基于多源数据机器学习的区域水质预测方法研究

随着社会经济快速发展和水资源系统复杂性的日益增强,我国水环境质量的演变逐渐呈现跨区域、多因素耦合影响的特点。围绕大空间范围的水质预测问题,针对传统水质预测方法中对水文、气象及社会经济多因素考虑的不足,以广东省31个水质监测站在2008年到2016年间每周的水质等级数据为训练样本,选取降雨、蒸发和气温等气象指标以及GDP、总人口数、人口密度等社会经济指标为预测参数,运用支持向量机、决策树以及人工神经网络等机器学习技术,建立区域水质等级的预测模型。结果表明,机器学习方法可融合气象和社会经济等多源的、不同时空尺度的数据,对水质等级进行预测。其中,基于随机森林的预测模型表现性能最佳,预测准确率达到77.11%;基于支持向量机的预测模型次之,预测准确率达到74.99%。与现有的水质预测方法相比,该方法的计算速度快、不需要提取数据的统计特征、操作简单、能够分析社会经济因素对水质的影响,更容易在水环境治理中使用。

基于灰狼优化算法的机器人羽流追踪方法

针对在室内扩散环境无法获得可靠的羽流流向/流速信息的情况下,解决寻源机器人源定位效率低、成功率低的问题,提出了一种基于灰狼优化算法的机器人羽流追踪方法。该方法以气体浓度值作为个体适应度,在不搭载羽流流速/流向传感器的情况下,通过寻源机器人模拟灰狼种群的社会机制与狩猎行为进行位置更新,使寻源机器人能高效地追踪羽流并定位源位置。分别将灰狼优化算法、粒子群算法、遗传算法、Z字形搜索策略进行四组机器人羽流追踪仿真实验,基于灰狼优化算法的寻源机器人的定位成功率分别为92%、94%、94%、94%。实验结果表明,基于灰狼优化算法的寻源机器人的定位成功率分别为95%、90%、90%,验证了基于灰狼优化算法的机器人羽流追踪方法的可行性和有效性。

基于改进信息趋向方法的源搜索研究

信息趋向策略能够以稳健的方式实现对稀疏扩散源的搜索,但在搜索时间方面是次优的。为引导机器人更快速地找到源,提出了一种基于距离度量的信息趋向两步预测方法。首先引入一个距离参数,量化机器人与估计源之间的距离,弥补香农熵在方向上的信息缺失;其次将信息趋向策略预测的一步信息增益扩展到两步;最后将该方法扩展到多机器人的源搜索中。仿真结果表明,所提方法在保证搜索准确性的前提下能够将搜索平均步数减少8%~15%,且搜索性能更加稳定,表明方法的有效性。

Design of DC regulated power supply based on single chip microcomputer

A DC regulated power supply with numerical control based on single chip microcomputer （SCM） is designed. SCM is the main controller and output voltage o{ DC power supply can be set by keyboard. The analog voltage can be obtained through D/A converter （DAC0832） so that different voltages can be provided by operational amplifier. The output voltage varies from 0 V to 12 V with the incremental value of 0. 1 V. The actual output voltage is shown in the nixietube. This DC regulated power supply is characterized by simple structure and easy operation.

A Method of Identifying Electromagnetic Radiation Sources by Using Support Vector Machines

Electromagnetic Radiation Source Identification(ERSI) is a key technology that is widely used in military and radiation management and in electromagnetic interference diagnostics.The discriminative capability of machine learning methods has recently been used for facilitating ERSI.This paper presents a new approach to improve ERSI by adopting support vector machines,which are proven to be effective tools in pattern classification and regression,on the basis of the spatial distribution of electromagnetic radiation sources.Spatial information is converted from 3D cubes to 1D vectors with subscripts as inputs in order to simplify the model.The model is trained with 187 500 data sets in order to enable it to identify the types of radiation source types with an accuracy of up to 99.9%.The influence of parameters(e.g.,penalty parameter,reflection and noise from the ambient environment,and the scaling method for the input data) are discussed.The proposed method has good performance in noisy and reverberant environment.It has an identification accuracy of 82.15% when the signal-to-noise ratio is 20 dB.The proposed method has better accuracy in a noisy environment than artificial neural networks.Given that each Electromagnetic(EM) source has unique spatial characteristics,this method can be used for EM source identification and EM interference diagnostics.

Decentralized Searching of Multiple Unknown and Transient Radio Sources with Paired Robots

In this paper, we develop a decentralized algorithm to coord inate a group of mobile robots to search for unknown and transient radio sources. In addition to limited mobility and ranges of communication and sensing, the robot team has to deal with challenges from signal source anonymity, short transmission duration, and variable transmission power. We propose a two-step approach: First, we decentralize belief functions that robots use to track source locations using checkpoint-based synchronization, and second, we propose a decentralized planning strategy to coordinate robots to ensure the existence of checkpoints. We analyze memory usage, data amount in communication, and searching time for the proposed algorithm. We have implemented the proposed algorithm and compared it with two heuristics. The experimental results show that our algorithm successfully trades a modest amount of memory for the fastest searching time among the three methods.

