电熔镁砂产品单吨能耗混合预报模型

产品的单吨能耗是反映电熔镁砂熔炼过程产品产量和能耗的综合生产指标. 通过分析炉内电热转换关系,利用能量守恒原理建立了产品单吨能耗模型. 针对模型的未知非线性和参数时变等综合复杂性提出了由基于机理分析的单吨能耗主模型和 基于神经网络的补偿模型组成的产品单吨能耗混合预报模型. 其中神经网络补偿模型用于补偿模型的未知非线性和参数不确定性对于预报模型准确性的影响. 采用某电熔镁砂熔炼过程实测数据验证了所建立的混合预报模型是有效的.     

电熔镁砂熔炼过程电极电流饱和约束一步最优控制

电熔镁砂熔炼过程通过电极电流熔化物料, 采用埋弧方式, 边熔化边加料, 其被控对象是以转动方向与频率为输入, 以电极电流为输出的三相电机. 本文通过引入中间变量并转化控制目标, 将电熔镁砂熔炼过程三相电极电流的复杂非线性控制问题简化为线性控制问题, 提出了一种简化的电极电流饱和约束一步最优控制方法, 并通过引入拉格朗日乘子向量和松弛向量验证了该方法的最优性. 理论分析和仿真对比实验结果表明本文所提简化控制方法的有效性和优越性. 此外, 当考虑电熔镁砂熔炼过程中存在的不可测外部干扰时, 在上述简化的电极电流饱和约束算法的基础上设计了高阶干扰观测器, 理论分析和仿真结果验证了具有高阶干扰观测器的简化算法的优越性.     

电熔镁砂熔炼过程带输出补偿的PID控制

电熔镁砂熔炼过程是以三相电机转动方向与频率为输入,以三相电极电流为输出的强非线性工业过程,其模型参数埋弧电阻率、熔池电阻率和熔池高度随熔炼过程和原矿颗粒长度及杂质成分的变化而变化.本文采用线性模型和未知高阶非线性项来描述电熔镁砂熔炼过程,其中未知高阶非线性项用已知的前一时刻高阶非线性项和其变化率来描述,采用线性模型设计PID控制器,并设计消除前一时刻高阶非线性项的补偿器和消除其变化率的补偿器,提出了带输出补偿的PID控制器,同时采用一步最优前馈控制律和一步最优调节律设计控制器参数.通过仿真实验和电熔镁炉的工业应用,表明当该过程的动态特性发生未知随机变化时,本文所提方法在所有运行时间内可以将电流跟踪误差控制在目标值范围内.     

层流冷却过程喷水系统的智能设定方法

针对热轧层流冷却过程具有强非线性、分布参数和时变等综合复杂特性,提出了基于案例推理技术的层流冷却过程喷水系统的智能设定方法.层流冷却过程的典型工况及喷水系统设定值以案例的形式存于案例库,对于待冷却的带钢,根据当前的工况描述特征在案例库中检索匹配的历史案例,经推理完成当前工况下喷水控制系统的设定.采用某钢铁公司热轧层流冷却生产过程的实际数据进行仿真实验,结果表明所提出的智能设定方法在工况变化时是有效的.     

基于知识挖掘和案例推理的电渣重熔过程智能优化设定控制

依据电渣重熔生产工艺特点、操作经验和历史数据库,提出了基于案例推理的电渣重熔生产过程智能 优化设定控制方法．采用粗糙集理论从积累的大量电渣重熔过程历史控制数据中获取知识,将典型工况总结成案例 的形式以构造案例库,并对案例推理过程中的案例检索、案例修正及存储方法进行详细描述．该智能控制策略应用 于某电渣重熔生产过程,稳定了电渣重熔过程工艺指标,取得了较好的应用效果．     

交流三相电熔镁炉的最佳运行分析

针对电熔镁炉是具有大时滞、强非线性、多变量的复杂系统,现场控制需要一个准确的工作模型的情况,以电熔镁炉的电弧电阻与熔池电阻为切入点,分析了其工作机理,建立了熔池功率场数学模型;提出了针对不同阶段优化操作方法、合理布料和改变熔池形状可提高成品生产率及质量合格率;对方镁石在电熔镁砂熔体中的结晶过程的研究表明,在电熔镁炉外部增加温控手段是获取优质电熔镁砂的关键.     

对抗样本训练图分类器进行模型推理质量评估

重叠社区发现是社交网络分析与挖掘中的一个重要研究问题,现有的大部分方法都要求采用人工方法预先设定社区个数[K],这样做存在很多问题。将无限潜特征模型推广应用到关系型数据,以非参数贝叶斯层次模型为框架建立带重叠社区结构的网络生成模型,就可以避免预先设定[K]的值。然而,关系型无限潜特征模型的后验参数推理结果是一个[N×K]列的0、1矩阵上的概率分布,如何对这种多变量结构参数进行后验推理结果总结和后验推理质量评估是一个挑战,因此提出了一种利用基于对抗样本训练图卷积神经网络的图分类器来帮助总结推理结果和估计推理质量的方法。     

