基于支持向量机与高斯分布估计的低NOx排放

燃烧优化的核心在于建立有效而快速的建模工具及寻优算法,以便于在线应用。为了研究新方法的适用性以及克服常用算法的缺点,本文利用支持向量回归建立了大型四角切圆燃烧电站锅炉NO_x排放特性模型。利用大量的热态实炉试验NO_x排放数据对模型进行了训练和验证。结果表明,支持向量回归模型能获得较神经网络模型更加准确的预测结果,相对于神经网络,支持向量回归能更好处理大样本量数据的非线性问题。随后,采用一种基于高斯概率密度 (GPDD)的分布估计优化算法对NO_x排放模型进行了寻优。研究发现,与遗传算法相比,GPDD具有更好的寻优能力与更快的收敛速度。结合支持向量回归与高斯概率密度分布(GPDD)算法能有效降低燃煤锅炉NO_x排放量,不到1 min的优化时间便于在线应用。研究结论可为该算法在实际电厂中推广应用提供参考依据。     

1.5 MW循环流化床锅炉内煤与垃圾混烧的烟气特性

通过对1.5 MW循环流化床锅炉内煤与垃圾混烧产生的烟气中的CO、HCl、SO₂、NO_x、H₂O、二噁英等成分进行在线监测,发现原煤燃烧排放的CO浓度要高于添加垃圾后排放的CO浓度,随垃圾加入比例的增大,不完全燃烧份额增加,相应的CO排放值逐渐提高。由于原煤含硫量远高于垃圾含硫量,因此随着垃圾加入比例的增大,烟气中的SO₂浓度有所降低。烟气中HCl浓度随着垃圾加入比例的增大几乎呈直线增加。而烟气中NO_x浓度则呈现出含量下降的趋势,这证明循环流化床锅炉可以抑制NO_x总量的生成,但N₂O的排放浓度会有所增加。此外,随着垃圾加入比例的增大,烟气中的H₂O和二噁英含量也有所增加,成为该工艺实际应用过程中需要考虑的问题。     

旋流浓淡燃烧器中煤粉浓缩器对煤燃烧NOx生成的影响

应用数值模拟方法研究了旋流燃烧器中煤粉浓缩器对煤燃烧NO_x生成的影响,给出了热NO_x和燃料NO_x生成的详细信息.预报结果表明：采用作者研制的弱旋煤粉浓缩器后,可以大大地降低燃烧器出口区域燃料NO_x的生成,同时可以保持煤粉颗粒较高的燃尽率.模拟结果也表明,燃烧器出口区域的NO_x生成主要是由燃料NO_x的生成机理来控制,热NO_x在总NO_x的生成量中所占比例不大.因此,该旋流浓淡燃烧器具有高效低污染性能.     

石化污泥与煤流化床混烧污染物排放特性

在一座热态循环流化床燃烧试验装置上对石化污泥与煤进行混烧试验,通过对焚烧过程中烟气成分进行分析,着重考察了质量掺混比、二次风率、过剩空气系数和床温对SO₂、NO_x和多环芳烃排放浓度的影响。试验结果表明,随着质量掺混比的增大,SO₂和NO_x的排放浓度下降,而多环芳烃排放浓度呈上升趋势。随着二次风率的增加,SO₂的排放浓度上升,而NO_x的排放浓度呈下降趋势。随着过剩空气系数的增加,SO₂的排放浓度下降,NO_x的排放浓度呈上升态势。随着床温或者过剩空气系数的增加,烟气中多环芳烃排放浓度均呈先下降后上升趋势。综合考虑稳定燃烧和降低污染物排放等因素,得出一系列最佳燃烧参数。燃烧温度应该控制在850～860℃,过剩空气系数应该控制在1.35左右,二次风率应该控制在40%左右,质量掺混比应该控制在30%左右。在本次试验范围内,各工况SO₂、NO_x和多环芳烃的排放浓度均满足国家排放标准。     

