A machine learning‐based operational control framework for reducing energy consumption of an amine‐based gas sweetening process

This study proposes a data‐driven operational control framework using machine learning‐based predictive modeling with the aim of decreasing the energy consumption of a natural gas sweetening process. This multi‐stage framework is composed of the following steps: (a) a clustering algorithm based on Density‐Based Spatial Clustering of Applications with Noise methodology is implemented to characterize the sampling space of all possible states of the operation and to determine the operational modes of the gas sweetening unit, (b) the lowest steam consumption of each operational mode is selected as a reference for operational control of the gas sweetening process, and (c) a number of high‐accuracy regression models are developed using the Gradient Boosting Machines algorithm for predicting the controlled parameters and output variables. This framework presents an operational control strategy that provides actionable insights about the energy performance of the current operations of the unit and also suggests the potential of energy saving for gas treating plant operators. The ultimate goal is to leverage this data‐driven strategy in order to identify the achievable energy conservation opportunity in such plants. The dataset for this research study consists of 29 817 records that were sampled over the course of 3 years from a gas train in the South Pars Gas Complex. Furthermore, our offline analysis demonstrates that there is a potential of 8% energy saving, equivalent to 5 760 000 Nm³ of natural gas consumption reduction, which can be achieved by mapping the steam consumption states of the unit to the best energy performances predicted by the proposed framework.     

基于改进熵权法的多元状态估计模型在汽轮机能效监测中的应用

为了提高汽轮机能耗预警水平,将多变量状态估计技术(MSET)作为汽轮机能效监测的数据挖掘方法,在完成不同工况机组能耗水平分类的基础上,利用改进的熵权法计算能效偏离度。将偏离度和警报阈值结合来判断汽轮机运行工况水平,及时获取能耗时间点,并定位引起能耗异常的特征参数,该方法克服了单一热耗率指标评价能效变化的局限性。以某电站600 MW机组的汽轮机历史运行数据为研究对象,借助聚类算法完成汽轮机热耗分类,以最佳热耗率所在类簇的部分运行数据作为训练样本建立MSET能耗模型,并完成模型正确性验证。利用剩余类簇在能耗模型下实际观测值和模型估计值的偏差,并结合信息熵权法分配与热耗相关的特征参数属性权重,计算获得偏离度指数,完成汽轮机能耗异常预警。结果表明：该方法可以为汽轮机能效异常变化提供及时的预警信息并定位导致能耗异常的参数。     

Hybrid intelligent strategy for multifactor influenced electrical energy consumption forecasting

ABSTRACT

This paper proposes a novel hybrid strategy based on intelligent approaches to forecast electricity consumptions. The proposed forecasting strategy includes three main steps: (a) the evaluation of a correlation coefficient for socio-economic indicators on electric energy consumptions, (b) the classification of historical and socio-economic indicators using the proposed feature selection method, (c) the development of a new combined method using Adaptive Neuro-Fuzzy Inference System and Whale Optimization Algorithm to predict electrical energy consumptions. The simulation results have been tested and validated by real data sets achieved within 1992 and 2010 in two pilot cases in a developing country (Iran) and a developed one (Italy). The research findings pinpointed the greater accuracy and stability of the new developed method for electrical energy consumption forecasting compared to existing single and hybrid benchmark models.     

A data-driven approach for steam load prediction in buildings

Predicting building energy load is important in energy management. This load is often the result of steam heating and cooling of buildings. In this paper, a data-driven approach for the development of a daily steam load model is presented. Data-mining algorithms are used to select significant parameters used to develop models. A neural network (NN) ensemble with five MLPs (multi-layer perceptrons) performed best among all data-mining algorithms tested and therefore was selected to develop a predictive model. To meet the constraints of the existing energy management applications, Monte Carlo simulation is used to investigate uncertainty propagation of the model built by using weather forecast data. Based on the formulated model and weather forecasting data, future steam consumption is estimated. The latter allows optimal decisions to be made while managing fuel purchasing, scheduling the steam boiler, and building energy consumption.     

