粒子群优化算法在源强反算问题中的应用研究

在危险化学品泄漏事故中泄漏源强是预测事故后果的主要影响参数,也是事故应急救援决策的基础。为了在化学品泄漏事故过程中快速准确地获取泄漏源强数据,将粒子群优化(PSO)算法应用于危险化学品泄漏源强的反算中。利用高斯烟羽扩散模型和下风向浓度测量数据,将计算浓度与测量浓度的误差平方和作为目标函数,采用粒子群算法来优化,以确定源强并通过模拟的测量浓度数据进行算法有效性验证。结果表明,PSO算法及其参数改进算法不依赖于初值的选择,计算速度快,能满足事故应急响应救援的需要。     

基于粒子群优化的DGM（1,1）模型在基坑变形安全预测中的研究

为确保基坑施工期间发生变形后能够正常使用,将变权缓冲算子结合DGM(1,1)模型构造出变权离散灰色模型,利用相对误差、后验差比,灰色绝对关联度3种精度检验法作为粒子群算法适应度建立模型,构造PSO-VWDGM(1,1)模型,并结合实际工程监测数据研究不同适应度对基坑变形预测精度的影响。研究结果表明:不同适应度函数对预测精度存在较大影响,以灰色绝对关联度作为适应度建立模型预测精度较高,可以更好应用在工程中。研究成果可为工程施工阶段的基坑变形预测、稳定性分析与灾害评估、预警提供参考。     

粒子群优化的RBF瓦斯涌出量预测

瓦斯涌出量是煤矿瓦斯灾害的主要来源,它直接影响煤矿安全生产和经济技术指标。瓦斯涌出量的传统预测方法是将其影响因素线性化后提出的,具有一定的局限性。本文基于群体智能理论,提出了一种基于粒子群算法优化的RBF神经网络瓦斯涌出量预测模型。研究表明RBF神经网络预测精度与网络权值和RBF参数初始值有很大关系,因此本文采用粒子群算法优化RBF网络权值和其他参数,形成PSO-RBF预测模型。该模型通过计算种群粒子的适应度,确定全局最优值,寻找网络参数的最优值。实验结果表明PSO-RBF优于传统的RBF预测模型,训练速度和预测精度显著提高。     

基于改进多目标粒子群算法的航空器改航研究

针对影响航行安全的动态危险天气,提出了一种基于改进多目标粒子群算法的改航路径规划方法。首先,获取实时动态气象数据,利用栅格法对改航环境进行建模并采集危险天气区域初始边界点的历史气象数据。然后采用灰色预测模型对上述初始边界点坐标进行位置预测,进而建立改进后的实时动态环境模型。最后利用改进环境模型的多目标粒子群算法对改航路径进行动态规划。在考虑改航路径角度和距离等约束条件的基础上,确定了改航路径危险系数和距离最优的双目标函数。对中东部沿海某次短时危险天气下的航空器改航进行仿真分析,仿真结果表明改进后算法具有一定的有效性和可行性。     

基于Multi-class SVM的车辆换道行为识别模型研究

自动安全换道是车辆实现无人驾驶的关键,为精确识别行驶车辆换道状态,保证行车安全,设计了一种基于多分类支持向量机(Multi-class Support Vector Machine,Multiclass SVM)的车辆换道识别模型。从NGSIM数据集中选取美国101公路车辆轨迹数据进行分类处理,并将车辆换道过程划分为车辆跟驰阶段、车辆换道准备阶段和车辆换道执行阶段。采用网格搜索结合粒子群优化算法(Grid Search-PSO)对SVM模型中惩罚参数C和核参数g进行寻优标定,利用多分类支持向量机换道识别模型对样本数据进行训练和测试,模型测试精度达97.68%。研究表明,模型能够很好地识别车辆在换道过程中的行为状态,为车辆换道阶段的研究提供支持。     

A prediction model for the flash point of binary liquid mixtures

A prediction model based on the partial least squares of the multivariate statistical analysis methods was developed for the flash point (FP) of binary liquid mixtures. Estimation of the FP of flammable substances is important for safety measures in industrial processes. Since experimental FP data of liquid mixtures are scarce in the literature, there have been many researches to estimate the FP of liquid mixtures using physicochemical laws. In this study, the partial least squares (PLS) method using experimental data was used as a prediction model of the FP of binary liquid mixtures. The FPs predicted from the PLS method were also compared to results from the existing calculating methods using physicochemical laws such as Raoult's law and the Van Laar equation.     

