基于因果分析的烧结生产状态预测模型

烧结是高炉炼铁系统中的重要生产单元,其生产水平高低直接关系炼铁企业的生产效益。烧结过程具有时滞性和非线性特征,为了实现对烧结生产状态的准确预测,本文综合自相关分析、收敛交叉映射和误差反向传播神经网络等方法,融合因果性机理和黑箱模型,建立了基于因果分析的烧结生产状态预测模型。该模型通过因果分析层选取解释变量集、自相关窗口和因果性窗口,并通过神经网络层实现对6个烧结生产状态关键变量的准确预测。经过工业数据测试,该模型预测平均误差控制在0.5%～3.1%之间,能够有效辅助工厂进行烧结状态调整。     

Time delay neural network modeling for particle size in SAG mills

Particle size is a very important variable in semi-autogenous grinding processes. It is desirable to measure the variable efficiently or even predict its variations in advance. In this paper, the time delay neural network model is developed to predict the feed particle size of a semi-autogenous grinding mill, and the Levenberg–Marquardt algorithm is used to train the network. Results show that the model predicted values fit well with the industrial operating data. The proposed model can predict the particle size in advance and allow adequate time to take corrective actions during abnormal operations, and therefore provide a great advantage in monitoring and control of the industrial processes.     

炼化装置故障链式效应定量安全预警方法

炼化装置故障及其故障链式效应对油气生产和人民生命安全所造成的危害严重。从故障链角度进行事故风险研究,提出炼化装置故障链式效应定量安全预警方法。首先分析炼化装置故障链式关系结构,基于目标树成功树-动态主逻辑图（GTST-DMLD）建立其故障链式效应关系模型,揭示炼化装置故障链式效应行为规律和关联本质,从而评价装置异常工况下的安全状态。进一步以马尔可夫过程为理论基础,建立故障链式效应预测模型,预测故障传播的后果和方向,并计算各后果的发生概率,为现场操作人员进行主动维修或应急处置提供依据。案例分析中通过对某化工厂常压塔装置、减压炉装置为研究对象进行应用与验证,结果表明该方法可以准确地对系统故障发生后的状态进行评价和预测,方法有效、可行,便于操作人员在处置已有故障的同时,注意预防其他异常工况的发生,降低油气生产加工过程中的整体风险。     

基于多数据空间全潜结构映射的化工过程性能评估方法

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。     

Characterization of crude feed and products from operating conditions by using continuous probability functions and inferential models

The purpose of this paper is to provide information for the characterization of the products and feed of a crude fractionator, hard to get from a hardware system, by using probability function and inferential model of realtime operating conditions. TBP is a major characteristic of CDU products and feed. It has become possible to consider that the TBP of component can be predicted by using an inferential modeling technique such as partial least square (PLS) or artificial neural network. On the other hand, knowing that the characteristic of each product of a crude distillation unit follows a continuous probability distribution function, variables of the probability distribution function can be calculated from operating conditions in the same way. In general, the proposed model can provide a tool for doing more efficient operations to maximize profit.     

Nonstationary fault detection and diagnosis for multimode processes

Fault isolation based on data‐driven approaches usually assume the abnormal event data will be formed into a new operating region, measuring the differences between normal and faulty states to identify the faulty variables. In practice, operators intervene in processes when they are aware of abnormalities occurring. The process behavior is nonstationary, whereas the operators are trying to bring it back to normal states. Therefore, the faulty variables have to be located in the first place when the process leaves its normal operating regions. For an industrial process, multiple normal operations are common. On the basis of the assumption that the operating data follow a Gaussian distribution within an operating region, the Gaussian mixture model is employed to extract a series of operating modes from the historical process data. The local statistic T² and its normalized contribution chart have been derived for detecting abnormalities early and isolating faulty variables in this article. © 2009 American Institute of Chemical Engineers AIChE J, 2010     

城市埋地钢质燃气管道预警系统研究

管道风险灾害预警是城市燃气埋地管网防御管道事故风险中重要的非工程措施之一。管道风险预警系统实际上是对管道危险状态和管道危险危害因素的发展趋势进行客观分析,得出管道安全预警等级,并对可能受影响的区域发出相应的行动通告,以便企业、社会做出及时、有效、恰当的响应。文章提出城市埋地钢质燃气管道预警系统目标,分析系统的四个阶段,研发了城市埋地钢质燃气管道预警系统的构建方法,并阐述了相应的流程。     