广东省温室气体减排综合评价模型研究

国外能源模型一般是在发达国家的市场经济基础上开发的,比较适合于市场体系较为完善的国家和地区的能源系统的模拟和预测。中国对能源与环境进行系统建模研究起步较晚,然而还是取得了较大的成果,但省域级别的能源环境经济模型的研究还比较少,尤其是对于像广东省这样经济发展很快,而资源、能源十分匮乏的省份,能源对经济发展的"瓶颈"作用特别突出,因此开展省级能源经济模型研究意义十分重大。利用日本京都大学和国立环境研究所开发的综合模型工具ExSS,建立了适合广东省实际情况的能源与环境评价模型,并设定三种情景,应用模型对广东省2015年的能源消费量、能源结构和温室气体排放进行预测。三种情景分别是基准情景、政策情景和低碳情景。2015年基准情景、政策情景和低碳情景的能源消费量分别为3.4×108t标煤、3.2×108t标煤和3.1×108t标煤;三种情景下二氧化碳排放量分别为6.4×108t、5.6×108t和5.1×108t。广东省在"十二五"期间应加大力度调整能源结构,增加天然气的使用量,减少煤炭的使用,使煤炭的消耗比例控制在合理范围内。     

A new modeling and solution method for optimal energy flow in electricity‐gas integrated energy system

With the increasing interdependency of electricity and gas, it is necessary to simultaneously investigate electric power system and natural gas system from the perspective of an electricity‐gas integrated energy system (EGIES). As an extension and integration of both optimal power flow (OPF) and optimal gas flow (OGF), optimal energy flow (OEF) is regarded as the cornerstone of the EGIES and lays an essential foundation for further research on the EGIES's operation and analysis considering stochastic conditions and contingency states. The objective of this paper is to develop a generalized mathematical model and a universally applicable simulation tool for the OEF problem. First, natural gas system is modeled in a way similar to electric power system according to electricity‐gas analogy analysis, where gas admittance, gas nodal admittance matrix, and the nodal equation of gas flow conservation are derived. Then, a generalized accurate OEF model is formulated by simultaneously integrating the OPF model and the OGF model as well as their coupling constraints in a unified modeling framework. Furthermore, an available hybrid optimization approach consisting of whale optimization algorithm, MATPOWER, hydraulic calculation iterative program, and nonstationary penalty function method is put forward to solve the OEF problem. The accuracy, feasibility, and applicability of the proposed modeling and solution method is finally demonstrated by analyzing Belgian 20‐node gas system combined with IEEE 30‐bus test system.     

Predicting electricity energy consumption: A comparison of regression analysis,decision tree and neural networks

This study presents three modeling techniques for the prediction of electricity energy consumption. In addition to the traditional regression analysis, decision tree and neural networks are considered. Model selection is based on the square root of average squared error. In an empirical application to an electricity energy consumption study, the decision tree and neural network models appear to be viable alternatives to the stepwise regression model in understanding energy consumption patterns and predicting energy consumption levels. With the emergence of the data mining approach for predictive modeling, different types of models can be built in a unified platform: to implement various modeling techniques, assess the performance of different models and select the most appropriate model for future prediction.     

用组合预测模型对我国能源需求量的研究

随着中国经济的快速发展,能源消费不断提高。利用能源消费量的历吏数据,建立了我国能源消费系统的ARMA模型和灰色预测模型的组合模型。通过组合模型和ARMA模型、灰色预测模型的具体比较分析,证明组合模型更为易行、有效,可以作为我国及地区未来能源消费量预测的有效工具。     

注汽锅炉系统用能分析及改进建议

建立了注汽锅炉系统及设备的能理平衡分析及火用分析模型,给出了评价准则及计算公式。根据测试数据对一在用的注汽锅炉系统进行了分析计算,给出了主要计算结果。本文完善了注汽锅炉的热力学分析方法,这为全面分析注汽锅炉的用能特性,提供了依据。     

