A critical review of the most popular types of neuro control

In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well‐known control technique. This attitude towards the extension of the application of well‐known control methods using ANNs was followed by the development of ANN model‐predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well‐known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

Hysteresis Compensation and Adaptive Controller Design for a Piezoceramic Actuator System in Atomic Force Microscopy

This paper presents an indirect adaptive controller combined with hysteresis compensation to achieve high accuracy positioning control of piezoceramic actuators and illustrates the results with an atomic force microscope (AFM) application. A dynamic model of a piezoceramic actuator system in AFM is derived and analyzed. A feedforward controller based on the Preisach model is proposed to compensate for the nonlinear hysteresis effects. Then an indirect adaptive controller is designed to achieve desired tracking performance as well as deal with the uncompensated nonlinearity from hysteresis and the system parameter variation due to creep. Experimental results indicate that the proposed controller can significantly improve the positioning control accuracy of the piezoceramic actuator as well as achieve high image quality of the AFM system. The maximum scanning error was reduced from 2µm to 0.3µm in comparison with a proportional‐integral‐derivative (PID) controller. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

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。     

近邻自适应局部尺度的谱聚类算法

提出一种在LUV空间中基于多层次化结构Nystrm方法的自适应谱聚类算法。首先引入LUV色彩空间,避免了RGB色彩空间中色彩辨别阈对分割的影响,在纹理、边缘区域取得了更好的分割效果;其次将谱聚类算法中基于多层次化结构的方法和基于Nystrm采样的方法结合起来,有效减少了运算时间、解决了数据量较大时计算过程中内存溢出的问题;最后在K均值聚类中通过对特征间隙(eigengap)的分析,自适应地选择K值的大小,解决了自动确定聚类数目的问题。将提出的方法在LUV色彩空间中和RGB色彩空间中分别进行图像分割实验,结果表明在LUV色彩空间中取得效果更加理想。同时也将提出的算法与基于Nystrm方法的谱聚类算法(spectral clustering-Nystrm,SC-N)进行比较。实验结果表明,该算法在数据运算量、运行时间和分割结果上都优于SC-N方法。     

基于种群多样性的自适应PSO算法求解VRPSPD问题

为有效求解逆向物流车辆路径(VRPSPD)模型,本文提出一种基于种群多样性的自适应PSO算法(SDAPSO)。在SDAPSO运行时,根据种群多样性,自适应地对种群中运行较差的粒子进行扰动操作,提升这些粒子向最优解收敛的能力;同时,对全局最优粒子进行概率扰动,以增加种群的多样性。标准检测函数的仿真结果表明SDAPSO算法是对基本PSO算法的有效改进。在对VRPSPD模型求解中,通过与其它粒子群算法相比,表明SDAPSO是求解该类问题的一种有效方法。     

低温裂纹张开位移预测方法的讨论

把低温影响下的COD试验数据用灰色理论中的累加方法进行累加，可以使一组没有规律的数据成为一条光滑的曲线．然后利用人工神经网络和自适应模糊推理系统两种方法进行预测，算例的结果表明用一次累加后的数列预测精度较高。     

真空烧结炉预估自适应温控系统设计

论文在分析真空炉温控对象特性的基础上,提出一种PID参数自适应控制算法,该算法首先在试生产阶段采用继电自整定方式得到几组基准PID参数,此后在每炉正式生产时,利用升温阶段的信息预估由于装炉量不同等原因所带来的参数变化,预估结束及时对这几组PID基准参数进行在线更新。实例改造结果表明,该智能控制方案简单、有效,完全满足硬质合金真空烧结炉温度的控制要求。     

开关磁阻电机转速调节器参数模糊自整定的研究

开关磁阻电机(SRM)具有较强的非线性,很难建立其准确的数学模型,在传统PID调速控制中难以获得整个调速范围内Kp、KI、KD 3个参数的最优组合。而固定参数的传统PID调节器,不利于系统调速的精准性与抗干扰性。通过分析传统PID调节器3个参数的控制特点,主要针对起动、调速、负载扰动等若干状态下,建立适当的、通用的模糊控制规则,将模糊控制和PID控制相结合,构成SRM的模糊PID转速调节器,实现Kp、KI、KD 3个控制参数的自适应调节,从而获得在整个调速范围内不同负载下较好的调速特性。仿真试验表明,所提出方法避免了固定参数转速调节器的比例积分环节导致的低速、轻载工况下的转速超调与振荡,克服了单纯模糊控制所导致的调速误差。     

自适应Fourier分解思想在再生核W2 1 [a,b]空间的应用

在再生核$W_2^1[a, b]$空间中研究自适应正交贪婪分解算法, 利用能量下降最快的原理自适应性地构造出最佳$n$项逼近函数, 并从理论上证明其收敛性成立。最后, 实验验证了在$W_2^1[a, b]$再生核空间中, 利用正交贪婪原理构造的$n$项数值原函数比用等分结点构造出的最佳$n$项数值原函数收敛效果更优。