共查询到18条相似文献,搜索用时 234 毫秒
1.
《化工学报》2016,(11)
针对经济性能评估方法中目标函数难以在线计算问题提出一种基于过程数据的在线经济性能分级评估方法。采用自回归潜结构映射(AR-PLS)算法对输入数据矩阵进行分解,在与输出潜变量相关的子空间上建立不同性能等级的离线模型,从而排除无关变化的干扰。然后采用"先标定分区,再对比邻级相似度"的策略设计一个相似度网格模型,将过程性能分为稳定性能级状态和过渡状态,并对离线模型中未出现过的因素造成的性能变化进行识别,以进一步丰富离线数据库。对于不属于最优性能级的过程数据,能够根据变量贡献度诊断造成性能变差的原因。乙烯裂解过程的现场数据测试实验表明本方法可以及时、准确地检测到经济性能的偏移。 相似文献
2.
针对化工过程运行状态在线评估的问题,提出多数据空间全潜结构映射(multi-space total projection to latent structures,MsT-PLS)性能评估方法。该方法采用“离线建模,在线评估”的评估策略。首先对历史多数据输入空间进行全面分解,结合多数据空间基向量提取方法,剔除多数据输入空间中与质量变量无关信息的干扰。在与质量变量相关的多数据输入空间上,建立不同运行性能等级的离线数据网络分类模型,实现“离线建模”。“在线评估”阶段,以数据滑动时间窗为评估单元,将过程性能分为稳定和过渡性能等级,把在线数据与历史性能等级进行相似度匹配。利用过程变量相对贡献度,对性能变化起决定性影响的过程变量进行识别和贡献度分析,为系统性能劣化原因的识别提供了参考。最后,应用到乙烯裂解过程在线性能评估中,说明了本评估方法可以对系统进行准确的在线性能评估。 相似文献
3.
针对化工过程运行状态在线评估的问题,提出多数据空间全潜结构映射(multi-space total projection to latent structures,Ms T-PLS)性能评估方法。该方法采用"离线建模,在线评估"的评估策略。首先对历史多数据输入空间进行全面分解,结合多数据空间基向量提取方法,剔除多数据输入空间中与质量变量无关信息的干扰。在与质量变量相关的多数据输入空间上,建立不同运行性能等级的离线数据网络分类模型,实现"离线建模"。"在线评估"阶段,以数据滑动时间窗为评估单元,将过程性能分为稳定和过渡性能等级,把在线数据与历史性能等级进行相似度匹配。利用过程变量相对贡献度,对性能变化起决定性影响的过程变量进行识别和贡献度分析,为系统性能劣化原因的识别提供了参考。最后,应用到乙烯裂解过程在线性能评估中,说明了本评估方法可以对系统进行准确的在线性能评估。 相似文献
4.
针对化工过程输入输出数据间非线性关系问题,提出一种基于多数据空间局部加权潜结构映射(multispace locally weighted projection to latent structures,Ms-LWPLS)的网络化性能分级评估方法。该方法将历史数据分成不同性能等级的集合,利用Ms-LWPLS方法提取不同性能等级训练数据的过程变化,获得训练数据与性能等级标签之间的非线性映射结构,实现输入数据与性能等级之间的网络化"离线建模"。得到模型后,以数据滑动时间窗为评估单元,将滑动窗口数据输入到训练好的神经网络模型中,根据网络输出划分过程当前性能等级,并构造过渡性能系数,将稳态性能等级和过渡性能等级进行识别和区分。最后,将该方法应用到乙烯裂解过程在线性能评估中,说明此性能评估方法的有效性和准确性。 相似文献
5.
针对化工过程输入输出数据间非线性关系问题,提出一种基于多数据空间局部加权潜结构映射(multi-space locally weighted projection to latent structures,Ms-LWPLS)的网络化性能分级评估方法。该方法将历史数据分成不同性能等级的集合,利用Ms-LWPLS方法提取不同性能等级训练数据的过程变化,获得训练数据与性能等级标签之间的非线性映射结构,实现输入数据与性能等级之间的网络化“离线建模”。得到模型后,以数据滑动时间窗为评估单元,将滑动窗口数据输入到训练好的神经网络模型中,根据网络输出划分过程当前性能等级,并构造过渡性能系数,将稳态性能等级和过渡性能等级进行识别和区分。最后,将该方法应用到乙烯裂解过程在线性能评估中,说明此性能评估方法的有效性和准确性。 相似文献
6.
