基于遗传算法学习的复合神经网络自适应温度控制系统

针对一类温度控制系统中存在的非线性和参数不确定等问题,提出一种复合神经网络自适应控制结构.在控制系统中构造了神经网络正模型来再现被控对象的动态特性,用神经网络控制器实现优化控制律的非线性映射.文中选用了被控对象80组历史数据作为样本集,并利用遗传算法的全局搜索能力及高效率来训练多层前向神经网络的权系数.最后用升降温工艺曲线作为输入对温度控制系统进行仿真.仿真结果表明,应用遗传算法能够提高神经网络的学习效率.保证神经网络全局快速收敛,从而克服了传统的误差反传学习算法的一些缺点.证明了采用这种神经网络自适应控制结构.使神经网络控制器的输出可以适应对象参数和环境的变化.使温度控制系统具有很好的学习和自适应控制能力,取得了良好的控制效果.     

Design of artificial neural networks for tool wear monitoring

An on-line scheme for tool wear monitoring using artificial neural networks (ANNs) has been proposed. Cutting velocity, feed, cutting force and machining time are given as inputs to the ANN, and the flank wear is estimated using the ANN. Different ANN structures are designed and investigated to estimate the tool wear accurately. An existing analytical model is used to obtain the data for various cutting conditions in order to eliminate the huge cost and time associated with generation of training and evaluation data. Motivated by the fact that the tool wear at a given instance of time depends on the tool wear value at a previous instance of time, memory is included in the ANN. ANNs without memory, with one-phase memory, and with two-phase memory are investigated in this study. The effect of various training parameters, such as learning coefficient, momentum, temperature, and number of hidden neurons, on these architectures is studied. The findings and experience obtained should facilitate the design and implementation of reliable and economical real-time systems for tool wear monitoring and identification in intelligent manufacturing.     

Robust adaptive control for greenhouse climate using neural networks

This paper presents a general framework for robust adaptive neural network (NN)‐based feedback linearization controller design for greenhouse climate system. The controller is based on the well‐known feedback linearization, combined with radial basis functions NNs, which allows the feedback linearization technique to be used in an adaptive way. In addition, a robust sliding mode control is incorporated to deal with the bounded disturbances and the approximation errors of NNs. As a result, an inherently nonlinear robust adaptive control law is obtained, which not only provides fast and accurate tracking of varying set‐points, but also guarantees asymptotic tracking even if there are inherent approximation errors. Copyright © 2010 John Wiley & Sons, Ltd.     

非线性系统神经网络自适应控制的发展现状及展望

简要回顾了神经网络控制及其应用的发展历程,重点论述了人们在连续、离散时间非线性系统的神经网络以及神经模糊稳定自适应控制研究方面所取得的主要进展,探讨了神经网络自适应控制研究方面存在的主要问题及解决问题的基本途径.作为当前解决神经网络自适应控制问题的途径之一,介绍了近来人们对二阶模糊神经网络以及量子神经网络的研究.最后,总结并指出了这一领域下一步的发展方向和有待解决的新课题.     

Modeling workpiece vibrations with neural networks

The entire workpiece on a lathe vibrates when it is excited at a single point. Frequency and time-domain/time-series techniques can estimate the force-displacement relationships between excitation and the individual points on the workpiece. In this paper, the use of single neural network is proposed to represent the force-displacement relationship between the applied excitation force and the vibration of the whole workpiece. The accuracy of the proposed approach is evaluated on the experimental data. Also, another neural network is used to store the frequency response characteristics of the workpiece.     

High performance accelerators for deep neural networks: A review

The availability of huge structured and unstructured data, advanced highly dense memory and high performance computing machines have provided a strong push for the development in artificial intelligence (AI) and machine learning (ML) domains. AI and machine learning has rekindled the hope of efficiently solving complex problems which was not possible in the recent past. The generation and availability of big-data is a strong driving force for the development of AI/ML applications, however, several challenges need to be addressed, like processing speed, memory requirement, high bandwidth, low latency memory access, and highly conductive and flexible connections between processing units and memory blocks. The conventional computing platforms are unable to address these issues with machine learning and AI. Deep neural networks (DNNs) are widely employed for machine learning and AI applications, like speech recognition, computer vison, robotics, and so forth, efficiently and accurately. However, accuracy is achieved at the cost of high computational complexity, sacrificing energy efficiency and throughput like performance measuring parameters along with high latency. To address the problems of latency, energy efficiency, complexity, power consumption, and so forth, a lot of state of the art DNN accelerators have been designed and implemented in the form of application specific integrated circuits (ASICs) and field programmable gate arrays (FPGAs). This work provides the state of the art of all these DNN accelerators which have been developed recently. Various DNN architectures, their computing units, emerging technologies used in improving the performance of DNN accelerators will be discussed. Finally, we will try to explore the scope for further improvement in these accelerator designs, various opportunities and challenges for the future research.     