火电机组能耗指标体系构建与经济性诊断研究

数据挖掘技术已广泛应用于传统火电行业的节能优化运行与管理,但目前基于数据挖掘的机组运行优化方法往往缺乏普遍性和实操性,针对少量典型工况挖掘得到的参数目标值,无法给予实际运行机组全面的指导。本文在分析锅炉和汽轮机等主要子系统性能指标影响因素的前提下,建立基于层次划分的火电机组能耗指标体系,提出了数据挖掘与火电机组能耗机理分析耦合的经济性诊断模型,有效提高了输出的鲁棒性。以供电煤耗为例,基于历史数据挖掘的火电机组经济性诊断模型和流程,准确分析出能耗水平高于报警阈70%是由于实时排烟氧量偏离基准值造成的,并给出符合实际工况的调节建议。     

延迟焦化装置的能耗分析及节能优化实践

中国海油惠州炼油分公司420× 104t/a延迟焦化装置通过停用解吸塔上重沸器3.5MPa蒸汽、停用柴油汽提塔1.0MPa汽提蒸汽、降低循环比、采用先进控制(APC)提高加热炉热效率、降低高压水泵和罐区减渣原料泵电耗、提高水的回用率、加大装置处理量等工艺优化措施,装置综合能耗比设计能耗39.03kg标油/t原料降低3kg标油/t原料.为了进一步降低装置能耗,达到国内其他先进装置的能耗水平,该装置在2011年利用检修时机,通过加热炉节能改造降低排烟温度、利用柴油低温热发生0.45MPa蒸汽、焦化富气压缩机叶轮更换、焦炭塔区特阀汽封线改造等节能改造措施.加热炉热效率由89％提高至91.5％,节约3.5MPa蒸汽用量约6.5t/h,同时减少了燃料气、蒸汽和电的消耗,使装置能耗总体降低3.16kg标油/t原料.装置节能改造每年可增加4000万元的经济效益.     

汽轮机叶片的建模及插补算法研究

为提高汽轮机的工作效率,汽轮机叶片的表面通常是设计成扭曲的变截面曲面,叶片形状十分复杂,因此,汽轮机叶片的精确几何造型对保证叶片加工质量十分重要。进行汽轮机叶片数学建模和数控插补算法研究,根据图纸数据对汽轮机叶片进行基于NURBS曲线和曲面的反求计算,建立了汽轮机叶片的精确数学模型。针对叶片高速高精度数控加工的要求,以叶片数学模型为基础,建立叶片截面的NURBS曲线组,利用MATLAB编程仿真,验证了采用不同插补算法进行叶片数控加工的适应性。     

扬子石化延迟焦化装置节能措施及实施效果

扬子石化0.8Mt/a延迟焦化装置由于建成较早,加工工艺落后,2011年综合能耗达到23.04kg标油/t。结合装置特点,实施燃料气、蒸汽及用水节能措施。燃料气降耗方面,对达到使用年限的加热炉空气预热器热管进行部分更换,加热炉效率由90%提高至92%;使用气体脱硫装置的富余0.5MPa蒸汽作为热源,对燃料气进行加热,减少燃料气实际耗量5.16%。蒸汽节能方面,利用富余0.5MPa蒸汽替代1.0MPa蒸汽,节省1.0MPa蒸汽用量5.11t/h;随着装置凝结水回收项目的竣工,计划改用凝结水替代部分大吹汽蒸汽;同时,现场消除蒸汽漏点,更换腐蚀、减薄的碳钢管线,将其材质升级为不锈钢。节水方面,使用硫回收净化污水替代工业水,节省工业水用量7000t/a;拟将装置各点排放的凝结水集中回收,补入装置除氧罐或放水罐,进一步节省工业水用量。上述措施的实施,使装置能耗由2012年的22.93kg标油/t降至2013年的21.25kg标油/t,降幅达7.3%。     

