Abstract ：

Municipal solid waste incineration (MSWI) process has been one of the important emission sources of dioxin (DXN) in terms of century posion. Untill now, the evolution mechanism and real-time detection of DXN emission concentration are still unsolved challenges. Existing studies mainly rely on available data to build data-driven modeling, and how to effectively combine the mechanism of combustion process for DXN detection is a problem that is not considered. To solve this problem, this article proposes DXN emission modelling method based on simulation mechanism and improved linear regression decision tree (LRDT). First, a numerical simulation model based on coupling fluid dynamic incinerator code (FLIC) and advanced system for process engineering Plus (Aspen Plus) software is used to obtain virtual mechanism data with multiple operating conditions. Then, virtual mechanism data is used to construct an improved LRDT combustion state representation variable CO2, CO, and O2 model. Next, a process mapping model (PMM) based on multiple input single output LRDT is constructed using real CO2, CO, and O2 as input and DXN as output. Semi-supervised learning and structural transfer learning based on PMM are used to obtain the mechanism mapping models1 (MMM1). Finally, the final MMM2 based on semi-supervised transfer learning is obtained by the structural growth learning of the MMM1. The proposed method was validated for industrial application on a hardware-in-loop simulation platform in the laboratory and an edge verification platform at an MSWI plant in Beijing. The experimental results show that the proposed method and the developed soft measurement system can effectively realize the on-line detection of DXN emission concentration. © 2024 Science Press. All rights reserved.

Keyword ：

Municipal solid waste incineration (MSWI) dioxin (DXN) linear regression decision tree (LRDT) combustion condition semi-supervised transfer learning numerical simulation-based mechanism

Cite：

Copy from the list or Export to your reference management。

Abstract ：

城市固废焚烧(Municipal solid waste incineration,MSWI)过程是"世纪之毒"二噁英(Dioxin,DXN)的重要排放源之一.截止目前为止,DXN的演化机理和实时检测仍是尚未解决的难题.现有研究主要基于离线化验数据构建数据驱动模型,DXN的检测未有效结合燃烧过程机理.针对该问题,本文提出基于仿真机理和改进线性回归决策树(Linear re-gression decision tree,LRDT)的DXN排放建模.首先,采用基于床层固废燃烧模拟软件FLIC(Fluid dynamic inciner-ator code)和过程工程先进系统软件(Advanced system for process engineering Plus,Aspen Plus)耦合的数值仿真模型,获取蕴含多运行工况的虚拟机理数据;接着,利用虚拟机理数据构建基于改进LRDT的CO2、CO和O2燃烧状态表征变量模型;然后,以真实CO2、CO、O2作为输入和以DXN真值作为输出,构建多入单出LRDT的过程映射模型(Process mapping model,PMM),再利用该模型进行半监督学习和结构迁移得到机理映射模型1(Mechanism mapping modelsl,MMM1);最后,通过结构增量学习获得基于半监督迁移学习的MMM2模型.在实验室的半实物平台和北京某MSWI厂的边侧验证平台对所提方法进行了工业应用验证.实验结果证明了所提方法与研发的软测量系统可有效实现二噁英排放浓度在线检测.

Keyword ：

线性回归决策树 数值仿真机理 半监督迁移学习 燃烧状态 城市固废焚烧 二噁英

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Dioxin (DXN) produced by municipal solid waste incineration (MSWI) processes is a highly toxic pollutant with unclear mechanism up to date. It is important to understand the boundary conditions of the formation, combustion and regeneration of DXN in the grate furnace for reducing pollution emissions. In this paper, a numerical simulation method of DXN emission concentration in grate furnace incineration processes for municipal solid waste was presented. First, according to the MSWI processes flow of a typical grate furnace, the mechanism of DXN-related reactions such as solid-phase combustion, gas-phase combustion, high-temperature heat exchange and low-temperature heat exchange in the incinerator was described. Then, according to the above divided areas, a numerical simulation model combined with the relevant parameters of actual MSWI process was constructed. Finally, a univariate analysis was performed based on the reactant concentrations characterized by the flue gas split fraction and the reaction temperatures in different regions to obtain the boundary conditions for the DXN concentration at G1. The effects of split fraction and reaction temperature on the DXN concentration at G1 were analyzed based on orthogonal experiments, and the optimal parameter combination was obtained. The validity of the model was proved by numerical simulation analysis and verification based on the actual data of a MSWI power plant in Beijing. It will provide support for the subsequent optimal control of DXN emission concentration at G1. © 2023 Chemical Industry Press. All rights reserved.

