Applied Sciences

Research

21 pages, 4901 KiB

Open AccessArticle

TF Entropy and RFE Based Diagnosis for Centrifugal Pumps Subject to the Limitation of Failure Samples

by Xuanyuan Su, Hongmei Liu and Laifa Tao

Appl. Sci. 2020, 10(8), 2932; https://doi.org/10.3390/app10082932 - 23 Apr 2020

Cited by 5 | Viewed by 2688

In practical engineering, the vibration-based fault diagnosis with few failure samples is gaining more and more attention from researchers, since it is generally hard to collect sufficient failure records of centrifugal pumps. In such circumstances, effective feature extraction becomes quite vital, since there [...] Read more.

In practical engineering, the vibration-based fault diagnosis with few failure samples is gaining more and more attention from researchers, since it is generally hard to collect sufficient failure records of centrifugal pumps. In such circumstances, effective feature extraction becomes quite vital, since there may not be enough failure data to train an end-to-end classifier, like the deep neural network (DNN). Among the feature extraction, the entropy combined with signal decomposition algorithms is a powerful choice for fault diagnosis of rotating machinery, where the latter decomposes the non-stationary signal into multiple sequences and the former further measures their nonlinear characteristics. However, the existing entropy generally aims at processing the 1D sequence, which means that it cannot simultaneously extract the fault-related information from both the time and frequency domains. Once the sequence is not strictly stationary (hard to achieve in practices), the useful information will be inevitably lost due to the ignored domain, thus limiting its performance. To solve the above issue, a novel entropy method called time-frequency entropy (TfEn) is proposed to jointly measure the complexity and dynamic changes, by taking into account nonlinear behaviors of sequences from both dimensions of time and frequency, which can still fully extract the intrinsic fault features even if the sequence is not strictly stationary. Successively, in order to eliminate the redundant components and further improve the diagnostic accuracy, recursive feature elimination (RFE) is applied to select the optimal features, which has better interpretability and performance, with the help of the supervised embedding mechanism. To sum up, we propose a novel two-stage method to construct the fault representation for centrifugal pumps, which develops from the TfEn-based feature extraction and RFE-based feature selection. The experimental results using the real vibration data of centrifugal pumps show that, with extremely few failure samples, the proposed method respectively improves the average classification accuracy by 12.95% and 33.27%, compared with the mainstream entropy-based methods and the DNN-based ones, which reveals the advantage of our methodology. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Figure 1

18 pages, 6193 KiB

Open AccessArticle

Research on a Nonlinear Dynamic Incipient Fault Detection Method for Rolling Bearings

by Huaitao Shi, Jin Guo, Xiaotian Bai, Lei Guo, Zhenpeng Liu and Jie Sun

Appl. Sci. 2020, 10(7), 2443; https://doi.org/10.3390/app10072443 - 3 Apr 2020

Cited by 22 | Viewed by 2694

Abstract

The incipient fault detection technology of rolling bearings is the key to ensure its normal operation and is of great significance for most industrial processes. However, the vibration signals of rolling bearings are a set of time series with non-linear and timing correlation, [...] Read more.

The incipient fault detection technology of rolling bearings is the key to ensure its normal operation and is of great significance for most industrial processes. However, the vibration signals of rolling bearings are a set of time series with non-linear and timing correlation, and weak incipient fault characteristics of rolling bearings bring about obstructions for the fault detection. This paper proposes a nonlinear dynamic incipient fault detection method for rolling bearings to solve these problems. The kernel function and the moving window algorithm are used to establish a non-linear dynamic model, and the real-time characteristics of the system are obtained. At the same time, the deep decomposition method is used to extract weak fault characteristics under the strong noise, and the incipient failures of rolling bearings are detected. Finally, the validity and feasibility of the scheme are verified by two simulation experiments. Experimental results show that the fault detection rate based on the proposed method is higher than 85% for incipient fault of rolling bearings, and the detection delay is almost zero. Compared with the detection performance of traditional methods, the proposed nonlinear dynamic incipient fault detection method is of better accuracy and applicability. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Figure 1

19 pages, 8956 KiB

Open AccessArticle

Transfer Learning Strategies for Deep Learning-based PHM Algorithms

by Fan Yang, Wenjin Zhang, Laifa Tao and Jian Ma

Appl. Sci. 2020, 10(7), 2361; https://doi.org/10.3390/app10072361 - 30 Mar 2020

Cited by 41 | Viewed by 5856

Abstract

As we enter the era of big data, we have to face big data generated by industrial systems that are massive, diverse, high-speed, and variability. In order to effectively deal with big data possessing these characteristics, deep learning technology has been widely used. [...] Read more.

