Applied Mechanics and Materials Vol. 686

Abstract: With more and more researches about improving BP algorithm, there are more improvement methods. The paper researches two improvement algorithms based on quasi-Newton method, DFP algorithm and L-BFGS algorithm. After fully analyzing the features of quasi-Newton methods, the paper improves BP neural network algorithm. And the adjustment is made for the problems in the improvement process. The paper makes empirical analysis and proves the effectiveness of BP neural network algorithm based on quasi-Newton method. The improved algorithms are compared with the traditional BP algorithm, which indicates that the improved BP algorithm is better.

Abstract: The paper design intelligent monitoring system of aquaculture based on CC2530 wireless sensor networks, combined with the actual situation, takes the tilapia as an example to analyze detailed of the process in intelligent high density culture. At the same time, the paper introduced each function module of aquaculture for the intelligent monitoring system and formulate control standard according to the aquatic products in different growth stages of demand, through the real-time monitoring of aquaculture environment, measured the standard parameter setting of parameters and the system automatically adjusts the aquaculture environment comparison. The test results show that the temperature error is in the range of 0.5°C, dissolved oxygen amount of error is in the range of 0.3mg/L, the error of pH value is within 0.3, system data transmission correct rate is more than 98%.

Abstract: The paper design hardware platform based on network node, and analyze ZigBee protocol architecture and standards of each layer; on based of ZigBee protocol stack, we design the application program of network coordinator and terminal node to realize the data acquisition; design of network system has the characteristics of low cost, small volume, test results show that the mesh topology, network support, can be rapidly deployed, temperature, humidity, light intensity information of the smooth reading environment, that can be used for domestic environmental monitoring field.

Abstract: This paper studies the management of intelligent community network at present and technology development of internet of thing at home and abroad, in-depth analyze the existing residential property management system, and design the green energy-saving software platform based on Internet of things for intelligent community, the system platform takes Microsoft Visual Studio 2010 as the development tool, taking SQL Server2008 as the database development environment. In order to meet the normal property management function demand, from the actual demand of the intelligent community management, increase the equipment management, file transfer, public security and other functions in the system. The software meet to the actual needs of the information society in the property management system, has a certain practical application prospect.

Abstract: Energy saving is the nature of the optimal balance between the optimization of performance and energy consumption. Due to the node's mobility of large-scale wireless sensor networks and the depletion of electrical energy causing the failure of communication path and network segmentation mong nodes, and because energy consumption of nodes is mainly its communication, to design the routing with energy saving, low latency, extensibility and improving the fault-tolerance is particularly important. Based on the large-scale wireless sensor networks, mainly through introducing the methods of nonlinear modeling, this paper analyzes the fine-grained mapping between the system of energy consumption and software, builds and optimizes the software model of energy consumption and energy consumption-balance model of service quality, and commits to form an effective energy saving to lay a foundation for construction of low energy consumption of wireless sensor network. Research achievement has significant theoretical and application value in public safety, disaster prevention, ecological and environmental protection, urban management, smart home, intelligent transportation, medical and health care, industrial monitoring, green agriculture and other fields.

Abstract: When senors transmit their data to the sink via multi-hop communication, the sensors closer to the sink are burdened with heavy relay traffic and tend to die early. On the contrary, if all sensors transmit datas to the sink via single-hop communication, the sensors further from the sink will die much more quickly than those closer to the sink. In this paper, we first develop an analytical model to derive the optimal cluster radius. Then we propose a mixed communication method on grid-based where the sensors can transmit data to the sink in either single-hop or multi-hop. Finally, we conduct extensive experiments and show that our method outperforms LEACH and HEED in terms of network lifetime by balancing energy consumption.

Abstract: For Wireless Sensor Networks (WSN) is responsible for sensing, collecting, processing and monitoring of environmental data, but it might be limited in resources. This paper describes in detail the compressed sensing theory, study the wireless sensor network data conventional compression and network coding method. The linear network coding scheme based on sparse random projection theory of compressed sensing. Simulation results show that this system satisfies the requirements of the reconstruction error of packets needed to reduce the number of nodes to the total number of 30%, improves the efficiency of data communications in wireless sensor network, reduce the energy consumption of the system. With other wireless sensor network data compression algorithm, the proposed algorithm has the advantages of simple realization, the compression effect is good, especially suitable for resource limited, and the accuracy requirements are not particularly stringent in wireless sensor networks.

Abstract: The production of coal mine environment is bad, very prone to various risk. In order to ensure the normal coal mining and production safety, the need for an important factor in the mine monitoring, real-time and effective such as temperature, wind speed, gas, dust, pressure and distance. Among them, the temperature acquisition and monitoring of the coal mining face and key parts of underground roadway, is to ensure that the monitoring project of the safety production in coal mine. In light of the current situation of practical work experience and mine temperature monitoring, design a kind of mine based on wireless sensor network as the core of the multi point temperature monitoring system, proved by practice, this system has many advantages such as high reliability, high precision and low energy consumption, the effective realization of the real-time and accurate temperature signal acquisition and monitoring of mine.

Abstract: IEEE802.15.4 is the communication protocol meeting the requirements of short distance and low transmission rate, and achieving the objective of low power. The technique is an emerging wireless communication standard. It is a two-way wireless communication technology with short distance, low complexity, low power consumption and low data transmission rate and low cost. The paper analyzes the features, framework,performance indicators and overall hardware platform structure of JN5121 chip which is used in JENNIC Corporation. And the paper researches the characteristics of actual products for project development.

Abstract: Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and humidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network (BP network), based on which the paper proposes introducing momentum to improve BP network.