Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Filters

2004 - 20102

Settings

Subject: search.filters.subject.Intelligent agents

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A distributed shop floor control system based on the principles of heterarchical control and multi agent paradigm : a dissertation presented in partial fulfilment of the requirements for a PhD degree in Production Technology - Computer Integrated Manufacturing (CIM) Systems at Massey University
    (Massey University, 2004) Colak, Goran D
    In progressive firms, major efforts are underway to reduce the time to design, manufacture, and deliver products. The programs have a variety of objectives, from reducing lead-time to increasing product quality. The process of improvement starts with customer requirements, which in turn lead to customer-driven manufacturing, incorporating customer requirements more directly into the manufacturing processes. Forecasting customer requirements has not become any easier, in fact, just the contrary. The implication is clear: that if demands cannot be forecast, the manufacturing function must be designed to respond to these demands. To do this rapidly, more and more of the manufacturing decisions are being delegated to the factory floor. To paraphrase; the customer is saying what is to be made, the due date is now, and the work force is figuring out how to do it online. As the manufacturing world moves toward the "zero everything" vision of the future (zero inventory, zero set-up time, zero defects, zero waste), fundamental changes will take place in the factory. These changes will necessitate changes in manufacturing planning and control systems and particularly changes in planning and control on the shop floor level. This dissertation addresses the possible direction that some of these changes might take on the shop floor. The starting preamble of this research is that forecasting in certain type of manufacturing systems is not possible. An example might be systems in which product orders arrive randomly, such as manufacturing facilities involved in production of replacement spare parts). Additionally, in many other manufacturing systems, forecasting generates results that are of a very low level of certainty. In many occasions they are practically useless, since they are applicable only for short time horizons. As an example, small-quantity batch manufacturing systems usually operate under conditions where frequent disturbances make this production unstable at all times. Therefore, addressing these systems, the main idea embodied in this dissertation could be expressed as follows: "Instead of focusing efforts on how to improve the old, or develop new methods for controlling material flows in manufacturing systems, methods that are solely based on the main premise of predicting the future circumstances, this research takes another course. It considers an alternative approach - developing of manufacturing control mechanisms that are "more reactive" to the changes in the systems and "less dependant on prediction" of future events. It is believed that the modern job shop manufacturing facilities, such as mentioned above, can further increase their competitiveness by adopting approaches for shop floor control systems that are discussed in this research study. This is because the proposed system is capable, both dynamically and in real time, of promptly responding to frequent changes in production conditions, always attempting to find the best possible solution for given circumstances.
  • Thumbnail Image
    Item
    Intelligent driver agent model for autonomous navigation in a computer simulated vehicular traffic network : a thesis presented in total fulfillment of the requirements for the degree of Master of Science in Computer Science at Massey University, Albany (Auckland), New Zealand
    (Massey University, 2010) Kotushevski, Gligor; Kotusheveski, Gligor
    The purpose of this study was to investigate the possibilities of automating vehicular traffic and decrease traffic congestion by developing an intelligent driver agent model that autonomously navigates through a computer simulated traffic network. The aim was to examine various path nding algorithms and cost evaluation functions through di erent traffic conditions so that a basic intelligent driver agent model is designed using the best combination of algorithms and cost functions found. A computer simulation of vehicular traffic has been implemented to study different agent models. The intelligent driver agents developed act as independent entities with their own emergent properties and individual behaviours. Each simulated vehicle was navigated through the traffic network to its destination using a user defined algorithm and cost function. The case studies conducted focused on measuring the travel times of each driver agent from the starting to the destination point. The results indicated that the agents traveled at higher average speeds under low density traffic conditions, while lowering their average speed as the traffic density increased. It was also discovered that hybrid cost evaluation functions (designed by combining two or more basic cost functions) perform better in low and medium density traffic, while basic cost functions perform better under high density traffic conditions. Finally, the results revealed that Dijkstra pathfinding using a hybrid combination of time and length cost functions should be used under low and medium density traffic conditions and D* pathfinding using congestion cost evaluation function under high density traffic conditions. The conclusion was that the intelligent driver agent model implemented is suitable to be used as a navigation model for self-driving vehicles in traffic simulation software, but also given the right technology and social acceptance it is suitable to be implemented as a navigation model for robot vehicles and deployed in real world traffic situations.