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.     

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。     

A beetle antennae search improved BP neural network model for predicting multi-factor-based gas explosion pressures

A gas explosion in an underground structure may cause serious damage to the human body and ground buildings and may result in huge economic losses. The pressure of the gas explosion is an important parameter in determining its severity and designating an emergency plan. However, existing empirical and computational fluid dynamics (CFD) methods for pressure prediction are either inaccurate or inefficient when considering multiple influencing factors and their interrelationships. Therefore, for a more efficient and reliable prediction, the present study developed a multifactorial prediction model based on a beetle antennae search (BAS) algorithm improved back propagation (BP) neural network. A total of 317 sets of data which considered factors of geometry, gas, obstacle, vent, and ignition were collected from previous studies. The results showed that the established model can predict pressures accurately by low RMSE (43.4542 and 50.7176) and MAPE (3.9666% and 4.9605%) values and high R² (0.7696 and 0.7388) values for training and testing datasets, respectively. Meanwhile, the BAS algorithm was applied to improve both the calculation efficiency and the accuracy of the proposed model by enabling a more intelligent hyperparameter tuning method. Furthermore, the permutation importance of input variables was investigated, and the length (L) and the ratio of length and diameter (L/D) of geometry were found to be the most critical factors that affect the explosion pressure level.     

Optimizing the preparation parameters of mesoporous nanocrystalline titania and its photocatalytic activity in water: Physical properties and growth mechanisms

Titania nanomaterial with an anatase structure and 5.6 nm crystallite size and 280.7 m² g⁻¹ specific surface areas had been successfully prepared by sol–gel/hydrothermal route. The effect of pH as a type of autoclave and calcination was studied. Crystallite size and phase composition of the prepared samples were identified. X-ray diffraction analyses showed the presence of anatase with little or no rutile phases. The crystallite size of the prepared TiO₂ with acidic catalyst was both smaller than that prepared with basic catalyst, and was increasing after acidic calcinations by a factor 4–5. Basic calcinations produced a specific increase of 1.5. Rutile ratio and the particle size were increased after calcination at 500 °C. However, TiO₂ powder synthesized using a basic catalyst persisted the anatase phase and a loosely aggregation of particles. Anatase TiO₂ as prepared with acidic catalyst in Teflon lined stainless steel autoclave demonstrated the highest photocatalytic activity for degradation of 2,6-dichlorophenol-indophenol under ultraviolet irradiation with t_½ 0.8 min.     

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。     

Inherently safer reactors: Improved efficiency of 3-picoline N-oxidation in the temperature range 110–125 °C

Alkylpyridine N-oxides are important intermediates in the pharmaceutical and agrochemicals industries. The N-oxides are produced via the homogeneously catalyzed oxidation of the respective alkylpyridines using a 50% excess of hydrogen peroxide. The competitive hydrogen peroxide decomposition produces oxygen in the flammable environment of alkylpyridines and thus forms a key hazard for this reaction. In this work, the N-oxidation was performed under pressure in the temperature range of 110–125 °C with different catalyst concentrations. It was shown that temperature had an undisputable positive effect on the N-oxidation efficiency. The accurate measurement of the pressure rise due to decomposition was difficult. However, only 5% of the added H₂O₂ decomposed when stoichiometric quantities were employed, even in the temperature of 110 °C. The N-oxidation was very efficient, even when the lowest concentration of catalyst employed in this study was used.     

Modeling and optimization of activated sludge bulking for a real wastewater treatment plant using hybrid artificial neural networks-genetic algorithm approach

Prediction of sludge bulking is a matter of growing importance around the world. Sludge volume index (SVI) should be monitored to predict sludge bulking for a wastewater treatment plant. This study was an effort to develop hybrid artificial neural network-genetic algorithm models (MLPANN-GA and RBFANN-GA) to accurately predict SVI. Operating parameters, including MLVSS, pH, DO, temperature, TSS, COD and total nitrogen were the inputs of neural networks. Genetic algorithm was utilized in order to optimize weights and thresholds of the MLPANN and RFBANN models. Training procedures for SVI estimation were successful for both the MLPANN-GA and RBFANN-GA models. The training and validation models showed an almost perfect match between experimental and predicted values of SVI. The results indicated that with low experimental values of input data to train ANNs, the MLPANN-GA compared with the RBFANN-GA is more accurate due to higher coefficient of determination (R²) and lower root mean squared error (RMSE) values. The values of RMSE and R² for the optimal models approached 0 and 1, respectively. The mean average error for the ANN models did not exceed 3% of the input values of the measured SVI. The GA increased the accuracy of all the MLPANN and RBFANN models.     

