基于注意力机制的Multi-head CNN-LSTM软测量建模

软测量建模通过选取辅助变量,建立辅助变量与关键质量变量关系,能够高效地实现对关键质量变量的预测。然而当辅助变量维数较高,且对关键质量变量的影响程度不一时,网络预测误差将较大。针对这一问题,提出一种基于注意力机制的Multi-head CNNLSTM模型,首先根据辅助变量自身属性和特点将其切分成多组子变量后,使用多组独立并行工作的CNN-LSTM群对其子变量进行单独处理;再提取各组子变量上的特征向量,融合注意力机制,实现子变量特征向量的权重分配。所提算法不需提前根据工艺知识选择辅助变量,而是通过深度学习机制自动选择特征;最后,在乙烯精馏塔塔顶乙烷浓度软测量建模中进行应用,所提模型的预测精度优于LSTM以及CNN-LSTM软测量模型。     

生物发酵过程变量的NN-MIV软测量模型

针对生物发酵过程中关键生化参量的在线检测问题,提出一种基于平均影响值的神经网络(NN-MIV)变量选择方法。发酵过程初始软测量模型含有多个辅助变量,MIV方法计算辅助变量对主变量的外部贡献率,NN方法计算辅助变量对主变量的内部贡献率,文中将两种方法综合提出了NN-MIV方法,其计算出的辅助变量对主变量的贡献率稳定性好。利用筛选出最优辅助变量建立软测量模型,对青霉素发酵过程做了数值仿真实验,与传统的变量筛选方法相比,该方法筛选出的辅助变量少,建立的软测量模型估计精度高。     

工业软测量模型结构与输入变量选择的研究

针对过程工业中难以直接测量的变量建立其软测量模型,对于实现关键指标的在线监测和实时控制具有十分重要的意义.变量的选择直接关系到神经网络软测量模型的预测性能,针对现有输入变量和网络结构选择方法在工业应用中的不足,提出了一种基于敏感度分析的方法来确定网络输入变量集和前馈神经网络隐含层节点个数,并建立了高密度聚乙烯(HDPE...     

基于互信息的软测量变量选择

针对软测量建模中的变量选择问题,提出了一种结合信息论中最大熵和互信息的方法。该方法采用最大熵原理,对软测量中各辅助变量和主导变量的概率分布进行估计,得到主导变量和各辅助变量间的互信息,这些互信息间接地反映了主导变量和各辅助变量间的相关性,包括线性相关和非线性相关。然后产生随机样本并计算和主导变量间的互信息,重复多次该过程就可以得到一个无关变量和主导变量间的互信息样本。用T检验寻找一个阈值作为判断相关性的标准。对于互信息小于阈值的变量作不相关变量处理,并结合测试效果筛选出最佳的软测量辅助变量。仿真结果证明,基于互信息的软测量变量选择方法具有直观、简单实用和可靠性高的优点,并且有效地改善了模型的估计精度。     

分布式伪线性卡尔曼滤波纯方位跟踪北大核心CSCD

针对纯方位跟踪(BOT)的非线性滤波和距离可观测性较差问题,提出了一种新的分布式多传感器辅助变量伪线性卡尔曼滤波器(DM-IVPLKF)。该滤波器利用辅助变量伪线性卡尔曼滤波器(IVPLKF)独立处理目标测量值,通过偏差补偿伪线性卡尔曼滤波器(偏差补偿PLKF)解决由于量测向量与伪线性噪声相关而产生的偏差,将递归辅助变量估计方法嵌入偏差补偿PLKF中,对目标状态估计和协方差进行修正。所提算法利用多传感器最优信息融合准则,对目标状态进行融合估计。然后,推导了多传感器BOT的克拉默-拉奥下界(CRLB)。通过仿真实验,将所提算法与传统算法进行对比,仿真结果证明了所提算法具有较高的跟踪精度。     

支持向量机在中药浓缩浓度软测量中的应用

针对中药浓缩过程中浓缩液浓度估计问题,提出了支持向量机的软测量建模方法。分析了中药浓缩过程及工艺,选择6个过程变量作为辅助变量,用支持向量回归的方法建立软测量模型,并利用过程数据进行参数寻优和校验。利用优化后的模型对中药浓缩过程浓度进行了预测,通过数据验证了模型的学习性能和泛化性能。结果表明建立的软测量模型实现了对中药浓度较为精确的预测,使用支持向量机方法建模用于小样本学习,计算速度快,具有较强的泛化性。     

