基于人工神经网络的城市火灾事故的预测方法

随着社会经济的飞速发展,城市化进程的加快和人口的迅速增长,城市火灾频繁发生,造成的损失呈上升趋势.针对城市火灾事故发生的特点,根据人工神经网络基本原理和特性,建立了城市火灾事故神经网络预测模型;为了更精确预测城市火灾事故的发生,将城市火灾事故分为了高峰期(春节)和非高峰期两个时段分别进行预测;应用神经网络预测模型和分时段相结合方法对某城市火灾事故进行了实际预测.结果表明,神经网络模型是城市火灾事故预测的有效工具,该模型与时段法的结合能准确预测火灾事故发生的趋势.     

一种处理爆炸多能法的新方法

以多能法中距离－超压关系图为例,介绍了一种运用前馈多层感知器网络对现行多能法中查图步骤进行改进的方法。此法从很大程度上解决了多能法在爆炸灾害评估中手工查图误差大且不方便的缺点。模拟结果表明,该处理方法能够很好的逼近多能法中的超压函数P＝f(R0,C),最后提出了人工神经网络方法在爆炸破坏效应评估中进一步应用的设想。     

An alternative work measurement method and its application to a manufacturing industry

Difficulties in determining the standard time justify the need to develop alternative methods to direct measurement procedures. The indirect methods which are comparison and prediction, standard data and formulation, predefined movement-time systems have several deficiencies in time measurement procedures. In this study, an alternative indirect work measurement method based on artificial neural networks (ANNs) is presented which is simple and inexpensive. For the application of the proposed method, the products that have similar production processes are selected among the whole product family produced in a manufacturing company. The standard times of the sampled products that are previously measured are used and the standard times of the remaining several products and semi-products are predicted by the proposed method. The model results show that the proposed method can be applied accurately in companies which produce similar products.     

基于神经网络的煤层自然发火的非线性预测

煤炭自燃是一典型的非线性现象.笔者论述了煤炭自燃的危害,从非线性理论的角度分析了煤炭自燃的本质特征;应用神经网络中BP网络这一高度非线性关系映射建立了自然发火预测模型,克服了传统预测方法的不足并在山东枣庄矿业集团公司柴里煤矿进行了预测分析,预测结果与验证结果基本吻合,取得了满意的效果, 为解决煤炭自燃的预测提供了一条良好的思路和方法,具有较大的理论意义和应用价值.     

The dynamic response of pressure relief valves in vapor or gas service,part I: Mathematical model

In order to prevent unstable operation, or “chatter”, of a pressure relief the API guidelines recommend limiting the irreversible pressure loss in the inlet line to a pressure relief valve to no more than 3% of the valve set pressure. This criterion is based on steady-state operating conditions and a typical blow-down pressure for the valve of about 7% of the set pressure. However, the stability of the valve is also influenced by other factors such as the dynamic response of the valve disk to the unsteady pressures and forces exerted by the fluid on the disk. A model for the opening lift dynamic response of a pressure relief valve in gas/vapor service is presented here which accounts for all of these effects through a set of five coupled nonlinear algebraic/differential equations. These equations are solved by a numerical method that can be implemented on a spreadsheet to predict the position of the valve disk as a function of time for given valve characteristics, operating conditions, and installation parameters. The model incorporates the influence of the various parameters on the stable/unstable nature of the disk response. An example is presented for a typical valve that illustrates the various modes of stable and unstable dynamic response that can be predicted by the model under various conditions. Two additional papers will be forthcoming: Part II – Experimental Investigation and Part III – Analysis of Data and Comparison with Model Predictions.     

Effects of ferric oxide on decompositions of methyl ethyl ketone peroxide

Methyl ethyl ketone peroxide (MEKPO) is a widely used initiator for polymerization reaction and hardener in glass-reinforced plastic. However, MEKPO is an unstable reactive chemical and has caused several serious accidents all over the world. This work studied the thermal stability of MEKPO in the presence of ferric oxide as the contaminant through calorimetric and kinetic studies. The calorimetry was performed using Automatic Pressure Tracking Adiabatic Calorimeter (APTAC) to identify the effects of ferric oxide (different concentration) on important reactive hazards such as onset temperature and pressure hazard. Kinetic modeling was then performed to study the kinetics of the runaway reaction and estimate important kinetic parameters. The results indicate that in the low concentration range (<0.3%), ferric oxide has no significant effect on the thermal stability of MEKPO. However, in the high and intermediate concentration range of ferric oxide (i.e., 10%), the negative effect on the thermal stability of MEKPO was observed. This result is in agreement with the kinetic study result that the activation energy and frequency factor decrease dramatically in the high ferric oxide concentration range. The results provide necessary process safety information for the handling of MEKPO and also technical basis for the further study in this area.     

