基于超标抑制策略的污水处理过程多目标优化控制

为解决污水处理过程出水氨氮和总氮浓度超标问题,提出了一种基于超标抑制策略的多目标优化控制方法。该方法利用长短期记忆网络的时序建模能力,对出水氨氮和总氮浓度建立预测模型,采用基于分解的动态种群多邻域多目标进化算法对水质和能耗进行优化,结合预测模型输出确定硝态氮和溶解氧浓度的最优设定值,并对设定值进行跟踪控制。当水质超标时,采取抑制策略对外回流量及外部碳源加以控制,调节溶解氧浓度并对硝态氮浓度进行二次优化以抑制峰值。所提优化控制方法在基准仿真1号平台进行验证。结果表明,所提方法能够有效抑制氨氮和总氮浓度超标,超标时长及能耗明显低于所对比控制方法。     

基于NLJ算法的污水处理过程优化控制

针对国际污水处理基准仿真1号(BSM1)模型,对第五池中氨氮浓度采用串级控制,对第二池中硝态氮浓度采用单回路控制。利用神经网络建立氨氮浓度和硝态氮浓度的设定值与能耗的神经网络模型。同样,利用神经网络建立氨氮浓度和硝态氮浓度的设定值与出水水质合格率的神经网络约束模型。优化问题的目标函数和约束条件均通过神经网络建立,并利用变搜索系数(NLJ)算法求解该优化问题。将最优解分别作为氨氮和硝态氮控制器的设定值。仿真结果表明在关键水质达标的基础上,降低了能耗。     

数据和知识驱动的城市污水处理过程多目标优化控制

城市污水处理过程优化控制是降低能耗的有效手段, 然而, 如何提高出水水质的同时降低能耗依然是当前城市污水处理过程面临的挑战. 围绕上述挑战, 文中提出了一种数据和知识驱动的多目标优化控制(Data-knowledge driven multiobjective optimal control, DK-MOC)方法. 首先, 建立了出水水质、能耗以及系统运行状态的表达关系, 获得了运行过程优化目标模型. 其次, 提出了一种基于知识迁徙学习的动态多目标粒子群优化算法, 实现了控制变量优化设定值的自适应求解. 最后, 将提出的DK-MOC应用于城市污水处理过程基准仿真模型1 (Benchmark simulation model No. 1, BSM1). 结果表明该方法能够实时获取控制变量的优化设定值, 提高了出水水质, 并且有效降低了运行能耗.     

污水处理过程多变量优化控制方法研究

为了解决污水处理过程的优化控制问题,提高出水水质达标率和降低能耗,提出了一种污水处理多变量优化控制方法.首先,通过分析污水处理过程参数与可控变量溶解氧与硝态氮的关系,建立能耗和出水水质模型;其次,提出一种动态惯性权重的多目标粒子群优化算法,该算法平衡了寻优过程中的局部搜索和全局搜索能力,同时提高了算法的收敛速度,获得最...     

基于PSO-DE算法的污水处理优化控制研究

针对目前污水处理系统能耗过大,处理效果差等问题,提出了基于改进型粒子群算法的优化控制;采用粒子群差分进化算法(PSO-DE)可以提高粒子全局搜索能力与收敛速度,克服粒子早熟现象;在实际应用中建立以溶解氧浓度(DO)与污泥排放量(Qw)为变量,以能耗与出水水质为约束条件的数学模型,通过算法全局寻优求解,验证结果表明该算法能保证出水水质前提下降低污水处理能耗。     

基于复合抗扰的溶解氧浓度控制

污水处理中, 出水水质受进水流量、组分以及浓度波动等因素影响. 要保证处理效果, 溶解氧浓度控制应有 较强的鲁棒性. 简单闭环控制的能耗及出水水质波动大. 为此, 本文以污水处理过程1号基准仿真模型模拟污水生 化处理过程, 提出基于扩张状态观测器和滑模控制的复合抗扰控制方法, 以降低对模型信息的依赖, 保证溶解氧浓 度控制效果. 数值仿真结果显示, 复合抗扰控制能够以较小的能耗获得期望的调控效果. 这表明, 复合抗扰控制具有 很好的适应性, 能够满足调控要求, 是一种具有较强实用性的污水处理溶解氧浓度控制方法.     

