基于缓冲区重采样的LSTM林火预测模型*

为提高林火风险预测精度,挖掘地图上隐含的空间信息、时间序列上隐含的长期趋势和循环波动,提出1种基于缓冲区重采样的长短期记忆（LSTM）林火预测模型,选取15个与林火相关的影响因素,以方差膨胀因子为评价指标对其进行多重共线性检验,方差膨胀因子大于10的因素具有共线性,并采用信息增益率验证筛选结果的合理性。考虑到火灾的空间聚集特性,采用缓冲区分析与过采样相结合方法减少样本不均衡现象的影响,最终得到176 732条样本。对12个影响因素和研究时间段的火点建立LSTM预测模型,对森林火灾发生风险进行预测。研究结果表明:基于缓冲区重采样的LSTM林火预测模型有效考虑时空上隐含的信息,预测模型准确率为87.06%,特异性为97.99%,敏感度为76.12%,阳性预测率为97.43%,阴性预测率为80.41%,ROC曲线与AUC值均优于随机森林（RF）和支持向量机（SVM）这2种基准算法。维尔克松秩和检验发现,本文提出的模型与基准算法结果具有显著性差异。研究结果可为提高林火风险预测精度提供参考。     

考虑公众选择偏好的应急避难安置双阶段选址-分配模型

为使开放避难场所符合公众自行避难的实际情况,借鉴Huff模型量化公众选择行为,构建双阶段选址-分配模型,第1阶段确定开放避难场所位置,第2阶段将溢出容量的灾民二次分配到有剩余容量的避难场所,并利用改进粒子群算法进行求解。研究结果表明：双阶段选址-分配模型能够实现同一需求点灾民前往不同避难场所的过程,管理者干预政策能够使服务人数大幅度增加,避免资源浪费、灾民流离失所且二次分配情况主要依赖于第1阶段的结果。研究结果可为管理部门规划应急避难场所提供参考。     

智能手机应用程序使用与操作的驾驶分心风险影响研究

为研究智能手机应用程序操作方式与使用行为对驾驶分心影响的问题,探讨智能手机程序操作方式对驾驶分心影响的优劣关系,基于结构方程模型提出4个因果关系假设,构建涵盖程序使用、驾驶分心、驾驶绩效等潜变量的智能手机使用行为影响的结构方程模型。通过收集线下问卷的方式进行调查,搭建模拟场景,设计6项实验方案,通过驾驶模拟实验方式收集相关数据,建立相对偏差矩阵。研究结果表明：手机通话功能的使用(路径系数0.472)对驾驶分心影响显著,手机导航功能使用(路径系数0.256)、手机音乐功能使用(路径系数0.249)对驾驶分心影响不显著。语音交互方式均优于手动操作方式,其中语音交互启动导航方式(F₃=0.019)的影响最小。研究结果可对道路驾驶情况下智能手机应用使用与操作方式的研究起推动作用。     

Cybersecurity and dynamic operation in practice: Equipment impacts and safety guarantees

Though dynamic operation of chemical processes has been extensively explored theoretically in contexts such as economic model predictive control or even considering the potential for cyberattacks on control systems creating non-standard operating policies, important practical questions remain regarding dynamic operation. In this work, we look at two of these with particular relevance to process safety: (1) evaluating dynamic operating policies with respect to process equipment fidelity and (2) evaluating procedures for determining the parameters of an advanced control law that can promote both dynamic operation as well as safety if appropriately designed. Regarding the first topic, we utilize computational fluid dynamics and finite element analysis simulations to analyze how cyberattacks on control systems could impact a metric for stress in equipment (maximum Von Mises stress) over time. Subsequently, we develop reduced-order models showing how both a process variable and maximum Von Mises stress vary over time in response to temperature variations at the boundary of the equipment, to use in evaluating how advanced control frameworks might impact and consider the stress. We close by investigating options for obtaining parameters of an economic model predictive control design that would need to meet a variety of theoretical requirements for safety guarantees to hold. This provides insights on practical safety aspects of control theory, and also indicates relationships between control and design from a safety perspective that highlight further relationships between design and control under dynamic operation to deepen perspectives from the computational fluid dynamics and finite element analysis discussions.     

