Dongmei Yu

A hybrid particle swarm optimisation algorithm and fuzzy logic for process planning and production scheduling integration in holonic manufacturing systems

Modern manufacturing systems have to cope with dynamic changes and uncertainties such as machine breakdown, hot orders and other kinds of disturbances. Holonic manufacturing systems (HMS) provide a flexible and decentralised manufacturing environment to accommodate changes dynamically. HMS is based on the notion of holon, an autonomous, co-operative and intelligent entity which is able to collaborate with other holons to complete the tasks. HMS requires a robust coordination and collaboration mechanism to allocate available resources to achieve the production goals. In this paper, a basic integrated process planning and scheduling system, which is applicable to the holonic manufacturing systems is presented. A basic architecture of holonic manufacturing system is proposed from the viewpoint of the process planning and the scheduling systems. Here, the process planning is defined as a process to select suitable machining sequences of machining features and suitable operation sequences of machining equipments, taking into consideration the short-term and long-term capacities of machining equipments. A fuzzy inference system (FIS), in choosing alternative machines for integrated process planning and scheduling of a job shop in HMS, is presented. Instead of choosing alternative machines randomly, machines are being selected based on the machines capacity. The mean time for failure (MTF) values are input in a fuzzy inference mechanism, which outputs the machine reliability. The machine is then being penalised based on the fuzzy output. The most reliable machine will have the higher priority to be chosen. In order to overcome the problem of un-utilisation machines, sometimes faced by unreliable machine, the hybrid particle swarm optimisation (PSO) with differential evolution (DE) has been applied to balance the load for all the machines. Simulation studies show that the proposed system can be used as an effective way of choosing machines in integrated process planning and scheduling.

A hybrid algorithm based on PSO and simulated annealing and its applications for partner selection in virtual enterprise

Partner selection is a very popular problem in the research of virtual organization and supply chain management, the key step in the formation of virtual enterprise is the decision making on partner selection. In this paper, a activity network based multi-objective partner selection model is put forward. Then a new heuristic algorithm based on particle swarm optimization(PSO) and simulated annealing(SA) is proposed to solve the multi-objective problem. PSO employs a collaborative population-based search, which is inspired by the social behavior of bird flocking. It combines local search(by self experience) and global search(by neighboring experience), possessing high search efficiency. SA employs certain probability to avoid becoming trapped in a local optimum and the search process can be controlled by the cooling schedule. The hybrid algorithm combines the high speed of PSO with the powerful ability to avoid being trapped in local minimum of SA. We compare the hybrid algorithm to both the standard PSO and SA models, the simulation results show that the proposed model and algorithm are effective.

A Hybrid Particle Swarm Optimization(PSO) Algorithm Schemes for Integrated Process Planning and Production Scheduling

Process planning and production scheduling play important roles in manufacturing systems. Their roles are to ensure the availability of manufacturing resources needed to accomplish production tasks result from a demand forecast. In this paper, instead of choosing alternative machines randomly, the fuzzy inference system is being introduced for the purposes of choosing appropriate machines. Machines will be chosen based on the machines reliability characteristics. This will ensure the capability of the machine in fulfilling the production demand. In addition, based on the capability information, the load for each machine is balanced by using the particle swarm optimization (PSO). Simulation study shows that the system can be used as an alternative way of choosing machines in integrated process planning and scheduling

A Hybrid Approach Based on Artificial Neural Network and Genetic Algorithm for Job-shop Scheduling Problem

Job-shop scheduling problem (JSSP) is very common in a discrete manufacturing environment. It deals with multi-operation models, which are different from the flow shop models. There are some difficulties that make this problem difficult. Firstly, it is highly constrained problem that changes from shop to shop. Secondly, its decision mainly depends on other decision which are not isolated from other functions. It is an NP-hard problem. In this paper, we proposed a new hybrid approach, combining ANN and GA, for the job-shop scheduling. The GA is used for optimization of sequence, neural network (NN) is used for optimization of operation start times with a fixed sequence, thanks to the NNs parallel computability and the GAs searching efficiency, the computational ability of the hybrid approach is strong enough to deal with complex scheduling problems. The results indicate that the proposed algorithm can obtain satisfactory for the job-shop scheduling problem

Integration of process planning and production scheduling with particle swarm optimization (PSO) algorithm and fuzzy inference systems