荆门石化气体分馏装置流程模拟技术应用

荆门石化总厂气体分馏装置处理能力为55×104t/a,采用脱丙烷塔、脱乙烷塔、丙烯塔(两塔)三塔流程。以该气体分馏装置为研究对象,采用Aspen Plus流程模拟软件,建立与装置实际工况相符合的稳态流程模拟模型。利用此模型,对脱丙烷塔、脱乙烷塔、丙烯塔等进行灵敏度分析,研究各塔压力、热负荷、回流比等参数间的相互关系,并以模型为指导,对装置进行如下优化调整:脱丙烷塔顶控制压力由1.85MPa下调到1.40MPa,既能满足产品质量要求,又能大幅降低装置蒸汽消耗,塔顶温度和塔底温度均大幅下降,塔底温度由109℃降到95℃左右,蒸汽流量平均值下降约5t/h,使蒸汽单耗下降到约0.1kg标油/t,该装置综合能耗下降7.6kg标油/t。装置年开工时数按8400h计算,全年减少蒸汽消耗4.2×104t,蒸汽价格按150元/t计算,则全年共创节能效益630万元,装置能耗大幅降低。     

Coal-fired oxy-fuel power unit – Process and system analysis

As oxy-fuel power generation is currently on the pre-demonstration stage of development many studies dealing with optimization and simulation aspects are still in progress. This paper is focused on the development of a simulation model of the integrated oxy-fuel system and cumulative energy analysis of an oxy-unit operation in separated national economy. The analyzed oxy-fuel system consists of a steam boiler, steam cycle, air separation unit, as well as a CO₂ purification and compression island. The built model is based on physical relations. It has been developed as a set of modules modelling isolated devices (e.g. combustion chamber or flue gas dehumidifier). Interconnections between these devices can be easily changed, which permits to analyse different oxy-fuel structures and operating parameters. The simulation model has been partially verified on the basis of literature data. Results of oxy fuel energy analysis have been presented for one selected structure and compared with an air combustion power unit, assuming the same steam cycle parameters. For both cases indices of cumulative primary energy consumption have been calculated. The obtained results show that the increase of oxy-fuel primary energy consumption (compared with air-based combustion) can be significantly reduced if by-produced nitrogen will be used for external applications.     

炼油联合装置节能减排优化措施

巴陵石化炼油联合装置以105× 104t/a MIP-CGP装置为核心,配套产品精制、气体分离及循环水、空压站等公用工程系统.该装置直接以200×104t/a常压装置的渣油为原料,具有多产高辛烷值汽油和气体烯烃的特点.针对重油催化装置高气体收率和大注汽量的工艺特点,从催化生焦理论人手,进一步分析了随着进料密度、残炭和重金属含量的增加,装置的能耗越显著,联合装置的用能优化越复杂.通过对再生器取热系统、烟气余热回收系统、蒸汽能量梯级利用、烟机系统、供风系统、加热炉燃烧器系统、高低温位热能回收以及循环水、酸性水、凝结水系统的用能分析及优化改造,充分综合利用了各类能源,减少了装置对水的消耗.炼油联合装置能耗由72.20kg标油/t原油降至61.74kg标油/t原油,吨原油取水南0,72t/t降至0.61t/t,吨原油排水由0.64t/t降至0.30t/t.     

Goal programming model for sustainable electricity production from biomass

In this paper, we present a goal programming model for block level energy planning in order to make a block self‐sufficient in electricity consumption, which includes the commercial energy consumption goal, the goal of generating electricity from biomass and food production goals with linear constraints on the available sources such as human power, animal power, tractor power, land area and on the requirement of the block such as cooking energy, lighting energy and energy for other operations, such as fodder for animal population. We try to achieve these goals through proper allocation of land for different crops. After reformulating the developed goal programming model into a linear programming format, we use the HYPER LINDO software package to solve it in a Pentium‐based IBM‐PC compatible computer system. The developed model is solved for a typical Indian block, namely Nilakkottai Block in Tamil Nadu, India. The model solution shows that the goal of generating electricity from biomass is achieved, the commercial energy consumption goal and pulses requirement goal are under‐achieved and the sugar requirement goal is over‐achieved. Furthermore, the cereal, vegetable and oilseed production goals are achieved. Copyright © 2000 John Wiley & Sons, Ltd.     