基于神经网络的安全评价指标重要度判定方法及应用

安全评价指标重要度判定对合理进行安全管理和有效采取安全对策具有重要意义,它是一个多指标非线性分类问题,很难用数学公式进行描述。以往的判定方法由于受人为因素及模糊随机性影响,准确性较低。神经网络作为一种新技术,具有非线性分类、人工智能的特点。基于此,提出了一种基于人工神经网络的安全评价指标重要度判定方法。该方法最大特点是直接从学习后的网络连接权重中提取评价指标重要度信息。讨论了网络的拓扑结构,以及如何从学习后的网络权重中提取评价指标重要度信息的方法。应用数理统计方法消除了网络学习初始权重对评价结果的影响。用一实例对提出的方法进行了验证,分析了网络隐含层节点数对判定结果的影响。实验表明,该方法具有很强的操作性和较高的准确性。     

基于BP网络的建筑安装施工现场安全综合评价的研究

针对目前我国建筑安装施工现场安全评价技术的不成熟和欠科学性的现状 ,笔者分析和综合了目前安全评价技术 ,结合建筑业特点 ,提出了基于BP神经网络的建筑安装施工现场安全评价方法 ,并对该评价模型的原理、方法及算法进行了研究。首先 ,结合建筑安装施工现场安全生产的特点建立评价指标体系 ,随后 ,运用层次分析法确定指标及准则层的权重 ,并运用模糊综合评价法生成评价样本集 ,最后 ,利用样本集训练BP网络 ,待误差满足要求后 ,即可运用训练成功的BP神经网络进行安全评价。     

Artificial neural network modelling of As(III) removal from water by novel hybrid material

The present study reported a method for removal of As(III) from water solution by a novel hybrid material (Ce-HAHCl). The hybrid material was synthesized by sol–gel method and was characterized by XRD, FTIR, SEM–EDS and TGA–DTA. Batch adsorption experiments were conducted as a function of different variables like adsorbent dose, pH, contact time, agitation speed, initial concentration and temperature. The experimental studies revealed that maximum removal percentage is 98.85 at optimum condition: pH = 5.0, agitation speed = 180 rpm, temperature = 60 °C and contact time = 80 min using 9 g L⁻¹ of adsorbent dose for initial As(III) concentration of 10 mg L⁻¹. Using adsorbent dose of 10 g L⁻¹, the maximum removal percentage remains same with initial As(III) concentration of 25 mg L⁻¹ (or 50 mg L⁻¹). The maximum adsorption capacity of the material is found to be 182.6 mg g⁻¹. Subsequently, the experimental results are used for developing a valid model based on back propagation (BP) learning algorithm with artificial neural networking (BP-ANN) for prediction of removal efficiency. The adequacy of the model (BP-ANN) is checked by value of the absolute relative percentage error (0.293) and correlation coefficient (R² = 0.975). Comparison of experimental and predictive model results show that the model can predict the adsorption efficiency with acceptable accuracy.     

Decolorization and degradation of acid dye with immobilized titania nanoparticles

This paper addresses the decolorization and degradation of acid dye by a heterogeneous photocatalytic process using immobilized nano-sized TiO₂ particles as the photocatalyst. Sackcloth fiber was used as a support to immobilize the nano-sized TiO₂ photocatalyst. The structural properties of the immobilized photocatalyst were characterized by XRD, SEM and EDX. UV–Vis absorption spectroscopy and the measurement of the chemical oxygen demand (COD) were also used for the process performance studies. The XRD results did not show significant changes in the structure of P25 as a consequence of the immobilization procedure. The formation of titania crystallites in the sackcloth fiber was confirmed by SEM/EDX. The photocatalytic activities of TiO₂-coated sackcloth fiber catalyst were evaluated using Acid Black 26 as a model organic contaminant and using UV-A radiation. Experimental results showed that after 60 min, the degradation of Acid Black 26 with the immobilized TiO₂ particles was higher than that with plain TiO₂. Based on the COD results, after 3 h, the TiO₂-coated sackcloth fiber effectively decomposed all of the organic compounds present in dye solution under the studied experimental conditions. The effects of the oxidant H₂O₂, initial dye concentration and pH on the photocatalytic degradation were also investigated. The presence of CO₃^2? as a dissolved inorganic anion had the highest inhibitory effect on the decolorization of the dye, when compared with the other anions investigated. Kinetics analysis indicates that the photocatalytic decolorization rate of Acid Black 26 can be described by a pseudo-first-order model.     