Structural equation model of the influence of noise annoyance on miners’ unsafe behavior in coal mines

Miners' unsafe behavior (UB) is the main cause of coal mine accidents. Previous research has suggested that excessive noise in tunnels impacts miners' temperaments and safe production behavior. To explore the influence of noise on UB, four different dimensions of noise annoyance were identified: cognitive, emotional, communication, and physical mechanism annoyance. The coal mine noise annoyance scale, miners' unsafe behavior intention (UBI) scale, and miners’ UB scale were developed according to different dimensions. In the first survey, a total of 200 questionnaires were distributed in the two coal mines, and 193 valid questionnaires were recovered. Exploratory factor analysis was conducted, and invalid items were removed according to the analysis results to form the final scale. Then, 500 final scales were distributed in two Chinese coal mines, and 482 valid questionnaires were collected. Confirmatory factor analysis was conducted by collating the data of the second questionnaire. Based upon the structural equation model (SEM), the SEM of the influence of noise annoyance degree on UB and the path analysis with latent variable path analysis with the latent variables (PA-LVs) mediating model of the effect of UBI on UB were established, and the path coefficients with fitting data of the model were analyzed. The results indicated that the four dimensions of coal mine noise annoyance had a strong positive impact on UB, which was reduced by less noise annoyance. In addition, the Bootstrap method was used to verify the mediating method among the four dimensions of noise annoyance, cognitive annoyance, emotional annoyance, with communication annoyance indirectly affecting UB through UBI. The research results provide theoretical support for reducing the UB of miners and improving coal mine safety levels.     

水污染源源解析研究最新进展

采取有效措施监测监管污染物排放是实现污染减排目标的必要条件,而准确掌握流域内污染物的来源是实现污染源有效监管的技术依据,文章对水污染源源解析目标化合物选取、污染物扩散模型研究和污染区域受体模型研究的最新进展进行了评述,对其发展趋势进行了展望.     

我国中小城市生活垃圾优化管理模型

根据我国中小城市生活垃圾基本特点,以区域优化、长期优化和综合处理优化管理为基本准则,以规划系统总处理费用最小为目标,提出我国中小城市生活垃圾处理的优化管理模型程序.模型程序为首先进行基础数据调查与评价,分析系统内生活垃圾状况,之后建立模型方程,通过参数赋值、求解,求出最终优化管理方案,为我国中小城市生活垃圾的运行组织管理和资本运行管理提供科学手段.     

基于结构方程模型的环境风险接受度影响因素分析

随着社会经济的发展和城市化进程的推进,我国环境风险事故频发。与此同时,公众对于美好环境的需求日益提升,公众与专家和政府之间的风险判断差异是不同规模的群体性事件发生的主要诱因。为识别公众环境风险接受度的影响因素,本研究基于结构方程模型分析了11种环境风险的客观风险水平和公众感知到的风险影响度、场域了解度、政府信任度、社会经济水平等因素对公众风险接受度的影响。研究结果显示,社会经济水平、风险影响度、场域了解度、政府信任度均直接影响公众的风险接受度;客观风险水平则通过风险影响度的中介作用间接影响风险接受度。因此,为在经济发展过程中降低公众风险感知偏差对生产生活的影响,我国除了通过更严格的风险管控手段降低风险事故发生概率和影响范围外,还需要通过信息公开、公众参与和生态科普等方式增强公众对风险场域的了解度和对政府的信任度以提升风险接受能力。     

某机械陀螺长贮性能演变规律及性能退化模型研究

目的 针对长期贮存后机械陀螺的性能退化会影响制导系统侧偏和射程的问题,提出一种性能退化预测模型的建立方法,用于掌握机械陀螺长贮性能退化规律。方法 首先,针对机械陀螺结构特性和贮存环境,确定敏感应力为温度,加速模型为阿仑尼乌斯模型,开展机械陀螺的加速贮存试验。其次,对加速贮存试验过程中的机械陀螺进行周期性的参数检测,分析各性能参数随试验时间的性能退化演变规律,确定垂直漂移为其退化敏感参数。最后,拟合垂直漂移参数在各温度应力下的性能退化曲线,建立性能退化轨迹模型。结果 采用实际自然环境贮存6、7、8、10 a的性能数据对模型进行验证,模型预测准确度分别为86.70%、96.28%、91.53%、85.92%。结论 建立的性能退化模型评估准确度在85%以上,该模型可应用于指定贮存时间下机械陀螺仪的性能退化行为预测。     

混合重金属对硝化颗粒污泥毒性作用的析因实验研究

分别测定了Cu2 、Zn2 和Cd2 对硝化颗粒污泥的单一毒性,采用析因实验研究了二元和三元重金属混合体系对硝化颗粒污泥的联合毒性.结果表明,Cu2 、Zn2 和Cd2 的2 h半抑制浓度EC50分别为95.23、62.11和12.48 mg/L,由析因实验所得的响应曲面模型具有较好的优度(其R2＞0.95),能够对混合体系的联合毒性很好地进行预测,析因实验可以用于环境领域混合体系联合毒性的研究.