基于泡沫图像特征的浮选槽液位智能优化设定方法

浮选生产过程中浮选槽液位通常根据经验人工设定,具有主观随意性﹑液位波动大,使精/尾矿品位不满足要求.为此,提出一种基于浮选泡沫图像多特征的浮选槽液位智能优化设定的方法.在浮选槽工作原理以及液位与泡沫图像特征间关系的分析基础上,将基于案例推理的浮选槽液位预设定﹑基于多泡沫图像特征的改进LS-SVM（Least squares support vector machine）品位预测及基于BP神经网络的自学习模糊推理智能补偿等模型有机集成,提出了充分利用泡沫图像特征的液位智能优化设定方法.将该方法在某铝土矿浮选生产过程进行应用验证,可使粗选槽液位波动减小,提高了粗选精/尾矿品位合格率、总精矿品位合格率及回收率.     

基于火焰动态纹理的电熔镁炉工况识别

电熔镁炉制备电熔镁砂的工艺过程中,会交替出现正常熔炼、加料和欠烧等不同工况,针对不同的工况需要采取相应的处理方式来保证生产过程的正常进行。目前,工况的识别主要依靠人工完成,这种方式存在工人劳动强度大、容易漏检误检等问题。本文依据不同工况下炉口火焰具有不同的动态可视化特征,提出一种基于动态纹理的工况识别技术。首先,通过建立炉口火焰的线性动态系统模型来刻画图像的动态特性,然后,设计了基于子空间角度的核函数来度量火焰动态模型相似度。对比实验表明本文设计的基于子空间角度的工况分类器具有更好的分类精度及鲁棒性。     

稀土萃取分离过程的优化设定控制

针对稀土萃取分离生产过程的特点,将机理分析与神经网络技术相结合,给出了实现稀土萃取分离生产过程组份含量在线预测的软测量模型及其校正算法．提出了基于案例推理和软测量技术相结合的稀土萃取分离生产过程智能优化设定控制技术．将该技术应用于某公司HAB双溶剂萃取提钇分离生产过程,实现了萃取分离生产过程的优化控制和优化运行,取得了明显的应用成效．     

数据驱动的工业过程运行优化控制

现代工业过程机理复杂使得很难对生产过程以及运行指标与被控变量之间关系精确建模.如何基于工业运行过程数据信息,不依赖模型参数给出设定值设计方案,优化运行指标是一挑战性难题.本文针对在稳态附近可以线性化的一类工业过程,考虑运行控制环和底层控制环不同时间尺度,提出一种基于Q--学习方法的次优设定值学习算法.此算法完全利用数据,学习得到次优设定值,实现运行指标以次优的方式跟踪理想值.浮选过程仿真结果表明本文所提方法的有效性.     

Development and evaluation of a Basestock-CONWIP pull production control strategy in balanced assembly systems

In this study, a new pull production control strategy called Basestock-Constant Work-in-Process (B-CONWIP) is proposed. It is used to control the flow of materials and information in balanced assembly production systems. This proposed control strategy uses one type of authorization cards called CONWIP card that limits the work-in-process (WIP) in the whole system. It has been applied in a single-product and a mixed-product assembly system balanced by two efficient Genetic algorithms introduced in literature. The performance of this control strategy is compared with another pull production control strategy called Basestock Kanban CONWIP (BK-CONWIP), which is a very promising production control strategy found in literature. The proposed strategy has two control parameters, CONWIP authorization cards and basestock levels while BK-CONWIP has three control parameters Kanban authorization cards, CONWIP authorization cards and basestock levels. The comparison is based on three performance measures average system WIP, percentage of satisfied customer demand (service level) and WIP variation between workstations. The performance of the proposed strategy B-CONWIP and BK-CONWIP is mainly similar in both types of assembly systems when mean demand rates are low with respect to mean service rates with the proposed strategy being easier to control and optimize. On the other hand, when mean demand rates are high with respect to mean service rates; B-CONWIP is preferable if service level is more important, while BK-CONWIP is preferable if WIP level is more important. Regarding WIP variation, it mainly depends on the efficiency of the balancing approach. The more efficient the balancing approach, the less WIP variation. Treating demand as lost instead of backordered results in decreased average system WIP and does not affect service levels in both PCSs. It is also shown that S-KDP is more flexible in dealing with situations of variable product mixes than d-KDP because control parameters can be used by any product which minimizes the effect of the unbalanced systems.     

