In recent years, deep learning models represented by convolutional neural networks have shown incomparable advantages in image recognition and have been widely used in various fields. In the diagnosis of sucker-rod pump working conditions, due to the lack of a large-scale dynamometer card data set, the advantages of a deep convolutional neural network are not well reflected, and its application is limited. Therefore, this paper proposes an intelligent diagnosis method of the working conditions in sucker-rod pump wells based on transfer learning, which is used to solve the problem of too few samples in a dynamometer card data set. Based on the dynamometer cards measured in oilfields, image classification and preprocessing are conducted, and a dynamometer card data set including 10 typical working conditions is created. On this basis, using a trained deep convolutional neural network learning model, model training and parameter optimization are conducted, and the learned deep dynamometer card features are transferred and applied so as to realize the intelligent diagnosis of dynamometer cards. The experimental results show that transfer learning is feasible, and the performance of the deep convolutional neural network is better than that of the shallow convolutional neural network and general fully connected neural network. The deep convolutional neural network can effectively and accurately diagnose the working conditions of sucker-rod pump wells and provide an effective method to solve the problem of few samples in dynamometer card data sets.

Based on the informatization and intelligent construction of an oilfield, this paper proposes a new method for calculating inflow performance relationship in sucker rod pump wells, which solves the limitations of current IPR curve calculation method in practical application. By analyzing the forming principle of the dynamometer card, the plate of abnormal dynamometer card is created innovatively, and the recognition model of abnormal dynamometer card based on “feature recognition” is established to ensure the accuracy of the dynamometer card. By analyzing the curvature of each point on the curve of downhole pump dynamometer card, the opening and closing points of standing valve and traveling valve are determined, and the models for calculating fluid production and bottom hole flowing pressure are established to obtain the data of fluid production and bottom hole flowing pressure of sucker rod pump wells. Finally, a calculation model of inflow performance relationship fitted with the calculated fluid production and bottom hole flowing pressure data based on genetic algorithm is established to realize calculation of oil well inflow performance relationship curve. The field application and analysis results show that the inflow performance relationship curve calculated by the model in this paper fits well with the measured data points, indicating that the calculation model has high accuracy and can provide theoretical and technical support for the field. Moreover, the real-time acquisition of dynamometer cards can provide real-time data source for this method, improve the timeliness of oil well production analysis, and help to reduce the production management costs and improve the production efficiency and benefit.

Classical decline methods, such as Arps yield decline curve analysis, have advantages of simple principles and convenient applications, and they are widely used for yield decline analysis. However, for carbonate reservoirs with high initial production, rapid decline, and large production fluctuations, with most wells having no stable production period, the adaptability of traditional decline methods is inadequate. Hence, there is an urgent need to develop a new decline analysis method. Although machine learning methods based on multiple regression and deep learning have been applied to unconventional oil reservoirs in recent years, their application effects have been unsatisfactory. For example, prediction errors based on multiple regression machine learning methods are relatively large, and deep learning sample requirements and the actual conditions of reservoir management do not match. In this study, a new equal probability gene expression programming (EP-GEP) method was developed to overcome the shortcomings of the conventional Arps decline model in the production decline analysis of carbonate reservoirs. Through model validation and comparative analysis of prediction effects, it was proven that the EP-GEP model exhibited good prediction accuracy, and the average relative error was significantly smaller than those of the traditional Arps model and existing machine learning methods. The successful application of the proposed method in the production decline analysis of carbonate reservoirs is expected to provide a new decline analysis tool for field reservoir engineers.

In order to prevent collision of complex structure well, accurate measurement of the distance of adjacent wells must be required during the development of the unconventional reservoir. The precision of the traditional survey tools and scanning software is not accurate enough. Based on the electromagnetic anticollision measuring calculation method, the electromagnetic anticollision detection tool was designed and simulation experiments were carried out. The influence of different position relations between sensor and casing on magnetic field strength detected by the sensor was analyzed. When the sensor and the casing were parallel and the distance of them was 0.5 m∼3 m, the tool could calculate accurately the distance and orientation of the adjoining well. When the angle between the sensor and the casing was within 50°, the calculation result was accurate. This research result validated the accuracy of the principle of the electromagnetic anticollision tool while drilling cluster well, and it could provide theoretical support for the development of electromagnetic detection tools.

How to design an optimal wearable device for human movement recognition is vital to reliable and accurate human-machine collaboration. Previous works mainly fabricate wearable devices heuristically. Instead, this paper raises an academic question: can we design an optimization algorithm to optimize the fabrication of wearable devices such as figuring out the best sensor arrangement automatically? Specifically, this work focuses on optimizing the placement of Forcemyography (FMG) sensors for FMG armbands in the application of arm movement recognition. Firstly, based on graph theory, the armband is modeled considering sensors' signals and connectivity. Then, a Graph-based Armband Modeling Network (GAM-Net) is introduced for arm movement recognition. Afterward, the sensor placement optimization for FMG armbands is formulated and an optimization algorithm with greedy local search is proposed. To study the effectiveness of our optimization algorithm, a dataset for mechanical maintenance tasks using FMG armbands with 16 sensors is collected. Our experiments show that using only 4 sensors optimized with our algorithm can help maintain a comparable recognition accuracy to using all sensors. Finally, the optimized sensor placement result is verified from a physiological view. This work would like to shed light on the automatic fabrication of wearable devices considering downstream tasks, such as human biological signal collection and movement recognition. Our code and dataset are available at https://github.com/JerryX1110/IROS22-FMG-Sensor-Optimization