Design of blasting pattern in proportion to the peak particle velocity (PPV): Artificial neural networks approach

Ground vibration is a side effect of blasting and causes the destruction of buildings and other surrounding facilities. Different damage mitigation standards have been presented in this connection. Ground vibration is affected by parameters of blasting pattern design, distance from blasting site and explosive weight. In this research, ground vibrations data generated by 20 blasts in Sarcheshmeh copper mine, Kerman, at 47 locations have been recorded. The artificial neural network (ANN) has been trained using these peak particle velocity (PPV) data and other parameters such as block volume and explosive type employed. The trained network is capable of presenting appropriate specifications for the safe blasting pattern, considering the structure in question and its allowable vibration. The network outputs include burden, spacing and total weight of explosive used. To verify training corrections, network was tested and correlation coefficients of 0.651, 0.77 and 0.963 were obtained for the total explosive weight, burden and spacing, respectively. The effects of explosive type were studied with due regards to recorded data.     

Optimum parameters for fault detection and diagnosis system of batch reaction using multiple neural networks

Batch process usually differs from the continuous process because of its time-varying variables and the process parameters. An early detection and isolation of faults in the process will help to reduce the process upsets and keep it safe and reliable. This paper discusses on the application of multi-layer perceptron neural network in detecting various faults in batch chemical reactor based on an esterification process that involves the reaction of ethanol and acetic acid catalyzed by sulfuric acid. A multi-layer feed forward neural network with double hidden layers has been used in the neural network architecture. The detection was based on the different patterns generated between normal and faulty conditions. An optimum network configuration was found when the network produced the minimal error with respect to the training, testing and data validation.     

基于BP神经网络不同输入变量的爆破振速预测

以某隧道爆破开挖为实例,利用BP神经网络解决复杂非线性函数逼近问题的能力,以最大段药量、爆心距、爆破分段数、泊松比、岩石基本质量指标作为影响爆破振动速度的主要因素,选取不同维数的输入变量建立BP神经网络模型来预测爆破振动速度。对比分析各组预测值与实测值之间的相对误差,选取合理维数的输入变量建立了爆破振动危害预测的BP神经网络模型。     

油锯手把的手传振动与主动防振动问题探讨

通过对油锯手把的手传振动状况分析发现，国产油锯产品质量仍有待加强，提出了油锯手把的主动防振动保护措施及建议。     

Predicting of blasting vibrations in Sarcheshmeh copper mine by neural network

Artificial Neural Networks (ANN) have proven to be an effective tool for solving complex engineering problems requiring estimation, pattern recognition, and classification of variables. Ground vibration caused by blasting imposes damages and financial penalties and as such must be predicted accurately. In this study, the potentials of ANN are investigated in prediction of ground vibrations due to blasting in open pit mines. Real vibration data is recorded using PDAS 100 seismometers, and used as input data for ANN. Using back propagation algorithm and performance function, root mean square error (RMSE) the network, containing four hidden layers and 23 data sets, was trained. Six sets of data were used to make sure that correct training had been carried out. This produced the coefficient correlation of 0.99355.     

Elman神经网络在矿井突水水源判别中的应用

矿井突水是矿建与生产过程中最具威胁的自然灾害之一,准确判别突水水源是防治水害的关键。选取6种离子的质量浓度作为突水水源的判别因素,将河南省焦作矿区不同水层的39组水化数据以2种样本设计方案进行Elman神经网络模型的构建与检验。以不同的35组水源样品作为训练样本,运用Matlab软件进行Elman神经网络训练,将所建立的判别模型应用于(相应的)4组待测样本的判别,并与DDA、FDA、Bayes三种判别方法的判别结果进行分析比较。2种方案应用结果表明:将具有非线性动态特征的Elman神经网络应用于突水水源判别,在结合相应的水文地质条件前提下,可以准确判断突水来源;矿井多年的开采促使地下各水层水质呈动态变化,Elman神经网络判别模型能够反映这种变化特性,对探寻地下水运移与演化具有一定的应用价值。     

应用电性拓扑状态指数预测烷烃自燃点

建立了一个基于人工神经网络的定量结构-性质相关性模型,用于52种烷烃化合物自燃点的预测研究。应用原子类型电性拓扑状态指数作为表征分子结构特征的描述符。该指数既能表征分子的电子特性,又反映其拓扑特征,同时易于计算,并有较强的同分异构体区分能力。采用误差反向传播（BP）神经网络方法对烷烃自燃点与电性拓扑状态指数间可能存在的非线性关系进行拟合。将52种烷烃样本随机划分为训练集（30种）、验证集（8种）和测试集（14种）,并通过“试差法”确定网络的最优参数。运用最佳网络结构[64—1]对实验样本进行模拟,结果表明,多数样本的自燃点预测值与实验值符合良好,对于测试集,平均预测绝对误差为8．4℃,均方根误差为11．8,优于多元线性回归方法和传统基团贡献法所得结果。该方法的提出为工程上提供了一种根据分子结构预测有机物白燃点的有效方法。     