基于GLSAFIS的氟化工过程操作单元可靠性监测

氟化工产物的剧毒特性,使得对于氟化工过程设备的运行可靠性监控异常重要。为此,提出了基于全局-局部结构分析的模糊推理系统（GLSAFIS）在线评估氟化工过程操作单元运行可靠性。依据氟化工工艺流程选取操作单元过程变量后,通过全局-局部结构分析算法（GLSA）对操作单元过程变量进行全局-局部特征提取。这些低维的全局-局部特征代替原始变量作为模糊推理系统（FIS）的输入,不仅可以克服噪声的影响,降低对专家知识的依赖,同时可以通过特征空间的降维压缩,大大加速后续模糊推理系统的逻辑设计。最后模糊推理系统的实施,使得本方法可以对化工过程操作单元可靠性进行在线评估。国内某氟化工厂二氟一氯甲烷（R-22）生产过程的实际应用以及田纳西伊斯曼模拟过程的仿真结果均证实了所提方法可以准确地反映实际化工过程操作单元的运行状况,大大提高了对实际化工过程的安全监控力度。     

Automatic HAZOP analysis method for unsteady operation in chemical based on qualitative simulation and inference

Comparing with continuous production process, unsteady operation process, such as startup and shutdown, tends to abnormal situations due to a large number of operations of operators and dynamic state changes involved. To guarantee a safe operation, process hazard analysis (PHA) is very important to proactively identify the potential safety problems. In the chemical process industry, hazard and operability (HAZOP) analysis is the mostwidely used method. In this paper, based on proposed qualitative simulation and inferencemethod, an automatic HAZOP analysis method for unsteady operation processes is proposed. Mass transfer and relationships among process variables are expressed by Petri net-directed graphmodel based fuzzy logic. Operating procedure is expressed according to a formal expression. Possible operation deviations from normal operating procedure are identified by using a group of guidewords. Hazards are identified automatically by qualitative simulation and inference when wrong operation process is performed. The method is validated by a rectification column system.     

Interactions between an electrochemical reactor and associated unit processes

It is shown that in the presence of interactive variables, the optimum operating conditions for a reactor cannot be determined in isolation from its associated unit operations. The argument is illustrated by a process model developed for a continuous electrochemical reactor linked to a distillation unit which recycles unconverted feedstock. The model reveals that if conditions in the distillation unit are ignored a false optimum well removed from the true optimum would be identified.     

Soft sensor modeling method based on hybrid model of nearest neighbor and neural network

Soft-sensing modeling can effectively solve the problems of large measurement lag, high price, and complex maintenance of online analytical instruments in the production process. At present, neural network based on data-driven is one of the main tools of soft sensor. In the process of modeling data collection, the collection of dominant variables is much more difficult than that of auxiliary variables, resulting in a large amount of unlabeled data. However, traditional soft sensor modeling methods ignore these unlabeled data and only use a small amount of labeled data for modeling, which has negative effect on the prediction accuracy of the model. To solve the problem of label missing, the nearest neighbor algorithm is used to pseudo label the unlabeled data. At the same time, a network structure is designed by combining convolution operation and gated recurrent unit neural network (GRU) to further utilize the unlabeled data, extract the dynamic feature from data at different time, and improve the prediction accuracy of the neural network. Finally, the method is applied to the prediction of propane concentration on the top of propylene distillation column. The results show that the model can solve the problem of label missing in the nonlinear dynamic system and has higher prediction accuracy.     

基于最近邻与神经网络融合模型的软测量建模方法

软测量建模能够有效地解决生产过程中在线分析仪表测量滞后大、价格昂贵、维护保养复杂等问题。目前,基于数据驱动的神经网络是软测量建模的主要工具之一。而在建模数据的采集过程中,主导变量的采集相对辅助变量要困难得多,由此产生了大量缺失标签的数据。但传统的软测量建模方法却忽视了这些无标签数据,只利用少量的有标签数据建模,从而影响了模型的预测精度。为了解决标签缺失的问题,采用最近邻算法对无标签数据进行伪标记,同时设计了由卷积操作与门限循环单元神经网络(GRU)结合的网络结构来进一步利用无标签数据,提取不同时刻数据中的动态特征,提高神经网络的预测精度。最后将该方法应用于丙烯精馏塔塔顶丙烷浓度的预测,实验结果表明该模型能有效处理非线性动态系统的标签缺失问题,具有更高的预测精度。     

水泥煅烧工段机理分析与神经网络预测方法

采用神经网络的方法建立水泥预分解窑煅烧工段的预测模型。选择合理的状态与控制变量,通过采集实际运行数据来训练神经网络。构建的基于BPNN神经网络的煅烧预测模型能够较好地拟合采样数据,具有较好的泛化能力。     

