The interpretation of well-testing data is a key means of decision-making support for oil and gas field development. However, conventional processing methods have many problems, such as the stochastic nature of the data, feature redundancies, the randomness of the initial weights or thresholds, and fluctuations in the generalization ability with slight changes in the network parameters. These result in a poor ability to characterize data features and a low generalization ability of the interpretation models. We propose a new integrated well-testing interpretation model based on a multi-feature extraction method and deep mutual information classifiers (MFE-DMIC). This model can avoid the low model classification accuracy caused by the simple training structures, lacking of redundancy elimination, and the non-optimal classifier configuration parameters. First, we obtained the initial features according to four classical feature extraction methods. Then, we eliminated feature redundancies using a deep belief network and united the maximum information coefficient method to achieve feature purification. Finally, we calculated the interpretation results using a hybrid particle swarm optimization–support vector machine classification system. We used 572 well-testing field samples, including five working stages, for model training and testing. The results show that the MFE-DMIC model had the highest total stage classification accuracy of 98.18% as well as the least of features (nine) compared with the classical feature extraction and classification methods and their combinations. The proposed model can reduce the efforts of oil analysts and allow accurate labeling of samples to be predicted.
The low-distortion processing of well-testing geological parameters is a key way to provide decision-making support for oil and gas field development. However, the classical processing methods face many problems, such as the stochastic nature of the data, the randomness of initial parameters, poor denoising ability, and the lack of data compression and prediction mechanisms. These problems result in poor real-time predictability of oil operation status and difficulty in offline interpreting the played back data. Given these, we propose a wavelet-based Kalman smoothing method for processing uncertain oil well-testing data. First, we use correlation and reconstruction errors as analysis indicators and determine the optimal combination of decomposition scale and vanishing moments suitable for wavelet analysis of oil data. Second, we build a ground pressure measuring platform and use the pressure gauge equipped with the optimal combination parameters to complete the downhole online wavelet decomposition, filtering, Kalman prediction, and data storage. After the storage data are played back, the optimal Kalman parameters obtained by particle swarm optimization are used to complete the data smoothing for each sample. The experiments compare the signal-to-noise ratio and the root mean square error before and after using different classical processing models. In addition, robustness analysis is added. The proposed method, on the one hand, has the features of decorrelation and compressing data, which provide technical support for real-time uploading of downhole data; on the other hand, it can perform minimal variance unbiased estimates of the data, filter out the interference and noise, reduce the reconstruction error, and make the data have a high resolution and strong robustness.
The light-pen coordinate measuring machine (LPCMM for short) is portable and flexible to measure features including invisible ones in-situ. Since different styluses are needed to measure different features and even during the process of measuring a single workpiece with complicated configurations, to improve the system measurement accuracy it is beneficial to calibrate the stylus tip center position after it is mounted to the light-pen before measurement in an industrial field. A novel and simple method aiming at self-calibrating the position of the tip center based on invariable distances is presented. The distinguishing feature of the proposed method is that the center position of the tip can be calibrated by using a kinematic seat with an inverted cone hole without any external reference and auxiliary devices. Calibration is based on that the distance between the tip center and that of any LED is invariable when the light-pen is swung smoothly with its spherical tip firmly touching the fixed cone seat. To ensure the repeatability of the algorithm some error constraint parameters are given. Based on invariable distances, the tip center position in the light-pen coordinate system can be obtained. Experiment results show that the self-calibration method has the advantage of good repeatability, with standard deviations 0.027, 0.023 and 0.014 mm in U, V and W directions, respectively. Experimental results of measuring a circle and a gauge block indirectly demonstrate the accuracy of the proposed self-calibration method.
Non-uniform rational B-spline (NURBS) surface fitting from data points is wildly used in the fields of computer aided design (CAD), medical imaging, cultural relic representation and object-shape detection. Usually, the measured data acquired from coordinate measuring systems is neither gridded nor completely scattered. The distribution of this kind of data is scattered in physical space, but the data points are stored in a way consistent with the order of measurement, so it is named quasi scattered data in this paper. Therefore they can be organized into rows easily but the number of points in each row is random. In order to overcome the difficulty of surface fitting from this kind of data, a new method based on resampling is proposed. It consists of three major steps: (1) NURBS curve fitting for each row, (2) resampling on the fitted curve and (3) surface fitting from the resampled data. Iterative projection optimization scheme is applied in the first and third step to yield advisable parameterization and reduce the time cost of projection. A resampling approach based on parameters, local peaks and contour curvature is proposed to overcome the problems of nodes redundancy and high time consumption in the fitting of this kind of scattered data. Numerical experiments are conducted with both simulation and practical data, and the results show that the proposed method is fast, effective and robust. What’s more, by analyzing the fitting results acquired form data with different degrees of scatterness it can be demonstrated that the error introduced by resampling is negligible and therefore it is feasible.
A light pen coordinate measuring system (LPCMS) is a kind of vision-based portable coordinate measuring technique. It implements coordinate measurement by analyzing the image of a light pen, which has several control points and a probe. The relative positions of control points need to be determined before measurement and serve as the measuring basis in LPCMS. How to accurately calibrate the relative positions of control points is the most important issue in system calibration. In this paper, a new method of control point position calibration based on a traditional coordinate measuring machine (CMM) is proposed. A light pen is fastened to the measuring arm of a CMM and performs accurate translational movement driven by the CMM. A camera is used to capture the images of control points at different positions, and the corresponding readings of the CMM are recorded at the same time. By establishing a separate coordinate system for each control point, the relative positions of the control points can be transformed to the differences of a series of translation vectors. Experiments show that the calibration repeatability of control point positions can reach 10 μm and the standard deviation of measurement of the whole LPCMS can reach 30 μm. A CMM is used to generate accurate translation, which provides a high accuracy basis of calibration. Through certain mathematical treatment, tremendous data acquired by moving the light pen to tens of thousands of different positions can be processed in a simple way, which can reduce the influence of random error. Therefore, the proposed method provides a high-accuracy solution of control point position calibration for LPCMS.
With the development of the modern manufacturing industry, the free-form surface is widely used in various fields, and the automatic detection of a free-form surface is an important function of future intelligent three-coordinate measuring machines (CMMs). To improve the intelligence of CMMs, a new visual system is designed based on the characteristics of CMMs. A unified model of the free-form surface is proposed based on T-splines. A discretization method of the T-spline surface formula model is proposed. Under this discretization, the position and orientation of the workpiece would be recognized by point cloud registration. A high accuracy evaluation method is proposed between the measured point cloud and the T-spline surface formula. The experimental results demonstrate that the proposed method has the potential to realize the automatic detection of different free-form surfaces and improve the intelligence of CMMs.