浅谈安全管理“三要素”

安全管理是安全科学的重要组成部分。“人—机—环境“是安全管理的 3个基本要素 ,安全管理必须围绕这 3个基本要素建立安全管理体系 ,协调“人—机—环境”的自然和谐 ,将“人—机—环境”建立在一个最优组合状态下 ,把安全问题由事后处理型转变为事先预防型 ,从而提高安全管理体系的效能和水平。     

污泥脱水机械的选择讨论

CaSO4沉淀污泥的脱水因化学性质的特殊性，在脱水机械的选用上应考虑一些影响其脱水的因素，对部分影响因素作一些探讨。     

高档普采工作面端面顶板的有效支护

端面顶板是高档普采工作面顶板管理的重点，分析了п型钢梁支护法的不足，提出了一种新的支护方法，通过应用取得了良好效果。     

边坡稳定性自动机器学习预测方法研究

为了简便有效地评估边坡稳定性状态,针对目前传统机器学习的算法选择与超参数优化等难题,提出1种边坡稳定性自动机器学习预测方法。首先,简要介绍5种主流开源自动机器学习框架;其次,以422组边坡稳定性样本为数据集,进行自动机器学习纯自动化训练,并与传统机器学习对比分析模型的性能与耗时;最后,综合讨论与比较典型自动机器学习框架的特性。研究结果表明：自动机器学习预测效果总体上优于传统机器学习,提升边坡稳定性预测准确率和稳健性,且无需人为干预。研究结果可为岩土工作人员准确可靠地评价边坡稳定性提供便捷条件。     

基于改进水平集算法的锅炉承压视觉预警技术

传统锅炉承压预警技术主要依靠人工巡查发现问题,在检测过程中受工作人员自身操作不稳定因素影响,存在故障预警实时性差、盲点多等问题,达不到相应的预警要求.针对此问题,提出基于改进采用水平集算法的锅炉承压预警技术.利用图像处理技术从图像中分割出锅炉承压关键部件,统计关键部件灰度值,并利用灰度值设定特征图像及初始轮廓,设计采用...     

Forecasting the impact of meteorological parameters on air pollutants in Andhra Pradesh using machine learning techniques

In the 21st century, air pollution has emerged as a significant problem all over the globe due to a variety of activities carried out by humans, such as the acceleration of industrialization and urbanization. SO₂, NO₂, and NH₃ are the key components contributing to air pollution. Moreover, these air pollutants have a significant connection to several climatic characteristics, such as the speed of the wind, the relative humidity, the temperature, the amount of precipitation, and the surface pressure. As a result, machine learning (ML) is regarded as a more effective strategy for predicting air quality than more conventional approaches such as probability and statistics, among others. In the research, Decision Tree (DT), Support Vector Regression (SVR), Random Forest (RF), and Multi-Linear Regression (MLR) algorithms are used to make predictions about air quality, and MSE (Mean Squared Error), RMSE (Root Mean Square Error), MAE (Mean Squared error), and R² are used to determine how accurate the predictions are.     

Drivers of future streamflow changes in watersheds across the Northeastern United States

Accurate projections of streamflow, which have implications for flooding, water resources, hydropower, and ecosystems, are critical to climate change adaptation and require an understanding of streamflow sensitivity to climate drivers. The northeastern United States has experienced a dramatic increase in extreme precipitation over the past 25 years; however, the effects of these changes, as well as changes in other drivers of streamflow, remain unclear. Here, we use a random forest model forced with a regional climate model to examine historical and future streamflow dynamics of four watersheds across the Northeast. We find that streamflow in the cold season (November–May) is primarily driven by 3-day rainfall and antecedent wetness (Antecedent Precipitation Index) in three rainfall-dominant watersheds, and 30-day rainfall, antecedent wetness, and 30-day snowmelt in the fourth, more snowmelt-dominated watershed. In the warm season (June–October), streamflow is driven by antecedent wetness and rainfall in all watersheds. By the end of the century (2070–2099), cold season streamflow depends on the importance placed on snow in the machine learning model, with changes ranging from −7% (with snow) to +40% (without snow) in a single watershed. Simulated future warm season streamflow increases in two watersheds (56% and 193%) due to increased precipitation and antecedent soil wetness, but decreases in the other two watersheds (−6% and −27%) due to reduced precipitation.     

基于传递熵与KELM的炼油化工过程风险传播路径分析方法

基于炼油化工过程复杂,设备众多,某一设备的监测变量发生扰动可能会传播至其相邻设备引发出一系列故障链。现有方法多是针对某一设备进行监测与诊断,以期降低事故后果,而忽视了对过程风险传播路径的预测以防止事故的发生。因此,提出一种基于传递熵与核极限学习机的炼油化工过程风险传播路径分析方法,该方法针对某一工艺扰动,分析其在风险发展过程中的扰动传播过程,基于传递熵分析法建立炼油化工过程风险传播推绎模型;并提出一种基于KELM的风险传播搜索方法,预测风险传播路径;将该方法应用于分馏塔冲塔过程。研究结果表明:该方法可辨识出未来一段时间内风险的可能传播路径,以便操作人员及时采取预防措施,保证过程安全及产品质量。     

基于HMM和DT的无人机异常检测方法

为了实时检测无人机异常状态,提出基于隐马尔可夫模型(Hidden Markov Model,HMM)和决策树(Decision Tree,DT)的无人机异常检测方法(HMMDT).首先根据异常致因将无人机异常分为干扰异常和硬件异常;然后结合HMM和DT建立无人机异常检测模型,定义无人机异常度衡量异常状态的严重程度,确定...     

基于SIFT与SVM的应急救援图像检测方法研究*

针对公共安全突发事件应急救援的封闭空间场景（Confined Space Scene,CSS）信息采集不通畅、不全面而影响救援等问题,提出1种基于不变特征转换（Scale invariant feature transform,SIFT）和支持向量机（Support Vector Machine,SVM）的图像信息异常检测方法。在场景内外信息传递“断环”情况下,该方法可利用物联网技术采集的图片,或以网络图片信息、历史类似场景数据等作为补充,通过SIFT特征提取、K means聚类处理以及SVM分类,实现场景的智能识别。经仿真分析,该方法能实现封闭空间内外部图像信息互通,“接补”因无法了解事件内部情况而产生的救援环节链条的“断环”,为救援提供决策参考。