水源水质预警系统的建立与应用

上海市某水厂水源取水口建立了一个原水早期预警系统,制订了预警的标准与方法,完善了不同污染条件下的预警机制,形成了一整套完善的供水水源自动水质监测预警体系,并进行了模拟效果验证。并以此及时了解供水水源水质状况,发生重大污染事故时能在最短的时间内可启动恰当的应急预案,及时调整水厂的工艺运行,保证出厂水水质。     

Optimal operation of RO system with daily variation of freshwater demand and seawater temperature

The optimal operation policy of flexible RO systems is studied in this work. The design and operation of RO process is optimized and controlled considering variations in water demands and changing seawater temperature throughout the day. A storage tank is added to the system layout to provide additional operational flexibility and to ensure the availability of freshwater to customer at all times. A steady state model for the RO process is developed and linked with a dynamic model for the storage tank. The membrane modules are divided into a number of groups to add flexibility in operation to RO network. The total operating cost of the RO process is minimized in order to find the optimal layout and operating variables at discreet time intervals for three design scenarios.     

基于物联网技术的旋转设备状态监测与预警系统

基于物联网提出针对大型石化装置中转动设备的状态监测与系统预警解决方案,即采用＂物联网技术＋智能预警＋专家分析＂技术路线的一个完整解决方案。在某公司的实际运行证明：采用实时监测振动及温度等转动设备的状态数据,实现了设备异常状态的智能预警与状态维修。     

Model-based control of a molten carbonate fuel cell (MCFC) process

To improve availability and performance of fuel cells, the operating temperature of molten carbonate fuel cells (MCFC) stack should be strictly maintained within a specified operation range, and an efficient control technique should be employed to meet this objective. While most modern control strategies are based on process models, many existing models of MCFC are not ready to be applied in synthesis and operation of control systems. In this study, we developed an auto-regressive moving average (ARMA) model and machine learning methods of least squares support vector machine (LS-SVM), artificial neural network (ANN) and partial least squares (PLS) for the MCFC system based on input-output operating data. The ARMA model showed the best tracking performance. A model predictive control method for the operation of MCFC system was developed based on the proposed ARMA model. The control performance of the proposed MPC methods was compared with that of conventional controllers using numerical simulations performed on various process models including an MCFC process. Numerical results show that ARMA model based control provides improved control performance compared to other control methods.     

Estimation of fouling in a plate heat exchanger through the application of neural networks

Pasteurization is an important, if not the most important, process step in the packaging of milk. It is subject to alterations stemming from the variation in the temperature, pH and raw milk quality. The variability may manifest itself in changes in the formation of the deposit (fouling) in the pasteurization unit, such that there is a need for tools, both instrumentation and computational, to help in monitoring the process and keeping it on the desired course. In this paper we describe a practical procedure based on artificial neural networks (ANN) that allows prediction of the deposit thickness, the overall heat transfer coefficient and the critical time (the time that the unit has to be stopped for cleaning) for reducing the impact of fouling on such processes. The procedure determines when the cleaning operation is required once the system is under critical conditions of operations. A combination of fundamental studies and plant measurements were used for study of the operating conditions and thus evaluation of the trades‐offs between operating conditions and longer operating life span. The results are encouraging, enough to validate current operating industrial techniques. Copyright © 2005 Society of Chemical Industry     

基于神经网络-遗传算法优化制氢工艺水碳比

根据某炼油厂制氢车间的生产数据,用人工神经网络(ANN)的反向传播(BP)算法建立了制氢装置转化生产中的水碳比神经网络预测模型,生产数据的检验表明,ANN方法能准确地关联和预报制氢装置转化生产中的水碳比,水碳比预测平均相对误差为2．83％;该神经网络预测模型用遗传算法优化并得到了最佳制氢工艺操作条件。     

基于可拓模糊理论的Texaco煤气化运行状况评估方法研究

Texaco煤气化装置是合成氨系统的核心设备,正确评估其运行状况,是关系整个合成氨安全生产和经济效益的关键因素。但合成氨是复杂系统,评估其运行状况的指标往往不止一个,多因素和多个指标之间往往相互影响,状态评价很复杂。针对Texaco煤气化运行状况多因素评价问题,将模糊数学与可拓学理论相结合,提出了六个影响气化工艺运行状况的评价参数,建立了一种新的Texaco煤气化装置运行工艺状况的可拓评估模型。算例的结果表明所提出的方法可以有效地解决复杂系统运行状态评估问题,并可以适用于其他化工过程系统长周期安全运行分析。