污水处理系统溶解氧的区间预测控制方法

针对污水处理系统溶解氧浓度难以控制和曝气耗能高的问题,提出了一种基于双层优化结构的加权区间预测控制方法。该方法首先通过动态矩阵控制算法建立污水处理过程预测模型,然后设计一种融合溶解氧区间控制和曝气能耗指标的双层目标优化控制策略,同时为减小模型失配和干扰因素对系统的影响,利用模型预测误差进行系统反馈校正。仿真结果表明,与传统PID控制和模型预测控制方法相比,在不同工况下,区间预测控制方法可较好的实现溶解氧浓度的动态稳定控制,具有较强的抗干扰能力与自适应性,且在保证出水水质的前提下能有效降低曝气能耗。     

基于Hopfield 神经网络的污水处理过程优化控制

针对前置反硝化污水处理过程的优化控制问题,提出一种基于拉格朗日乘子法的Hofield神经网络优化方法.构造了污水处理过程约束优化问题的数学表达式,通过Hopfield神经网络优化计算生化池第5分区溶解氧浓度和第2分区硝态氮浓度的设定值,并采用PID控制器实现底层的跟踪控制.基于国际标准的Benchmark基准仿真平台进行仿真实验,结果表明污水处理系统在出水关键水质达标的基础上,能够显著降低能耗.     

基于混合群智能的节能虚拟机整合方法

数据中心的虚拟机（virtual machine,VM）整合技术是当今云计算领域的一个研究热点.要在保证服务质量（QoS）的前提下尽可能地降低云数据中心的服务器能耗,本质上是一个多目标优化的NP难问题.为了更好地解决该问题,面向异构服务器云环境提出了一种基于差分进化与粒子群优化的混合群智能节能虚拟机整合方法（HSI-VMC）.该方法包括基于峰值效能比的静态阈值超载服务器检测策略（PEBST）、基于迁移价值比的待迁移虚拟机选择策略（MRB）、目标服务器选择策略、混合离散化启发式差分进化粒子群优化虚拟机放置算法（HDH-DEPSO）以及基于负载均值的欠载服务器处理策略（AVG）.其中,PEBST,MRB,AVG策略的结合能够根据服务器的峰值效能比和CPU的负载均值检测出超载和欠载服务器,并选出合适的虚拟机进行迁移,降低负载波动引起的服务水平协议违约率（SLAV）和虚拟机迁移的次数;HDH-DEPSO算法结合DE和PSO的优点,能够搜索出更优的虚拟机放置方案,使服务器尽可能地保持在峰值效能比下运行,降低服务器的能耗开销.基于真实云环境数据集（PlanetLab/Mix/Gan）的一系列实验结果表明：HSI-VMC方法与当前主流的几种节能虚拟机整合方法相比,能够更好地兼顾多个QoS指标,并有效地降低云数据中心的服务器能耗开销.     

基于改进粒子群算法的污水处理过程神经网络优化控制

针对活性污泥法污水处理过程高能耗的问题,综合考虑污水处理出水水质和生化反应参数之间的关系,文中设计了一种智能优化控制系统.该系统以国际水协(IWA)开发的基准仿真模型BSM1为研究对象,利用改进粒子群算法优化BSM1第2分区的硝态氮浓度和第5分区的溶解氧浓度、混合液悬浮物固体浓度的设定值;同时利用感知器神经网络预测污水处理过程的输出,在出水水质达标的前提下降低污水处理能耗.仿真实验结果表明,系统总能耗相比闭环控制策略降低4.614%,该神经网络智能优化控制系统能够有效降低污水处理的能耗.     

插电式混合动力汽车车速预测及整车控制策略

本文针对插电式混合动力汽车(plug-in hybrid electric vehicle,PHEV)这一典型混杂系统,提出了一种基于车速预测的混合逻辑动态(mixed logical dynamical,MLD)模型预测控制策略.首先,通过对发动机和电动机能量消耗模型进行线性化,建立双轴并联插电式混合动力城市公交车的动力传动系统数学模型;其次,运用模糊推理进行驾驶意图分析,提出基于驾驶意图识别和历史车速数据相结合的非线性自回归(nonlinear auto-regressive models,NAR)神经网络车速预测方法进行未来行驶工况预测.然后,以最小等效燃油消耗为目标建立PHEV的混合逻辑动态模型,运用预测控制思想对车速预测时域内最优电机转矩控制序列进行求解.最后,通过仿真实验验证了本文所提出控制策略在特定的循环工况下与电动助力策略相比,能够提高燃油经济性.     