As we enter the era of big data, we have to face big data generated by industrial systems that are massive, diverse, high-speed, and variability. In order to effectively deal with big data possessing these characteristics, deep learning technology has been widely used. However, the existing methods require great human involvement that is heavily depend on domain expertise and may thus be non-representative and biased from task to similar task, so for a wide variety of prognostic and health management (PHM) tasks, how to apply the developed deep learning algorithms to similar tasks to reduce the amount of development and data collection costs has become an urgent problem. Based on the idea of transfer learning and the structures of deep learning PHM algorithms, this paper proposes two transfer strategies via transferring different elements of deep learning PHM algorithms, analyzes the possible transfer scenarios in practical application, and proposes transfer strategies applicable in each scenario. At the end of this paper, the deep learning algorithm of bearing fault diagnosis based on convolutional neural networks (CNN) is transferred based on the proposed method, which was carried out under different working conditions and for different objects, respectively. The experiments verify the value and effectiveness of the proposed method and give the best choice of transfer strategy. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Graphical abstract

15 pages, 5988 KiB

Open AccessArticle

Sparse Low-Rank Based Signal Analysis Method for Bearing Fault Feature Extraction

by Baoxiang Wang, Yuhe Liao, Rongkai Duan and Xining Zhang

Appl. Sci. 2020, 10(7), 2358; https://doi.org/10.3390/app10072358 - 30 Mar 2020

Cited by 5 | Viewed by 2696

Abstract

The condition monitoring of rolling element bearings (REBs) is essential to maintain the reliable operation of rotating machinery, and the difficulty lies in how to estimate fault information from the raw signal that is always overwhelmed by severe background noise and other interferences. [...] Read more.

The condition monitoring of rolling element bearings (REBs) is essential to maintain the reliable operation of rotating machinery, and the difficulty lies in how to estimate fault information from the raw signal that is always overwhelmed by severe background noise and other interferences. The method based on a sparse model has attracted increasing attention because it can capture deep-level fault features. However, when processing a signal with complex components and weak fault features, the performance of sparse model-based methods is often not ideal. In this work, the fault information-based sparse low-rank algorithm (FISLRA) is proposed to abstract the fault information from a noisy signal interfered with by background noise and external interference. Concretely, a sparse and low-rank model is formulated in the time-frequency domain. Then, a fast-converging algorithm is derived based on the alternating direction method of multipliers (ADMM) to solve the formulated model. Moreover, to further highlight the periodical transients, a correlated kurtosis-based thresholding (CKT) scheme proposed in this paper is also incorporated to solve the proposed low-rank spares model. The superiority of the proposed FISLRA over the traditional sparse low-rank model (TSLRM) and spectral kurtosis (SK) is proved by simulation analysis. In addition, two experimental signals collected from a bearing test rig are utilized to demonstrate the efficiency of the proposed FISLRA in fault detection. The results illustrate that compared to the TSLRM method, FISLRA can effectively extract periodical fault transients even when harmonic components (HCs) are present in the noisy signal. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Figure 1

14 pages, 12524 KiB

Open AccessArticle

Simulation Research on Sparse Reconstruction for Defect Signals of Flip Chip Based on High-Frequency Ultrasound

by Xiaonan Yu, Hairun Huang, Wanlong Xie, Jiefei Gu, Ke Li and Lei Su

Appl. Sci. 2020, 10(4), 1292; https://doi.org/10.3390/app10041292 - 14 Feb 2020

Cited by 13 | Viewed by 3253

Abstract

Flip chip technology has been widely used in various fields. As the density of the solder balls in flip chip technology is increasing, the pitch among solder balls is narrowing, and the size effect is more significant. Therefore, the micro defects of the [...] Read more.

Flip chip technology has been widely used in various fields. As the density of the solder balls in flip chip technology is increasing, the pitch among solder balls is narrowing, and the size effect is more significant. Therefore, the micro defects of the solder balls are more difficult to detect. In order to ensure the reliability of the flip chip, it is very important to detect and evaluate the micro defects of solder balls. High-frequency ultrasonic testing technology is an effective micro-defect detection method. In this paper, the interaction mechanism between high-frequency ultrasonic pulse and micro defects is analyzed by finite element simulation. A transient simulation model for the whole process of ultrasonic scanning of micro defects is established to simulate scanning in acoustic microscopy imaging. The acoustic propagation path map is obtained for analyzing acoustic energy transmission during detection, and the edge blurring effect in micro-defect imaging detection is clarified. The processing method of the time-domain signal and cross-section image signal of micro defects based on sparse reconstruction is studied, which can effectively improve the accuracy of detection and the signal-to-noise ratio. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Figure 1

11 pages, 2066 KiB

Open AccessArticle

Rolling Bearing Fault Diagnosis Based on Wavelet Packet Transform and Convolutional Neural Network

by Guoqiang Li, Chao Deng, Jun Wu, Zuoyi Chen and Xuebing Xu

Appl. Sci. 2020, 10(3), 770; https://doi.org/10.3390/app10030770 - 22 Jan 2020

Cited by 61 | Viewed by 4499

Abstract

Timely sensing the abnormal condition of the bearings plays a crucial role in ensuring the normal and safe operation of the rotating machine. Most traditional bearing fault diagnosis methods are developed from machine learning, which might rely on the manual design features and [...] Read more.

