天然气集输站泄漏监控系统研究

为克服目前天然气集输站站控系统存在的主要技术问题,探讨了建立泄漏监控安全系统的技术要求.该系统应用负压波检漏技术、模式识别技术和虚拟仪器技术,实现了.对天然气泄漏的信号检测、处理、传输和实时动态显示等.借助于这些技术开发的天然气泄漏监控系统,具有数据处理准确可靠,精度高,误报率低等特点.通过该系统,可以及时获取相关参数和信息,实现早期预警,降低天然气泄漏的事故风险.     

The Integration of a Genetic Programming-Based Feature Optimizer With Fisher Criterion and Pattern Recognition Techniques to Non-Intrusive Load Monitoring for Load Identification

Identification of electricity energy consumption on individual household appliances used in a smart house is the first important step for making the use and conservation of electricity energy more efficient. In the past, Non-Intrusive Load Monitoring (NILM) techniques, which are part of smart grid techniques realized to improve electricity energy usage efficiency, have been developed to identify individual appliances with avoiding installing many smart meters for appliances in a field. In this paper, a new NILM technique that integrates an efficient Genetic Programming (GP)-based feature optimizer with pattern recognition techniques is proposed to identify which appliance is being turned on or off. The proposed GP-based feature optimizer with Fisher criterion is used to generate a more efficient feature than original potential transient features extracted from captured transient response of household appliances through analysis of NILM. The new feature generated by GP is used by pattern recognition techniques as load identifiers for load identification. The load identifiers used and compared in this paper include k-Nearest-Neighbor Rule, Back-Propagation Artificial Neural Network, and Learning Vector Quantization. Experiments are conducted under different single-load and multiple-load operation circumstances at different actual experimental environments with small disturbances. As shown from the experimental results, the proposed is confirmed to be feasible and usable.     

属性识别理论模型应用于土壤重金属污染评价

土壤重金属污染评价是土壤环境质量评价研究的重要组成部分。基于模糊数学理论建立的属性识别理论模型在其他环境要素评价中已有所应用,现将其应用到土壤重金属污染评价中。该法能较好地把握土壤环境质量各级标准界限的模糊性,并继承了模糊数学方法本身在评价领域应用的优点,实际操作较为简便。为较客观地反映评价因子对土壤环境质量的影响,模型中引入重金属生物有效性的概念与传统权重系数确定法相结合构造各指标权重。该模型评价结果基本上与其他评价方法的结果相一致,并能较为客观地反映出土壤环境的污染状况。     

遥感震害快速评估技术在汶川地震中的应用

2008年5月12日四川汶川8.0级大地震发生后,在地面交通严重受阻、通信中断的情况下,遥感技术成为了地震灾情获取、地震应急和震后快速评估的重要手段。提出了利用高分辨率遥感影像进行地震应急和震后快速评估的技术流程,该流程涉及到遥感影像的数据管理、快速校正、图像增强、震害信息提取、地震灾情快速评估和评估结果网络发布等关键技术。利用遥感震害识别和快速评估技术准确提取了汶川地震的震害信息,绘制的基于遥感数据的汶川地震烈度分布图与中国地震局公布的基于地面调查结果的地震烈度分布图非常接近,首次实现了在震害遥感影像获取后的2~6h内,提供准确的宏观灾情分布情况以及初步的地震损失评估结果,在汶川地震的灾情获取、地震应急和震后快速评估中发挥了重要的作用。     

支持向量机法在煤与瓦斯突出分析中的应用研究

通过分析采煤工作面煤与瓦斯涌出量与地质构造指标的对应关系,应用支持向量机(SVM)方法对煤与瓦斯涌出类型及涌出量进行分析。建立两类突出识别的SVM模型、多类型突出识别的H-SVMs模型以及预测瓦斯涌出量的支持向量回归模型。研究结果表明:SVM方法能够很好地对煤与瓦斯突出模式进行识别,所建立的采煤工作面瓦斯涌出量预测模型的精度高于应用BP神经网络预测精度;SVM理论基础严谨,决策函数结构简单,泛化能力强,并且决策函数中的法向量W可以反映突出模式识别的地质结构指标的权重。     

基于未确知测度理论的安全生产状况评价研究

为研究我国省市的安全生产级别,基于未确知测度理论,建立安全生产状况评价的等级模型。根据实际情况,选取5项评价指标,建立各评价指标的未确知测度函数。利用熵确定各项指标的权重,避免人为主观性对评价的影响,根据多指标综合测度评价向量和置信度识别准则进行评判。结合2009年9省市对应指标统计数据,采用未确知理论对安全生产状况进行评价,并结合实际进行分析。该理论为省、市安全生产提供了指导性的建议和依据。     

Schooling decisions in guppies (Poecilia reticulata) are based on familiarity rather than kin recognition by phenotype matching

Evidence from a number of freshwater species indicates that fish prefer to school with familiar individuals. Do they also choose to associate with kin? Our experiment tested this idea using the Trinidadian guppy, Poecilia reticulata, a species whose reproductive biology favours the association of kin groups. Juveniles reared together were able to recognise one another on the basis of either visual or chemical cues, but showed no preference for schooling with unfamiliar kin. We therefore conclude that any naturally occurring kin groups in this species will occur as a result of familiarity rather than as a consequence of kin recognition based on phenotype matching.     

Sensory complementation and the acquisition of predator recognition by salmonid fishes

Following disturbance, some aquatic prey species release chemicals that act as a warning cue and increase vigilance in nearby conspecifics. Such disturbance cues evoke consistent low intensity anti-predator responses. In contrast, alarm cues from injured conspecifics often evoke stronger intensity responses in prey animals. In this study, we test the sensory complement hypothesis, which suggests that multiple cues act in an additive or synergistic fashion to provide additional information for risk assessment by prey. In the first experiment, we showed that juvenile rainbow trout pre-exposed to disturbance cues respond to a given concentration of damage-released alarm cues with a higher intensity of response than the trout that were pre-exposed to cues from undisturbed conspecifics. The two cues acted in an additive fashion. In the second experiment, we demonstrated that disturbance cues alone were not enough to elicit a conditioned response to the odour of a novel predator. We also showed that while disturbance cues elicit an increase in the response of trout to alarm cues, this increase does not translate into a stronger learned response to the predator when the predator odour is paired with alarm cues. Future studies should take into account sensory complementation to avoid underestimating the responses of prey to predators.     

基于无人机的施工扬尘污染源自动监测系统设计与实现

施工扬尘是大气污染物的主要来源和施工环境监测的重点对象,但传统监测手段的效率和效果有限。为此,综合使用无人机和图像识别技术,以HSV特征提取、直方图对比、非零像素点计算为核心,设计了施工扬尘污染源自动监测系统的结构、功能及运行流程,并对运行效果进行了测试。研究和测试表明:该系统可实现监测区航拍、污染源特征提取、污染源存在性检验、污染源种类判定和污染源分布区面积计算;该系统污染源存在性检验正确率为71%,污染源面积计算效率较高,污染源特征比对效果相对稳定,基本满足施工扬尘污染源监测需求。     

改进属性识别模型及其在城市环境质量综合评价中的应用

应用属性识别模型进行综合评价时,评价指标权重向量的计算具有一定的主观性。据此提出基于数据驱动技术的改进方法以使权重的确定更趋合理。实例说明,改进的属性识别模型不仅原理直观,评价结果准确,而且计算简便,在复杂系统综合评价中具有较广的适用性。