Enhanced control of DFIG-used back-to-back PWM VSC under unbalanced grid voltage conditions

This paper presents a unified positive-and negative-sequence dual-dq dynamic model of wind-turbine driven doubly-fed induction generator(DFIG) under unbalanced grid voltage conditions. Strategies for enhanced control and operation of a DFIG-used back-to-back(BTB) PWM voltage source converter(VSC) are proposed. The modified control design for the grid-side converter in the stationary αβ frames diminishes the amplitude of DC-link voltage ripples of twice the grid frequency,and the two proposed control targets for the rotor-side converter are alternatively achieved,which,as a result,improve the fault-ride through(FRT) capability of the DFIG based wind power generation systems during unbalanced network supply. A complete unbalanced control scheme with both grid-and rotor-side converters included is designed. Finally,simulation was carried out on a 1.5 MW wind-turbine driven DFIG system and the validity of the developed unified model and the feasibility of the proposed control strategies are all confirmed by the simulated results.

Force Requirement for Stump Lifting

In cutting areas, soil preparation is occasionally necessary before reforestation. The aim of this action is a spatial planning that enables to perform further operations without problems. The removal, collection and transportation of stumps from the soil are part of this action. Issues related to climate change and the shortcoming of fossil energy sources call attention to increase the rate of renewable energy sources. Using the stumps removed from the soil as fuel is a significant resource within the biomass potential. For lifting a stump together with its roots, a grab mounted on a shovel is generally used. The utilisation of the lifted stumps for energy purposes increased worldwide, especially in the Scandinavian countries. In order to rationalise this operation, analyses of stump lifting time have been carried out. Results of some Hungarian experiments are presented below. The authors tested a machine mounting one grab for stump lifting on three tree types （Scots pine, robinia and poplar） and found functions correlating stump extraction force and stump diameter, which can be used in order to choose the right machine and determine the cost of the operation.

Large power analysis of switched reluctance machine system for coal mine

The conventional structures in the Switched Reluctance machines are introduced, such as three-phase 12/8 structure Switched Reluctance machine, three-phase 6/4 structure Switched Reluctance machine, four-phase 16/12 structure Switched Reluctance machine, and four-phase 8/6 structure Switched Reluctance machine. Three-phase 12/8 structure Switched Reluctance machine is the best choice for the large power Switched Reluctance machine system in coal mines. The asymmetric bridge power converter main circuit and the bifilar winding power converter main circuit are also introduced. Three-phase asymmetric bridge power converter main circuit is the best choice for the large power Switched Reluctance machine system in coal mines. The magnetic paths of the designed large power motor are given with one phase excitation and double phases excitation. The phase current waveforms are also given.

Fault Ride-Through Capability of Full-Power Converter Wind Turbine

In order to ensure power system stability, modern wind turbines are required to be able to endure deep voltage dips. The specifications that determine the voltage dip versus time are called fault r/de-through （FRT） requirements. The purpose of this paper is not only to examine the FRT behavior of a full-power converter wind turbine but also to combine the power system viewpoint to the studies. It is not enough for the turbine to be FRT capable; the loss of mains （LOM） protection of the turbine must also be set to allow the FRT. Enabling FRT, however, means that the LOM protection settings must be loosen, which may sometimes pose a safety hazard. This article introduces unique real-time simulation environment and proposes an FRT method for a wind turbine that also takes the operation of LOM protection relay into account. Simulations are carried out using the simulation environment and results show that wind turbine is able to ride-through a symmetrical power system fault.

Single-stage active clamp power factor correction AC/DC converter

A simple single-stage AC/DC converter circuit with active clamp is presented. The operation theory and state are analyzed. The experimental results show that the voltage across main switch can be clamped to a certain value,and zero voltage switching (ZVS) can be achieved. The voltage stress and switching loss are both decreased. In range of the whole load,power factors can be always more than 97%,and the highest efficiency can reach 88%.

Control-Based Stabilization of DC Microgrid for More Electric Aircraft

Electrifying the on-board subsystems of aircraft becomes an inevitable process as being faced with the environmental pollution,along with the proposed concept called more electric aircraft(MEA).With the increasing number of on-board power electronic based devices,the distribution system of the aircraft can be regarded as an onboard microgrid.As it is known that the load power electronic converters can exhibit constant power load(CPL)characteristics and reduce the system stability,it is necessary to accurately predict and enhance the system stability in designing process.This paper firstly analyzes the stability of an on-board DC microgrid with the presence of CPL.Then,discusses the reasons behind instability and proposes a control strategy to enhance system stability.Finally,the simulation results are worked out to validate the analysis and the effect of the proposed control strategy.