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.     

Diphenylmethane diisocyanate self-polymerization: Thermal hazard evaluation and proof of runaway reaction in gram scale

Thermal analysis by differential scanning calorimetry and thermogravimetric/differential thermal analysis mass spectrometry, adiabatic calorimetry, a gram-scale heating test, and infrared spectroscopy were performed to evaluate the thermal hazards of diphenylmethane diisocyanate (MDI) and prove the occurrence of a runaway reaction. The self-polymerization of MDI was found to occur at about 340 °C under rapid heating conditions. Carbon dioxide was eliminated and heat was generated to allow polymerization. Under adiabatic and closed conditions, the runaway reaction of MDI can begin at least from 220 °C. Besides it is highly probable that the runaway reaction of MDI can begin from a lower temperature in an actual process scale. More heat was generated than in the previous case and the pressure rose rapidly. A closed 2-mm-thick glass vessel exploded because of the runaway reaction of MDI even if the temperature was lower than 300 °C. Therefore, MDI could cause fatal runaway reactions below 300 °C, where MDI had been assumed to self-polymerize by eliminating carbon dioxide previously.     

东部发达城市智慧水务建设探析

在互联网技术飞速发展,于各传统行业运用的建设大背景下,智慧水务的构想应运而生。结合当前水务发展遇到的实际问题和国家战略部署阐述了智慧水务的建设。最后提出应落实发展信息技术,加快技术融合,为智慧城市的建设添砖加瓦。     

The influence of ClO− and acidity in the reaction between H2O2 and CuCl2

The potentially explosive reaction of hydrogen peroxide (H₂O₂) and copper chloride (CuCl₂) was investigated. Pressure tests revealed that the reaction was strongly temperature - dependent and can easily undergo runaway reaction. Nevertheless, there was only a slight pressure increase at the low temperatures studied or when using low concentrations of CuCl₂. Under the conditions generating the slight pressure increase, hypochlorite anions (ClO⁻) are generated and the acidity increases. As the reaction reaches completion, ClO⁻ disappears, and the acidity decreases. Interestingly, the addition of phosphate buffer to maintain the weakly acid conditions led to a runaway reaction, and the use of basic ClO⁻ promoted the exothermic reaction. Based on the results, acidity has a strong impact on the reaction behaviour.     

Degradation of Rhodamine B by an electrochemical ozone generating system consist of a Ti anode coated with nanocomposite of Sn–Sb–Ni oxide

An ozonation process was performed using a recycled electrochemical ozone generator system. A titanium based electrode, coated with nanocomposite of Sn–Sb–Ni was applied as anode in a laboratory-made electrochemical reactor. A constant flow rate of 192 mg/h of generated ozone was entered to an ozonation reactor to contact with a typical target pollutant, i.e., Rhodamine B (Rh.B) molecules in aqueous solution. Four operational parameters such as: initial dye concentration, pH, temperature and the contact time were evaluated for the ozonation process. Experimental findings revealed that for a solution of 8 mg/L of the dye, the degradation efficiency could reach to 99.5% after 30 min at pH 3.7 and temperature of 45 °C as the optimum conditions. Kinetic studies showed that a second order equation can describe the ozonation adequately well under different temperatures. Also, considering to the importance of process simulation, a three-layered feed forward back propagation artificial neural network model was developed. Sensitivity analysis indicated order of the operational parameter's relative importance on the model output as: time ≫ pH > Rh . B initial concentration > temperature.     

基于案例推理的化工园区应急资源需求预测

为确定化工园区突发事故的应急资源需求,提出了一种基于案例推理的化工园区应急资源需求预测方法.该方法主要由三部分组成:(1)基于案例推理的模型构建;(2)化工园区事故的案例描述;(3)基于人工神经网络的案例适应.最后,以石化园区火灾爆炸事故的应急资源需求预测验证该方法的有效性.研究表明,该方法可以实时地对化工园区应急资源...