煤在O2/CO2中燃烧的Nox释放规律

利用一维沉降炉,对3种煤在O₂/CO₂和空气两种气氛下燃烧NO_x析出特性进行了比较,分析了炉膛温度、过量空气系数对NO_x生成量的影响,并对O₂/CO₂气氛下NO_x的生成和破坏机理进行了分析.研究发现两种气氛下NO_x都有一个峰值出现,挥发分含量高的煤种峰值靠前, 挥发分含量低的煤种峰值靠后,O₂/CO₂条件下,峰值出现较空气条件下提前且有所下降;空气条件下NO_x的生成量随温度提高较快地增加,而O₂/CO₂气氛中NO_x的生成量随温度变化比较缓慢;在两种气氛下NO_x的峰值均随过量空气系数的增加而增加,高挥发分煤在O₂/CO₂气氛下NO_x峰值低于空气条件下峰值,而低挥发分煤则受影响较小.     

变负荷工况下NOx排放量预测控制

NO_x是火电厂排放的主要污染物之一,降低NO_x的排放是火电厂面临的主要问题。针对火电厂变负荷工况下的NO_x排放量最小化问题,本文提出了一种基于最小二乘支持向量机（LSSVM）的非线性模型预测控制算法。根据电站锅炉实际历史数据建立锅炉负荷预测模型和NO_x排放预测模型,并以交叉验证的方法优化模型参数,从而获得高精度模型。在此基础上以NO_x的排放量最小为优化目标,考虑锅炉负荷约束,构建锅炉燃烧优化模型。采用差分进化算法求解优化模型得到控制参数的最优设定值。为了验证本文提出算法的有效性,采用实际生产数据进行实验。实验结果表明本方法能够在变负荷工况下有效降低NO_x排放量,在不增加电厂改造成本上,为电厂提供了有效的控制手段,具有一定应用前景。     

机器学习驱动锅炉燃烧优化技术的现状与展望

伴随可再生能源发电装机容量快速增加,深度调峰过程中负荷多变、燃烧失稳等不稳定工况对火电机组的燃烧优化控制提出了更高要求,快速发展的人工智能技术与深度学习算法为锅炉参数预测建模及优化提供了重要手段。在机器学习算法方面,总结了特征筛选与建模算法的研究现状,提出了传统统计学方法与线性降维方法的科学解释性较差且不能很好地辨识高维数据,结合深度学习算法的特征筛选方法在处理复杂的火电机组数据时优势更明显;对比了多种神经网络在NO_x排放浓度建模中的优缺点,其中长短期记忆神经网络与卷积神经网络在处理时序数据时效果更好、集成模型通过组合不同学习器的优势可提高整个模型的泛化能力和鲁棒性。在预测模型的应用方面,通过对SCR脱硝系统建立预测模型可以方便运行人员模拟并修正可调参数,同时作为软测量手段监测燃烧系统运行状态;引入NO_x排放浓度预测模型的前馈控制和模型预测控制等先进控制手段可有效改善火电机组传统PID控制效果较差的问题;在多目标优化中NO_x脱除效率通常与锅炉效率或脱硝成本共同作为优化目标,以期实现经济效益与社会效益的和谐统一。     

支持向量回归在乙烯裂解产物收率软测量中的应用

乙烯裂解产物收率的实时预报对于裂解炉的生产具有重要意义。针对有效的样本数据较少的问题,采用支持向量回归方法建立裂解产物收率的软测量模型。对于支持向量机中模型参数的选取,采用了微粒群优化算法进行参数寻优,提高了建模效率和模型精度。基于现场数据的建模实验结果表明,基于支持向量回归方法的乙烯裂解产物收率软测量模型预报精度较高,趋势跟踪性能良好。     

