基于深度置信网络的管网泄漏故障诊断方法研究

针对当前管网系统数据量大不利于传统模型方法诊断故障的问题，设计了1种基于深度置信网络的管网故障诊断算法。首先，对管网数据结构以及管网系统运行状态进行分析，选取管网主要数据作为故障诊断网络的输入，确定相应运行状态作为诊断网络输出；其次，设计了基于多个受限制玻尔兹曼机与Softmax分类器级联的深度置信网络，并且利用对比散度算法和BP算法对模型进行预训练与调优，使模型参数达到全局最优；最后，通过实验测试确定所设计的深度置信网络的训练迭代次数与网络层数，使算法诊断准确率达到最优。研究结果表明:提出的基于深度置信网络的管网故障诊断算法对管网故障诊断可以达到良好的诊断结果，泄漏预测准确率在验证集样本上可达96.87%，在管网泄漏检测方面，相较于传统基于模型的方法优势明显。     

对开发闽台民间信仰文化旅游的思考

闽台文化是中国传统文化的重要组成部分,加强海峡两岸民间信仰文化的交流与旅游开发,对促进海峡两岸旅游区的建设发展和祖国统一都有着重要的意义。闽台民间信仰文化旅游开发具有市场、区位及政治优势,但目前存在"散、小、弱、差"等问题。在开发闽台民间信仰文化旅游时要注意闽台合作、联合开发、重点开发、突出女神文化牌和加强人力资源开发,使之成为海峡两岸旅游区的精品。     

谈新大学生军训中的思想和作风收获

本文立足军训大学生思想作风素质的提升,为进一步巩固校园来之不易的军训成果,结合大一新生的军训实际,从思想意识、意志力水平、作风纪律性、生活自立精神等六个方面概括了大学生在军训中的思想和作风收获.     

Application of a Modified Health Belief Model to the Pro‐Environmental Behavior of Private Well Water Testing

A social cognition model of health behavior, the health belief model, was applied to the pro‐environmental behavior of private well water testing. Conceptualizing environmental behaviors as health behaviors may provide new insight into pro‐environmental behavior change. A groundwater education program was provided to K‐12 children throughout New England. Both child participants and their parents completed surveys pertaining to private well water behavior. Results indicate that perceived barriers and socioeconomic status significantly influenced past well water testing of parent participants. Perceived barriers included: participants' concern related to the cost of treating their water, and how a well water problem would influence their property value. Parent participants also indicated that they would perform future well water testing if they received a reminder cue to action that might include: getting a discount or reminder in the mail, if a well testing program was available, and state or local requirement. Our findings reinforce the need for continued private well water research and parallels to additional environmental behaviors.     

Recovery or decline of the northwestern Black Sea: A societal choice revealed by socio-ecological modelling

During recent decades anthropogenic activities have dramatically impacted the Black Sea ecosystem. High levels of riverine nutrient input during the 1970s and 1980s caused eutrophic conditions including intense algal blooms resulting in hypoxia and the subsequent collapse of benthic habitats on the northwestern shelf. Intense fishing pressure also depleted stocks of many apex predators, contributing to an increase in planktivorous fish that are now the focus of fishing efforts. Additionally, the Black Sea's ecosystem changed even further with the introduction of exotic species. Economic collapse of the surrounding socialist republics in the early 1990s resulted in decreased nutrient loading which has allowed the Black Sea ecosystem to start to recover, but under rapidly changing economic and political conditions, future recovery is uncertain.     

Exploring risk,resistance and the power of myths among coastal fishing communities in Kerala,India

This paper attempts to capture the socially constructed nature of risk by analyzing the discourses embedded in community beliefs, myths and experiential narratives regarding coastal hazards and fishworkers' livelihoods. This paper draws insights from the works of James Scott on power and resistance in the everyday life of marginalized populations. Qualitative data for the study was collected using semi‐structured interview schedules, in‐depth group interviews, oral histories and storytelling across twenty marine fishing villages in Kerala. A significant finding of the study is that the communal discourse of coastal hazards or kolu is an integral part of fishworkers' resistance against formal authority and scientific knowledge systems in coastal management. The myths and beliefs of fishworkers are expressions of their concerns about present forms of development and coastal resource management.     

CVM中的抗议性响应:动机与影响——以胶州湾浒苔治理支付意愿为例

抗议性响应是意愿调查法应用中受访者表现出的典型策略性行为,可能导致对资源环境物品或服务的估值出现偏差。识别抗议性响应影响因素并降低其对支付意愿的影响,有助于提高CVM估值效度。以胶州湾海域居民浒苔治理支付意愿为例,以抗议性信念作为受访者抗议性响应的度量指标,筛选抗议性信念的驱动因素,量化各驱动因素对支付意愿的影响方向及程度。研究结果表明:（1）愿意支付的受访者仍然具有抗议性信念,且在个别测量题项中,其抗议性信念甚至高于拒绝支付群体。（2）环境关注、搭便车顾虑、暖光效应等变量均对受访者抗议性信念存在影响。（3）抗议性信念水平对受访者参与决策与支付意愿金额均存在显著负向影响,抗议性信念变量对参与和支付决策的影响方向与程度存在差异,进一步证明参与和支付决策是不同的机制。研究结论将对优化CVM问卷设计、规范操作流程、减少评估偏差具有指导意义。     

Tri-generation investment analysis using Bayesian network: A case study

The increasing energy demand, increasing energy dependency, energy supply security, and environmental concerns have become a part of business policies since COP21 agreements in Paris, 2015. Combined cooling, heating, and power (CCHP or tri-generation) systems play an important role in paying the necessary attention to these policies. Tri-generation investment is a complex decision with hybrid use of energy resources. This article aims to reduce the complexity of this decision by the use of Bayesian belief networks in pre-investment stage of tri-generation investment project cycle. The proposed model gives an insight into decision analysis and helps the decision-makers either generate or purchase from it in order to meet the energy demand with different scenarios. The model is studied for a university case. The investment decision for a CCHP (tri-generation) system will be discussed as an alternative for purchasing the electricity and natural gas from the national grids.     

Belief Networks: A Framework for the Participatory Development of Natural Resource Management Strategies

Successful long-term management of natural resources requires the development of strategies which recognise the constraints pertaining to the environmental system and can therefore be realistically expected to work. This paper presents a new technique for strategy formulation using belief networks, a framework based on Bayesian probability calculus that supports the investigation of complex environmental systems by the user and analysis of all constraints. While mathematical in nature, belief networks are superficially simple and allow concepts to be expressed in terms with which a wide range of user will be familiar. This offers a participatory approach to the development of management strategies through consideration of the impact of potential management options with consequent benefits for strategy implementation.