煤尘润湿接触角的BP神经网络估算方法研究

通过采集和测定35个矿区煤样品的化学组成、结构参数和润湿接触角,构建了以13个影响因子为输入参数和以接触角为输出目标的3层BP人工神经网络,并利用该模型估算煤尘润湿接触角。结果表明,隐含层节点数为19时,接触角估算值与实测值的决定系数R2=0.957,平均相对误差为4.59%,表明基于BP神经网络建立的煤尘润湿接触角估算模型具有很高的精度。     

基于极限学习机的炭化可燃物着火时间预测

机器学习技术近年来在许多传统科学领域取得了应用,针对火灾中炭化可燃物着火时间与物性参数及环境参数之间关系复杂的特点,提出了一种基于极限学习机的预测方法以实现不同物性及环境参数时着火时间的快速准确预测,为防治及扑救火灾提供参考。首先建立炭化可燃物热解数值模型,考虑了可燃物热解过程中的含水率以及热解反应、气体流动等复杂物理化学反应过程,然后搭建极限学习机,以数值模拟数据为基础进行训练及验证工作。结果表明基于极限学习机的预测方法能够有效实现炭化可燃物着火时间的快速准确预测,平均相对误差小于3%。     

人工神经网络对矿山安全状态的评判能力分析

通过改变神经网络训练样本等方法,对比分析了神经网络对不同训练样本的反映能力,讨论了人工神经网络对矿山安全程度进行评价的适应性.为了研究人工神经网络用于矿山安全评价时的优化设计,通过改变神经网络的神经元数目及初值赋值方式等方法,测试了不同结构、不同参数的神经网络对相同训练样本的评价结论.本文的研究为人工神经网络用于矿山安全评价时的进一步改进及其优化设计提出了合理的建议.     

基于人工神经网络的气体泄爆最大超压预测研究

为解决传统经验公式在预测气体泄爆中最大超压出现时的较大偏差或过于保守的问题,提出使用人工神经网络预测气体泄爆最大超压。基于124组实验数据,采用BP与RBF神经网络,通过优化算法计算与迭代循环对泄爆样本中的影响因素进行降维与选择,并确定2类神经网络本身在学习与计算气体泄爆样本时的相关参数。结果表明:PCA（主成分分析法）在当前样本条件下的降维效果较差,而通过迭代对比确认气体泄爆样本中的5类特征全部保留时神经网络的训练模拟效果最好;通过对124组实验数据进行随机挑选训练集与测试集的训练模拟结果发现,神经网络对气体泄爆中最大超压的预测效果较好;通过对比Molkov提出的和经Fakandu等改进的NFPA 68经验公式以及2类神经网络的预测结果表明,神经网络相比于传统气体泄爆经验公式具有明显优势。     

基于BP神经网络的安全生产事故统计情况预测分析

通过对1990—2008年安全生产事故统计情况进行分析,梳理了社会经济发展的各项指标,选择其中的人均GDP、第三产业比重、非农就业人口比重、城镇居民可支配收入、万人大学生数、万人医生数等反映经济发展的主要指标作为神经网络的输入端,以安全生产事故起数和死亡人数为输出端,以2007年全国各地区经济发展指标和事故统计情况为样本训练BP神经网络,进行不同省份安全生产情况的预测。其结果与实际情况符合性较好,为目前安全生产形势分析提供了一种新方法,该法对预测安全生产监督管理工作提供参考。     

岩层移动角选取的神经网络方法研究

岩层移动角是进行各类保护煤柱设计时的关键性参数 ,涉及地表建 (构 )筑物的安全。在综合分析影响岩层移动角因素的基础上 ,采用人工神经网络方法建立岩层移动角选取的模型。该模型采用改进的BP算法 ,运用我国典型的地表移动观测站资料作为学习训练样本和测试样本 ,对模型的计算结果与实测值进行了对比分析。分析结果表明 :用人工神经网络方法求算岩层移动角考虑的因素更为全面 ,结果更接近于实际。笔者为岩层移动角的理论计算探索出了一种新的方法。     

非爆破施工震动安全判据引用探讨

通过几个非爆破施工振动影响相邻建筑的鉴定检测实例,结合国内外爆破振动安全判据标准,提出爆破施工振动和非爆破施工振动2个概念,根据这2种施工振动的各自特点,初步探讨非爆破施工中的振动如何引用爆破振动安全判据,并提出非爆破施工振动安全判据质点振动速度范围值以供探讨.     

