José Ricardo Pelaquim Mendes

Case-based reasoning in offshore well design

Petroleum well drilling is an expensive and risky operation. In this context, well design presents itself as a fundamental key to decrease costs and risks involved. Experience acquired by engineers is notably an important factor in good drilling design elaborations. Therefore, the loss of this knowledge may entail additional problems and costs. In this way, this work represents an initiative to model a petroleum well design case-based architecture. Tests with a prototype showed that the system built with this architecture may help in a well design and enable corporate knowledge preservation.

Development of intelligent systems for well drilling and petroleum production

Domains where knowledge representation is too complex to be described analytically and in a deterministic way is very common in the petroleum industry, particularly in the field of exploration and production. In these domains, applications of artificial intelligence techniques are very suitable, especially in cases where the preservation of corporate and technical knowledge is important. The Laboratory for Research on Artificial Intelligence Applied to Petroleum Engineering (LIAP) at Unicamp, has, during the last 10 years, dedicated research efforts to build intelligent systems in well drilling and petroleum production fields. In the following sections, recent advances in intelligent systems, under development in the research laboratory, are described.

Generalized Nakagami-m phase crossing rate

This paper provides simple, exact, new closed-form expressions for the generalized phase crossing rate of Nakagami-m fading channels. Sample numerical results obtained by simulation are presented that validate the formulations developed here. A special case of this formulation is the Rayleigh case, whose result agrees with that obtained elsewhere in the literature. In passing, several new closed-form results concerning the statistics of the envelope, its in-phase and quadrature components, phase, and their time derivatives are obtained.

Closed-form generalized power correlation coefficient of the Hoyt fading signal

Exact, closed-form and general expressions of the marginal and joint moments as well as-of the correlation coefficient of the instantaneous powers of two Hoyt (Nakagami-q) signals are derived. All provided statistics are expressed as finite sums of simple functions of the model parameters. The model allows for environments where the variances of the quadrature components of a signal are different from their counterparts of the other signal. Some numerical results illustrate the generalized power correlation coefficient provided in this work, simulations support the theoretical results, and an approximation to the envelope correlation coefficient of the Hoyt Model is proposed

Classification of Petroleum Well Drilling Operations Using Support Vector Machine (SVM)

During the petroleum well drilling operation many mechanical and hydraulic parameters are monitored by an instrumentation system installed in the rig called a mud-logging system. These sensors, distributed in the rig, monitor different operation parameters such as weight on the hook and drillstring rotation. These measurements are known as mud-logging records and allow the online following of all the drilling process with well monitoring purposes. However, in most of the cases, these data are stored without taking advantage of all their potential. On the other hand, to make use of the mud-logging data, an analysis and interpretationt is required. That is not an easy task because of the large volume of information involved. This paper presents a support vector machine (SVM) used to automatically classify the drilling operation stages through the analysis of some mud-logging parameters. In order to validate the results of SVM technique, it was compared to a classification elaborated by a Petroleum Engineering expert.

Second-order statistics for diversity-combining of non-identical correlated hoyt signals

In this paper, exact expressions for the level crossing rate (LCR) and average fade duration (AFD) for two-branch selection, equal-gain and maximal-ratio combining systems in a Hoyt fading environment are presented. The expressions apply to unbalanced, non-identical, correlated diversity channels and have been validated by specializing the general results to some particular cases whose solutions are known. In passing, the joint bidimensional envelope-phase Hoyt distribution with arbitrary fading parameters is obtained.

Artificial immune systems for classification of petroleum well drilling operations

This paper presents two approaches of Artificial Immune System for Pattern Recognition (CLONALG and Parallel AIRS2) to classify automatically the well drilling operation stages. The classification is carried out through the analysis of some mud-logging parameters. In order to validate the performance of AIS techniques, the results were compared with others classification methods: neural network, support vector machine and lazy learning.

A General Bivariate Ricean Model and Its Statistics

In this paper, an extensive and detailed investigation of the joint statistics of two narrowband signals with space-frequency separation in a Ricean fading channel is carried out. All the analysis and its results include nonstationary environments, where the parameters of the bivariate Ricean model differ from one signal to the other. A general treatment of the angles of arrival of the multipath propagation waves is also performed. A comprehensive expression for the space-frequency correlation coefficient of arbitrary orders of the envelopes is provided. Some insightful plots of this coefficient are presented and examined. The coherence distance (or time) and the coherence bandwidth are obtained and analyzed

Case-based system: indexing and retrieval with fuzzy hypercube

In some applications with case-based systems, the attributes available for indexing are better described as linguistic variables instead of receiving numerical treatment. In these applications, the concept of fuzzy hypercube can be applied to give a geometrical interpretation of similarities among cases. The paper presents an approach that uses geometrical properties of fuzzy hypercube space to make indexing and retrieval processes of cases.

A Genetic Neuro-Model Reference Adaptive Controller for Petroleum Wells Drilling Operations

Motivated by rising drilling operation costs, the oil industry has shown a trend towards real-time measurements and control. In this scenario, drilling control becomes a challenging problem for the industry, especially due to the difficulty associated to parameters modeling. One of the drill-bit performance evaluators, the rate of penetration (ROP), has been used in the literature as a drilling control parameter. However, the relationships between the operational variables affecting the ROP are complex and not easily modeled. This work presents a neuro-genetic adaptive controller to treat this problem. It is based on the auto-regressive with extra input signals model, or ARX model, to accomplish the system identification and on a genetic algorithm (GA) to provide a robust control for the ROP. Results of simulations run over a real offshore oil field data, consisted of seven wells drilled with equal diameter bits, are provided.