结合张量投票和Snakes模型的SAR图像道路提取

目的 Snakes模型对曲线轮廓具有良好的拟合能力,被广泛应用于遥感图像的道路提取。但SAR图像受乘性斑点噪声影响严重,因此利用Snakes模型从SAR图像提取道路时,传统的以图像灰度负梯度为外部能量的方法难以取得理想结果。针对这一问题,利用计算机视觉中的张量投票算法可以从噪声掩盖的图像中提取显著结构特征的特点,将张量投票与Snakes模型结合从SAR图像提取道路。方法 首先利用模糊C均值分割法从SAR图像中分割出道路类,然后对道路类进行张量投票获得每点的曲线显著性值,最后以该曲线显著性值的负值作为Snakes模型外部能量从SAR图像提取道路。在Snakes模型能量最小化阶段,提出了一种优化的拟合策略,一边内插节点一边最小化Snakes模型能量。结果 利用机载和星载不同场景的SAR图像进行实验,与同类的基于Snakes模型的半自动方法相比,本文方法对曲率较大的道路仅需较少控制点即可取得较好的拟合效果;与基于MRF模型的自动方法相比,本文方法对道路提取的完整率、正确率、检测质量都优于基于MRF模型的方法,并且提取的时间远远快于基于MRF模型的方法,对于大范围的道路网提取将更为实用。结论 本文方法充分考虑到道路的几何形态特征,利用张量投票算法对该特征进行量化,并利用优化的拟合策略来最小化Snakes模型能量来提取道路。基于机载和星载SAR图像的实验表明本文方法可以较好地提取不同场景中的主要道路目标和道路网。     

Multi-model ensemble prediction model for carbon efficiency with application to iron ore sintering process

Iron ore sintering is one of the most energy-consuming process in steel industry. Accurate prediction of carbon efficiency for this process is beneficial to energy savings and consumption reduction. Considering the sintering process exhibits strong nonlinearities, multiple parameters, multiple operating conditions, etc., a multi-model ensemble prediction model based on the actual run data is developed to achieve the high-precision prediction of carbon efficiency. It takes the comprehensive coke ratio (CCR) as a metric (index) of carbon efficiency in the sintering process. First, an affinity propagation clustering algorithm is used to realize the automatic identification of multiple operating conditions. Then, different models are established under different operating conditions by using the proposed least squares support vector machine (LS-SVM) with hybrid kernel modeling method. Finally, a partial least-squares regression method is employed as an ensemble strategy to combine the different models to form the multi-model ensemble prediction model for the CCR. The simulation results involving the actual run data demonstrate that the proposed model can predict the CCR accurately when compared with other prediction methods. The results of actual runs show that the coefficient of determination for the proposed model is 0.877. The proposed model satisfies the requirements of actual sintering process and enables the real-time prediction.     

Physics-based machine learning method and the application to energy consumption prediction in tunneling construction

Representing causality in machine learning to predict control parameters is state-of-the-art research in intelligent control. This study presents a physics-based machine learning method providing a prediction model that guarantees enhanced interpretability conforming to physical laws. The proposed approach encodes physical knowledge as mapping relationships between variables in engineering dataset into the learning procedure through dimensional analysis. This derives causal relationships between the control parameter and its influencing factors. The proposed machine learning method's objective function is further improved by the penalty term in the regularization strategy. Verifications on the energy consumption prediction of tunnel boring machine prove that, the established model accords with basic principles in this field. Moreover, the proposed approach traces the impact of three major factors (structure, operation, and geology) along the construction section, offering each component's contribution rates to energy consumption. Compared with several commonly used machine learning algorithms, the proposed method reduces the need for large amounts of training data and demonstrates higher accuracy. The results indicate that the revealed causality and enhanced prediction performance of the proposed method advance the applicability of machine learning methods to intelligent control during construction.     

基于支持向量回归的多时间序列自回归方法

能耗时间序列涉及多种能源,且各种能源间关系复杂,主要通过多个独立的单时间序列进行预报,这种方式忽略了多时间序列之间的依赖性。为了充分利用多时间序列之间的关联信息以提高预报的准确性,根据机器学习中的向量值函数学习和多任务学习理论,采用支持向量回归(SVR)算法建立了多时间序列的向量值自回归方法和多任务自回归方法。实验结果证明,与多个独立的单时间序列模型相比,通过这种方法建立的多时间序列自回归模型在焦化工序能耗预报中表现出了更好的性能。     

基于最小二乘支持向量机和遗传算法的氧化铝悬浮焙烧能耗估计建模

针对氧化铝悬浮焙烧能耗信息表征和模型应用的实际需求,建立一种最小二乘支持向量机(LS-SVM)能耗估计模型。基于该类模型结合遗传算法(GA)提出一种模型参数优化和工业应用策略。采用灰关联分析确定模型的主输入为主炉温度、烟气含氧量、原料含水量;采用K折交叉验证优化样本数据;采用比较模型预测误差确定核函数为径向基函数(RBF)核。建立输入为能耗参数,输出为模型标志的支持向量机工况模型选择器。能耗估计模型的自学习与动态优化通过样本的更新和聚类实现,模型的选择和投运通过模型选择器依据工况状态实施切换。实验结果表明,建立的焙烧能耗估计模型和模型应用策略,能提高模型的泛化能力、增强模型的工况适应性,是一种有效的焙烧能耗参数估计和分析方法。     

