Integrating process planning and control for flexible production systems

Fabian, Martin; Lennartson, Bengt; Gullander, Per; Adlemo, Anders; Andreasson, Sven Arne

doi:10.23919/ecc.1997.7082452

Cited by 12 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The design of the sequential control program for a manufacturing system, i.e the ordered sequence of actions with all of the actions of devices needed to transform the raw products into the manufactured ones, is a difficult task which is traditionally carried out by engineers by hand using modelling tools. Artificial intelligence techniques are proving to be very useful in solving this task, allowing for an error-free, fast and low cost building process of these control programs [23,26,41,42,47,50,52]. In particular, it is becoming an area of growing interest for researchers from the field of AI planning systems [4,15,37,63].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning in Hybrid Hierarchical and Partial-Order Planners for Manufacturing Domains

Fernández

Aler

Borrajo

2005

Applied Artificial Intelligence

View full text Add to dashboard Cite

The application of AI planning techniques to manufacturing systems is being widely deployed for all the tasks involved in the process, from product design to production planning and control. One of these problems is the automatic generation of control sequences for the entire manufacturing system in such a way that final plans can be directly used as the sequential control programs which drive the operation of manufacturing systems. Hybis is a hierarchical and nonlinear planner whose goal is to obtain partially ordered plans at such a level of detail that they can be used as sequential control programs for manufacturing systems. Currently, those sequential control programs are being generated by hand using modelling tools. This document describes a work whose aim is to improve the efficiency of solving problems with Hybis by using machine learning techniques. It implements a deductive learning method that is able to automatically acquire control knowledge (heuristics) by generating bounded explanations of the problem solving episodes. The learning approach builds on Hamlet, a system that learns control knowledge in the form of control rules.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning in Hybrid Hierarchical and Partial-Order Planners for Manufacturing Domains

Fernández

Aler

Borrajo

2005

Applied Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…This problem is usually approached by means of AI planning techniques and it is becoming a breakthrough research area. Perhaps the best known AI planning approach to this problem is a research area called computer-aided process planning (CAPP) (Gil 1991, Park et al 1993, Mun 4 oz-Avila and Huellen 1995, Nau et al 1995, Fabian et al 1997, Maropoulos 1995, Luger 1998 which focuses on automatically obtaining machining sequences for ® nal manufactured workpieces. This research area has been dealt with extensively in the literature covering planning techniques which range from classical planning to case-based planning or hierarchical planning, but they are only concerned with a subset of the operations that actually take place in the entire manufacturing systems.…”

Section: Introductionmentioning

confidence: 99%

Mixing expressiveness and efficiency in a manufacturing planner

Castillo¹,

Fdez-Olivares²,

González³

2001

Journal of Experimental & Theoretical Artificial Intelligen

View full text Add to dashboard Cite

Abstract. The application of arti® cial intelligence planning techniques to real world problems is a very di cult task which usually implies overcoming expressiveness and e ciency handicaps. Expressiveness in order to cope with the great amount of knowledge involved in these problems and also to obtain results directly, or almost directly, applicable in the ® eld of study. E ciency to achieve a good course through the potentially enormous search spaces and, therefore, a satisfactory response capability. This work describes Ma c h i n e , a manufacturing planning architecture which is able to obtain sequential control programs for manufacturing systems, the steps given to overcome these expressiveness and e ciency handicaps and how it is able to solve some real size problems.

show abstract

“…By modeling the possible and desired behavior of the module in a formal manner, this model can be used for generating the control code for the module itself, and also function as input to simulations and formal verifications of the manufacturing system. Modular process models result in high degree of flexibility in reconfiguration of the system and in introduction of new products (Adlemo et al 1995, Fabian et al 1997. Code generation would guarantee that the model coincides with the actual behavior.…”

Section: Module Behaviormentioning

confidence: 99%