矿井提升机-外文翻译

1、外文翻译部分：英文原文Mine-hoist fault-condition detection based on the wavelet packet transform and kernel PCAAbstract: A new algorithm was developed to correctly identify fault conditions and accurately monitor fault development in a mine hoist. The new method is based on the Wavelet Packet Transform (WPT) a

2、nd kernel PCA (Kernel Principal Component Analysis, KPCA). For non-linear monitoring systems the key to fault detection is the extracting of main features. The wavelet packet transform is a novel technique of signal processing that possesses excellent characteristics of time-frequency localization.

3、It is suitable for analyzing time-varying or transient signals. KPCA maps the original input features into a higher dimension feature space through a non-linear mapping. The principal components are then found in the higher dimension feature space. The KPCA transformation was applied to extracting t

4、he main nonlinear features from experimental fault feature data after wavelet packet transformation. The results show that the proposed method affords credible fault detection and identification.Key words: kernel method; PCA; KPCA; fault condition detection1 IntroductionBecause a mine hoist is a ver

5、y complicated and variable system, the hoist will inevitably generate some faults during long-terms of running and heavy loading. This can lead to equipment being damaged , to work stoppage, to reduced operating efficiency and may even pose a threat to the security of mine personnel. Therefore, the

6、identification of running faults has become an important component of the safety system. The key technique for hoist condition monitoring and fault identification is extracting information from features of the monitoring signals and then offering a judgmental result. However, there are many variable

7、s to monitor in a mine hoist and, also, there are many complex correlations between the variables and the working equipment. This introduces uncertain factors and information as manifested by complex forms such as multiple faults or associated faults, which introduce considerable difficulty to fault

8、 diagnosis and identification 1.There are currently many conventional methods for extracting mine hoist fault features, such as Principal Component Analysis(PCA) and Partial Least Squares (PLS) 2. These methods have been applied to the actual process. However, these methods are essentially a linear

9、transformation approach. But the actual monitoring process includes nonlinearity in different degrees. Thus, researchers have proposed a series of nonlinear methods involving complex nonlinear transformations. Furthermore, these non-linear methods are confined to fault detection: Fault variable sepa

10、ration and fault identification are still difficult problems.This paper describes a hoist fault diagnosis feature exaction method based on the Wavelet Packet Transform (WPT) and kernel principal component analysis(KPCA). We extract the features by WPT and then extract the main features using a KPCA

11、transform, which projects low-dimensional monitoring data samples into a high-dimensional space. Then we do a dimension reduction and reconstruction back to the singular kernel matrix. After that, the target feature is extracted from the reconstructed nonsingular matrix. In this way the exact target

12、 feature is distinct and stable. By comparing the analyzed data we show that the method proposed in this paper is effective.2 Feature extraction based on WPT and KPCA2.1 Wavelet packet transformThe wavelet packet transform (WPT) method 3,which is a generalization of wavelet decomposition, offers a r

13、ich range of possibilities for signal analysis. The frequency bands of a hoist-motor signal as collected by the sensor system are wide. The useful information hides within the large amount of data. In general, some frequencies of the signal are amplified and some are depressed by the information. Th

14、at is to say, these broadband signals contain a large amount of useful information: But the information can not be directly obtained from the data. The WPT is a fine signal analysis method that decomposes the signal into many layers and gives a better resolution in the time-frequency domain. The use

15、ful information within the different frequency bands will be expressed by different wavelet coefficients after the decomposition of the signal. The concept of “energy information” is presented to identify new information hidden the data. An energy eigenvector is then used to quickly mine information

16、 hiding within the large amount of data.The algorithm is: Step 1: Perform a 3-layer wavelet packet decomposition of the echo signals and extract the signal characteristics of the eight frequency components, from low to high, in the 3rd layer. Step 2: Reconstruct the coefficients of the wavelet packe

17、t decomposition. Use 3 j S (j=0, 1, , 7) to denote the reconstructed signals of each frequency band range in the 3rd layer. The total signal can then be denoted as: （1）Step 3: Construct the feature vectors of the echo signals of the GPR. When the coupling electromagnetic waves are transmitted underg

18、round they meet various inhomogeneous media. The energy distributing of the echo signals in each frequency band will then be different. Assume that the corresponding energy of 3 j S (j=0, 1, 7) can be represented as3 j E (j=0, 1, , 7). The magnitude of the dispersed points of the reconstructed signa

19、l 3 j S is: jk x (j=0,1, , 7; k=1, 2, , n), where n is the length of the signal. Then we can get: （2）Consider that we have made only a 3-layer wavelet package decomposition of the echo signals. To make the change of each frequency component more detailed the 2-rank statistical characteristics of the

