Search

The low flowback efficiency of fracturing fluid would severely increase water saturation in a near-fracture formation and limit gas transport capacity in the matrix of a shale gas reservoir. Formation heat treatment (FHT) is a state-of-the-art technology to prevent water blocking induced by fracturing fluid retention and accelerate gas desorption and diffusion in the matrix. A comprehensive understanding of its formation damage removal mechanisms and determination of production improvement is conducive to enhancing shale gas recovery. In this research, the FHT simulation experiment was launched to investigate the effect of FHT on gas transport capacity, the multi-field coupling model was established to determine the effective depth of FHT, and the numerical simulation model of the shale reservoir was established to analyze the feasibility of FHT. Experimental results show that the shale permeability and porosity were rising overall during the FHT, the L-1 permeability increased by 30- 40 times, the L-2 permeability increased by more than 100 times. The Langmuir pressure increased by 1.68 times and the Langmuir volume decreased by 26%, which means the methane desorption efficiency increased. Results of the simulation demonstrate that the FHT process can practically improve the effect of hydraulic fracturing and significantly increase the well production capacity. The stimulation mechanisms of the FHT include thermal stress cracking, organic matter structure changing, and aqueous phase removal. Furthermore, the special characteristics of the supercritical water such as the strong oxidation, can not be ignored, due to the FHT can assist the retained hydraulic fracturing fluid to reach the critical temperature and pressure of water and transform to the supercritical state. The FHT can not only alleviate the formation damage induced by the fracturing fluid, but also make good use of the retained fracturing fluid to enhance the permeability of a shale gas reservoir, which is an innovative method to dramatically enhance gas transport capacity in shale matrix.

In view of the problems existing in the processing of duck products, such as complicated technology, difficulties in information collection and information linkage, and lack of dedicated information collection equipment, the duck product traceability information of the Institute of Things automatic collection system was developed. Acquisition system is mainly composed of sensing terminals, bus structure, and host computer management system. Perceiving the terminal can automatically perceive the information of each link and transmit the perception information to the upper computer management system through the bus. The upper computer management system realizes the functions of storing the sensing information, intelligent analysis, and alarm prompting. The long-term operation results show that the system performance is stable and reliable; the collection of data is efficient, complete, and accurate; and the degree of automation of the system is high, which significantly improves the product quality and safety supervision capabilities of the company.

The i.i.d assumption is the corner stone of most conventional machine learning algorithms. However, reducing the bias and variance of the learning model on the i.i.d dataset may not help the model to prevent from their failure on the adversarial samples, which are intentionally generated by either the malicious users or its rival programs. This paper gives a brief introduction of machine learning and adversarial learning, discussing the research frontier of the adversarial issues noticed by both the machine learning and network security field. We argue that one key reason of the adversarial issue is that the learning algorithms may not exploit the input feature set enough, so that the attackers can focus on a small set of features to trick the model. To address this issue, we consider two important classes of classifiers. For random forest, we propose a type of random forest called Weighted Random Forest (WRF) to encourage the model to give even credits to the input features. This approach can be further improved by careful selection of a subset of trees based on the clustering analysis during the run time. For neural networks, we propose to introduce extra soft constraints based on the weight variance to the objective function, such that the model would base the classification decision on more evenly distributed feature impact. Empirical experiments show that these approaches can effectively improve the robustness of the learnt model against their baseline systems.

Wireless sensor networks (WSNs) have been pushed to the forefront in the past decade, owing to the advert of the Internet of Things. Our research suggests that the reliability and lifetime performance of a typical application in WSNs depends crucially on a set of parameters. In this paper, we implemented our experiments on the nearest closer protocol with the J-Sim simulation tool. We then analyze the closure relationships among the density, reliability and lifetime, and reveal the trade-off among them based on our analysis on the experiment results. Next, we propose five intelligent evaluation models that are applicable to such situations. Our research allows the WSN users to predict the significant evaluation parameters directly from the settings while costly simulations are no longer necessary.

