竖炉焙烧过程的多变量智能优化控制

针对铁矿选矿中的竖炉焙烧过程具有综合复杂性和产品质量指标一磁选管回收率难以在线测量因而不易实现优化控制的难题,通过对焙烧过程动态特性和人工操作模式的分析,将智能方法与前馈、反馈控制相结合,提出一种基于磁选管回收率、台时产量、煤气消耗等综合生产指标的多变量智能优化控制方法.根据综合生产指标的目标值和边界条件的变化在线对控制回路的设定值进行自动调整而实现优化控制.将提出的方法应用于国内某大型选矿厂竖炉焙烧过程,实现了综合生产指标的优化控制,取得显著应用效果.     

基于并发改进偏最小二乘的质量相关和过程相关的故障诊断

并发潜结构投影(CPLS)与传统贡献图法是多元统计过程监控中常用的故障检测与诊断方法.过程监控通常要求监测的时效性与诊断的准确性,然而,由于CPLS计算复杂以及传统贡献图诊断结果易受初始贡献较大的变量影响,因此它们反馈的监控结果可能并不准确.针对上述问题分别提出一种并发改进偏最小二乘(CMPLS)方法和新的相对贡献图法...     

磁选管回收率智能混合预报方法

针对衡量竖炉焙烧过程焙烧矿质量好坏的关键工艺指标磁选管回收率难以在线测量、化验结果滞后的难题，采用神经网络、案例推理和专家系统技术，提出了由神经网络预报模型、案例推理预报模型、自校正模型组成的磁选管回收率智能混合预报模型，讨论了模型的结构、主要功能和实现算法，并成功应用于赤铁矿选矿厂竖炉焙烧过程．应用效果表明，在工况正常与异常两种情况下，所提出的方法均能准确预报磁选管回收率．将磁选管回收率预报模型应用于竖炉焙烧过程的优化控制，使磁选管回收率保持在最优工艺指标范围之内，取得了明显的成效．     

基于参量预报的磁选管回收率智能优化控制

竖炉焙烧过程的关键工艺指标磁选管回收率难以实时测量,因而实现优化控制很困难.将优化设定、参量预报与回路控制技术相结合,提出一种磁选管回收率的智能优化控制方法.基于案例推理的优化设定模型根据工况的变化和磁选管同收率的实时预报值给出基础控制回路的设定值,并通过先进的控制方法实现回路的稳定控制.该方法应用于竖炉焙烧过程的生产实际,使磁选管回收率的实际值保持在其目标值范围内,取得显著应用成效.     

基于T-PLS贡献图方法的故障诊断技术

多变量统计过程监控对于复杂工业过程是一种有效的故障检测和诊断技术. 最小二乘(或称潜空间投影)模型是多变量统计过程监控中常用的一种投影模型, 能够同时对过程数据和质量数据进行建模. 讨论了一种新的基于全潜空间投影模型的故障诊断技术. 全潜空间投影模型中有4个检测统计量. 提出了一种新的T2贡献图计算方法, 对于所有检测统计量, 得到了相应的贡献图算法. 为了确定一个变量是否发生了故障, 计算所有变量贡献图的控制限. 该技术可以将辨识到的故障变量分为与Y有关和与Y无关的两类. 基于Tennessee Eastman过程的案例研究表明了该技术的有效性.     

数字电路并发差错检测的新概念

并发差错检测是提高数字电路与系统可信的重要技术。文中建立了一种基于并发差错检测电路的结构模型。它由实现电路基本功能的基本功能模块和实现电路并发差错检测功能的检测器部分联所构成;提出了表征基于部分自校验概念的并发差错检测机制的一组新概念：精简强故障保险、精简强变量分离、精简强自校验、ｋ－容错精简强故障保险、ｋ－容错精简强变量分离和ｋ－容错精简强自校验,并研究了数字电路并发差错检测的主要概念之间的关系     

