Optimization of HSE in maintenance activities by integration of continuous improvement cycle and fuzzy multivariate approach: A gas refinery

Gas refineries have been continuously focusing on Health, Safety and Environment programs to improve maintenance activities. Several researches have studied on this area with different analysis methods. This study presents an integrated approach for optimization of factors contributing to the implementation of Health, Safety and Environment (HSE) in maintenance activities. HSE managers in each sector answered standard questionnaire whit respect to HES. The methodology is based on fuzzy data envelopment analysis (FDEA) and Deming's continuous improvement cycle. Also, this method is used to rank the relevant performance efficiencies in certain and uncertain conditions of each HSE sectors whit considering HSE in maintenance activities. It corresponds and integrates its registered HSE-MS with OHSAS 18001:2007 and ISO 14001:2004 to evaluate multiple inputs and outputs of over 36 subsidiary HSE divisions with parallel mission and objectives simultaneously. Also, it determines efficient target indices and could assure continuous improvement in the organization. This is the first study that introduces an integrated approach to improve HSE management programs in a gas refinery by a robust and continuous improvement approach.     

A new practical approach to risk management for underground mining project in Quebec

The mining industry worldwide is currently experiencing an economic boom that is contributing to economic recovery and social progress in many countries. For this to continue, the mining industry must meet several challenges associated with the start-up of new projects. In a highly complex and uncertain environment, rigorous management of risks remains indispensable in order to repel threats to the success of mining.In this article, a new practical approach to risk management in mining projects is presented. This approach is based on a novel concept called “hazard concentration” and on the multi-criteria analysis method known as the Analytic Hierarchy Process (AHP). The aim of the study is to extend the use of this approach to goldmines throughout Quebec. The work is part of a larger research project of which the aim is to propose a method suitable for managing practically all risks inherent in mining projects.This study shows the importance of taking occupational health and safety (OHS) into account in all operational activities of the mine. All project risks identified by the team can be evaluated. An adaptable database cataloguing about 250 potential hazards in an underground goldmine was constructed. In spite of limitations, the results obtained in this study are potentially applicable throughout the Quebec mining sector.     

多因素耦合条件下硫化矿自燃神经网络动态预测模型研究

硫化矿石自燃是多种因素、多场耦合综合作用的结果,是一典型的非线性问题。笔者应用人工神经网络技术,以Matlab软件为平台,通过现场调查和理论分析,建立了矿石含硫量、通风强度、环境温度3因素与硫化矿石自燃之间的预测模型;通过数据样本学习与部分现场监测数据相结合进行模拟,研究表明预测数据与实测结果基本吻合,误差控制在10%以内,取得了较好的效果。该研究为预防硫化矿石自燃提供一个新的思路和方法,具有一定的理论意义和应用价值。     

基于神经网络的尘肺病预测模型研究

针对尘肺病对人体的危害这一现实,本文通过建立神经元网络模型,开发了神经元网络预测系统,利用预测模块对获得的尘肺病发病数据进行了学习并以此形成了稳定的预测模式,以某矿尘肺病发病情况为例进行了评价;结果表明神经元网络模型克服了传统预测模型须建立函数的难题,且预测精度较度,具有重要理论与实际应用价值.     

A new approach for layout optimization in maintenance workshops with safety factors: The case of a gas transmission unit

In this study, an Integrated Simulation-Data Envelopment Analysis (DEA) approach is presented for optimum facility layout of maintenance workshop in a gas transmission unit. The process of repair of incoming parts includes various operations on different facilities. The layout problem in this system involves determining the optimum location of all maintenance shop facilities. Layout optimization plays a crucial role in this type of problems in terms of increasing the efficiency of main production line. Standard types of layouts including U, S, W, Z and straight lines are considered. First, the maintenance workshop is modeled with discrete-event-simulation. Time in system, average waiting time, average machine utilization, average availability of facilities, average queue length of facilities (AL) and average operator utilization are obtained from simulation as key performance indicators (KPIs) of DEA. Also, safety index and number of operators are considered as other KPIs. Finally, a unified non-radial Data Envelopment Analysis (DEA) is presented with respect to the stated KPIs to rank all layouts alternatives and to identify the best configuration. Principle Component Analysis (PCA) is used to validate and verify the results. Previous studies do not consider safety factor in layout design problems. This is the first study that presents an integrated approach for identification of optimum layout in a maintenance workshop of gas transmission unit by incorporating safety and conventional factors.     