分数阶细胞神经网络自适应同步控制设计及电路仿真

构建一个新的分数阶细胞神经网络系统,设计驱动系统非线性参数已知而响应系统非线性参数值未知的驱动–响应系统,运用自适应同步控制器及参数自适应调整律实现该驱动–响应系统同步.数值仿真和动力学分析结果表明新的分数阶细胞神经网络系统具有混沌特性.结合分数阶电路理论设计出新的分数阶细胞神经网络系统同步控制的电路原理图.本方案实际可实现4096种多元组合电路,为简洁起见,选取分数阶qi(i=1,2,3)相同值(即q1=q2=q3=0.95)的组合电路进行电路仿真.仿真结果表明,多元电路仿真和数值仿真实验结果具有很高的吻合度.从而证实了该自适应同步控制方法在物理上的可实现性,在工程领域中具有现实的应用价值.     

采用自适应自回归小波神经网络的单步预测控制

针对非线性系统的控制问题,提出一种基于神经网络辨识的单步预测控制算法。算法在自回归小波神经网络的基础上,利用混沌机制消除了神经网络易陷入局部极值的缺点．采用自适应性学习率,提高神经网络的收敛能力和速度．以该神经网络为预测模型,引入输出反馈和偏差校正克服预测误差,以此构造一步加权预测控制性能指标。然后采用Brent一维搜索方法求取控制律,Brent法无需任何相关的导数信息,需调整的参数少,使得Brent法适合实时控制．仿真研究说明了该非线性预测控制器的有效性。     

一种基于自适应遗传算法的神经网络学习算法

结合遗传算法与梯度下降法优点,提出了一种训练神经网络权值的混合优化算法,同时能够优化网络的结构。首先利用全局搜索能力可靠的遗传算法,采用递阶编码方案和自适应变异概率,同时优化网络的权值和结构,在进化结束时,能够寻到全局最优点附近的点。在遗传算法搜索结果的基础上,利用局部寻优能力较强的梯度下降法,从此点出发,进行局部搜索,最终达到网络的训练目标。与单一的遗传算法或者梯度下降法比较而言,混合优化算法的收敛速度明显提高。     

Robust adaptive control of uncertain non-linear systems using neural networks

This paper presents a robust adaptive output feedback control design method for uncertain non-affine non-linear systems, which does not rely on state estimation. The approach is applicable to systems with unknown but bounded dimensions and with known relative degree. A neural network is employed to approximate the unknown modelling error. In fact, a neural network is considered to approximate and adaptively make ineffective unknown plant non-linearities. An adaptive law for the weights in the hidden layer and the output layer of the neural network are also established so that the entire closed-loop system is stable in the sense of Lyapunov. Moreover, the robustness of the system against the approximation error of neural network is achieved with the aid of an additional adaptive robustifying control term. In addition, the tracking error is guaranteed to be uniformly and asymptotically stable, rather than uniformly ultimately bounded, by using this additional control term. The proposed control algorithm is relatively straightforward and no restrictive conditions on the design parameters for achieving the systems stability are required. The effectiveness of the proposed scheme is shown through simulations of a non-affine non-linear system with unmodelled dynamics, and is compared with a second-sliding mode controller.     

Robust adaptive control for a class of uncertain non-affine nonlinear systems using affine-type neural networks

A robust adaptive control is proposed for a class of single-input single-output non-affine nonlinear systems. In order to approximate the unknown nonlinear function, a novel affine-type neural network is used, and then to compensate the approximation error and external disturbance a robust control term is employed. By Lyapunov stability analysis for the closed-loop system, it is proved that tracking errors asymptotically converge to zero. Moreover, an observer is designed to estimate the system states because all the states may not be available for measurements. Furthermore, the adaptation laws of neural networks and the robust controller are given out based on the Lyapunov stability theory. Finally, two simulation examples are presented to demonstrate the effectiveness of the proposed control method.     