O2/N2、O2/CO2和O2/CO2/NO气氛下煤粉燃烧NOx排放特性

利用滴管炉研究了O₂/N₂、O₂/CO₂和O₂/CO₂/NO气氛下煤燃烧过程中NO_x的排放特性。实验结果表明,在O₂/N₂和O₂/CO₂气氛下,高温或高O₂浓度均使NO排放量增加。O₂/CO₂气氛下NO排放量比O₂/N₂气氛下NO排放量低大约30%～40%。在O₂/CO₂/NO气氛下,温度不同时,O₂浓度变化对NO排放量的影响规律不同,对循环NO降解的影响规律也不同。高温不利于循环NO降解。随停留时间的延长NO排放量出现两个峰值。     

基于GA-SVM的烟气含氧量软测量

针对电站锅炉烟气含氧量传统硬件测量方法成本昂贵、使用寿命短等缺陷,提出一种基于支持向量机的软测量方法。首先结合机理分析和数据相关性分析选取相关过程参数作为模型输入参数,使用遗传算法对支持向量机进行参数寻优,构建基于遗传算法参数优化的支持向量机(GA-SVM)软测量模型。实验结果表明:该模型能较好地反映烟气含氧量的变化趋势。     

大尺度代谢网络通量平衡分析的进展与应用

利用大尺度代谢网络分析生物体内部复杂的生化机制已经研究了很多年,大尺度代谢网络的算法也有很多,在这其中通量平衡分析是一个有效的定量研究基因组尺度代谢网络的方法,并在很多分析中都有应用。总结了通量平衡分析算法的最新进展,包括基本的通量平衡分析以及扩展的通量平衡分析算法,然后介绍了一些应用通量平衡分析算法模拟大型生物网络的单机的和在线的工具,最后还比较了这些工具的优缺点,并讨论了目前代谢网络分析算法与软件存在的难题和未来的研究方向。     

Generalized initialization for the dynamic simulation and optimization of grade transition processes using two-dimensional collocation

Optimization modeling tools are essential to determine optimal design specifications and operation conditions of polymerization processes, especially when quality indices based on molecular weight distributions (MWDs) must be enforced. This study proposes a generalized MWD-based optimization strategy using orthogonal collocation in two dimensions, which can capture the dynamic features of MWDs accurately. To enable the strategy, this study considers generalized initialization methods for large-scale simulation and optimization. Here, a homotopy method based on intermediate solutions is adopted to generate initial values for general steady-state simulation models, starting from an arbitrary known solution for any steady-state simulation model. For dynamic simulation models, the response of a first-order linear system is adopted to initialize the state variables. Case studies show the effectiveness of this procedure to enable systematic, reliable, and efficient solution of the optimization problem.     

Synthesis and optimization of utility system using parameter adaptive differential evolution algorithm☆

Synthesis and optimization of utility system usual y involve grassroots design, retrofitting and operation optimi-zation, which should be considered in modeling process. This paper presents a general method for synthesis and optimization of a utility system. In this method, superstructure based mathematical model is established, in which different modeling methods are chosen based on the application. A binary code based parameter adaptive differential evolution algorithm is used to obtain the optimal configuration and operation conditions of the sys-tem. The evolution algorithm and models are interactively used in the calculation, which ensures the feasibility of configuration and improves computational efficiency. The capability and effectiveness of the proposed approach are demonstrated by three typical case studies.     

基于自适应采样算法的芳烃异构化代理模型

异构化是芳烃生产中的重要环节,提高异构化环节的建模和优化效率对工业生产有着重要意义。但是,直接使用机理模型的优化过程耗时较长,优化效率低。代理模型可以有效地对机理模型进行近似,而代理模型采样方法对模型精度有很大影响。提出了一种新的基于稀疏度和最邻近期望的自适应采样算法,该方法可以平衡全局搜索和局部搜索,通过求解优化问题找到反映函数关键信息的新采样点,再加入原始样本集中,使得代理模型精度不断提高。多个测试函数结果表明,相比于其他自适应采样算法,该算法能有效提升代理模型精度和建模效率。该算法在芳烃异构化环节代理模型中也得到了有效验证,与本文中其他算法对比,该算法模型误差减少5%以上,建模时间缩短30%以上。     

Automated reformulation of disjunctive constraints in MINLP optimization

In this paper, a general method for handling disjunctive constraints in a MINLP optimization problem is presented. This method automates the reformulation of an, in a abstract modeling language given, optimization problem into a mathematical problem that is solvable with existing optimization tools. This implementation can use common MILP solvers for linear problems and nonlinear methods for quasi-convex optimization problems. It also includes the possibility to use the logics in the system and solve the system logically using subproblems.     