基于PSO-Elman模型的火电厂烟气含氧量预测

针对火电厂烟气含氧量测量精度较低、测量成本较大等问题,提出基于PSO-Elman网络模型的烟气含氧量预测方法。选择合理的相关辅助变量,引入Elman神经网络建立辅助变量与烟气含氧量的关系模型;利用PSO对Elman中所有的权值、阈值进行寻优,将其最优权值和阈值作为初值赋给Elman;经过训练,建立基于PSO-Elman模型的预测模型,完成火电厂烟气含氧量的软测量。通过仿真,与Elman网络和LSSVM模型的预测结果作对比,所提模型具有较高的预测精度和良好的泛化能力。     

基于改进BP神经网络的菌体浓度软测量

提出一种改进的BP神经网络(IBPNN)用以建立发酵过程中菌体浓度软测量模型.结合菌体浓度变化范围大这一特点,将传统BP网络的误差函数进行了改进,并利用最优停止法对网络进行训练.避免了过拟合现象.最后针对诺西肽发酵过程中茵体浓度的估计问题,根据隐函数定理选取辅助变量,应用IBPNN建立菌体浓度软测量模型,实验结果验证了所提方法的有效性.     

软测量模型的建立

软件测量是采用过程中比较容易测量的辅助变量，构造推断估计器来推算出难以测量或根本无法测量的关键工艺参数；是根据某种最优准则，选择一组既与主导变量有密切联系又容易测量的变量，即辅助变量，通过构造某种数学关系，用计算机软件实现对主导变量的在线估计，介绍了软测量的核心技术，并重点阐述了软测量模型建立的方法，还给出了建立一个完整的软测量模型的步骤。     

一种基于EGMM的高斯过程回归软测量建模

提出了一种基于误差高斯混合模型（EGMM）的高斯过程回归（GPR）软测量方法．首先,选择合适的变量组成误差数据集,利用贝叶斯信息准则优化得到合适的高斯成分的个数;然后用EGMM对误差数据进行拟合计算得到条件误差均值和方差的表达式;最后当新的数据到来时,用建立的GPR模型进行输出预测,并利用EGMM模型得到的条件误差均值对输出进行补偿,从而得到更加精确的建模结果．通过数值仿真及硫回收装置（SRU）的H₂S浓度的软测量,进一步验证所提算法的可行性和有效性．     

Optimal composite structures by deflection-variable programming

This paper deals with the problem of optimising multilaminar fibre-reinforced continua. A formulation is proposed in which primary optimisation variables are the nodal deflections of the finite element model. This leads to a decomposition of the problem into an inner and an outer subproblem; algorithms for solving both are described and numerical results given. It is shown that this approach is convenient for solving the nonlinear mixed integer program involved and allows the optimal number of layers in each element, the layer thicknesses and the fibre angles are to be determined simultaneously for very general inequality constraints on stresses and deflections. The case of structures of maximum stiffness is particularly considered.     

The reduced cost branch and bound algorithm for mixed integer programming

A different branch and bound algorithm for mixed integer programming is presented. Unlike standard linear programming based branch and bound algorithms, where a single fractional variable (or Special Ordered Set) is selected for problem separation, the proposed method selects groups of variables for separation on the basis of their reduced cost in an LP relaxation. The proposed method restricts a large portion of the integer variables to zero on one branch. The net effect is that the original integer program is solved by optimizing a series of smaller, more tightly restricted, integer programs. The authors have programmed the algorithm using the Extended Control Language of the IBM MPSX/370-MIP/370 mixed integer programming package. Computational results are presented that demonstrate the efficiency of the method on problems where the $\text{0}\text{1}$ variables are partitioned into multiple choice constraints containing special ordered sets of variables. While the computational results are limited to this class of problems the algorithm can, in theory, be applied to any mixed integer programming problem.     

Heuristic algorithms for the general nonlinear separable knapsack problem

We consider the nonlinear knapsack problem with separable nonconvex functions. Depending on the assumption on the integrality of the variables, this problem can be modeled as a nonlinear programming or as a (mixed) integer nonlinear programming problem. In both cases, this class of problems is very difficult to solve, both from a theoretical and a practical viewpoint. We propose a fast heuristic algorithm, and a local search post-optimization procedure. A series of computational comparisons with a heuristic method for general nonconvex mixed integer nonlinear programming and with global optimization methods shows that the proposed algorithms provide high-quality solutions within very short computing times.     