基于数据变化率和重构贡献图的微小故障诊断方法

针对复杂工业过程的微小故障诊断问题,提出一种数据预处理与重构贡献图相结合的故障诊断方法;为了克服非高斯分布数据对故障检测准确性的影响,通过基于数据变化率的方法对样本原始数据进行预处理后,可以有效地检测过程变量的微小故障,以此建立故障诊断主元分析模型;检测出系统故障后,为了提高故障辨识准确度,采用一种平均残差差值重构贡献图的方法对故障进行辨识;通过正常样本数据和故障数据在残差子空间中的投影,获取两个数值的残差差值向量,计算重构贡献值来确定故障变量;以田纳西-伊斯曼(TE)过程为对象进行了故障诊断仿真实验,并与传统贡献图和重构贡献图方法的辨识准确率相比较,结果表明所提方法具有良好的故障诊断性能。     

基于核直接分解的过热蒸汽系统故障诊断方法

为提高过热蒸汽系统的运行效率并减少非紧要故障的报警率,本文提出一种质量相关的非线性故障检测与诊断方法.首先,利用核函数将过程变量映射到高维特征空间以消除原始变量之间的非线性耦合.然后,在特征空间进行核直接分解得到两个正交子空间,并在两个子空间中分别设计统计量指标进行质量相关的故障检测.在此基础上,利用偏微分贡献图提取每个变量对联合统计量指标的贡献率,并根据贡献率大小最终确定故障变量.仿真结果表明,所提出的方法能够准确区分影响过热蒸汽温度和不影响过热蒸汽温度的故障,有效降低了非紧要故障的报警率,提高了过热蒸汽系统的运行效率.     

竖炉焙烧过程综合自动化系统

针对竖炉焙烧过程的工艺特点及技术要求,基于智能技术提出了实现综合生产指标优化的竖炉焙烧过程综合自动化系统,讨论了由智能优化、过程控制和过程管理三层结构组成的综合自动化系统的结构、功能和控制策略。用智能优化设定模型、炉况诊断模型、智能预报模型及回路控制,实现了优化综合生产指标的目标。所提出的系统成功应用于桌选矿厂竖炉焙烧生产过程,实现了竖炉焙烧生产过程的优化控制、优化运行和优化管理,取得了明显的应用成效。     

基于案例推理的竖炉故障预报系统

为降低竖望炉焙烧过程的故障发生率,基于故障机理的分析,将过程参量预报与案例推理技术相集成,提出了竖炉焙烧过程的智能故障预报方法.参量量预报模型对不易在线连续测量但能反映故障征兆的关键工艺参数进行实时预报,在此基础上,采用案例推理技术对焙烧过程进行全面分析并给出一些典型故障发生的概率和操作指导.将所建立的故障预报系统成功应用于竖炉焙烧过程的生产实际中,故障发生率明显降低,取得了显著应用成效.     

Hybrid intelligent control for optimal operation of shaft furnace roasting process

A hybrid intelligent control method is proposed to control the technical indices into their desired range. This is realized by on-line adjusting the set-points of control loops for optimal operation of the shaft furnace in response to changes in operating points. The controller consists of six modules, namely a pre-setting model for control loop set-points, a predictive model for technical index, a feedforward compensator using predictive model, a feedback compensator, a fault working situation diagnosis and a fault tolerant control model. The proposed approach has been successfully applied to the roasting process of shaft furnace in a mineral processing plant in China and its efficiency has been verified by the practical application results.     

运行控制系统集中式容错控制方法

本文针对运行控制系统,建立了运行优化控制过程的双层结构模型.在此基础上,通过建立相应的自适应故障诊断算法,提出了保证在系统有故障和干扰时仍能渐近优化指标的集中式容错控制方法,利用李雅普诺夫稳定性理论分析了自适应故障诊断算法的构建.已证明:该方法通过调整已优化的设定值来保证在回路控制层出现故障时整个运行控制仍可收敛到其原有的优化控制效果.该方法属于非完备容错控制,仿真结果验证了所提方法的有效性.     