基于粗糙集——粒子群神经网络的建设项目安全预测研究

回顾施工项目安全管理和安全管理研究现状,建立建设项目安全管理指标体系。利用人工神经网络非线性函数逼近能力,对项目风险因素程度预测。针对该网络当数据量大时,其结构复杂、收敛慢,易陷入局部最优的缺点,引入粗糙集对影响建设项目安全目标的不确定性因素进行约简,找出最小不确定性风险因素集,大大简化网络输入信息的表达空间维数。并结合粒子群算法收敛速度快、全局最优的寻优能力强的优点,建立基于粗糙集——粒子群神经网络的建设项目安全预测系统。通过实例验证该系统的科学性和有效性。     

Fuzzy fault tree analysis for fire and explosion of crude oil tanks

Crude oil tank fire and explosion (COTFE) is the most frequent type of accident in petroleum refineries, oil terminals or storage which often results in human fatality, environment pollution and economic loss. In this paper, with fault tree qualitative analysis technique, various potential causes of the COTFE are identified and a COTFE fault tree is constructed. Conventional fault tree quantitative analysis calculates the occurrence probability of the COTFE using exact probability data of the basic events. However, it is often very difficult to obtain corresponding precise data and information in advance due to insufficient data, changing environment or new components. Fuzzy set theory has been proven to be effective on such uncertain problems. Hence, this article investigates a hybrid approach of fuzzy set theory and fault tree analysis to quantify the COTFE fault tree in fuzzy environment and evaluate the COTFE occurrence probability. Further, importance analysis for the COTFE fault tree, including the Fussell–Vesely importance measure of basic events and the cut sets importance measure, is performed to help identifying the weak links of the crude oil tank system that will provide the most cost-effective mitigation. Also, a case study and analysis is provided to testify the proposed method.     

Classification technique for danger classes of coal and gas outburst in deep coal mines

In this investigation a new classification technique based on artificial neural network (ANN) and exponent evaluation method (EEM) has been developed to classify the danger classes of coal and gas outburst in deep mines. A weight computing model of mutual affecting factors is derived from backward algorithm of ANN (BA-ANN), which diminishes the influence of factitious factor, the environment factor and the time factor to the weight. The BA-ANN model is used for modeling the correlation between danger class and 12 affecting factors of coal and gas outburst and calculating weights of interconnection factors, which performs very well. In order to classify danger classes in a daily routine, the EEM with the well trained weights which are from BA-ANN, is performed in a deep mine. The case study shows that this new technique is useful to classify danger classes with quick and accurate computation. Moreover, the weight computing model of BA-ANN can be extended to other safety issue in different fields as well.     

Assessment and improvement of integrated HSE and macro-ergonomics factors by fuzzy cognitive maps: The case of a large gas refinery

This study analyzes and assesses the integrated health, safety, environment (HSE) and ergonomics (HSEE) factors by fuzzy cognitive maps (FCM) approach. This is achieved through integrating ergonomic and macro-ergonomic as well as occupational health and safety arrangements in an integrated modeling for assessment of their multi-faceted impact on workers' productivity, injury rate and satisfaction. This paper uses FCM to assess the direct and indirect effects of HSEE factors on system performance indicators. The results of FCM are used to develop leading indicators useful for proactive management of productivity, injury rate, and job satisfaction. The result of a comprehensive survey of 37 experts in control rooms and maintenance activities in a large gas refinery is used to show the applicability and usefulness of FCM approach. Moreover, FCM results are used to determine the causal structure of HSEE factors and system performance indicators. It is concluded that macro-ergonomics factors such as instructions and education, familiarity with organization's rules, and proper communications most contribute to improve workers' safety, satisfaction, and productivity.     