A comparison of gradient ascent, gradient descent and genetic-algorithm-based artificial neural networks for the binary classification problem

Abstract: We compare log maximum likelihood gradient ascent, root-mean-square error minimizing gradient descent and genetic-algorithm-based artificial neural network procedures for a binary classification problem. We use simulated data and real-world data sets, and four different performance metrics of correct classification, sensitivity, specificity and reliability for our comparisons. Our experiments indicate that a genetic-algorithm-based artificial neural network that maximizes the total number of correct classifications generally fares well for the binary classification problem. However, if the training data set contains inconsistent decisions or noise then the log maximum likelihood maximizing gradient ascent may be the best classification approach to use. The root-mean-square minimizing gradient descent approach appears to overfit training data and has the lowest reliability among the approaches considered for our research. At the end of the paper, we provide a few guidelines, including computational complexity, for selection of an appropriate technique for a given binary classification problem.     

Application and development of biologically plausible neural networks in a multiagent artificial life system

The present article introduces the system BioAnt, which is a computational simulation of a small colony of ants (up to 99 members) in which every ant relies on a biologically more plausible artificial neural networks as control mechanism for guidance. The environment, in which the ants are placed, is three-dimensional, consisting of the anthill, sugar, water, earth elevations, walls and predators. The ants’ foraging behavior was successfully implemented as well as some basic defense mechanisms. Typical sensors and actuators of ants were modeled and the efficiency of the connectionist approach has been validated by the comparison with a simple symbolical approach. Apart from several surprising results on technical details, which are reported, the present approach clearly demonstrates the feasibility of such an implementation with connectionist and biologically more plausible principles, offering promising perspectives as a basis for further artificial life systems.     

小波神经网络自学习算法用于红外图像分割

在红外动目标序列图像跟踪过程中,由于目标本身的红外特征具有较大的不可预测性,使ATR系统在目标探测阶段产生大量的虚警讯息。因此,必须设法在复杂背景抑制段将虚警探测讯息滤除掉。提出了一种新颖的基于小波神经网络构架的FLIR图像分割技术,旨在将小波变换的时-频局域特性和神经网络的自学习能力相结合,从而使FLIR图像的分割算法具有较强的逼近和容错能力。该算法在FLIR-ATR系统中得到应用,对于FLIR目标图像轮廓的提取和抑制杂散背景方面获得了良好的效果。     

自组织区间二型模糊神经网络及其自适应学习算法

针对复杂不确定非线性系统的辨识问题,提出一种基于聚类的自组织区间二型模糊神经网络学习算法.首先采用具有两个不同加权参数的FCM算法对输入数据进行划分来获取规则前件的不确定均值,同时结合聚类有效性标准确定模糊规则数目,从而自动完成神经网络的结构辨识和规则前件参数辨识;随后给出了基于梯度下降法和Lyapunov函数稳定收敛定理的规则后件权向量学习速率的自适应学习算法.通过非线性系统辨识实例,验证了该算法与其他方法相比具有更快的收敛速度和更高的逼近精度;并且利用该算法建立了某市电力短期负荷预测模型,结果表明该模型具有较高的预测精度,泛化性能更佳.     

基于RENN 的柔性关节机械臂自适应动态面控制

针对面贴式永磁同步电机驱动的柔性关节机械臂动力学模型具有非线性、不确定性和未知外部扰动等特点,提出一种自适应动态面控制方法来实现其关节轨迹跟踪控制．控制律由动态面技术得到,降低了反推控制器的复杂性．模型不确定因素由递归Elman神经网络在线补偿,神经网络权值自适应律通过Lyapunov稳定性分析推导得到．仿真研究表明,该方法对于载荷不确定和外界扰动具有较强的鲁棒性,与传统动态面法相比,大大提高了柔性关节的位置跟踪精度．     

Distributed machining control and monitoring using smart sensors/actuators

The study of smart sensors and actuators led, during the past few years, to the development of facilities which improve traditional sensors and actuators in a necessary way to automate production systems. In another context, many studies have been carried out aimed at defining a decisional structure for production activity control and the increasing need of reactivity leads to the autonomization of decisional levels close to the operational system. We study in this paper the natural convergence between these two approaches and we propose an integration architecture, dealing with machine tool and machining control, that enables the exploitation of distributed smart sensors and actuators in the decisional system.     

3D computer vision based on machine learning with deep neural networks: A review

Recent advances in the field of computer vision can be attributed to the emergence of deep learning techniques, in particular convolutional neural networks. Neural networks, partially inspired by the brain's visual cortex, enable a computer to “learn” the most important features of the images it is shown in relation to a specific, specified task. Given sufficient data and time, (deep) convolutional neural networks offer more easily designed, more generalizable, and significantly more accurate end‐to‐end systems than is possible with previously employed computer vision techniques. This review paper seeks to provide an overview of deep learning in the field of computer vision with an emphasis on recent progress in tasks involving 3D visual data. Through a backdrop of the mammalian visual processing system, we hope to also provide inspiration for future advances in automated visual processing.