Active fault-tolerant control against actuator fault and performance analysis of the effect of time delay due to fault diagnosis

This paper discusses the problem of fault-tolerant control against actuator fault, derives the time spent at each steps in fault diagnosis which is called as the time delay due to fault diagnosis and quantitatively analyzes its effect on the faulty system’s performance. A fault diagnosis algorithm is first proposed. The proposed fault tolerant controller is designed to guarantees that all signals in the closed-loop system are semi-globally uniformly ultimately bounded, where the controller singularity is avoided without projection algorithm. What’s more, the analytical expression of the time delay is derived strictly. Further, the quantitative analysis of system performance which is degraded by the time delay is developed, and the conditions that the magnitudes of the faults should be satisfied such that the faulty system controlled by the normal controller remains bounded even stable during the time delay are derived. In addition, the corresponding solution to the adverse effect of the time delay is proposed. Finally, an experimental test shows that the proposed control algorithm has a very reliable efficiency.     

Quality relevant nonlinear batch process performance monitoring using a kernel based multiway non-Gaussian latent subspace projection approach

Multiway kernel partial least squares method (MKPLS) has recently been developed for monitoring the operational performance of nonlinear batch or semi-batch processes. It has strong capability to handle batch trajectories and nonlinear process dynamics, which cannot be effectively dealt with by traditional multiway partial least squares (MPLS) technique. However, MKPLS method may not be effective in capturing significant non-Gaussian features of batch processes because only the second-order statistics instead of higher-order statistics are taken into account in the underlying model. On the other hand, multiway kernel independent component analysis (MKICA) has been proposed for nonlinear batch process monitoring and fault detection. Different from MKPLS, MKICA can extract not only nonlinear but also non-Gaussian features through maximizing the higher-order statistic of negentropy instead of second-order statistic of covariance within the high-dimensional kernel space. Nevertheless, MKICA based process monitoring approaches may not be well suited in many batch processes because only process measurement variables are utilized while quality variables are not considered in the multivariate models. In this paper, a novel multiway kernel based quality relevant non-Gaussian latent subspace projection (MKQNGLSP) approach is proposed in order to monitor the operational performance of batch processes with nonlinear and non-Gaussian dynamics by combining measurement and quality variables. First, both process measurement and quality variables are projected onto high-dimensional nonlinear kernel feature spaces, respectively. Then, the multidimensional latent directions within kernel feature subspaces corresponding to measurement and quality variables are concurrently searched for so that the maximized mutual information between the measurement and quality spaces is obtained. The I² and SPE monitoring indices within the extracted latent subspaces are further defined to capture batch process faults resulting in abnormal product quality. The proposed MKQNGLSP method is applied to a fed-batch penicillin fermentation process and the operational performance monitoring results demonstrate the superiority of the developed method as apposed to the MKPLS based process monitoring approach.     

基于动态建模与重构的列车轴承故障检测和定位

列车运行时轴承故障的检测与定位对于列车运行安全与健康维护至关重要. 现有的轴承故障报警系统主要是基于单一轴温变量的规则诊断, 报警不及时. 针对上述问题, 本文结合运行于相似环境和速度的同车多轴轴温的相关性及轴温动态性, 提出了一种数据驱动的基于多轴轴温动态潜结构的列车轴承故障检测与定位方法. 首先, 提出基于动态内在典型相关分析(Dynamic-inner canonical correlation analysis, DiCCA)的列车多轴轴温动态潜结构建模方法; 其次, 利用所建立的模型, 提出基于DiCCA综合指标的列车轴承故障检测方法; 在此基础上, 提出基于DiCCA多向重构的列车轴承故障定位方法. 利用某列车实际运行时的轴温数据进行验证, 结果表明了所提方法的有效性.     

Real-time SVD-based detection of multiple combined faults in induction motors

Early detection of induction motor faults has been a main subject of investigation for many years. Several approaches have been proposed for identifying one or more faults treated in an isolated way. Multiple combined faults on induction motors represent a big challenge since the reliable diagnosis of a faulty condition under the presence of two or more simultaneous faults is really difficult. This work introduces a novel methodology that merges singular value decomposition, statistical analysis, and artificial neural networks for multiple combined fault identification. Obtained results demonstrate its high effectiveness on detecting faulty bearings, unbalance, broken rotor bars, and all their possible combinations. The developed field programmable gate array-based implementation offers a portable low-cost solution for online classification of the rotating machine condition in real time. Thanks to its generalized nature, the introduced approach can be extended for detecting multiple combined faults under different working conditions by a proper calibration.