Applying Hierarchical Loglinear Models to Nonfatal Underground Coal Mine Accidents for Safety Management

Underground mining is considered to be one of the most dangerous industries and mining remains the most hazardous occupation. Categorical analysis of accident records may present valuable information for preventing accidents. In this study, hierarchical loglinear analysis was applied to occupational injuries that occurred in an underground coal mine. The main factors affecting the accidents were defined as occupation, area, reason, accident time and part of body affected. By considering subfactors of the main factors, multiway contingency tables were prepared and, thus, the probabilities that might affect nonfatal injuries were investigated. At the end of the study, important accident risk factors and job groups with a high probability of being exposed to those risk factors were determined. This article presents important information on decreasing the number accidents in underground coal mines.     

作业条件危险性评价法在深水钻完井作业评价中的应用研究

深水钻完井作业长期暴露于危险环境中,被普遍认为是高危作业。同时深水事故的发生给人类带来深刻的教训,例如墨西哥漏油事件造成恶劣的海洋环境污染,有必要提高钻完井作业的安全性。由于深水钻完井作业复杂,其危险性复杂多样,需从作业单元入手详细分析其危险性。本文采用作业条件危险性评价法（LEC）对深水钻完井作业进行危险性评价。首先,辨识危险有害因素;其次,在对作业条件危险性评价法进行改进的基础上分析深水油气田钻完井作业火灾爆炸危险性。分析结果表明改进后的作业条件危险性评价法能够更准确地确定危险等级,为对深水钻完井作业其它危险因素评价提供了参考。     

基于EMD-MFOA-ELM的瓦斯涌出量时变序列预测研究

为准确分析工作面绝对瓦斯涌出量的非平稳特征,实现瓦斯涌出量的准确预测,基于经验模态分解(EMD)、修正的果蝇优化算法(MFOA)和极限学习机(ELM)基本原理,构建瓦斯涌出量的EMD-MFOA-ELM多尺度时变预测模型。通过EMD将瓦斯涌出量时变序列进行深层次分解,获得多尺度本征模态函数(IMF);采用MFOA-ELM对各IMF时变序列建立动态预测模型,等权叠加各预测值,得到模型最终预测结果。以晋煤某矿瓦斯涌出量监测时序样本为例进行研究分析,结果表明:EMD能充分挖掘出监测数据隐含信息,有效降低数据复杂度;该模型预测相对误差为0.024 3%~0.651 0%,平均值仅为0.252 6%,预测精度和泛化能力高于未经EMD分解模型,能很好地适用于非平稳时变序列预测。     

Risk assessment of sour gas inter-phase onshore pipeline using ANN and fuzzy inference system – Case study: The south pars gas field

Nowadays, pipelines have been extensively used for transporting oil and gas for long distances. Therefore, their risk assessment could help to identify the associated hazards and take necessary actions to eliminate or reduce the risk. In the present research, an artificial neural network (ANN) and a fuzzy inference system (FIS) were used to prepare a new model for pipeline risk assessment with higher accuracy. To reach this objective, the Muhlbauer method, as a common method for oil and gas pipeline risk assessment, was used for determining important and influential factors in the pipeline performance. Mamdani fuzzy model was developed in Matlab software by considering expert knowledge. The outcomes of this model were used to develop an ANN. To verify the developed model, the inter-phase shore pipe of phase 9–10 refinery in the South Pars Gas field was considered as a case study. The results showed that the proposed model gives a higher level of accuracy, precision, and reliability in terms of pipe risk assessment.     

An intelligent algorithm for performance evaluation of job stress and HSE factors in petrochemical plants with noise and uncertainty

This study presents an intelligent algorithm based on Adaptive Neuro-Fuzzy Inference System (ANFIS) and statistical methods for measuring job stress in noisy and complex petrochemical plants. Job stress is evaluated against health, safety, environment and ergonomics (HSEE) program in the integrated algorithm. The algorithm is composed of seventeen distinct steps. To achieve the objectives of this study, standard questionnaires with respect to HSEE are completed by operators. The average results for each category of HSEE are used as inputs and job stress is used as output for the algorithm. Moreover, operators' stress level with respect to HSEE is evaluated by the algorithm. Finally, operators with weak stress level are identified. The advantage and superiority of the intelligent algorithm are shown by error analysis in contrast with conventional regression approaches. This is the first study that introduces an integrated intelligent algorithm for assessment and improvement of job stress and HSEE in noisy, complex and uncertain environment.     