An analytical approach to improving due-date and lead-time dynamics in production systems

A deterioration of due-date reliability is often attributed by planners to external causes rather than to their own planning behavior. Particularly, planners tend to underestimate the effects of time delays, and may not sufficiently take control actions into account that have been initiated but are not yet demonstrating any effects. Unfavorable dynamic behavior can result if planners react inappropriately to short-term decreases in due-date reliability and, for example, use their intuition to adjust planned lead times. A better understanding is needed of the impact of time delays and lead-time-related adjustments on resulting system behavior and of how often plans and associated work releases should be adjusted in practice.In this paper, two planning and control approaches are modeled and analyzed: First, a production system is modeled in which planned lead times and work input are adjusted periodically if the average lead time deviates from the planned lead time. Second, a production system is modeled in which regulation of lead time towards a planned lead time is accomplished by adjusting the work input. For both approaches, discrete (z-transform) equations are obtained that allow trends in dynamic behavior to be characterized as a function of delays in obtaining production information, and delays in making lead time adjustment decisions and implementing them. Industrial data from a steel-producing company are used to illustrate the potential effects of time delays and of averaging of lead time data, as well as to illustrate how analytical results can be used to guide selection of the adjustment period and of lead time regulation parameters. The analytical approach presented here can be used as a tool for quantifying and guiding improvements in the performance, the robustness, and the agility of production systems. This is of particular interest with respect to cyber-physical technologies such as autonomous data collection and embedded models that present significant future opportunities for reducing delays in decision making and decision implementation.     

控制与保护开关电器电源模块参数检测系统

智能型低压电器中,电源模块的供电质量关系着整个产品的工作状态,在研发和生产过程中对其检测必不可少。针对某型智能型控制与保护开关电器(CPS),研制了基于LabVIEW平台的PCI总线电源模块参数自动检测系统。详细介绍了系统的硬件电路设计,具体阐述了系统软件实现过程。实践表明,该系统具有测试精度高、抗干扰能力强、检测效率高、实时性好等优点。     

Selection of a pull production control policy under different demand situations for a manufacturing system by AHP-algorithm

A multistage serial production system is considered in the present paper. A generalized model has been developed with the use of probabilistic demand situations for the end product. The demand situations considered are binomial, exponential, lognormal and Poisson. These demand patterns are used as input parameter for various production control policies. The output values for performance parameters are obtained by simulation. The production policies analyzed are Kanban, CONWIP and Hybrid as alternatives for controlling the engineering manufacture. In the presence of several performance measures, it often becomes difficult for the management to select the most appropriate policy. Analytic hierarchy process (AHP) has been implemented for the purpose of selection. Computational results have been reported along with the sensitivity analysis after designing and conducting various experiments.     

Fuzzy knowledge representation and reasoning using a generalized fuzzy petri net and a similarity measure

In the study of weighted fuzzy production rules (WFPRs) reasoning, we often need to consider those rules whose consequences are represented by two or more propositions connected by “AND” or “OR”. To enhance the representation capability of those rules, this paper proposes two types of knowledge representation parameters, namely, the input weight and the output weight, for a rule. A Generalized Fuzzy Petri Net (GFPN) is also presented for WFPR reasoning. Furthermore, this paper gives a similarity measure to improve the evaluation method of WFPRs and the multilevel fuzzy reasoning in which the consequences and their certainty factors are deduced synchronously by using a GFPN.     

Edge-cloud cooperation driven self-adaptive exception control method for the smart factory

Production exceptions often occur due to the uncertainties of resources such as random machine broken, urgent production tasks. The timely identification and optimal control of the production exceptions are the core issues to ensure the reliable operation of smart manufacturing system. However, due to the evolution mechanism of uncertain factor is hard to describe, and the current cloud-based production analysis and decision-making mode often requires a long processing time. As a result, the extraction of abnormal events often delays and the optimal control decisions are hard to made. To meet this issue, an edge-cloud cooperation driven self-adaptive exception control method is proposed for the smart factory. Firstly, the advanced industrial Internet of things and embedded edge-computing technologies are applied to create an intelligent environment where the resources are made smart with the ability of self-sensing, self-analytics and self-optimization. Then, the fuzzy Bayesian network is used to extract the production exceptions and diagnose their causes, where fuzzy sets are used to describe the production status. After that, a self-adaptive production exception handling method is involved through an edge-cloud cooperation mechanism. The machines will adjust their production parameters at first, and then the horizontal collaboration among machines at same production level and vertical cooperation between different production levels will be used to deal with exceptions self-adaptively. Lastly, a case from casting post-processing system is used to demonstrate the proposed method, and results show that the proposed method can largely improve the production efficiency.     

基于DSP的金刚石压机智能控制系统设计

本文提出了一种金刚石压机的新型控制模式—基于DSP(TMS320LF2407)的嵌入式控制系统,并介绍了该控制系统的软硬件设计。在算法上,根据工艺要求采用智能PID控制和模糊PID控制策略代替传统的PID控制,对人造金刚石生产中的工艺参数加热功率和加压压力实现有效控制,极大地提高了人造金刚石的质量和品级。     

FMS的模型参考自适应调度

用运筹学研究生产线调度问题已有几十年的历史,但由此得出的调度策略的实时性很差.1986年自动控制工作者提出了“PMS动态自适应计算机调”一词.令人感到十分新奇.可惜.从未见到任何有关的论文.本文研究FMS的模型参考自适应调度.本文采用我们提出的考虑了有限缓冲器容量的极大代数模型.环境的影响反映于对象参数的摄动,本文采用我们提出的摄动计算方法.调度器的设计采用次梯度法,以求解连续变量和离散变量混合的优化问题,附有数字实例,计算和仿真表明:FMS的模型参考自适应调度是可行的,是值得继续深入研究的。