能效优先的用户关联与功率控制协同优化机制

在异构蜂窝网络中,针对系统的能效,提出了一种基于效用函数最大化模型的用户关联与功率控制协同优化方案,该方案表示为非线性混合整数问题。为了求得该问题的最优解,设计了一种迭代算法,首先将原问题转换为带参数的多项式形式的问题,在外层循环利用Dinkelbach方法求得最佳的能效因子,然后在内层循环分别求得最佳的用户关联矩阵和传输功率。最终实验结果表明,用户关联与功率控制协同的优化方案在能效和负载平衡方面比固定功率条件下的用户关联策略的性能更优。     

Optimization of nonlinear trusses using a displacement-based approach

A displacement-based optimization strategy is extended to the design of truss structures with geometric and material nonlinear responses. Unlike the traditional optimization approach that uses iterative finite element analyses to determine the structural response as the sizing variables are varied by the optimizer, the proposed method searches for an optimal solution by using the displacement degrees of freedom as design variables. Hence, the method is composed of two levels: an outer level problem where the optimal displacement field is searched using general nonlinear programming algorithms, and an inner problem where a set of optimal cross-sectional dimensions are computed for a given displacement field. For truss structures, the inner problem is a linear programming problem in terms of the sizing variables regardless of the nature of the governing equilibrium equations, which can be linear or nonlinear in displacements. The method has been applied to three test examples, which include material and geometric nonlinearities, for which it appears to be efficient and robust. Received December 4, 2000     

一类混杂系统建模和优化控制的研究

为解决混杂系统优化控制的计算复杂性问题,针对结合逻辑规则的工业过程混杂模型,采用结合约束程序的混合整数非线性规划算法,求解这种混杂模型的优化控制。计算实例表明,通过混杂建模方法,可以充分利用工业对象的机理模型以及操作工经验或专家经验,建立系统的更精确模型;结合约束程序混合整数非线性规划算法可以较迅速地求解混杂模型优化控制问题,从而使该方法可以用于工业过程实时控制中。     

Jamming layered membrane gripper mechanism for grasping differently shaped-objects without excessive pushing force for search and rescue missions

A gripper comprising a jamming membrane was developed with the capability of grasping collapsible, soft, and fragile objects without applying heavy pressure. In disaster sites, it is necessary for robots to grab various types of objects, such as fragile objects. Deformable grippers that contain bags filled with powder cannot handle collapsible or soft objects without excessive pressure. Changing powder density relatively by changing inner volume is one approach to overcome this problem. By expanding the concept and simplifying the variable inner volume of the gripping mechanism, we developed a jamming membrane comprising the following three layers: outer layer and inner layer made of rubber and a powder layer in between the outer and inner rubber layer. This jamming membrane allows collapsible, soft, or fragile objects to be held securely without applying too much pressure. We designed and developed a prototype of the jamming membrane gripper. Our experiments confirmed the validity of the proposed jamming membrane mechanism.     

An interactive approach based on a discrete differential evolution algorithm for a class of integer bilevel programming problems

This paper presents an interactive approach based on a discrete differential evolution algorithm to solve a class of integer bilevel programming problems, in which integer decision variables are controlled by an upper-level decision maker and real-value or continuous decision variables are controlled by a lower-level decision maker. Using the Karush--Kuhn–Tucker optimality conditions in the lower-level programming, the original discrete bilevel formulation can be converted into a discrete single-level nonlinear programming problem with the complementarity constraints, and then the smoothing technique is applied to deal with the complementarity constraints. Finally, a discrete single-level nonlinear programming problem is obtained, and solved by an interactive approach. In each iteration, for each given upper-level discrete variable, a system of nonlinear equations including the lower-level variables and Lagrange multipliers is solved first, and then a discrete nonlinear programming problem only with inequality constraints is handled by using a discrete differential evolution algorithm. Simulation results show the effectiveness of the proposed approach.     

一类非线性系统最大可控不变集求解

针对非线性系统线性化在状态约束下最优鲁棒控制求解问题,提出了一种基于混合系统的非线性系统最大鲁棒控制不变集的方法.对于一类非线性系统通过平衡点线性化的方法转化为多模态的混合系统,并进行了混合逻辑动态模型(MLD)的建模,在不变集基本理论的基础上,通过多参数规划的混合整数规划(MIQP)的方法迭代求解最大可控不变集,并求得不变集内的最优控制器,解决系统的状态约束问题.通过一个非线性系统的实例进行建模、仿真,证明了本方法的可行性.