大规模非线性优化软件包UniOptima的设计和开发

根据将SQP算法应用于大规模问题求解的两种改造思路,并结合目前这方面的研究成果,在M atlab环境下开发了大规模非线性优化工具箱Un iOptim a。Un iOptim a包括两个非线性求解器RSQP和THSQP,RSQP专门应用于自由度相对较小的等式约束优化问题,THSQP则应用于一般的非线性优化问题。本优化工具箱采用M atlab语言开发,并与M atlab优化工具箱保持了良好的兼容性,大大方便了用户使用。求解器中设有很多优化选项,用户可根据不同情况或不同需要选择不同的优化选项,增强了用户和程序的交互性。     

Recent progress on equation-oriented optimization of complex chemical processes

Process optimization in equation-oriented (EO) modeling environments favors the gradient-based opti-mization algorithms by their abilities to provide accurate Jacobian matrices via automatic or symbolic differentiation.However,computational inefficiencies including that in initial-point-finding for Newton type methods have significantly limited its application.Recently,progress has been made in using a pseudo-transient (PT) modeling method to address these difficulties,providing a fresh way for-ward in EO-based optimization.Nevertheless,research in this area remains open,and challenges need to be addressed.Therefore,understanding the state-of-the-art research on the PT method,its principle,and the strategies in composing effective methodologies using the PT modeling method is necessary for further developing EO-based methods for process optimization.For this purpose,the basic concepts for the PT modeling and the optimization framework based on the PT model are reviewed in this paper.Several typical applications,e.g.,complex distillation processes,cryogenic processes,and optimizations under uncertainty,are presented as well.Finally,we identify several main challenges and give prospects for the development of the PT based optimization methods.     

Process modeling and optimization of industrial ethylene oxide reactor by integrating support vector regression and genetic algorithm

This article presents an artificial intelligence‐based process modeling and optimization strategies, namely support vector regression–genetic algorithm (SVR‐GA) for modeling and optimization of catalytic industrial ethylene oxide (EO) reactor. In the SVR‐GA approach, an SVR model is constructed for correlating process data comprising values of operating and performance variables. Next, model inputs describing process operating variables are optimized using Genetic Algorithm (GAs) with a view to maximize the process performance. The GA possesses certain unique advantages over the commonly used gradient‐based deterministic optimization algorithms The SVR‐GA is a new strategy for chemical process modeling and optimization. The major advantage of the strategies is that modeling and optimization can be conducted exclusively from the historic process data wherein the detailed knowledge of process phenomenology (reaction mechanism, kinetics, etc.) is not required. Using SVR‐GA strategy, a number of sets of optimized operating conditions leading to maximized EO production and catalyst selectivity were obtained. The optimized solutions when verified in actual plant resulted in a significant improvement in the EO production rate and catalyst selectivity.     

A multilevel coordinate search algorithm for well placement,control and joint optimization

Determining optimal well placements and controls are two important tasks in oil field development. These problems are computationally expensive, nonconvex, and contain multiple optima. The practical solution of these problems requires efficient and robust algorithms. In this paper, the multilevel coordinate search (MCS) algorithm is applied for well placement and control optimization problems. MCS is a derivative-free algorithm that combines global and local search. Both synthetic and real oil fields are considered. The performance of MCS is compared to generalized pattern search (GPS), particle swarm optimization (PSO), and covariance matrix adaptive evolution strategy (CMA-ES) algorithms. Results show that the MCS algorithm is strongly competitive, and outperforms for the joint optimization problem and with a limited computational budget. The effect of parameter settings for MCS is compared for the test examples. For the joint optimization problem we compare the performance of the simultaneous and sequential procedures and show the utility of the latter.