提出了一种基于过程迁移的间歇过程质量预报方法,旨在解决新间歇过程数据不足难以建立准确预报模型的问题。该方法基于多元统计回归分析模型,通过构建相似间歇过程间的共同潜变量空间,将已有相似间歇过程的数据信息迁移应用到未建模的新间歇过程中,实现新间歇过程的快速建模和质量预报。在线应用时,利用在线数据不断更新过程迁移模型;同时,实时估计模型预测误差的置信区间,判断预报模型预测误差的稳定性;为克服相似过程间可能存在的差异给迁移模型带来的不利影响,根据数据相似度逐步剔除相似间歇过程数据。最后,通过仿真实验验证了所提方法的有效性。 相似文献
7.
提出了一种基于过程迁移的间歇过程质量预报方法,旨在解决新间歇过程数据不足难以建立准确预报模型的问题。该方法基于多元统计回归分析模型,通过构建相似间歇过程间的共同潜变量空间,将已有相似间歇过程的数据信息迁移应用到未建模的新间歇过程中,实现新间歇过程的快速建模和质量预报。在线应用时,利用在线数据不断更新过程迁移模型;同时,实时估计模型预测误差的置信区间,判断预报模型预测误差的稳定性;为克服相似过程间可能存在的差异给迁移模型带来的不利影响,根据数据相似度逐步剔除相似间歇过程数据。最后,通过仿真实验验证了所提方法的有效性。 相似文献
8.
针对化工过程中因输入输出数据间非线性关系造成在线性能评估准确度不足的问题,提出一种基于多数据空间非线性迭代偏最小二乘和高斯过程回归(multi-space nonlinear iterative partial least squares and Gaussian process regression,Ms-NIPLS-GPR)的性能分级评估方法。首先将性能相近的过程历史数据划分成不同性能等级的集合,利用Ms-NIPLS方法提取不同性能等级训练数据的特征子空间,然后用GPR获得特征子空间与性能等级标签之间的非线性映射结构,建立输入数据与性能等级之间的离线模型。得到模型后,在线评估当前过程性能等级,同时通过构造过渡性能系数来区分稳态性能等级和稳态性能等级间的过渡性能状态。最后,将该方法应用到乙烯裂解过程在线性能评估中,说明该性能评估方法的有效性和准确性。 相似文献
9.
从建立潜变量自回归(AR)模型的角度出发,提出了一种基于潜变量自回归(LVAR)算法的化工过程动态建模与监测方法,旨在提取动态潜变量的同时给出各潜变量的AR模型。LVAR算法在最小化潜变量的AR模型残差的约束下,通过同时搜寻投影变换向量与AR系数向量,实现了对动态潜变量的特征提取及其AR模型的建立。此外,LVAR算法通过先提取动态潜变量后提取静态成分信息的方式,有效地区分了采样数据中的自相关性与交叉相关性。在对比实验中,通过比较分析LVAR方法与其他三种典型的动态过程监测方法在经典化工过程对象上的故障监测结果,验证了LVAR方法在动态过程监测上的优越性与可靠性。关键词:主成分分析;故障检测;缺失数据;过程系统 相似文献
10.
从建立潜变量自回归(AR)模型的角度出发,提出了一种基于潜变量自回归(LVAR)算法的化工过程动态建模与监测方法,旨在提取动态潜变量的同时给出各潜变量的AR模型。LVAR算法在最小化潜变量的AR模型残差的约束下,通过同时搜寻投影变换向量与AR系数向量,实现了对动态潜变量的特征提取及其AR模型的建立。此外,LVAR算法通过先提取动态潜变量后提取静态成分信息的方式,有效地区分了采样数据中的自相关性与交叉相关性。在对比实验中,通过比较分析LVAR方法与其他三种典型的动态过程监测方法在经典化工过程对象上的故障监测结果,验证了LVAR方法在动态过程监测上的优越性与可靠性。 相似文献
11.
近红外光谱分析技术作为一种非侵入性的分析手段在工业上得到了广泛应用。然而,大多数近红外模型的波长选择方法是离线建立的,无法有效跟踪过程特性的变化。提出了一种新的在线自适应波长选择方法——在线自适应区间高斯过程回归波长选择方法(adaptive interval Gaussian process regression, AIGPR),并用于汽油调和过程中的近红外模型的建立。该方法可以根据待测样本的特性对波长结构进行调整。为了降低在线应用的计算成本,该方法分为离线和在线两个部分,离线部分将光谱分割成若干个波长区间,并在每个波长区间上建立局部模型,为在线应用做准备;在线部分中根据划分规则将采样得到待测样本光谱进行分割并代入相应的局部模型中计算波长区间重要性指标,获得最优波长区间。在汽油辛烷值的光谱数据上证明了该方法的有效性。与重要变量投影法和改进的相关系数法相比,该方法具有更好的性能。 相似文献
12.