Model predictive control of dissolved oxygen concentration based on a self-organizing RBF neural network

The dissolved oxygen (DO) concentration in activated sludge wastewater treatment processes (WWTPs) is difficult to control because of the complex nonlinear behavior involved. In this paper, a self-organizing radial basis function (RBF) neural network model predictive control (SORBF-MPC) method is proposed for controlling the DO concentration in a WWTP. The proposed SORBF can vary its structure dynamically to maintain prediction accuracy. The hidden nodes in the RBF neural network can be added or removed on-line based on node activity and mutual information (MI) to achieve the appropriate network complexity and the necessary dynamism. Moreover, the convergence of the SORBF is analyzed in both the dynamic process phase and the phase following the modification of the structure. Finally, the SORBF-MPC is applied to the Benchmark Simulation Model 1 (BSM1) WWTP to maintain the DO concentration. The results show that SORBF-MPC effectively provides process control. The performance comparison also indicates that the proposed model's predictive control strategy yields the most accurate for DO concentration, better effluent qualities, and lower average aeration energy (AE) consumption.     

A two-stage method for predicting and scheduling energy in an oxygen/nitrogen system of the steel industry

As essential energy resources in steel industry, oxygen and nitrogen are massively utilized in many production procedures, such as iron-making by blast furnaces, steel-making by converters, etc. The trends of the energy generation/consumption flows along with the related scheduling works play a pivotal role on the energy management of steel enterprises. Aiming at an oxygen/nitrogen system of a steel plant in China, a two-stage predictive scheduling method is proposed in this study for resolving the optimal energy decision-making problem. Given the high cost of time consuming on the load change of air separation units (ASU) of the oxygen/nitrogen system, a Granular-Computing (GrC)-based prediction model is firstly established at the stage of prediction, which extends the predicting length to even a day based on data segment rather than generic point-wise mode. At the stage of optimal scheduling, a mixed-integer program model is constructed on the basis of constraining the number of adjustable energy units, which considers not only the actual capacity of the energy devices, but the practical energy conversion procedure as well. The experiments employing the real data coming from this plant also involve two stages, the long-term prediction and the energy scheduling, and the experimental results exhibit both satisfactory accuracy and practicability. Furthermore, the results of system application also indicate the effectiveness of the proposed method.     

一种基于MBRC值的关系型数据库负载能耗预测模型

数据库负载的能耗解析与建模是构建节能的绿色数据库的基础。针对数据库负载的高能耗问题,将SQL语句消耗的系统资源(CPU和磁盘)映射为时间代价与功率代价,为数据库负载构建能耗预测模型。首先,根据负载的系统资源消耗模式,计算负载的功耗代价;然后,根据负载资源消耗产生的时间代价,为负载构建动态能耗预测模型;最后,利用MBRC值的设置对预测模型的准确度进行深入的研究。实验结果表明,所构建的预测模型能够对数据库负载的能量消耗进行较准确的预测,预测模型的准确度研究有助于在不同的系统环境配置下提升动态能耗预测模型的稳定性与精确度。     

Data-driven modeling and optimization of thermal comfort and energy consumption using type-2 fuzzy method

In the research domain of intelligent buildings and smart home, modeling and optimization of the thermal comfort and energy consumption are important issues. This paper presents a type-2 fuzzy method based data-driven strategy for the modeling and optimization of thermal comfort words and energy consumption. First, we propose a methodology to convert the interval survey data on thermal comfort words to the interval type-2 fuzzy sets (IT2 FSs) which can reflect the inter-personal and intra-personal uncertainties contained in the intervals. This data-driven strategy includes three steps: survey data collection and pre-processing, ambiguity-preserved conversion of the survey intervals to their representative type-1 fuzzy sets (T1 FSs), IT2 FS modeling. Then, using the IT2 FS models of thermal comfort words as antecedent parts, an evolving type-2 fuzzy model is constructed to reflect the online observed energy consumption data. Finally, a multiobjective optimization model is presented to recommend a reasonable temperature range that can give comfortable feeling while reducing energy consumption. The proposed method can be used to realize comfortable but energy-saving environment in smart home or intelligent buildings.