Integration of process planning with scheduling by considering the manufacturing systems capacity, cost and capacity in its workshop is a critical issue. The concurrency between them can also eliminate the redundant process and optimize the entire production cycle, but most integrated process planning and scheduling methods only consider the time aspects of the alternative machines when constructing schedules. In this paper, a fuzzy inference system (FIS) in choosing alternative machines for integrated process planning and scheduling of a job shop manufacturing system is presented. Instead of choosing alternative machines randomly, machines are being selected based on the machines reliability. The mean time to failure (MTF) values is input in a fuzzy inference mechanism, which outputs the machine reliability. The machine is then being penalized based on the fuzzy output. The most reliable machine will have the higher priority to be chosen. In order to overcome the problem of un-utilization machines, sometimes faced by unreliable machine, the particle swarm optimization (PSO) have been used to balance the load for all the machines. Simulation study shows that the system can be used as an alternative way of choosing machines in integrated process planning and scheduling.

Application of A Hybrid Particle Swarm Optimization Algorithm to Dynamic Holon Reconfiguring Problem

In this paper, dynamic re-configuration and task optimization of holonic manufacturing system (HMS) model is put forward. The concept of dynamic virtual clustering is extended to the control process of a holarchy or holonic organization. A task-oriented clustering mechanism and a corresponding optimization algorithm are presented as an efficient approach to the holonic control in HMS domain. A hybrid algorithm based on PSO for holon task allocation is described to support the optimum organization of a holarchy. Convergence property of PSO is analyzed to guide the parameter selection of it. The simulation results show that the proposed model and algorithm are effective

An improved particle swarm optimization based training algorithm for neural network

The Particle Swarm Optimization (PSO) method was originally designed by Kennedy and Eberhart in 1995 and has been applied successfully to various optimization problems. The PSO idea is inspired by natural concepts such as fish schooling, bird flocking and human social relations. Backpropagation (BP) is generally used for neural network training. It is very important to choose a proper algorithm for training a neural network. In this paper, we present a modified particle swarm optimization based training algorithm for neural network. The proposed method modify the trajectories (positions and velocities) of the particle based on the best positions visited earlier by themselves and other particles, and also incorporates population diversity method to avoid premature convergence. Experimental results have demonstrated that the modified PSO is a useful tool for training neural network.

A Multiagent Genetic Particle Swarm Optimization

The efforts of this paper are proposing a multi-agent genetic particle swarm optimization algorithm (MAGPSO) by introducing the multi-agent system to the particle swarm optimization(PSO) algorithm. Through the competition and cooperation operation with its neighbors, the neighborhood random crossing operation within its neighboring area, the mutation operation, and combining the evolutionary mechanism of the PSO algorithm, every individual senses local environment unceasingly, and affects the entire agent grid gradually, so that it enhances its fitness to the environment. This algorithm can maintain the diversity of the swarm effectively, and improve the precision of optimization, and simultaneously, restrain the prematurity phenomenon efficiently. The results of testing three high dimension benchmark function and comparing with some optimization results of other methods illustrate this algorithm has higher optimization performance in the field of high dimension functions optimization.

A database realization method to product information model based on STEP

Product data exchange and interfacing between different CAD/CAM systems are very important to the development of concurrent integrated design. In this paper, an integrated STEP-based production information model for mechanical systems is presented. First, an architecture of this system is established using a three-layer architecture (application, logic and physical layers) recommended by STEP, and an information model using database implementation approach is defined using STEPs EXPRESS language. This model includes GIM (general information model), SIM (structure information model), SCM (shape construction model), PFM (physical feature model), and MIM (management information model). Then, the database implementation method to information model is analyzed thoroughly, which include how to build data dictionary, how to transfer EXPRESS entity to base table in relational database and how to access product data in database. The information model and its application can make heterogeneous CAD system integration more convenient.

An information modeling approach in conceptual design for cooperative design

Information modeling is critical to the integration of conceptual design and process planning. An information model for conceptual design is provided in this paper. Conceptual design is a key activity in early product development. It determines product functions, form, and the basic structure. Since major manufacturing cost is determined in early design, it is critical to be able to assess manufacturability and cost as early as possible in the design process. A literature review of the current status of computer-aided design (CAD) and computer-aided process planning (CAPP) software technologies, reveals the lack of interface standards to enable the integration of these systems. In order to develop interface standards, information models have to be first developed to define the interfaces. An initial information model for conceptual process planning has been developed. This model includes an activity model and an object model for manufacturing process selection, resource selection, and cost and time estimation. The activity model sets the context in which the objects are used for information sharing and exchange. The object model defines classes used in conceptual process planning. The main purpose of developing this model is to initiate the development of standard interface specifications that are necessary for design and process planning integration.