Search

At present, oil recovery is generally carried out by pumping unit in oilfield development. Monitoring working status of pumping unit in real time is vital to avoid inefficient production, prevent and control hidden dangers. The condition diagnosis is one of the important contents which often rely on analyzing and classifying the dynamometer card. The traditional method of dynamometer card identification is insufficient to process the huge dynamometer card data in real time. Moreover, the experience and knowledge of the onsite engineers will affect the accuracy of identification. Therefore, in this paper, Freeman chain code and differential code are adopted to extract the characteristics of the dynamometer card data of the pumping unit. Then BP neural network based diagnosis model is proposed to realize the automatic identification of the fault type of the pumping unit according to the dynamometer card. The experimental result shows that the proposed model achieves an accuracy of 94.79%, thus can be used to assist decision making in actual production.

Haze pollution is a serious weather condition which occurs frequently in mainland China. As there has been an increasing worldwide research interest around topics in environment protection and human health, PM2.5 concentration is regarded as a vital index to reflect the air quality. The current PM2.5 prediction algorithm has the problems of single index and insufficient features. In this paper, based on XGBoost, a PM2.5 prediction model is proposed. Such model adopts the random forest algorithm for feature selection. Then, the optimal feature subset that affects PM2.5 concentration is selected. The experiment is conducted on real dataset of daily air quality and weather observations in Beijing from 2017 to 2019. The results show that the daily average concentration of PM2.5 can be accurately predicted with root mean square error at 8.63, and correlation at 95.41%.

City Petrol Supply Management System(CPSMS) is very important in current society. Effective CPSMS could reduce the waiting time of user, reduce pollution gas by incomplete combustion from engine idling, decrease the air pollution and promote the service quality of petroleum enterprise. But via centralized management model of traditional CPSMS, system is not flexible to get good timeliness performance. In this paper, we propose an Autonomous Community Architecture and construction technology to solve this problem. In this architecture, each petrol station could real-timely share information with each other. It could also share information with users. So that each petrol station could make decision to cooperate with each other to construct community. Each user could select most adequate petrol station for filling service. Waiting time for petrol filling service could be decreased.

In this paper, an attribute clustering based collaborative filtering algorithm is applied for development well recommendation towards exploratory wells argumentation. The algorithm utilizes similarity characteristics of exploratory and development well related attributes, especially porosity, permeability and oil saturation, to filter redundant data by feature selection. Experiment use practical well data of the oil company for clustering. By integration of a scaled rating scheme on properties and the collaborative filtering philosophy to provide the recommend cluster. Such cluster contains the candidate development wells for recommendation. Finally, by calculating the similarity between exploratory and development wells, the scheme is able to provide the geologist the selected development wells for the decided exploratory in well argumentation.

Spam text including e-mails, SMS and etc, is a real and growing problem primarily due to the availability of digital handset and internet. To filter spam text is to be the utmost topic over varies study area. Text bodies of different forms of communication expose channel for spammers. In this study, text dataset in English and Chinese are pre-processed. Classical classifiers are applied on the pre-processed dataset to evaluate the accuracy of the same classifier. The behavior of classifiers among English and Chinese is evaluated. The paper also discussed the result of experiments. In addition, different from most existing text spam detection methods which are based on English, classifiers suited for English text classification is insufficient for Chinese text classification.

Security and efficiency of messages transmission are crucial requirements for multicast data origin authentication, especially in time-critical scenarios, such as pay-TV and the smart grid. However, how to balance such equirements is still a difficult issue. Through analysis, we find that TV-HORS is more suitable for the time-critical scenarios than RSA-based and MAC-based scheme. However, the reuse times of TV-HORS scheme is still too small to suit some scenarios. In this paper, we present a Game Model of Multicast Data Origin Authentication (GMMDOA), to describe the relationship between security and efficiency for the time-critical multicast communication, contra posing the TV-HORS scheme. By analyzing our model with Shannons information and game theory, we propose an optimization scheme for update the private key. Through the security analysis of our model, the signature valid time is negligible compared with the adversary attacking time. Thus, the security of our scheme is still secure even in the lowest risk-level parameter. We present measurement results from experiments and discuss performance comparisons. It shows that, our scheme does significantly to promote the efficiency of multicast data origin authentication.

Wireless Sensor Network is widely used in Emergency Management System to assure safety. If emergency appears, real-timely emergency information's transmission should be assured. However, if fault appears, emergency information's transmission is stopped until available route is constructed. Conventional approaches make efforts to improve fault tolerance such as retransmission based and replication based approaches. However, they could not apply to emergency situation as long interval. Thus, autonomous fault tolerance technology is proposed. Each community member will cooperate with each other to locally reconstruct community to continue transmitting. The evaluation results indicate improvement of fault tolerance performance.

In compare with the traditional Artificial Neural Network, PSO-BP neutral network has fast convergence and is immune to local minimum. This paper presents an application of PSO-BP neural network for dynamic predicting small layer reservoir parameters of fault block E1f11-1 in well ZHuang 2. By defining input and output neuron number, our method firstly realizes quantization of input neuron. Then we choose proper samples for training neural network in order to build a dynamic prediction model of reservoir parameters. Such model has been successfully tested and the model itself is appropriate for predicting unknown reservoir parameters. Testing result indicates that PSO-BP neural network is superior to the genetic algorithm optimized BP neural network and the pure neural network. Finally, PSO-BP neural network gained certain achievements for dynamically predicting reservoir parameters according as dynamic production information.