Timely sensing the abnormal condition of the bearings plays a crucial role in ensuring the normal and safe operation of the rotating machine. Most traditional bearing fault diagnosis methods are developed from machine learning, which might rely on the manual design features and prior knowledge of the faults. In this paper, based on the advantages of CNN model, a two-step fault diagnosis method developed from wavelet packet transform (WPT) and convolutional neural network (CNN) is proposed for fault diagnosis of bearings without any manual work. In the first step, the WPT is designed to obtain the wavelet packet coefficients from raw signals, which then are converted into the gray scale images by a designed data-to-image conversion method. In the second step, a CNN model is built to automatically extract the representative features from gray images and implement the fault classification. The performance of the proposed method is evaluated by a real rolling-bearing dataset. From the experimental study, it can be seen the proposed method presents a more superior fault diagnosis capability than other machine-learning-based methods. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Figure 1

21 pages, 7325 KiB

Open AccessArticle

A Theoretical Model with the Effect of Cracks in the Local Spalling of Full Ceramic Ball Bearings

by Huaitao Shi, Zimeng Liu, Xiaotian Bai, Yupeng Li and Yuhou Wu

Appl. Sci. 2019, 9(19), 4142; https://doi.org/10.3390/app9194142 - 3 Oct 2019

Cited by 16 | Viewed by 4538

Abstract

For full ceramic ball bearings, cracks occur frequently in the spalling on the rings, which leads to impacts on the bearing dynamic characteristics. In this paper, the spalling is set on the outer ring, and the dynamic model considering the effect of crack [...] Read more.

For full ceramic ball bearings, cracks occur frequently in the spalling on the rings, which leads to impacts on the bearing dynamic characteristics. In this paper, the spalling is set on the outer ring, and the dynamic model considering the effect of crack is proposed. The crack is considered to be related to the strain energy, and the effect on the stiffness of the outer ring is also analyzed. Results show that the appearance of cracks leads to the reduction of the full ceramic bearing stiffness, and the vibration amplitude of bearing increases. The effect of a crack depends on its size, and the vibration of the bearing with cracks of different widths and depths vary greatly. This study provides theoretical basis for the calculation of full ceramic bearing and is of great significance for the state monitoring and fault diagnosis. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures

Figure 1

19 pages, 9928 KiB

Open AccessArticle

A Cost-Effective Solution to Improving the Electrical Performance of Metal Contacting Interfaces in IC System under Temperature-Humidity Environment

by Yupeng Li, Weiying Meng, Huaitao Shi, Zhijun Gao, Ke Zhang, Guochang Li and Bing Wang

Appl. Sci. 2019, 9(19), 3950; https://doi.org/10.3390/app9193950 - 20 Sep 2019

Viewed by 2887

Abstract

Temperature-humidity (TH) induced failure mechanism (FM) of metal contacting interfaces in integrated circuit (IC) systems has played a significant role in system reliability issues. This paper focuses on central processing unit (CPU)/motherboard interfaces and studies several factors that are believed to have a [...] Read more.

Temperature-humidity (TH) induced failure mechanism (FM) of metal contacting interfaces in integrated circuit (IC) systems has played a significant role in system reliability issues. This paper focuses on central processing unit (CPU)/motherboard interfaces and studies several factors that are believed to have a great impact on TH performance. They include: Enabling load, surface finish quality, and contacting area. Test vehicles (TVs) of Clarkdale package and of Ibex peak motherboard were designed to measure low level contact resistance (LLCR) for catching any failure. Several sets of design of experiments (DOE) were conducted on 85°C/85% relative humidity and test results were analyzed. A proposal that correlates asperity spots and contact tip design with contact resistance was proposed and thus a cost-effective solution for improving electrical performance under TH was deduced. The proposal has proven to be reasonably effective in practice. Full article

(This article belongs to the Special Issue A Special Paper Collection from the Asia Pacific Conference of the Prognostics and Health Management (PHM) Society 2019 (PHMAP 2019))

► Show Figures