20、 reconstructed signal is also regarded as a feature vector: （3）Step 4: The 3 j E are often large so we normalize them. Assume that, thus the derived feature vectors are, at last:T= （4） The signal is decomposed by a wavelet package and then the useful characteristic information feature vectors are ex

21、tracted through the process given above. Compared to other traditional methods, like the Hilbert transform, approaches based on the WPT analysis are more welcome due to the agility of the process and its scientific decomposition.2.2 Kernel principal component analysisThe method of kernel principal c

22、omponent analysis applies kernel methods to principal component analysis45.The principal component is the element at the diagonal after the covariance matrix，has been diagonalized. Generally speaking, the first N values along the diagonal, corresponding to the large eigenvalues, are the useful infor

23、mation in the analysis. PCA solves the eigenvalues and eigenvectors of the covariance matrix. Solving the characteristic equation6: （5）where the eigenvalues and the eigenvectors is essence of PCA.Let the nonlinear transformations, : RN F , xX , project the original space into feature space, F. Then

24、the covariance matrix, C, of the original space has the following form in the feature space: （6）Nonlinear principal component analysis can be considered to be principal component analysis ofin the feature space, F. Obviously, all the eigenvalues of C and eigenvectors, V F 0 satisfyV =V . All of the

25、solutions are in the subspacethat transforms from （7）There is a coefficient Let （8）From Eqs.(6), (7) and (8) we can obtain: （9）where k =1, 2, ., M . Define A as an MM rankmatrix. Its elements are: （10）From Eqs.(9) and (10), we can obtain MAa =a . This is equivalent to:Ma =Aa . (11)Make as As eigenva

26、lues, and,as the corresponding eigenvector.We only need to calculate the test points projections on the eigenvectorsthat correspond to nonzero eigenvalues in F to do the principal component extraction. Defining this asit is given by: (12)Principal component we need to know the exact form of the non-

27、linear image. Also as the dimension of the feature space increases the amount of computation goes up exponentially. Because Eq.(12) involves an inner-product computation, according to the principles of Hilbert-Schmidt we can find a kernel function that satisfies the Mercer conditions and makesThen E

28、q.(12) canbe written: (13)Here is the eigenvector of K. In this way the dot product must be done in the original space but the specific form ofneed not be known. The mapping, and the feature space, F, are all completely determined by the choice of kernel function 78.2.3 Description of the algorithmT

29、he algorithm for extracting target features in recognition of fault diagnosis is:Step 1: Extract the features by WPT; Step 2: Calculate the nuclear matrix, K, for each sample, in the original input space, andStep 3: Calculate the nuclear matrix after zero-mean processing of the mapping data in featu

30、re space;Step 4: Solve the characteristic equation Ma =Aa ;Step 5: Extract the k major components using Eq.(13) to derive a new vector. Because the kernel function used in KPCA met the Mercer conditions it can be used instead of the inner product in feature space. It is not necessary to consider the

31、 precise form of the nonlinear transformation. The mapping function can be non-linear and the dimensions of the feature space can be very high but it is possible to get the main feature components effectively by choosing a suitable kernel function and kernel parameters9. 3 Results and discussionThe

32、character of the most common fault of a mine hoist was in the frequency of the equipment vibration signals. The experiment used the vibration signals of a mine hoist as test data. The collected vibration signals were first processed by wavelet packet. Then through the observation of different time-f

33、requency energy distributions in a level of the wavelet packet we obtained the original data sheet shown in Table 1 by extracting the features of the running motor. The fault diagnosis model is used for fault identification or classification.Experimental testing was conducted in two parts: The first

34、 part was comparing the performance of KPCA and PCA for feature extraction from the original data, namely: The distribution of the projection of the main components of the tested fault samples. The second part was comparing the performance of the classifiers, which were constructed after extracting

35、features by KPCA or PCA. The minimum distance and nearest-neighbor criteria were used for classification comparison, which can also test the KPCA and PCA performance. In the first part of the experiment, 300 fault samples were used for comparing between KPCA and PCA for feature extraction. To simpli

36、fy the calculations a Gaussian kernel function was used: 10The value of the kernel parameter, , is between 0.8 and 3, and the interval is 0.4 when the number of reduced dimensions is ascertained. So the best correct classification rate at this dimension is the accuracy of the classifier having the b

37、est classification results. In the second part of the experiment, the classifiers recognition rate after feature extraction was examined. Comparisons were done two ways: theminimum distance or the nearest-neighbor. 80% of the data were selected for training and the other 20% were used for testing. T

38、he results are shown in Tables 2 and 3.From Tables 2 and 3, it can be concluded from Tables 2 and 3 that KPCA takes less time and has relatively higher recognition accuracy than PCA.4 ConclusionsA principal component analysis using the kernel fault extraction method was described. The problem is fir

