1 December 2020 in Energy Reports
25 December 2018 in IEEE Access
In order to satisfy the requirements of on-line monitoring of the suspension system under complex conditions, a fault detection method for maglev train suspension system based on multi-model switching is proposed. In the proposed method, the healthy samples are extracted through the moving time window, and then the features of the healthy samples are extracted by the Fast Walsh–Hadamard transform and filtered by the median filter. Then, the normalization is used to eliminate the difference of feature vectors, and then the principal component analysis method is used to reduce the dimension and de-correlation of the feature matrix contributing to a hyper-sphere space. Finally, the health threshold and the fault threshold are determined by Euclidean distance, then fault detection models are established for various operating conditions. Taking the positive line operation condition as an example, the proposed method is compared with the method based on the original feature and support vector data description based on the original feature. The results demonstrate that the proposed method is superior to the other two methods in terms of health detection rate and false positive rate. In addition, the proposed method is of the characteristics of low computational complexity, no-parameter optimization, and good robustness. It can be applied in practical engineering providing a certain research basis for data deep mining such as fault diagnosis and fault prediction.
14 July 2021 in IEEE Transactions on Vehicular Technology
At present, in the suspension system of maglev train, the self-diagnosis of most of the components can be realized employing direct sensor measurement, however, there are still some components that cannot be directly measured by sensors or model-based methods, such as the power components in the suspension control box, electromagnetics and related connectors. And although the detection method based on Stable Kernel Representation (SKR) can detect the fault, the length of the data used for SKR affects the speed and results of the detection. To obtain better detection results with the shortest possible data, this paper studies a component-level fault detection method based on autocorrelation length and SKR. This method uses the autocorrelation length to determine the length of the data used to identify the SKR, and then applies the SKR to build a residual generator and set the residual threshold. The experimental results show that the studied method can detect faults of the suspension control box in real-time and effectively, and the simulation results show that the studied method can detect faults of the electromagnet in real-time and effectively. In addition, compared with the traditional method, the method in this paper can obtain better results with less data.
6 May 2019 in IEEE Access
Although the canonical correlation analysis (CCA)-based method has been successfully applied to Gaussian processes, the methods cannot obtain good results for the non-Gaussian processes. Meanwhile, due to the different operating conditions of the systems in actual operation, the data generated under different operating conditions is greatly different, which makes the fault detection more difficult. To deal with these problems, a fault detection method based on multiple canonical correlation analysis models and Box-Cox transformation is proposed. The method divides all conditions into some categories of conditions and builds the switching rules. Then the current condition is determined and switched in real time through real-time status data and switching rules. Since the systems are the non-Gaussian processes, the quadratic statistic established by the CCA for each condition is a non-negative and non-Gaussian distributed variable. So, Box-Cox transformation is used to convert quadratic statistic into Gaussian distributed variables, such that the properties of Gaussian distribution can be employed to determine the ranges of the quadratic statistic corresponding to different health conditions. Finally, the fault detecting thresholds of the models are established based on a 99.7.
26 June 2020 in IEEE Access
To overcome the influence of multiple operating conditions for fault detection, this paper proposes a method to detect fault for the suspension system of maglev trains. Firstly, the complex operating condition of the maglev train is divided into some simple conditions, and the operating samples are extracted through the time window in the same simple operating condition. Secondly, the features of the extracted samples are extracted by the Fast Walsh-Hadamard transform, and the noise is removed by the median filtering. Thirdly, after adopting principal component analysis to reduce the dimensionality of the feature, the mean of the feature is calculated and applied to calculate the Euclidean distance from the features of the new data obtained by the same processing in each time. Fourthly, the new Euclidean distance obeying the Gaussian distribution is obtained through the Box-Cox transformation. Finally, the fault threshold in each simple operating condition is established through the characteristics of Gaussian distribution. Taking a certain operating condition as an example, the method is compared with the three similar methods. The results reveal that the proposed method can detect the faults timely and has a low false alarm rate. Moreover, the proposed sub-healthy data are within an acceptable range. Based on these results, the proposed method can be applied in fault detection of the maglev train, providing a certain basis for fault diagnosis.
7 September 2020 in IEEE Access
With the increasing development of industrial technology, fault detection technology has been widely applied in many complex systems. Aiming at the problems of multi-operation conditions and the data length needed for fault detection using Kullback- Leibler Divergence (KLD), a novel fault detection method for complex systems based on optimized KLD under multi-operation conditions is proposed in this paper. In the first place, based on the historical data of the system, the complex operation conditions of the system are divided into several simple mutually exclusive operation conditions, and the division standard is established. In the next place, the optimal length can be quickly determined by autocorrelation analysis and applied to various operation conditions. After the next, in the training stage, the KLD values of all training data are calculated with the benchmark that is the initial optimal data length of each operation condition. And the maximum value is taken as the threshold for fault detection. Afterward, in the test phase, it starts by judging the type of operation condition that the data belongs to, then the corresponding KLD value is calculated, which is compared with the corresponding threshold, so as to determine whether the fault occurs. Eventually, this method is applied to the suspension system of the maglev train and respectively compared with the fault detection methods based on Euclidean distance or Mahalanobis distance. The results show that the proposed method possesses a low false alarm rate and high sensitivity.