基于信息融合的自然灾害等级评估方法研究

为对自然灾害灾情等级进行准确评估,在BP神经网络模型的基础上,结合DS证据理论建立基于信息融合的自然灾害灾情等级评估模型。该模型通过对输入的灾害评估指标数据进行分类,建立网络组,对网络组的输出,建立对于各类信任度的基本概率分配函数,最后利用DS证据理论融合,从而实现灾害的最终等级评估。在MATLAB环境下,以我国45个自然灾害的灾情历史资料数据为训练样本进行模型训练,并对2009年自然灾害灾情进行评估测试。结果表明,该模型能改善单一BP神经网络不稳定、误差大的缺点,得到较优的结果。     

Prediction of ultimate bearing capacity of Tubular T-joint under fire using artificial neural networks

An artificial neural network (ANN) model is developed for the prediction of the ultimate bearing capacity of tubular T-joint under fire. The input parameters of the network are composed of the diameter ratio (β), the wall thickness ratio (τ), the diameter–thickness ratio (γ) and the temperature (T). The output parameter is composed of the ultimate bearing capacity. In this paper, the training and testing data of the neural network are obtained using the finite element program ABAQUS. The network is trained by 216 dataset and tested by 27 dataset. In the process of training of the network, the Levenberg-Marquardt back-propagation algorithm is adopted. The ‘tansig’ function is adopted in the hidden layer, and the ‘purelin’ function is adopted in the output layer. The results predicted by ANN are compared with the results simulated by finite element method (FEM). These results show that the prediction of the ultimate bearing capacity using the network model is accurate and effective.     

The photocatalytic degradation of carbamazepine and prediction by artificial neural networks

The three layer artificial neural network model was applied to predict the degradation efficiency for carbamazepine in photocatalytic oxidation under UV radiation. Titania–zirconia was employed as a catalyst for the photooxidation. The catalyst was prepared using titanium isopropoxide and zirconium oxychloride by sol–gel method and characterized by transmission electron microscopy and BET analysis. Different process parameters such as, initial concentration of carbamazepine, pH of the solution, catalyst concentration and time of UV irradiation were employed as the input to the artificial neural network model and the output of the network was degradation efficiency of carbamazepine. The multilayer feed-forward networks with the Levenberg–Marquardt (trainlm) backpropagation training algorithm was used for the network training. The smallest mean square error was obtained for three-layer network with ‘logsig’ transfer function and five neurons in the hidden layer gave optimal results. A comparison between the predicted values and selective experimental data of degradation efficiency showed a high correlation coefficient (R²) of 0.997.     

The Effect of Protective Gloves on Manual Dexterity in the Cold Environments

This article presents a study on the effect of different protective gloves (which are commercially available and commonly used in the cold) on manual dexterity in cold environments. The experiments compared statistically four different types of gloves and two different types of gloving (outer or double) at +19 °C and -10 °C. Performance was determined both objectively and subjectively using two manual dexterity tasks: bolt-nut and pick-up tasks. The response measured was the time of performing each task. Statistical analysis showed that all independent factors such as glove type, participant, object size, and temperature had significant effects on the hand cooling reaction. A significant difference in the performance between the gloves was found in the bolt-nut task. It was also found that outer-inner combination gloving may be an approach to use for precision tasks.     

基于RBF神经网络的火灾报警系统失效概率预测

报警系统失效主要包括漏报、误报,对系统进行失效概率预测,可以帮助判断设备质量优劣,评估系统效能。利用Matlab软件编程,通过神经网络预测失效概率。根据不同场所正在使用的火灾报警器的失效数据作为原始数据,归纳总结失效原因,建立事故树,结合专家打分法与模糊理论得到网络的输入值与输出值。通过网络训练,得到可以对系统失效概率进行预测的RBF神经网络,测算效率大幅提高。以70组不同品牌、用途的火灾报警系统作为算例,通过训练数据,最终达到输入底事件发生概率可直接输出顶事件发生概率的目的。结果表明,RBF神经网络相较于BP网络与事故树算得的失效概率具有更高的拟合度,RBF神经网络模型在进行系统失效概率预测时具有可靠性。     

基于人工神经网络的烟气及温度实时预测模型*

为监测建筑火灾事故区域的危险程度,实现更加安全、高效的火灾应急救援,以通廊式建筑为研究对象,基于转置卷积神经网络及数值模拟方法开发1种可实时预测走廊位置处烟气扩散和温度分布的神经网络模型。首先,依托Python建立包含全连接、转置卷积、反池化等在内的19层神经网络模型的整体架构;其次,建立包含99个火灾场景,共7 920组图像数据的火场信息数据库用于模型训练;最后,使用测试集对模型进行可靠性验证。研究结果表明:烟气（温度）预测模型在不同火灾场景下的预测精度达到95%,训练完成后模型的预测时间一般为1~2 s。研究结果可为应急策略的快速制定提供数据参考。