Adaptive computational resource allocation for sensor networks

To efficiently utilize the limited computational resource in real-time sensor networks, this paper focuses on the challenge of computational resource allocation in sensor networks and provides a solution with the method of economics. It designs a microeconomic system in which the applications distribute their computational resource consumption across sensor networks by virtue of mobile agent. Further, it proposes the market-based computational resource allocation policy named MCRA which satisfies the uniform consumption of computational energy in network and the optimal division of the single computational capacity for multiple tasks. The simulation in the scenario of target tracing demonstrates that MCRA realizes an efficient allocation of computational resources according to the priority of tasks, achieves the superior allocation performance and equilibrium performance compared to traditional allocation policies, and ultimately prolongs the system lifetime.

Two Modifications on IKE Protocol with Pre-shared Key Authentication

This paper proposed two modifications on IKE protocol with pre-shared key authentication. The first modification can improve its immunity against DDoS attack by authenticating the initiator before the responder generates the computation-intensive Diffie-Hellman public value. The second modification can improve its efficiency when the attack on messages occurs because it can detect the attack quickly by replacing the centralized authentication in origical IKE protocol with immediate authentication. In addition, the two modifications can be integrated into one protocol compactly.

A Review of Direct Driven PMSG for Wind Energy Systems

This paper presents a comprehensive overview study of the DDPMSG （direct driven permanent magnet synchronous generator） for wind energy generation system. Wind turbine controls are provided. The PMSG （permanent magnet synchronous generator） is introduced as construction and model. Configurations of different power converters are presented for use with DDPMSG in wind systems at variable speed operation and maximum power capture. Control techniques for the system are discussed for both machine-side and grid-side in details. Grid integration is provided with focus on how to insure power quality of the system and the performance at disturbances.

Scheduling optimization problem considering time-of-use tariffs and piece-rate machine maintenance in EAF steelmaking

An operating schedule of the parallel electric arc furnaces(EAFs)considering both productivity and energy related criteria is investigated.A mathematical model is established to minimize the total completion time and the total electricity cost.This problem is proved to be an NP-hard problem,and an effective solution algorithm,longest processing time-genetic(LPT-gene)algorithm,is proposed.The impacts of varied processing energy consumption and electricity price on the optimal schedules are analyzed.The integrated influence of the different weight values and the variation between the peak price and the trough price on the optimal solution is studied.Computational experiments illustrate that considering the energy consumption costs in production has little influence on makespan;the computational performance of the proposed longest processing time-genetic algorithm is better than the genetic algorithm(GA)in the issue to be studied;considerable reductions in the energy consumption costs can be achieved by avoiding producing during high-energy price periods and reducing the machining energy consumption difference.The results can be a guidance for managers to improve productivity and to save energy costs under the time-of-use tariffs.

Energy efficient mechanism using flexible medium access control protocol for hybrid wireless sensor networks

Energy efficiency is a primary consideration in a wireless sensor network (WSN). This is also a major parameter when designing a medium access control (MAC) protocol for WSNs. Hierarchical clustering structure is regarded suitable for WSNs due to its good performance in energy conservation. In this work, an adequately flexible mechanism for clustering WSNs is designed, in which some creative or promotional metrics are utilized, such as cluster head selection algorithm, cluster optional reconstruction, interested data transmission, multiple path routing protocol. All these strategies were cooperated to maximize energy saving of whole system. An appropriate MAC protocol for this mechanism is proposed, by flexibly switching the status of diverse sensor nodes in different strategies. The simulation results show that the proposed MAC protocol is suitable for clustering WSNs and performs well in aspects of energy efficiency, flexibility and scalability.

Experimental Performance Assessment of Multi-Phase Alternators Supplying Multiple AC/DC Power Converters

DC distribution networks are often employed in isolated power systems like in marine and aeronautical applications. An interesting alternative to DC machines for the supply of DC grids is constituted by a three-phase alternator feeding an AC/DC rectifier. In this paper, alternative solutions are investigated where the AC alternator is equipped with more （iV） three-phase windings and feeds the DC load through more （N） cascade-connected rectifiers. The advantages of this solution with respect to the conventional three-phase topology are highlighted along with their dependence on the number （N） of the alternator windings. For this purpose, test results are reported and discussed on a prototype generator whose stator coils can be differently connected to obtained one, two, three or four windings. The major benefits （in terms of DC output current quality and field current ripple） are found when passing from the three-phase solution to the dual winding topology; conversely, relatively little advantage is gained by increasing the number of stator windings above two.

Passive Matrix Organic Electroluminescent Display for 3G Cellular Phone

The major features of the display technologies for 3G cellular phone are reviewed. The comparison between their potential candidates for 3G cellular phone is given, and a detailed discussion is made on passive matrix organic electroluminescent display technology. A novel method to improve display contrast ratio is presented. Finally several 3G phone set prototypes with OLED display panels are given as well as the market forecast.

Innovation Shapes a Better Futur

In the past few years China has consistently and increasingly encouraged innovation,making great headway in such sectors as heavy equipment manufacturing,high-speed rail,biopharmaceuticals,new energy and robotics.Innovation has become an important engine boosting economic and social development in China.