39、st transformed from a nonlinear space into a linearhigher dimension space. Then the higher dimension feature space is operated on by taking the inner product with a kernel function. This thereby cleverly solves complex computing problems and overcomes the difficulties of high dimensions and local mi

40、nimization. As can be seen from the experimental data, compared to the traditional PCA the KPCA analysis has greatly improved feature extraction and efficiency in recognition fault states. References1 Ribeiro R L. Fault detection of open-switch damage in voltage-fed PWM motor drive systems. IEEE Tra

41、ns Power Electron, 2003, 18(2): 587593.2 Sottile J. An overview of fault monitoring and diagnosis in mining equipment. IEEE Trans Ind Appl, 1994, 30(5):13261332.3 Peng Z K, Chu F L. Application of wavelet transform in machine condition monitoring and fault diagnostics: areview with bibliography. Mec

42、hanical Systems and Signal Processing, 2003(17): 199221.4 Roth V, Steinhage V. Nonlinear discriminant analysis using kernel function. In: Advances in Neural Information Proceeding Systems. MA: MIT Press, 2000: 568574.5 Twining C, Taylor C. The use of kernel principal component analysis to model data

43、 distributions. Pattern Recognition, 2003, 36(1): 217227.6 Muller K R, Mika S, Ratsch S, et al. An introduction tokernel-based learning algorithms. IEEE Trans on Neural Network, 2001, 12(2): 181.7 Xiao J H, Fan K Q, Wu J P. A study on SVM for fault diagnosis. Journal of Vibration, Measurement & Diag

44、nosis,2001, 21(4): 258262.8 Zhao L J, Wang G, Li Y. Study of a nonlinear PCA fault detection and diagnosis method. Information and Control,2001, 30(4): 359364.9 Xiao J H, Wu J P. Theory and application study of feature extraction based on kernel. Computer Engineering,2002, 28(10): 3638.中文译文基于小波包变换和核

45、主元分析技术的矿井提升机的自我故障检测摘要： 这是一种新的运算法，它能正确识别矿井提升机的故障并且准确地监测矿井提升机故障的发展过程。这种方法是基于小波包变换（WPT）和核主成份分析（KPCA，核主成份分析）技术。对于非线性监听系统，故障检测的关键是提取主要特征。小波包变换是时间频率的局部化分析，尤其适合于非平稳信号。KPCA就是将最初输入的数据特征透过非线性映射映射到高维特征空间，然后在高维特征空间发现其主要组成部分。KPCA变换适用于从经过小波包变换的实验故障特征数据中提取主要的非线性特征。结果表示，该方法能提供可靠的故障检测和鉴定。关键词：核心方法;主成分分析;核主元分析;故障检测1介绍

46、因为矿井提升机是一种复杂的可变性比较大的系统，提升机在长期运行和重载情况下难免会产生一些故障。这些都有可能损坏设备，停工，降低工作效率，甚至对我们员工的安全带来威胁。因此，运行中故障的检测已经变成安全系统的一个重要组成部分。 提升机状态监测与故障识别的关键技术是从监测信号特征中提取的信息和提供一个判断的结果。但是，在矿井提升机的检测中有很多不同的情况，而且在各种各样的工作设备之间有许多复杂的相互关系。这里不确定因素和数据由复杂的形式所表现，如多个故障或相关故障，这些故障的诊断和鉴定是相当困难的。目前有许多传统的方法可以提取矿井提升机故障特征，如主成分分析（PCA）和偏最小二乘法（PLS）。这些

47、方法已经被熟练的运用于我们的实际生产中来。然而，这些方法基本上是一个线性变换方法。但实际监测过程包括不同程度的非线性。因此我们的研究员已经提出了一系列涉及复杂的非线性变换非线性方法。此外，这些非线性方法只限于故障检测，故障变量分离和故障识别仍然是难以解决的问题。这篇论文是介绍了一种基于小波包变换 （WPT）和核主成份分（KPCA）的矿井提升机故障诊断的特征提取方法。我们用WPT提取特征数据然后用核主成分分析变换提取主要数据特征，这种变换将低维的监测数据样本映射到高维的特征空间。然后我们做了降维和重建并备份到奇异核矩阵。在这之后，目标特征从重构的非奇异矩阵提取出来。用这样的方法我们得到清楚又稳定

