Past research on the process of extinguishing a fire typically used a traditional linear water jet falling point model and the results ignored external factors, such as environmental conditions and the status of the fire engine, even though the water jet falling point location prediction was often associated with these parameters and showed a nonlinear relationship. This paper constructed a BP (Back Propagation) neural network model. The fire gun nozzle characteristics were included as model inputs, and the water discharge point coordinates were the model outputs; thus, the model could precisely predict the water discharge point with small error and high precision to determine an accurate firing position and allow for the timely adjustment of the spray gun. To improve the slow convergence and local optimality problems of the BP neural network (BPNN), this paper further used a genetic algorithm to optimize the BPNN (GA-BPNN). The BPNN can be used to optimize the weights in the network to train them for global optimization. A genetic algorithm was introduced into the neural network approach, and the water jet landing prediction model was further improved. The simulation results showed that the prediction accuracy of the GA-BP model was better than that of the BPNN alone. The established model can accurately predict the location of the water jet, making the prediction results more useful for firefighters.
Information security is the foundation for building trust between the Internet of Things (IoT) and its users. Due to the sharp increase of information quantity and the limitation of hardware resources, it is difficult to maintain the high performance of hardware equipment, while also enhancing information security. To solve the problem of high consumption and low flexibility of multiple cryptographic algorithms hardware implementation, we have designed the Dynamically Reconfigurable Encryption and Decryption System, which is based on Field Programmable Gate Array. Considering the functional requirements, the cryptographic algorithm reconfigurable module files stored in External Memory could be configured dynamically into the assigned on-chip Reconfigurable Partition, supported by Core Controller and the Reconfiguration Control Platform. The experiment results show that, compared with the Static Encryption and Decryption System, our design reduces the logic resources by more than 30% and completes the algorithm swapping at the configuration speed of 15,759.51 Bytes/ms. It indicates that our design could reduce logic resources consumption and improve utilization efficiency and system flexibility.
Most applications of WSN are monitoring or inspection of the phenomenon, which determined its inability of isolation but for necessity of interconnection with external network. IPv6, the kernel protocol of next generation networks, since its advantages in huge addresses, support of address's auto-configuration and mobility, research of whose implementation on remote management and configuration of WSN is of great significance. Therefore, with the research and analysis on current interconnection schemes for WSN and IPv6-based internet, in this paper, a new scheme of interconnection is proposed considering simplicity, flexibility, reliability and low power consumption, meanwhile simulation shows its greatly potential advantages, worthy of further research.
A method of pattern recognition based on correlation of intrinsic mode function (IMF) and Support Vector Machine (SVM) was proposed.Firstly, the rolling bearing vibration signal was decomposed into a finit series of IMFS by EMD. Secondly, useful IMFS which contained main fault information were chosen through correlation coefficient threshold filtering method. Finally the correlation dimensions of the main IMFS were computed and served as input characteristic parameters of SVM classifiers to classify normal state,outner and inner fault of the rolling bearing The method has been applied on pattern recognition of the NO. 6205 rolling bearing . The results show that the proposed approach can identify the working state and fault pattern for the bearing system accurately and effectively and provide a reliable way for the fault diagnosis of mechanical device in the electrical power system.
ZigBee standard is a developing low-cost, low power consumption, short-distance wireless communication standard and routing algorithm improvement plays an important part in updating the protocol. Based on the analysis of existed ZigBee routing algorithm, this paper proposes an improvement by comprehensive using of Cluster-Tree algorithm and the "piggyback" technology to increase effective load capacity of the network, and run the simulation in NS-2, verified its feasibility. Simulation results show that the improved algorithm does not affect the other properties and reduces the number of routing control packets, so the effective load capacity has been improved.
ConclusionsAiming at improving ZigBee routing algorithm, this article proposes an efficient use of the relevant parameters of Cluster-tree and relative algorithms, merging the piggyback technology commonly seen in computer network protocols, and then use NS-2 simulation platform for the validation and comparative analysis.
In order to improve the dynamical respond of the weighing system and to meet the demand of rapid weighing, a new method based on radial basis function neural network (RBFNN) is introduced in this paper. The dynamic system is described as a network and the output values of steady state are predicted by an on-line modeling before the platform has settled to the steady state. The sample weight is calculated according to weighted moving average. The experimental results proved that the neural network method in this paper can be used to effectively reduce the weighing time and to increase the accuracy simultaneously.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.