故障树法和改进PSO-PNN网络的电梯故障诊断模型

针对电梯故障问题,提出一种将故障树分析法、改进的粒子群优化算法和概率神经网络相结合的方法用于电梯的故障诊断。以电梯的安全回路系统为例,用故障树法对回路进行分析,获得训练样本与故障类型;使用粒子群算法对概率神经网络的平滑因子进行优化,在优化过程中,针对粒子群算法存在易陷入局部最优的缺陷,提出对惯性权重的改进策略;采用相对误差对诊断效果做出评估,并与传统的概率神经网络和基本粒子群算法优化的概率神经网络在各种故障类型输出和最大相对误差等方面进行比较,结果表明:该模型能够有效诊断电梯故障。     

基于PSO-SVM模型的隧道水砂突涌量预测研究

复杂工程地质条件下,隧道水砂混合物突涌的预测防控是隧道安全建设的基础,准确预测水砂混合物突涌量,为工程提供安全保障至关重要。为提高预测准确性,提出一种基于粒子群算法优化的支持向量机(PSO-SVM)的隧道水砂突涌量预测模型。综合考虑地质构造、气象条件、施工影响三类因素,选取七个因子,结合某公路隧道,利用PSO-SVM建立隧道水砂突涌量预测模型,并对该隧道水砂突涌量进行预测,结果与实际突涌量一致。证实综合粒子群算法和支持向量机优势的PSO-SVM方法预测精度高,且易于实现,为类似隧道工程突涌预测提供参考与借鉴。     

An improved grey wolf optimizer algorithm for identification and location of gas emission

Identification of the leakage of hazardous gases plays an important role in the environment protection, human health and safety of industry production. However, lots of current optimization algorithms, such as particle swarm optimization (PSO) and Grey Wolf Optimizer (GWO), suffer from poor global optimization capability and estimation accuracy. In this work, a hybrid differential evolutionary and GWO (DE-GWO) algorithm is proposed. Tested by simulation cases and Prairie Grass emission experimental data, DE-GWO shows higher estimation accuracy than GWO. Compared with the other four optimization algorithms, DE-GWO exhibits finer robust stability under different population sizes, fewer iterations, as well as higher estimation accuracy with fewer search agents. Importantly, simulation results demonstrate that DE-GWO is more suitable to apply in the scene with a small number of sensors. Therefore, the proposed in this paper outperforms other optimization algorithms for the gas emission inverse problem. DE-GWO can provide reliable estimation towards gas emission identification and positioning, which shows huge potential as the data analysis module of real-time monitoring and early warning system.     

基于IPSO-BP模型的火灾气体传感器气压补偿算法

为完善飞机火灾检测系统,设计一套方案,模拟试验不同气压下CO、CO2气体传感器采集气体的体积分数值,并与理论值比较,进而提出一种根据粒子适应度值动态调整学习因子的粒子群算法.采用改进的粒子群(IPSO)算法寻找反向传播(BP)神经网络的最优初始权值阈值,再利用寻优后的BP神经网络修正CO、CO2气体传感器的检测结果,消...     

基于支持向量机的化工工艺安全评价模型构建及优化研究*

为解决现阶段基于风险分级的安全评价方法仍存在着高维数据处理不当、评价智能化程度不高等问题,创建支持向量机的安全评价模型,利用核函数解决安全评价因子分类问题,粒子群算法（PSO）寻找最适合模型的正则项C,进一步提升安全评价模型的正确率,形成适用高维数据的化工工艺安全评价方法。研究结果表明:该模型与经典支持向量机模型和BP神经网络评价模型相比具有更高的正确率,研究结果对借用机器学习来创新安全评价理论及工程应用具有现实意义及理论价值。     

基于改进型萤火虫群优化算法泄漏源源强及位置反算研究*

针对标准萤火虫群优化算法（GSO）在危化品泄漏源源强及位置反算中存在精度不高,容易陷入局部最优等局限,提出混合萤火虫-Nelder Mead单纯形算法（GSO-NM）,并与基于步长的改进萤火虫群优化算法（MGSO）以及单纯形搜索混合协同进化萤火虫群优化算法（HCGSOSSM）进行比较分析,将3种改进型萤火虫群优化算法应用于泄漏源源强及位置反算中进行比较分析。研究结果表明:GSO-NM算法可以有效提高定位精度和稳定性,能较为精确地反算出泄漏源源强及位置,为泄漏源源强及位置反算研究提供1种新思路。     

Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines

Rockburst possibility prediction is an important activity in many underground openings design and construction as well as mining production. Due to the complex features of rockburst hazard assessment systems, such as multivariables, strong coupling and strong interference, this study employs support vector machines (SVMs) for the determination of classification of long-term rockburst for underground openings. SVMs is firmly based on the theory of statistical learning algorithms, uses classification technique by introducing radial basis function (RBF) kernel function. The inputs of models are buried depth H, rocks’ maximum tangential stress σ_θ, rocks’ uniaxial compressive strength σ_c, rocks’ uniaxial tensile strength σ_t, stress coefficient σ_θ/σ_c, rock brittleness coefficient σ_c/σ_t and elastic energy index W_et. In order to improve predictive accuracy and generalization ability, the heuristic algorithms of genetic algorithm (GA) and particle swarm optimization algorithm (PSO) are adopted to automatically determine the optimal hyper-parameters for SVMs. The performance of hybrid models (GA + SVMs = GA-SVMs) and (PSO + SVMs = PSO-SVMs) have been compared with the grid search method of support vector machines (GSM-SVMs) model and the experimental values. It also gives variance of predicted data. A rockburst dataset, which consists of 132 samples, was employed to evaluate the current method for predicting rockburst grade, and the good results of overall success rate were obtained. The results indicated that the heuristic algorithms of GA and PSO can speed up SVMs parameter optimization search, the proposed method is robust model and might hold a high potential to become a useful tool in rockburst prediction research.     

IAFSA-GRNN在油田集输管道CO2腐蚀速率预测中的应用

为提高油田集输管道CO₂腐蚀速率预测的准确性,针对原始广义回归神经网络(GRNN)预测精度低的问题,提出改进的群智能算法优化原始GRNN的预测模型;分别使用GRNN模型、人工鱼群算法(AFSA)优化的GRNN(AFSA-GRNN)模型和自适应改进的AFSA-GRNN(IAFSA-GRNN)模型预测X65管线钢的CO₂腐蚀速率。结果表明:采用AFSA和IAFSA优化光滑因子S后,能大大提高GRNN模型的预测精度,预测结果的平均相对误差由36.09%分别减小至7.20%和6.90%;与AFSA相比,IAFSA优化的GRNN不仅具有更高的预测精度,还具有更快的收敛速度。AFSA-GRNN在第164次迭代计算时收敛,而IAFSA-GRNN在第109次迭代计算时收敛,说明AFSA经自适应优化能提高优化过程的收敛速度和GRNN的预测精度。     

Optimization of gas detector placement considering scenario probability and detector reliability in oil refinery installation

Gas detection system is a critical layer of protection in process safety. Leak scenario probability and detector reliability are two key factors in the optimization of gas detector placement. However, they are easily neglected in previous studies, which may lead to an inaccurate evaluation of the optimization solutions. In this study, a stochastic programming (SP) optimization method is proposed considering these two factors. In order to quantitatively represent the probability of leak scenarios, a complete accident scenario set (CASS) is built combining leak sources and wind fields. Then, the computational fluid dynamics (CFD) method is adopted for consequence modeling of gas dispersion. The Markov model is developed to predict the detector reliability. With the objective of minimal cumulative detection time (MCDT), the SP formulation considering scenario probability and detector reliability (MCDT-SPR) is proposed. By introducing the particle swarm optimization (PSO) algorithm, the optimization formulations can be solved. A case study is investigated on a diesel hydrogenation refining unit. Results validate this approach is promising to improve the detection efficiency. This method is more practical and matching with the actual industrial environment, where the leak scenarios and the detector reliability can change dynamically in real process setting.     

Prediction of gas explosion pressures: A machine learning algorithm based on KPCA and an optimized LSSVM

