Field development studies by neuro-simulation: an effective coupling of soft and hard computing protocols

This paper establishes the principles of a novel simulation methodology tha t effectively brings together the specific advantages of hard and soft comp uting techniques. Accordingly, the work described in this paper conjoins th e accurate and precise nature of the existing hard computing algorithmic ap proaches with the pragmatic nature of soft computing techniques. The capabi lities of the proposed approach are demonstrated by the implementation of t he process to various field development studies practised in the petroleum and natural gas industry. In structuring the proposed methodology, full adv antages of the deterministic techniques tin terms of the accurate descripti on of the physical phenomena) and the parallel processing power of the arti ficial neural network technology are taken into account to ensure the solut ion integrity and solution speed during the overall implementation of the p rocess. By applying the neuro-simulation methodology to field development p roblems, it is shown that a substantial reduction in cost, energy and time factors of the conventional simulation approach are achieved by the pragmat ic character of the artificial neural network technology. Various case stud ies involving different reservoirs with different flow dynamics in an incre asing level of complexity are examined to illustrate the implementation of the neuro-simulation guidelines as well as to highlight the power of the pr oposed methodology. (C) 2000 Elsevier Science Ltd. All rights reserved.