In order to strengthen the scientific management of saline-alkali land and the accurate management of agricultural production, a scientific data governance platform for saline-alkali land was developed. Based on the data accumulation of big data platform, the relationship between wheat growth and meteorology was taken as the research object. Thirteen variables including atmospheric pressure, temperature, light, and precipitation were extracted from surface meteorological data for correlation analysis, and temperature, precipitation, and sunshine were selected as the characteristic variables; through discretization processing, we have finally determined the three indicators that can be categorized: accumulative temperature, sunshine hours, and temperature. Finally, the three indicators are combined with months to build a model of farming season and weather based on Apriori. The results show that when judging the farming season with the month as the index, the accuracy of the model is between 78.81 and 100%. When the temperature or accumulated temperature is taken as the index to judge the winter wheat farming time, the accuracy of the model is above 90%. This shows that accurate analysis of farming season can be achieved through big data correlation analysis, which provides technical support for the timely adoption of agricultural production.

The security of network information in the Internet of Things faces enormous challenges. The traditional security defense mechanism is passive and certain loopholes. Intrusion detection can carry out network security monitoring and take corresponding measures actively. The neural network-based intrusion detection technology has specific adaptive capabilities, which can adapt to complex network environments and provide high intrusion detection rate. For the sake of solving the problem that the farmland Internet of Things is very vulnerable to invasion, we use a neural network to construct the farmland Internet of Things intrusion detection system to detect anomalous intrusion. In this study, the temperature of the IoT acquisition system is taken as the research object. It has divided which into different time granularities for feature analysis. We provide the detection standard for the data training detection module by comparing the traditional ARIMA and neural network methods. Its results show that the information on the temperature series is abundant. In addition, the neural network can predict the temperature sequence of varying time granularities better and ensure a small prediction error. It provides the testing standard for the construction of an intrusion detection system of the Internet of Things.

Farmland's microclimate is a vital environmental factor that affects crop growth and yield formation. Based on clear perception, reliable transmission and intelligent processing of IoT concepts, a monitoring system of farmland microclimate is developed. The monitoring system consists of three layers. The perception layer integrates meteorological, soil, hydrological and other sensors to form a ground to air sensor cluster. The transport layer utilises the GPRS technology which covers the entire country for long distance and effectively transfers the collected data to the server in real time. The application layer is developed for receiving PC software and data storage. After three years of system operation, we have done statistical analysis on the length of life, the loss of data and the reliability of data. Results reveal that the system could ensure more than 80% of data integrity, and it can also secure good stability and reliability of the data.

Agroclimatological resources provide material and energy for agricultural production. This study is aimed to analyze the impact of selected climate factors change on wheat yield over the different growth period applied quantitatively method, by comparing two different time division modules of wheat growth cycle- monthly empirical-statistical multiple regression models ( From October to June of next year ) and growth stage empirical-statistical multiple regression models (Including sowing stage, seedling stage, tillering stage, overwintering period, regreening period, jointing stage, heading stage, maturity stage) analysis of relationship between agrometeorological data and growth stage records and winter wheat production in Yanzhou, Shandong Province of China. Correlation analysis(CA)was done for 35 years (from 1981 to 2015) between crop yield and corresponding weather parameters including daily mean temperature, sunshine duration, and average daily precipitation selected from 18 different meteorological factors. The results shows that the greatest impact on the winter wheat yield is the precipitation overwintering period in this area, each 1mm increase in daily mean rainfall was associated with 201.64 kg/hm2 lowered output. Moreover, the temperature and sunshine duration in heading period and maturity stage also exert significant influence on the output, every 1°C increase in daily mean temperature was associated with 199.85kg/hm2 adding output, every 1h increase in mean sunshine duration was associated with 130.68kg/hm2 reduced output. Comparing with the results of experiment which using months as step sizes and using farming as step sizes was in better agreement with the fluctuation in meteorological yield, offered a better explanation on the growth mechanism of wheat. Eventually the results indicated that 3 factors affects the yield during different growing periods of wheat in different extent and provided more specific reference to guide the agricultural production management in this area.