Effect of ventilation strategies on air contaminant concentrations and energy consumption in buildings

Considering the diversity of indoor contaminant characteristics and generation patterns, finding an appropriate ventilation strategy that can secure acceptable indoor air quality with minimum energy consumption is a challenging task for HVAC system designers and operators. This study theoretically models and investigates the impact of various ventilation strategies on contaminant concentration behaviour and corresponding ventilation cooling energy requirements for a single‐zone enclosure. Two types of contaminants are considered; carbon dioxide as an occupancy dependent and formaldehyde, which is independent of occupancy. An airflow model is used to predict space pressure and air leakage rates across the enclosure envelope, and an air quality model is used to predict time‐varying contaminant concentrations. In addition, a building energy simulation model is utilized to predict the corresponding ventilation cooling energy requirements under hot climatic conditions. Results from this study show that acceptable contaminant concentrations during occupied periods can be achieved by different ventilation strategies but at substantially different ventilation energy requirements. More than 50 per cent reduction in ventilation energy requirements can be obtained while maintaining acceptable IAQ if proper ventilation strategy is employed. Copyright © 2001 John Wiley & Sons, Ltd.     

洛阳石化延迟焦化装置节能分析

洛阳石化140×104t/a延迟焦化装置采用"一炉两塔"和"可灵活调节循环比"的工艺流程,2008年和2009年装置综合能耗分别为35.42kg标油/t和33.36kg标油/t,与设计值、中国石化平均水平(24.27kg标油/t)相比差距较大。综合分析,能耗较高的原因包括蜡油汽包产0.4MPa蒸汽未计入能耗、1.0MPa蒸汽放空、低温热回收系统未投用、蜡油热输出量小、装置加工负荷率低以及加热炉效率低等。为此,对装置采取用0.4MPa蒸汽替代1.0MPa蒸汽;回收分馏塔顶油气、接触冷却塔顶油气和冷焦水低温热量;增加稳定汽油热出料流程;增设节电变频设施,减少电耗;降低加热炉排烟温度和炉外壁温度;加热炉进料泵叶轮抽级或更换为小叶轮,降压节能;增上加热炉先进控制(APC)手段,保证加热炉最佳燃烧;加热炉出口管线保温及管托更新换型,增加空气预热器等措施,有效降低装置能耗。     

Use of MCDM techniques for energy policy and decision‐making problems: A review

Energy consumption increases all over the world as a result of industrialization in recent years. In this context, it has become important to meet increasing energy demand. It is significant to find alternative energy sources because of limited nonrenewable energy sources such as coal, petroleum, and natural gas. At this point, renewable energy sources have an important role to meet energy requirement. As a result, decision and policy making for energy is completely critical issue for countries. Various technical, economic, environmental, and social criteria are used to solve energy policy and decision‐making problems such as evaluation of energy projects, selection among energy alternatives, power plant site selection, and determining energy policy. Multicriteria decision‐making (MCDM) methods are used as effective tools to help decision makers while solving energy problems. There are a large number of studies including articles, conference papers, and book chapters, which examine energy problems by using MCDM methods in the literature. Therefore, analyzing these studies according to different features such as publication year, MCDM method, document type, statistical analyses, country, and published journal can be beneficial for leading researchers who study in energy decision‐making field. In this study, published papers, which use traditional MCDM methods to handle energy problems, are examined systematically. By the way, it is aimed to lead to researchers regarding MCDM methods which are utilized in energy applications. It also conducted some statistical analyses to obtain trends between years and MCDM methods. Besides, recent developments in energy field are presented through this comprehensive literature review.