A gas explosion, as a common accident in public life and industry, poses a great threat to the safety of life and property. The determination and prediction of gas explosion pressures are greatly important for safety issues and emergency rescue after an accident occurs. Compared with traditional empirical and numerical models, machine learning models are definitely a superior approach. However, the application of machine learning in gas explosion pressure prediction has not reached its full potential. In this study, a hybrid gas explosion pressure prediction model based on kernel principal component analysis (KPCA), a least square support vector machine (LSSVM), and a gray wolf optimization (GWO) algorithm is proposed. A dataset consisting of 12 influencing factors of gas explosion pressures and 317 groups of data is constructed for developing and evaluating the KPCA-GWO-LSSVM model. The results show that the correlations among the 12 influencing factors are eliminated and dimensioned down by the KPCA method, and 5 composite indicators are obtained. The proposed KPCA-GWO-LSSVM hybrid model performs well in predicting gas explosion pressures, with coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE) values of 0.928, 26.234, and 12.494, respectively, for the training set; and 0.826, 25.951, and 13.964, respectively, for the test set. The proposed model outperforms the LSSVM, GWO-LSSVM, KPCA-LSSVM, beetle antennae search improved BP neural network (BAS-BPNN) models and reported empirical models. In addition, the sensitivity of influencing factors to the model is evaluated based on the constructed database, and the geometric parameters X1 and X2 of the confined structure are the most critical variables for gas explosion pressure prediction. The findings of this study can help expand the application of machine learning in gas explosion prediction and can truly benefit the treatment of gas explosion accidents.     

Simulation-based fault propagation analysis—Application on hydrogen production plant

Recently production of hydrogen from water through the Cu–Cl thermochemical cycle is developed as a new technology. The main advantages of this technology over existing ones are higher efficiency, lower costs, lower environmental impact and reduced greenhouse gas emissions. Considering these advantages, the usage of this technology in new industries such as nuclear and oil is increasingly developed. Due to hazards involved in hydrogen production, design and implementation of hydrogen plants require provisions for safety, reliability and risk assessment. However, very little research is done from safety point of view. This paper introduces fault semantic network (FSN) as a novel method for fault diagnosis and fault propagation analysis by using evolutionary techniques like genetic programming (GP) and neural networks (NN), to uncover process variables’ interactions. The effectiveness, feasibility and robustness of the proposed method are demonstrated on simulated data obtained from the simulation of hydrogen production process in Aspen HYSYS^®. The proposed method has successfully achieved reasonable detection and prediction of non-linear interaction patterns among process variables.     

基于改进PSO-BPNN的输油管道内腐蚀速率研究

为解决输油管道易腐蚀,且腐蚀程度难以测量的问题,提出使用改进的粒子群算法（PSO）优化误差反向传播神经网络（BPNN）对输油管道内腐蚀速率进行预测。改进的PSO算法提升了自身搜索到全局最优的能力,可为BPNN提供最优初始权值和阈值,从而有效避免BPNN易陷入局部最优的问题发生。以某条输油管线为例,分别运用标准的BPNN模型、PSO-BPNN以及改进的PSO-BPNN对该管线内腐蚀速率进行预测。结果表明:基于改进的PSO-BPNN的预测结果平均相对误差为5.57%,预测精度较BPNN和PSO-BPNN有明显提升。使用改进的PSO-BPNN预测输油管道的腐蚀速率可为管道的检测维修提供可靠的理论和技术支撑。     

Study of chemical supply system of high-tech process using inherently safer design strategies in Taiwan

The photoelectric, semiconductor and other high-tech industries are Taiwan's most important economic activities. High-tech plant incidents are caused by hazardous energy, even when that energy is confined to the inside of the process machine. During daily maintenance procedures, overhauling or troubleshooting, engineers entering the interior of the machines are in direct contact with the source of the energy or hazardous substances, which can cause serious injury. The best method for preventing such incidents is to use inherently safer design strategies (ISDs); this approach can fully eliminate the dangers from the sources of hazardous energy at a facility.This study first conducts a lithography process hazard analysis and compiles a statistical analysis of the causes of the fires and losses at high-tech plants in Taiwan since 1996, the aim being to establish the necessary improvement measures by using the Fire Dynamics Simulation (FDS) to solve relevant problems. The researchers also investigate the lithography process machine in order to explore carriage improvement measures, and analyse the fires' causes and reactive materials hazardous properties, from 1996 to 2012. The effective improvement measures are established based on the accident statistics. The study site is a 300 mm wafer fabrication plant located in Hsinchu Science Park, Taiwan.After the completion of the annual maintenance jobs improvement from September 2011 to December 2012, the number of lithography process accidents was reduced from 6 to 1. The accident rate was significantly reduced and there were no staff time losses for a continuous 6882 h. It is confirmed that the plant safety level has been effectively enhanced. The researchers offer safety design recommendations regarding transport process appliances, chemical storage tanks, fume cupboard devices, chemical rooms, pumping equipment, transportation pipelines, valve manual box (VMB) process machines and liquid waste discharge lines. These recommendations can be applied in these industries to enhance the safety level of high-tech plants, facilities or process systems.