回采工作面瓦斯涌出量预测的神经网络方法

回采工作面瓦斯涌出量受煤层瓦斯含量、工作面产量和采煤方法等各种因素的影响 ,笔者通过研究得出 :回采工作面瓦斯涌出量与煤层的赋存条件和开采条件之间是一种非线性关系 ,但目前还难以用精确的数学建模来求解。因此 ,提出了一种应用BP人工神经网络模型和算法 ,建立工作面瓦斯涌出量预测模型 ,从而预测不同开采条件下回采工作面瓦斯涌出量。实际应用表明 ,模型精度能满足要求。笔者还对隐含层神经元数目对步长影响作了讨论。     

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。     

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.     

两类新型神经网络及其在安全评价中的应用

详细讨论小波神经网络(WNN)和模糊神经网络(FNN)的构造以及训练学习过程,并针对安全评价问题分别完成算例。典型算例表明:小波神经网络具有很好的逼近与映射能力,并且有很强的泛化能力;模糊神经网络将模糊数学与人工神经网络相互融合起来,有效提升了系统的智能功能。两类新型神经网络使得人-机-环境系统工程中的许多安全评价问题有了更广泛的量化工具,并具有安全评价的量化较准确的特点。     

Synthesis of CuO nanoparticles through green route using Citrus limon juice and its application as nanosorbent for Cr(VI) remediation: Process optimization with RSM and ANN-GA based model

In present investigation, an attempt has been made for the synthesis of cupric oxide nanoparticles (CuONPs) through a green route by utilizing lemon juice extract as a bioreductant. The synthesized CuONPs were characterized through UV–visible spectroscopy, Fourier-transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), field-emission scanning electron microscopy (FE-SEM) and transmission electron microscopy (TEM). The CuONPs were utilized for Cr(VI) removal from water through adsorption method in batch mode at different initial Cr(VI) concentration, pH, temperature and CuONPs dosage. The maximum uptake capacity of CuONPs was found to be 16.63 mg of Cr(VI)/g at pH 4.0. Implementation of response surface methodology (RSM) followed by artificial neural network hybridized with genetic algorithm (ANN-GA) approach has resulted maximum Cr(VI) adsorption of 98.8% under the optimized conditions of initial metal concentration 22.5 mg/L, pH 3.81, CuONPs dose 1.28 g/L and temperature 37.1 °C. Under optimum conditions, adsorption isotherm study was conducted, which showed that the fitness of experimental data was well achieved with Langmuir isotherm model illustrating monolayer pattern of adsorption. Thermodynamic study revealed that the process was spontaneous and endothermic in nature, while adsorption kinetics was best explained by pseudo-second order kinetic model.     

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.     

常州市燃气管网破坏的人工神经网络预测模型

作为一种高效清洁的能源,燃气已经成为城市能源中的重要一员,燃气管网破坏亦成为城市所面临的重大安全隐患。城市埋地燃气管网的破坏风险,往往受到多种影响因素的共同作用。通过分析常州市埋地燃气管网破坏的影响因素,确定了地面沉降、地裂缝、城市内涝、土壤腐蚀等4个风险评价因子。运用MATLAB中的人工神经网络工具,通过人工神经网络计算,优化了模型网络结构,建立了常州市埋地燃气管网破坏风险预测的人工神经网络模型。分析计算结果,并为常州市埋地燃气管网的安全防护提供了建议。     

An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines

A fast calculation of the reliability is meaningful to the in-line inspection of corroding natural gas pipelines. However, the traditional Monte Carlo simulation(MCS) method is time consuming for the low possibilities of the pipeline failure. The artificial neural network(ANN) is preferable for the complex nonlinear situation. An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines is proposed in this paper. To reduce the influence of training sets random behaviors on the calculation results, some algorithms are used to optimize the sequence of the training samples and the initial parameters of ANN models. The optimized model is applied to the reliability assessment of a corroded pipe with two successive inline inspections. According to the physical parameters of the pipeline, the trend of corroding pipeline reliability in time is predicted. The comparison between the trained ANN model, the MCS method and non-optimized ANN model shows the advantages the proposed modeling process. The methodology given in this paper is general and it can be applied to evaluate the reliability of other kind of structure safeties in practical systems.