48、的目标特征。通过比较分析数据，我们得出本文提出的方法是有效的。2基于小波包变换和主成分分析技术的特征提取2.1小波包变换 小波包变换（小波包变换）方法 3 ，这是一种小波的分解的概括，为信号分析提供了很多可能。传感器系统收集到的升降器的信号频带是非常广泛的。有用的信息隐藏在大量的数据中。一般情况下，某些频率的信号被放大，某些频率的信号被抑制。这就是说，这些宽带信号包含大量有用的信息：但是从这些信息中不能直接获得有用数据。小波包变换是一个很好的信号分析方法，它把信号分解成很多层的信号并在时频域给出了一个更好的分辨率，不同频段内的有用信息在信号分解后将被不同的小波系数表达。该信号的提出，是以确定新

49、的信息隐藏在数据的中新信息。然后一种能量特征向量快速挖掘隐藏在大量的数据中的有用信息。该算法是：第1步：将回波信号执行3层小波包分解，并提取8个频率成分的信号特征在第三层，从低到高。第2步：重构小波包分解的系数。利用3 j S (j=0, 1, , 7) 指每个重建信号的频带范围内的第3层。总的信号就可以被命名为： （1）第3步：构建的探地雷达回波信号的特征向量。当电磁波的耦合传输他们满足各种地下非均匀介质。能源分布的回波信号在每个频带然后将不同：承担相应的能量 3 j S (j=0, 1, , 7) 可以代表3 j E (j=0, 1, , 7 ).的规模分散点的重建信号3 j S 是 jk

50、 x (j=0,1, , 7; k=1, 2, , n),其中n是长度的信号。然后，我们可以得到： （2）考虑到我们做的只有3层的回波信号的小波包分解。为了使每个频率成分的变化更详细，重构信号的2级的统计特性也被视为一个特征向量： （3）(4)第4步3 j E往往大，所以我们将他们标准化。假设，从而得出的特征向量是，最后：T = 信号通过小波包变换分解，然后提取有用的特征信息的特征向量通过上述过程。相对于其他传统方法，像希尔伯特变换，基于小波包变换分析方法更受欢迎，这是由于它敏捷的过程和它的科学分解。2.2核主成份分析核主成分份析方法就是将核心方法应用在主成分分析法中 4-5 。主要组成部分是

51、在对角线元素后，协方差矩阵，已是结尾 。一般而言，第一次N值山对角线长，相应的大特征值，是有用的信息在数据分析.PCA解决了特征值和特征向量的协方差矩阵。求解特征方程 6 ：如果特征值和特征向量，是属于PCA的。使非线性变换，RNF ,xX项目原始空间到特征空间，楼然后，协方差矩阵，中，原来的空间具有下列表格中的功能空间： (6)非线性主成分分析可被认为是主成分分析的功能空间，楼显然，所有的C抗原值和特征向量，V F 0 满足V V。所有的解决方案是在子这一转变从 （7）使系数 可以得到 （8）从6 7 8式我们可以得到 (9)使k =1, 2, ,M 定义A是MM的矩阵，它的要点是 （10）

52、从9和10式我们可以得到MAa =a这就相当于Ma= Aa . （11） 使作为A的特征值，以及相应的特征向量。我们只需要计算测试点的预测的特征向量对应的非零特征值的F这样做主要成分的提取。界定这种因为它是由： (12) 主要组成部分，我们需要知道确切形式的非线性图像。还为层面的特征空间增加了计算量随之呈指数。由于均衡器。由于式（12）涉及内积计算，根据希尔伯特 - 施密特的原则，我们可以找到一个内积函数，满足的默瑟条件下，方程（12）可以改写成 这里是K的一个变量。这样，点积必须在原来的空间，但(x)的具体形式没必要知道。特征空间F，完全取决于选择的核心特征 7-8 。2.3说明算法在故障诊

53、断的识别中提取目标特征的算法是：第1步：用小波包变换提取特征;第2步：计算每个样本的核矩阵，K 在原始的空间输入，和第3步：在特征空间进行测绘数据的均值处理，然后计算核矩阵;第4步：求解特征方程Ma =Aa ;第5步：利用方程提取的K式的重要组成部分(13)，制定出一个新的载体。由于核函数在核主成分分析要满足Mercer的条件，可用于代替内积的特征空间。没有必要考虑的具体形式的非线性变换。映射功能可以非线性和特征空间的尺寸可以很高，但有它可能得到有效的主要成分通过选择合适的核函数和内核参数 9 。3结果与讨论 矿井提升机的最常见的故障特征可以在设备振动信号的频率中提取出来。实验中使用矿井提升机的振动信号作为测试数据，将收集到的振动信号首先进行小波包处理,然后通过在一个水平的小波包上观察不同的时频能量分布，接着我们将获得的原始数据列于表1并提取电机的运行特征。该故障诊断模型用于故障识别或分类。实验测试被分两部分进行： 第一部分是比较核主元分析和主成分分析从原来的数据中提取特征的性能，即：测试故障样本的主要组成部分的投影分布。那个第二部分是比较分类的性能，这些分类是