Résumé -Nouveau modèle pour l'optimisation de la conception 3D des puits -Ce travail utilise un logiciel se servant d'un algorithme génétique pour déterminer la profondeur optimale de puits directionnels et horizontaux dans un espace 3D. Nous utilisons une fonction spécifique de pénalité, la mutation, les probabilités croisées et un critère de terminaison pour obtenir le minimum global de profondeur de forage. Ce minimum est atteint aux valeurs minimales du point de démarrage, de l'angle de forage et des taux d'augmentation et de déclin de production. Les valeurs minimales de ces paramètres amoindrissent la sévérité des virages, entraînant une réduction des problèmes en opération. La conception optimisée est comparée pour deux puits à la conception conventionnelle (à base d'une méthode d'essai et d'erreur) et au logiciel WELLDES (à base d'une technique de minimisation séquentielle sans contraintes). La conception optimisée permet de réduire la longueur totale de forage des deux puits, tout en maintenant les autres paramètres opérationnels dans les contraintes imposées. Dans la conception conventionnelle et le logiciel WELLDES, quelques variables sortent de leurs limites de contrainte. Oil & Gas Science and Technology -Rev. IFP, Vol. 59 (2004) total drilling measured depth, m T dogleg severity, °/30.48 m ANG1U upper limit on inclination angle after first build section, m ANG2U upper limit on inclination angle after drop section, m ANG3U upper limit on inclination angle after second build section, m ANG1L lower limit on inclination angle after first build, m ANG2L lower limit on inclination angle after drop section, m ANG3L lower limit on inclination angle after second build section, m DKMAX upper limit on depth of kickoff point, m DKMIN lower limit on depth of kickoff point, m CASD1U upper limit on casing setting depth after first build, m CASD2U upper limit on casing setting depth after drop section, m CASD3U upper limit on casing setting depth after second build section, m CASD1L lower limit on casing setting depth after first build, m CASD2L lower limit on casing setting depth after drop section, m CASD3L lower limit on casing setting depth after second build section, m D v2 true vertical depth after at end of first hold section, m D v3 true vertical depth after at end of drop section, m AANG1U upper limit on azimuth angle at kickoff point, degrees AANG2U upper limit on azimuth angle after first build, degrees AANG3U upper limit on azimuth angle after first hold section, degrees AANG4U upper limit on azimuth angle after drop section, degrees AANG5U upper limit on azimuth angle after second hold section, degrees AANG6U upper limit on azimuth angle after second build section, degrees AANG1L lower limit on azimuth angle at kickoff point, degrees AANG2L lower limit on azimuth angle after first build, degrees AANG3L lower limit on azimuth angle after first hold section, degrees AANG4L lower limit on azimuth angle after drop section, degrees AANG5L lower limit on azimuth angle after second hold section, degrees AAN...
In recent years, knowledge-based software technology has proven itself to be a valuable tool for solving hitherto intractable problems. Developers of knowledge-based systems must ensure that the system will give its users accurate advice or correct solutions to their problems. Thus, knowledgebased systems must be debugged and validated just like any other piece of software. It has been found that one of the most important problems in developing knowledge-based systems is the lack of methods to verify and validate its KB. The aim of this article is to define a methodology and its supporting tool set that are used together in order to completely test knowledge-based systems. The suggested testing methodology couples different verification and validation activities that are collectively valuable in raising the level of system correctness 1.Introduction Knowledge-based systems (KBSs) can be defined to be "A computerized system that uses knowledge about some domain to arrive at a solution to a problem from that domain. This solution is essentially the same as that concluded by a person knowledgeable about the domain of a problem when confronted with the same problem" [Avelino & Douglas, 1993]. One fundamental characteristic of all KBSs is the clear and clean separation between the knowledge that the system is using and the program that utilize it for problem solving. The two components that compose the intelligent program are therefore, a knowledge base (KB) and an inference engine (IE). Since the inference engine is algorithmic software i.e., conventional software, software engineering testing techniques can be applied on it. Therefore, in the field of AI testing for KBSs is limited to testing of KB [Vicat, Brezillon & Nottola, 1995]. In fact, the quality of a KBSs is often adequate to the quality of the knowledge stored in the KB [Smith & Kandel, 1993]. Our suggested testing methodology focus on improving the correctness related aspects of the KB that go towards the creation of high quality KBSs.
This paper introduces a new software that uses the genetic algorithm to givethe optimum drilling depth of directional &horizontal wells in 3-D. Aspecial penalty function, mutation, crossover probabilities, and a specialaccuracy of the stopping criterion were used to get the global minimum of theproblem. The minimum drilling depth is achieved at the minimum values forkick-point, inclination, and angle build-up and drop-off rates. The minimumparameters reduce the dogleg severity, which in turn reduce the chances foroperational problems like high torque and drag. The optimized design has beencompared with the conventional design (based on trial and error method) andWELLDES program (based on Sequential Unconstraint minimization Technique) for awell drilled in the Gulf of Suez (application I) and with conventional designfor a theoretical well (Application II). Results of the comparison have beenvalidated by genetic algorithm software. The optimization model reduced thetotal drilling length of the two applications. This was achieved while allother operational parameters were kept within the limiting constraints andcasing setting depths were taken into consideration. In contrast, WELLDESprogram and conventional design have some variables within their constraintlimits and the casing setting depths are outside their consideration. Introduction Minimizing the drilling cost of the directional or the horizontal well is amajor concern of the drilling engineers. Cost is traditionally optimizedthrough improving elements of the operations like bit selection, weight androtary speed, drilling time, casing length... etc. Optimizing well trajectoryin case of 3D deviated wells directly impacts well cost since it is casinglength, cemented parts, mud volumes, drilling time...etc. Review of thepublished literature in the last two decades shows that well design dependstrongly on the designers, experience, judgment and tuition, and the resultsobtained can be not be guaranteed to be the best due to lack of strictmathematical models and corresponding optimization theories. Furthermore, repeatedly selecting and adjusting of the design parameters is time consumingand inefficient 1–3. Helmy4 proposed the first practical well-design modelbased on nonlinear optimization theory, in which the constraints such askickoff point, build up rate, drop-off rate, inclination, casing - settingdepth were involved. The building of this model was in 2D and was solved usingsequential unconstrained minimization technique. This work followed by anotherwork also in Cairo University to optimize the well trajectory in 3D, due toconsideration constrained from casing setting depth in its simulator program5.Today no body knows if some faster exact algorithm exists. Proving ordisproving this remains as a big task for new researchers. Today many peoplethink that such an algorithm does not exist and so they are looking for somealternative methods6.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.