Real-time prediction of the formation pressure gradient is critical mainly for drilling operations. It can enhance the quality of decisions taken and the economics of drilling operations. The pressure while drilling tool can be used to provide pressure data while drilling, but the tool cost and its availability limit its usage in many wells. The available models in the literature for pressure gradient prediction are based on well logging or a combination of some drilling parameters and well logging. The well-logging data are not available for all wells in all sections in most wells. The objective of this paper is to use support vector machines, functional networks, and random forest (RF) to develop three models for real-time pore pressure gradient prediction using both mechanical and hydraulic drilling parameters. The used parameters are mud flow rate (Q), standpipe pressure, rate of penetration, and rotary speed (RS). A data set of 3239 field data points was used to develop the predictive models. A different data set unseen by the model was utilized for the validation of the proposed models. The three models predicted the pore pressure gradient with a correlation coefficient (R) of 0.99 and 0.97 for training and testing, respectively. The root-mean-squared error (RMSE) ranged from 0.008 to 0.021 psi/ft for training and testing, respectively, between the predicted and the actual pore pressure data. Moreover, the average absolute percentage error (AAPE) ranged from 0.97% to 3.07% for training and testing, respectively. The RF model outperformed the other models by an R of 0.99 and RMSE of 0.01. The developed models were validated using another data set. The models predicted the pore pressure gradient for the validation data set with high accuracy (R of 0.99, RMSE around 0.01, and AAPE around 1.8%). This work shows the reliability of the developed models to predict the pressure gradient from both mechanical and hydraulic drilling parameters while drilling.

Introduction to the practice of statistics (2nd edition), by D. S. Moore and G. P. McCabe. Pp 854. £19-95. 1993. ISBN 0-7167-2250-X (Freeman)

Data-Driven Modeling Approach for Pore Pressure Gradient Prediction while Drilling from Drilling Parameters.

Rationale

The pathobiology of ventilator-associated pneumonia (VAP) in children is poorly understood; investigation has been limited by lack of universally applied diagnostic criteria and reliable biomarkers for this condition.



Objectives

We evaluated the clinical pulmonary infection score (CPIS) in diagnosing VAP and prospectively characterized the relationship between surfactant protein-D (SP-D) metabolism and VAP.



Methods

Children admitted to an Egyptian PICU requiring intubation were screened for the absence of primary pulmonary pathology. Thirty-nine children underwent two evaluations: during the first 36 hr following intubation and after 4 days of mechanical ventilation. During both, bronchoalveolar lavage fluid (BALF) was obtained for culture and SP-D assay. CPIS was computed during the second evaluation.



Results

Optimum performance of the CPIS against BALF culture occurred at a cutoff value of 6, (ROC AUC of 0.89 ± 0.05). Children who developed VAP had significantly higher SP-D levels, both preceding (129.9 ± 33.5 ng/ml at the 1st BAL)—and following positive BALF culture (249.5 ± 51.2 ng/ml at the 2nd BAL), compared to children whose BALF remained sterile (62.6 ± 18.1 ng/ml and 64.9 ± 9.4 ng/ml; P < 0.001). This increase in SP-D levels was most evident in children infected with Pseudomonas aeruginosa compared to children with Klebsiella pneumonia or S. aureus.



Conclusions

The CPIS performed well against BALF culture. We observed a bacterial species-specific difference in SP-D levels in children who developed VAP; this change preceded detection of infection by CPIS or BALF culture. Pediatr Pulmonol. 2012; 47:292–299. © 2011 Wiley Periodicals, Inc.

Evolution of surfactant protein-D levels in children with ventilator-associated pneumonia.

Formation Resistivity Prediction Using Decision Tree and Random Forest

This research addresses the problem of efficient function approximation for systems-on-a-chip. In these systems, high speed, minimal chip size, and efficient computation are necessary. Examples include computing temperature using a thermistor and evaluating trigonometric functions. For function approximation, system engineers commonly use an off-the-shelf package to generate an approximating polynomial from a set of sampled data. The floating-point coefficients are rounded to integer values that match the target architecture’s size. The induced rounding errors can actually be due to this solution space translation. To minimize or eliminate the rounding effect, the optimal coefficient set should be found using the restricted target’s integer space. This is an integer programming problem, which is NP-hard. To find the optimal coefficients, the restricted target space can be enumerated, but this takes an excessive amount of processing time. Alternatively, a heuristic such as a genetic algorithm can be used to find a feasible solution. In this research, a genetic algorithm is devised to find a set of polynomials, with integer coefficients, that in a piecewise fashion minimizes the sum-ofsquared error over a set of experimentally gathered or function sampled data. Copyright 2001 James William Hauser All Rights Reserved

background

Approximation of Nonlinear Functions for Fixed-Point and ASIC Applications Using a Genetic Algorithm

There is a range of contract types and project delivery systems (PDS) that owners can use in executing facilities. Examples include the traditional Design-Bid-Build (DBB) process, Design-Build (DB) and Construction Management-at-Risk (CM-R). A number of owners in Saudi Arabia, particularly governments, prefer some form of competitive bidding (typically the DBB method), and most of the time they insist on it. However, the use of non-traditional delivery systems is increasing, and the system variations are becoming numerous. The selection of project delivery system influences the entire life-cycle of a construction project, from concept through construction into operation and decommissioning. Owners, engineers, contractors, material suppliers and laborers are all affected by the decisions that owners make concerning project delivery systems. Owners need to assess what type of construction services procurement program is best suited to their needs. Selecting a PDS means choosing the best delivery system to carry out a particular project, which is not always an easy and clear decision. The success or failure of a project can depend on the project delivery method, and whether the method is suited to the project. There are many factors and parameters or key considerations, such as cost (budget), time (schedule), quality (level of expertise), risk assessment (responsibility) and safety which determine whether a particular style of PDS is suited to a project. A model is a representation of a real or planned system and can be used as an aid in choosing a PDS. The purpose of this research is to try to develop a project delivery system decision framework (PDSDF) by identifying the factors and parameters that have to be considered in such a model. A survey was conducted to determine the values of factors and key parameters from completed projects. The research attempts to identify patterns of project factors, owner objectives, and project parameters that could best be met by one or another PDS. This model is intended to be very easy for owners to use, while at the same time providing meaningful results that can be used in making a selection of a suitable project delivery system.A weighting factors approach and the analytic hierarchy process (AHP) was used to construct the decision framework. In this process the relative advantages of the three project delivery systems are compared according to each criterion. The relative importance of the criterion is determined on the basis of the owner's needs and project characteristics. The results of comparing the three delivery systems according to each criterion and of determining the order of importance among the criteria were integrated into a model to help the owner reach a decision about which project delivery system he should adopt.

/pdf/project-delivery-system-decision-framework-using-the-3fb7fgrh4t.pdf

Project delivery system decision framework using the weighting factors and analytic hierarchy process methods

https://www.cambridge.org/core/services/aop-cambridge-core/content/view/4B7A3E1B21C9E48FCD60A6EA5F4F7D84/S0025557200149010a.pdf/div-class-title-introduction-to-the-practice-of-statistics-2nd-edition-by-d-s-moore-and-g-p-mccabe-pp-854-19-95-1993-isbn-0-7167-2250-x-freeman-div.pdf