共查询到18条相似文献,搜索用时 125 毫秒
1.
针对传统的基于最小二乘法板形模式识别方法抗干扰能力差、精度低,神经网络方法在实际应用中效果不佳的板形识别问题,根据实际生产中带钢板形控制的要求,以勒让德正交多项式作为表述板形缺陷的基本模型,将模糊分类理论与混沌优化算法相结合,建立一种新型的板形模式软测量方法,该方法简单、实用、识别精度较高,效果较稳定。实际应用结果表明,该方法能够满足高精度的板形控制对板形缺陷模式识别的精度和速度的要求。 相似文献
2.
板形模式识别是板形高精度控制过程中的技术难点之一.本文提出了一种基于小波分析和神经网络相结合的方法,可以较好地解决这个难题.首先利用非线性小波变换阈值法有效去除板形检测数据中噪声干扰,从而提高模式识别系统的准确率;然后利用神经网络的鲁棒性使目标的识别更加接近实际.该方法不仅能有效地对复合板形进行正确分类,而且能分辨出所属类型的程度,为制定出相应的优化控制策略提供了重要的依据. 相似文献
3.
4.
基于分层神经网络模型的数据挖掘算法 总被引:1,自引:0,他引:1
介绍了建立带钢板形缺陷模式识别的数据挖掘过程。针对普通神经网络识别精度较低的缺陷,提出一种基于分层神经网络进行数据挖掘的新方法。该方法采用二叉树型结构,通过分层来细化预测范围并选用多个神经网络进行递推。实验结果证明了分层神经网络模型比普通神经网络模型的预测精度有较大提高,完全可以满足实际生产需要。 相似文献
5.
基于人工神经网络的板形模式识别方法 总被引:2,自引:0,他引:2
根据带钢板形控制的要求,运用人工神经网络理论,提出了一种新的板形识别方法,代替了传统的多项式最小二乘拟合法,该法具有很强的容错性和抗干扰能力,编制了板形模式识别软件,识别效果很好。 相似文献
6.
针对离散Hopfield 神经网络(DHNN) 结构复杂的问题, 提出一种基于贡献率的结构优化算法. 该算法利用奇异值分解方法对连接权值进行设计, 进而利用贡献率的方法对DHNN进行结构优化. 优化后的网络降低了DHNN结构的复杂程度, 使网络具有类似生物神经网络的稀疏结构, 实现了DHNN网络结构的优化. 最后, 通过水质评价和数字识别对该算法进行验证, 表明了所提出算法的有效性和可行性, 同时, 还验证了其对于大规模DHNN的有效性和适用性.
相似文献7.
为了提高带钢生产中板形模式识别精度,提出了基于支持向量机(sVM)的改进径向基(RBF)网络板形模式识别方法,由SVM回归确定RBF网络优化的初始参数,解决了传统方法存在的学习时间长、易陷入局部极小值等问题。此外,分别将输入样本与一对互反的基本模式问的模糊距离之差作为RBF网络的三个输入,使输入节点减少一半,进一步简化了网络模型。实验表明,该方法有效地提高了模式识别精度和速度,可推广到其他具有两两互反性基本模式的模式识别系统中。 相似文献
8.
针对离散Hopfield 神经网络(DHNN) 的权值设计问题, 提出一种改进型学习算法, 并在DHNN动力学分析的基础上设计该学习算法. 利用矩阵分解的方法(MD) 得到正交矩阵, 并采用得到的正交矩阵直接计算DHNN的权值矩阵. 通过该学习算法得到的权值矩阵, 可以很好地存储训练样本的信息, 使测试样本收敛到稳定点. 该学习算法不需要进行分块计算, 减少了计算步骤和计算量, 降低了网络的迭代次数, 从而提高了网络运行速度. 最后, 将该学习算法应用于水质评价, 验证了其有效性和可行性. 相似文献
9.
基于PSO-BP网络的板形智能控制器 总被引:1,自引:0,他引:1
为了解决传统的板形识别与控制中的识别精度低,控制速度慢等问题,将粒子群优化(particle swarm optimization,PSO)算法和误差反传递(back propagation,BP)算法混合训练的PSO-BP网络引入到板形的识别与控制中.首先根据板形轧制的历史数据,建立预测板形的神经网络,得到反映板形控制手段对板形特征参数影响的效应矩阵,同时根据理论数据建立对板形进行模式识别的神经网络.这些都是离线进行的,而且对一批板材只需训练一次神经网络,在线轧制过程中只需要根据识别网络的识别结果和效应矩阵,便可以很快的得到需要的控制量.这种方法可以简化板形控制过程,提高控制速度,最后的仿真实验进一步说明了这种方法的有效性. 相似文献
10.
通过对国内某厂热连轧机板形控制系统的分析与研究,根据带钢板形控制的要求,提出一种利用神经网络理论建立板形数学模型的新方法,并采用MATLAB语言对该系统进行离线仿真。仿真与实际测量结果比较表明所建立的模型的正确性,同时该方法可避开多项式回归运算,具有很强的抗干扰能力。 相似文献
11.