Keyword ：

numerical simulation orthogonal experiment municipal solid waste incineration (MSWI) univariate analysis dioxin (DXN) optimal parameter

Cite：

Copy from the list or Export to your reference management。

Abstract ：

针对构建城市固废焚烧(municipal solid waste incineration,MSWI)过程剧毒污染物二噁英(dioxin,DXN)排放风险预警模型的样本极为稀少的问题,提出一种基于主动学习机制生成对抗网络(generative adversarial network,GAN)的DXN排放风险预警建模方法.首先,以DXN风险等级作为条件信息使得GAN生成候选虚拟样本;然后,利用基于最大均值差异和多视角可视化分布信息的主动学习机制进行虚拟样本的初筛和评估,以获得期望虚拟样本;最后,基于混合样本构建DXN排放风险预警模型.通过基准数据集和MSWI过程数据集验证了所提方法的有效性.基于主动学习机制GAN的DXN排放风险预警建模方法可以有效解决样本稀少的问题,提高模型精度.

Keyword ：

主动学习 虚拟样本生成(virtual sample generation 城市固废焚烧(municipal solid waste incineration 最大均值差异 GAN) VSG) DXN)排放风险预警 MSWI) 二噁英(dioxin 生成对抗网络(generative adversarial network

Cite：

Copy from the list or Export to your reference management。

Abstract ：

To solve the problem that the samples to construct a risk warning model of dioxin (DXN) emission in municipal solid waste incineration (MSWI) process are extremely scarce, a modeling method of DXN emission risk warning based on generative adversarial network (GAN) with active learning mechanism was proposed. First, the risk level of DXN was added as condition information to GAN, so that the generator generated candidate virtual samples with specified requirement. Then, the active learning mechanism based on maximum mean discrepancy and multi-view visual distribution information was used to evaluate and screen the virtual samples that met the experts' expectations. Finally, the DXN emission risk warning model was constructed based on the mixed samples composed of virtual samples and real samples. The validity and rationality of the proposed method were verified by using benchmark and MSWI process data sets. The proposed modeling method of DXN emission risk warning based on GAN with active learning mechanism can effectively solve the problem of scarce samples and improve the accuracy of the model. © 2023 Beijing University of Technology. All rights reserved.

Keyword ：

active learning dioxin (DXN) emission risk warning generative adversarial network (GAN) maximum mean discrepancy virtual sample generation (VSG) municipal solid waste incineration (MSWI)

Cite：

Copy from the list or Export to your reference management。

Abstract ：

二噁英(Dioxin,DXN)是导致城市固废焚烧(Municipal solid waste incineration,MSWI)建厂存在"邻避现象"的主要原因之一.工业现场多采用离线化验手段检测DXN浓度,难以满足污染物减排控制的需求.针对上述问题,本文提出了基于潜在特征选择性集成(Selective ensemble,SEN)建模的DXN排放浓度软测量方法.首先,采用主元分析(Prin-cipal component analysis,PCA)分别提取依据工艺阶段子系统及全流程系统过程变量的潜在特征,并依据预设贡献率阈值进行特征初选;接着,采用互信息(Mutual information,MI)度量初选特征与DXN间的相关性,并自适应确定再选的上下限及阈值;最后,采用具有超参数自适应选择机制的最小二乘-支持向量机(Least squares—support vector machine,LS-SVM)算法建立多源特征的候选子模型,基于分支定界(Branch and bound,BB)优化和预测误差信息熵加权算法进行集成子模型的优化选择和加权组合,进而得到软测量模型.基于某MSWI焚烧厂DXN检测数据仿真验证了所提方法的有效性.

Keyword ：

最小二乘-支持向量机 多源潜在特征 城市固废焚烧 选择性集成建模 二噁英

Cite：

Copy from the list or Export to your reference management。