to widening the gap between theory and practice. In this paper, an agent-based approach for a comprehensive scheduling for FMS is presented. This approach allows for generating a production schedule under consideration of the affecting resources. This is made possible by representing resources as agents. The generation of a schedule results from the goal-oriented interaction among the concerned agents. Based on the illustration of application scenarios, it is shown that this approach results in enhancing the overall performance.

Integrating transportation scheduling with production scheduling for FMS: An agent-based approach

Flexible manufacturing systems (FMS) are distinguished by their machine and routing flexibility. The existence of a large number of routing alternatives makes the integration of transportation scheduling with production ( or machine) scheduling inevitable for achieving the required scheduling objectives. Conventional integration approaches lack the support for the dynamics of real FMS. In this paper, an agent-based approach for integrated scheduling under consideration of the dynamics of the FMS is proposed. Agents representing jobs and resources cooperate at different levels of abstraction to optimize the schedule from the different perspectives. The reaction to the dynamics of the environment is automated based on a disturbance handling method. In handling disturbances, efficiency and stability are taken into consideration. Based on the illustration of an application scenario, it is shown that this approach results in enhancing the resource utilization of the entire FMS as well as improving the required short-term and long-term flexibility.

Extending an agent-based FMS scheduling approach with parallel genetic algorithms

Flexible manufacturing systems (FMS) aim at efficiently reacting to changing market needs to stand the increasing competitiveness. This imposes efficiency and flexibility requirements on FMS scheduling. Manufacturing scheduling is the process of allocating available manufacturing resources to the set of planned jobs over time. It is an optimization process by which limited manufacturing resources are to be allocated to several jobs of different products efficiently. The agent-based scheduling approach has shown the ability to fulfill the flexibility requirement. Although this approach emphasizes flexibility, it lacks the optimization support. In this paper, an agent-based scheduling approach is extended with parallel genetic algorithms (PGA) to provide the required optimization support. Test results have shown a remarkable enhancement to the optimality of the generated schedules with respect to the predefined set of manufacturing objectives. The extended approach fulfils both flexibility and efficiency requirements on manufacturing scheduling.

Integrated Scheduling for Make-to-Order Multi-factory Manufacturing: An Agent-Based Cloud-Assisted Approach

The fourth revolution currently envisioned for manufacturing is characterized by the interconnection of distributed manufacturing facilities and the provision of their services through cloud computing. Customers will be allowed to customize products in a make-to-order strategy and select among the available facilities and services. This paper addresses the integrated scheduling of customer orders for a multi-factory, make-to-order manufacturing environment. Distributed facilities are represented as autonomous agents that generate the schedule through goal-oriented negotiations. Scheduling agents are abstracted from facilities-related data, which are made available along with auxiliary scheduling tools in the cloud. In this way, the proposed scheduling provides a generic solution that generates efficient schedules flexibly.

An agent-based method for automating disturbance handling for FMS

Flexible manufacturing systems (FMS) are characterized by their highly dynamic environment, manifested in the frequent occurrence of disturbances that necessitate the continuous update of the production schedule. In practice, these disturbances are handled manually which results in low productivity and fails to utilize the high potential of automation possessed by the flexible resources on the shop floor of FMS. In this paper, we introduce an agent-based method for automating disturbance handling for FMS. The proposed method is designed to handle the different types of disturbances as machine breakdown and rush orders. A case study of a real FMS in Egypt is described and used to test the feasibility of the proposed method. Test results show a very good potential of the proposed method in automating disturbance handling while optimizing two measures, namely makespan and machine utilization and maintaining good reactivity.

Incorporating GA-Based Optimization into a Multi-Agent Architecture for FMS Scheduling

Abstract Scheduling for flexible manufacturing systems (FMS) poses the challenge of optimizing the generated schedule while exhibiting flexibility to environmental dynamics. While the agent-based paradigm has been shown to tackle the inherent complexity of the problem and exhibit the required flexibility, it hinders the global optimization due to its decentralized structure. In this paper, genetic algorithms (GA) are incorporated into an agent-based scheduling architecture to overcome this shortcoming of agents and to achieve the required combination of flexibility with efficiency. Based on GA, individual agents optimize the schedule from their local view. Through the cooperation among the individual agents, a near-optimal schedule under consideration of the different optimization objectives is attained. Test results prove that the proposed integration yields near-optimal schedules with low computational complexity.

A framework for automatic analysis of digital fundus images

The optic disc (OD), the blood vessels and the macula are the most important features in the retinal images. These features are used for automatic eye screening systems that provide an accurate and efficient tool for the early detection of many eye diseases. A method for detecting these features is presented in this paper. First, the blood vessels are detected by using the mathematical morphology. Then, based on the percentage of the brightest pixels in the OD, the temporal side is detected since it contains the brightest region in the OD. By combining the information from temporal side and blood vessels, the whole OD is segmented. Finally, the macula is extracted by using the spatial relationship with the OD. The proposed method is tested on two publicly databases DRIVE and DIARETDB1. The detection of the OD achieved a success rate of 97.5% and 95.5% for DRIVE and DIARETDB1 respectively while the macula is detected correctly with a success rate of 100% and 97.6% respectively.

Considering multi-evaluation perspectives in an agent-based FMS scheduling approach

For flexible manufacturing systems (FMS), scheduling approaches have been introduced to achieve optimized schedules while considering multiple optimization objectives. These objectives correspond mainly to the existing evaluation perspectives, namely, the system view and the customer view. The system view corresponds mainly to the maximization of resource utilization. The customer view corresponds to the minimization of jobs-makespans required for customer jobs to finish execution. These correspondent optimization objectives, in practice, are often conflicting and subject to certain constraints. In this paper, an agent-based scheduling approach for FMS is proposed. This approach takes into account both existing evaluation perspectives while generating FMS schedules. It seeks the maximization of the resource utilization and, simultaneously, the minimization of the involved jobs-makespans. Evaluation results recorded near-optimal schedules by the proposed scheduling process.

A generic simulation environment for agent-based FMS scheduling

Manufacturing scheduling is a classical optimization problem which is associated with high computational complexity causing low reactivity of conventional solutions. Scheduling for flexible manufacturing systems (FMSs) has to be performed dynamically with good reactivity and flexibility to adapt to the changing customer requirements. Agent-based scheduling is strongly advocated to tackle this challenge of combining the efficiency of the generated schedules with the flexibility of the scheduling process. The wide adoption of agent-based scheduling is hindered by the lack of simulation-based evaluation techniques. In this paper, a generic simulation environment for agent-based FMS scheduling is proposed. Details about the generation of dynamic FMS models and linking them to an agent-based scheduling framework, described in previous work, are given. By applying this generic simulation environment, the behavior of agent-based scheduling can be assessed for different shop floor control settings.