Data-rich environments in modern rolling processes provide a great opportunity for more effective process control and more total quality improvement. Flatness is a key geometrical feature of strip products in a cold rolling process. In order to achieve good flatness, it is necessary to reveal the factors that often influence the flatness quality, to develop a general flatness pattern prediction model that can handle the varying operating condition during the rolling of products with different specifications and to realize an effective flatness feedback control strategy. This paper develops a practical data mining-based flatness pattern prediction method for cold rolling process with varying operating condition. Firstly, the high-dimensional process measurements are projected onto a low-dimensional space (i.e., the latent variable space) using locality preserving projection method; at the same time, the Legendre orthogonal polynomials are used to extract the basic flatness patterns by projecting the high-dimensional flatness measurements into several flatness characteristic coefficients. Secondly, a mixture probabilistic linear regression model is adopted to describe the relationships between the latent variables and the flatness characteristic coefficients. Case study is conducted on a real steel rolling process. Results show that the developed method has not only the satisfactory prediction performance, but good potentials to improve process understanding and strip flatness quality. 相似文献
12.
13.
14.
Hsien-Yu Tseng 《Journal of Intelligent Manufacturing》2006,17(3):301-306
The measurement of flatness for manufactured parts is one of the most frequently used procedures in automated manufacturing
systems. Measuring instruments are commonly utilized in taking measurement data from manufactured surfaces for inspection
purposes. The measurement data is then used to evaluate the geometric information, from errors associated with its surface.
The study proposes the computational approaches for flatness with respect to ASME Y14.5M-1994 standard. The proposed methods
consider the trade-off between the accuracy of flatness and the efficiency of inspection. Two approaches of computational
metrology based on genetic algorithms are proposed to explore the optimality of flatness measurement and the flatness feasibility
analysis. The results show that the optimization algorithms provide exact flatness errors and adequate tolerance size.
Received: February 2004 / Accepted: September 2005 相似文献
15.
Optimal periodic control (OPC) is of interest in many engineering applications. In practice, the numerical solution of the OPC problem has been found to be quite challenging. In this note, we present a method which uses differential flatness for the solution of OPC problems. The OPC problem is reformulated using the flatness of the underlying dynamical system to eliminate the differential equations and the periodicity constraints, resulting in simpler and generally more efficient computation. The effect of point-wise constraints and the analytical computation of the Jacobian matrix are also discussed. The approach is demonstrated using two examples. 相似文献
16.
Grancharov V. Plasberg J.H. Samuelsson J. Bastiaan Kleijn W. 《IEEE transactions on audio, speech, and language processing》2008,16(1):57-64
Postfilters are commonly used in speech coding for the attenuation of quantization noise. In the presence of acoustic background noise or distortion due to tandeming operations, the postfilter parameters are not adjusted and the performance is, therefore, not optimal. We propose a modification that consists of replacing the nonadaptive postfilter parameters with parameters that adapt to variations in spectral flatness, obtained from the noisy speech. This generalization of the postfiltering concept can handle a larger range of noise conditions, but has the same computational complexity and memory requirements as the conventional postfilter. Test results indicate that the presented algorithm improves on the standard postfilter, as well as on the combination of a noise attenuation preprocessor and the conventional postfilter. 相似文献
17.
Peter Veelaert 《Journal of Mathematical Imaging and Vision》1993,3(2):205-221
This paper investigates the properties of digital hyperplanes of arbitrary dimension. We extend previous results that have been obtained for digital straight lines and digital planes, namely, Hung's evenness, Rosenfeld's chord, and Kim's chordal triangle property. To characterize digital hyperplanes we introduce the notion of digital flatness. We make a distinction between flatness and local flatness. The main tool we use is Helly's First Theorem, a classical result on convex sets, by means of which precise and verifiable conditions are given for the flatness of digital point sets. The main result is the proof of the equivalence of local flatness, evenness, and the chord property for certain infinite digital point sets in spaces of arbitrary dimension. 相似文献
18.
群集智能是指复杂的集体智能来自简单个体之间以及个体同环境之间的相互作用. 通常对群集智能的研究主要借助于群居生物行为的观察. 蚁群觅食行为是研究简单个体产生复杂行为的一个典型的例子. 首先建立群体觅食宏观序参数模型. 模型考虑了食物源的量和分布以及环境噪声对个体决策的随机影响. 给出2个食物源下系统模型的数值解,表明在较大的噪声影响下,系统有一定的概率会脱离最优解,到达次优解. 在Starlogo仿真平台下的实验结果表明,觅食蚂蚁的数量同任务完成时间以及碰撞频率之间呈现出幂指数关系. 这对自组织系统和群集智能的研究有一定的理论意义,并可以用来指导设计更加有效、适应、可靠的智能系统. 相似文献