Search

This paper addresses challenges in extracting effective information from rolling bearing fault signals and handling strong correlations and information redundancy in high-dimensional feature samples post-extraction. A rolling bearing fault diagnosis method is proposed on the basis of hierarchical discrete entropy (HDE) combined with semi-supervised local Fisher discriminant analysis (SELF). Firstly, hierarchical discrete entropy is extracted from signals preprocessed via variational mode decomposition. We assess entropy stability under different parameters using the coefficient of variation and select optimal parameters accordingly. Secondly, we employ the SELF method to remap the multidimensional feature sample set extracted, performing dimensionality reduction. Finally, a fault diagnosis model classifies the dimensionality-reduced feature samples for fault identification. Experimental results demonstrate that entropy samples extracted via HDE achieve higher diagnostic accuracy after dimensionality reduction with the SELF method. Specifically, accuracy rates of 100 % and 98.2 % are achieved for two types of fault samples, respectively, validating the feasibility and effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Aiming at monitoring of gearbox faults, a gear fault feature extraction method based on variational mode decomposition (VMD) and multi-scale discrete entropy (MDE) is proposed in this paper. Firstly, the gear fault signal is decomposed into a series of intrinsic modal function (IMF) by VMD with selected parameters; Secondly, the decomposed IMF are extracted by MDE feature extraction method to form a feature sample set; Finally, the least square support vector machine (LSSVM) is used to classify the data set after feature extraction. The experiment results show that the proposed method owns the higher fault diagnosis accuracy than the traditional multi-scale entropy methods. [ABSTRACT FROM AUTHOR]

The traditional multiscale entropy algorithm shows inconsistency because some points are ignored when the signal is coarsened. To solve this problem, this paper proposes an improved multiscale permutation entropy (IMSPE). Firstly, the fault signal is decomposed into several product functions (PF) by local mean decomposition (LMD). Secondly, IMSPE is proposed to extract fault features of product functions. IMSPE integrates the information of multiple coarse sequences and solves problems of entropy inconsistency. Finally, the proposed method based on LMD and IMSPE is applied into gear fault diagnosis system. The experiment shows the proposed method can distinguish different gear fault types with a higher accuracy than traditional methods. [ABSTRACT FROM AUTHOR]

Bearing is the key component to determine the health of machinery, and it is of great significance to monitor its working status in real time and predict its remaining useful life. In recent years, the RUL prediction method based on deep learning has been widely used and achieved good prediction results. Here, a bearing life prediction method based on convolution neural network (CNN), long short term memory (LSTM) and attention mechanism (AM) is proposed. First of all, the time domain and frequency domain features of the original vibration signals of rolling bearings are extracted, and the extracted feature set is normalized as the input of CNN. The main function of CNN is to extract spatial features and reduce the dimension of the data. Then, using LSTM to extract the information that may be ignored by CNN, the feature information extracted by CNN-LSTM is input to the attention mechanism for weighting, and the key information is screened. And then more accurately represent the degradation characteristics of the equipment, and finally get the bearing remaining life. The performance of the model is verified by two sets of public data sets, and the experimental results show that it is compared with the CNN-LSTM method. The root mean square error (RMSE) index based on CNN-LSTM-AM method is reduced by 14.6 % and 13.8 % respectively, and the score index is increased by 2.0 % and 2.4 % respectively. The results show that the proposed method has higher accuracy in bearing RUL prediction. [ABSTRACT FROM AUTHOR]

Aiming at the fault classification problem of the rolling bearing under the uncertain structure parameters work condition, this paper proposes a fault diagnosis method based on the interval support vector domain description (ISVDD). Firstly, intrinsic time scale decomposition is performed for vibration signals of the rolling bearing to get the time-frequency spectrum samples. These samples are divided into a training set and a test set. Then, the training set is used to train the ISVDD. Meanwhile, the dynamic decreasing inertia weight particle swarm optimization is applied to improve the training accuracy of ISVDD model. Finally, the performance of the four interval classifiers is calculated in rolling bearing fault test set. The experimental results show the advantages of the ISVDD model: (1) ISVDD can extend the support vector domain description to solve the uncertain interval rolling bearing fault classification problem effectively; (2) The proposed ISVDD has the highest classification accuracy in four interval classification methods for the different rolling bearing fault types. [ABSTRACT FROM AUTHOR]

An interval support vector deterministic optimization model (ISVD) is proposed for the fault classification problem of uncertainty samples in this paper. Firstly, based on the order relation theory, support vector machines using interval samples is transformed into ISVD, which is a two-objective optimization problem, with the midpoint and the radius optimized at the same time. Then, ISVD is converted into a single objective optimization model by the linear combination. The single objective optimization model includes Lagrange multiplier vector and interval sample vectors, both of which are nested. Thus, the nested particle swarm optimization (PSO) based on dynamic decreasing inertia weight is applied to select the optimal Lagrange multiplier vector of this model. Lastly, the effectiveness of the proposed method is proved by the data set of University of California Irvine (UCI) and the roller bearing fault experiments. The experimental results show: ISVD owns outstanding generalization ability with the help of the structured risk minimization and global optimization. The accuracy of the proposed ISVD is better than that of the native Bayes uncertain classification method 1 (NBU1), native Bayes uncertain classification method 2 (NBU2) and the formula-based Bayes classifier (FBC). [ABSTRACT FROM AUTHOR]

Traditionally, gear faults can be classified with the ignorance of the sample uncertainty. In this paper, a novel approach is proposed for the problem diagnosis of uncertain gear interval faults. First, a statistical property interval feature vector composed of mean, standard deviation, skewness, kurtosis, etc. is proposed. Then, the native Bayes uncertain classification (NBU) is used for the diagnostics of these uncertain gear interval faults. Conventionally, the NBU utilizes all the attributes to distinguish fault types. However, each fault type has its own distinct classification accuracy for different feature vector attributes. Thus, the particle swarm optimization (PSO) is used to select the optimal feature vector attributes for each fault type in the NBU (NBU_PSO_EACH). The experimental results show: (1) the accuracy of the proposed method is better than that of NBU1, NBU2 or FBC; (2) in terms of accuracy, the proposed method is also more advanced than the method which selects the same optimal attributes for all fault types based on the PSO (NBU_PSO); (3) the proposed method can reduce the physical size of feature vectors. [ABSTRACT FROM AUTHOR]