建设项目安全管理的智能化技术研究

明确建设项目安全管理的意义;简述建设项目安全管理技术的国内外研究现状;指出当前的建设项目安全管理研究存在的主要不足;提出笔者研究的思路和研究的主要内容;收集详细的施工现场资料,参考相关历史文献资料,提取可能引起安全事故的原始不确定风险因素,建立安全管理风险评价指标体系;并利用人工神经网络(ANN)强大的非线性函数逼近能力,将BP神经网络引入建设项目风险控制,构建基于BP神经网络的建设项目安全控制系统,从而实现建设项目安全管理的智能化。通过工程实例验证:该方法具有可行性和有效性,为实现建设项目安全管理目标及工期、成本、质量目标打下坚实的基础。     

Measuring and analyzing adaptive capacity at management levels of resilient systems

Resilience engineering (RE) is capable of handling disruptive events and controlling their consequences in process industries such as petrochemical plants. This study aims at analyzing the level of adaptive capacity and identifying effective factors on developing adaptive capacity in the organizational structure of process industries. The data of this study were obtained through direct observation and a structured questionnaire in a petrochemical plant. Managers at all levels participated in the survey. Data envelopment analysis (DEA), which is a mathematical approach, was used to compute and analyze the role of the factors contributing to adaptive capacity. The results indicated that reporting safety issues played a central role in enhancing adaptive capacity at all management levels. Both middle management and low-level management emphasized the importance of management commitment, whereas top-level management considered flexibility as a vital factor in managing disruptions and reducing accidents. The findings of this study could be useful for managers and other decision-makers to improve safety in process industries.     

基于AHP与重要性指标筛选的神经网络评价模型与应用

以对评价目标有影响的所有评价指标作为神经网络的输入,会导致网络模型复杂、降低其性能和影响计算精度的问题,因而提出基于层次分析法和重要性指标筛选法的神经网络评价建模方法即首先运用层次分析法对评价指标进行重要度排序,然后利用重要性指标筛选法过滤出对评价目标有重要影响的指标,以其结果作为神经网络的输入。该法不仅简化网络模型,而且提高网络的性能和计算精度。运用该法对企业安全工作评价,结果证明,不仅是可行的,而且达到了预期的目的。     

建设项目职业病危害预评价方法探讨

目前,建设项目职业病危害预评价方法比较单一,只能反映拟建项目在职业病危害方面与现行法规、标准的符合程度,并不能对项目进行全面、动态的评估,也无法评价职业危害事故风险。通过分析环境影响评价、安全评价中相关的评价方法在评价职业病危害因素分布、长期作用的影响、危害分级、事故风险等方面的优势,探讨其在建设项目职业病危害预评价中的应用。笔者提出,合理借鉴环境影响评价、安全评价方法,可拓展职业病危害预评价的深度和广度,在拟建项目职业病防治、建设项目职业危害分级管理和职业危害事故防范等方面都具有积极的指导作用。     

Possibilistic regression analysis of influential factors for occupational health and safety management systems

The code of occupational health and safety (OHS) is an influential regulation to improve the on-the-job safety of employees. A number of factors influence the planning and implementation of OHS management systems (OHSMS). The evaluation of OHSMS practice is the most important component when forming a health and safety environmental policy for employees. The objective of this research is to develop an intelligent data analysis (IDA) in which possibilistic regression being endowed with a convex hull approach is used to support the analysis of essential factors that influence OHSMS. Given such subjective terms, the obtained samples can be conveniently regarded as fuzzy input/output data represented by membership functions. The study offers this vehicle of intelligent data analysis as an alternative to evaluate the influential factors in a successful implementation of OHS policies and in this way decrease an overall computational effort. The obtained results show that several related OHSMS influential factors need to be carefully considered to facilitate a successful implementation of the OHSMS procedure.