Although industrial processes often perform perfectly under design conditions,they may deviate from the optimal operating point owing to parameters drift,environmental disturbances,etc.Thus,it is necessary to develop efficacious strategies or procedure to assess the process performance online.In this paper,we explore the issue of operating optimality assessment for complex industrial processes based on performance-similarity considering nonlinearities and outliers simultaneously,and a general enforced online performance assessment framework is proposed.In the offline part,a new and modified total robust kernel projection to latent structures algorithm,T-KPRM,is proposed and used to evaluate the complex nonlinear industrial process,which can effectively extract the optimal-index-related process variation information from process data and establish assessment models for each performance grades overcoming the effects of outlier.In the online part,the online assessment results can be obtained by calculating the similarity between the online data from a sliding window and each of the performance grades.Furthermore,in order to improve the accuracy of online assessment,we propose an online assessment strategy taking account of the effects of noise and process uncertainties.The Euclidean distance between the sliding data window and the optimal evaluation level is employed to measure the contribution rates of variables,which indicate the possible reason for the non-optimal operating performance.The proposed framework is tested on a real industrial case:dense medium coal preparation process,and the results shows the efficiency of the proposed method comparing to the existing method. 相似文献
13.
This paper is concerned with developing an online algorithm for detecting and estimating systematic errors (gross errors) in mass and energy balances from measurement data. This method has its application in diagnosing problems in an oil sands process. Conventional techniques for detecting gross errors presently exist for offline application. The proposed online method entitled Dynamic Bayesian Gross Error Detection (DBGED) is a dynamic Bayesian analogue of traditional gross error detection, and can be considered as a type of Switching Kalman Filter. As such, related topics such as Kalman Filtering, observability and Dynamic Bayesian Inference are discussed. In addition to detecting gross errors, the DBGED also estimates detected gross error magnitudes in real time (as an augmented state variable) so that future measurements can be corrected. When the estimate converges to yield satisfactory prediction errors, gross error estimation is stopped and instruments are corrected with a constant gross error correction term. DBGED performance is demonstrated through a simulation example and an example of an industrial application. 相似文献
14.
Nazatul Aini Abd MajidMark P. Taylor John J.J. ChenBrent R. Young 《Computers & Chemical Engineering》2011,35(11):2457-2468
This paper describes the development of a new ‘cascade’ monitoring system for the aluminium smelting process that uses latent variable models. This system is based on the changes of variability patterns within a feeding cycle which are used to provide indications of faults and their possible causes. The system has been tested offline using 31 data sets. The performance of the system to detect an anode effect has been compared with a typical latent variable model that monitors the change of behaviour at every time instant. The results show that the ‘cascade’ monitoring system is able to detect abnormal events. It was possible to relate each event with specific patterns associated with abnormalities thus facilitating later fault diagnosis. 相似文献
15.
16.
17.
Hiromasa Kaneko Masamoto Arakawa Kimito Funatsu 《American Institute of Chemical Engineers》2009,55(1):87-98
Soft sensors are used widely to estimate a process variable which is difficult to measure online. One of the crucial difficulties of soft sensors is that predictive accuracy drops due to changes of state of chemical plants. To cope with this problem, a regression model can be updated. However, if the model is updated with an abnormal sample, the predictive ability can deteriorate. We have applied the independent component analysis (ICA) method to the soft sensor to increase fault detection ability. Then, we have tried to increase the predictive accuracy. By using the ICA‐based fault detection and classification model, the objective variable can be predicted, updating the PLS model appropriately. We analyzed real industrial data as the application of the proposed method. The proposed method achieved higher predictive accuracy than the traditional one. Furthermore, the nonsteady state could be detected as abnormal correctly by the ICA model. © 2008 American Institute of Chemical Engineers AIChE J, 2009 相似文献
18.
BACKGROUND: Online measurements of key emulsion polymerization attributes, such as conversion and molar mass distribution, are unavailable. Costly offline measurements at low sampling frequencies with time delays usually lead to insurmountable challenges in real‐time product quality monitoring and process/product control. RESULTS: We developed an online calorimetric method monitoring the evolution of conversion and molecular weight in complex polymerization reactors. Our experiments were carried out in a 1 L reactor to produce polystyrene homopolymer. Monomer conversion was obtained in real time from polymerization rate, which was estimated from temperature measurements using platinum thermal transducers. The calorimetric model was validated offline for batch and semi‐batch emulsion polymerization of styrene with and without transfer agents. The conversion was validated using offline gravimetry. The molecular weights measured offline via size exclusion chromatography with multiple detectors compared well with those estimated online using the calorimetric method. CONCLUSION: We found that a semi‐batch emulsion polymerization process can be controlled online to approach living polymerization involving transfer agents. Thus our model is suitable as a ‘soft‐sensor’ for real‐time control applications. Copyright © 2009 Society of Chemical Industry 相似文献