A New Deep Dual Temporal Domain Adaptation Method for Online Detection of Bearings Early Fault

With the quick development of sensor technology in recent years, online detection of early fault without system halt has received much attention in the field of bearing prognostics and health management. While lacking representative samples of the online data, one can try to adapt the previously-learned detection rule to the online detection task instead of training a new rule merely using online data. As one may come across a change of the data distribution between offline and online working conditions, it is challenging to utilize the data from different working conditions to improve detection accuracy and robustness. To solve this problem, a new online detection method of bearing early fault is proposed in this paper based on deep transfer learning. The proposed method contains an offline stage and an online stage. In the offline stage, a new state assessment method is proposed to determine the period of the normal state and the degradation state for whole-life degradation sequences. Moreover, a new deep dual temporal domain adaptation (DTDA) model is proposed. By adopting a dual adaptation strategy on the time convolutional network and domain adversarial neural network, the DTDA model can effectively extract domain-invariant temporal feature representation. In the online stage, each sequentially-arrived data batch is directly fed into the trained DTDA model to recognize whether an early fault occurs. Furthermore, a health indicator of target bearing is also built based on the DTDA features to intuitively evaluate the detection results. Experiments are conducted on the IEEE Prognostics and Health Management (PHM) Challenge 2012 bearing dataset. The results show that, compared with nine state-of-the-art fault detection and diagnosis methods, the proposed method can get an earlier detection location and lower false alarm rate.     

Infrared thermography based diagnosis of inter-turn fault and cooling system failure in three phase induction motor

Thermography has been widely used as a technique for anomaly detection in induction motors. International Electrical Testing Association (NETA) proposed guidelines for thermographic inspection of electrical systems and rotating equipment. These guidelines help in anomaly detection and estimating its severity. However, it focus only on location of hotspot rather than diagnosing the fault. This paper addresses two such faults i.e. inter-turn fault and failure of cooling system, where both results in increase of stator temperature. Present paper proposes two thermal profile indicators using thermal analysis of IRT images. These indicators are in compliance with NETA standard. These indicators help in correctly diagnosing inter-turn fault and failure of cooling system. The work has been experimentally validated for healthy and with seeded faults scenarios of induction motors.     

基于动态核主元分析的大功率LED阵列动态光源在线状态观测与故障诊断

大功率LED阵列动态光源工作过程中光电热参数具有不确定性和时变时滞非线性特点,利用动态核主元分析方法(DKPCA)对大功率LED阵列动态光源进行在线状态观测与故障诊断能有效地捕捉观测数据的非线性和相关性特征,根据历史数据的主元特征计算出的统计量阈值和在线数据的统计特征实现故障检测,利用重构贡献图法实现故障的分离.仿真实...     

基于独立成分分析的高光谱图像异常检测

针对高光谱图像中背景及目标先验知识未知条件下的异常目标检测问题,提出了一种基于独立成分分析(ICA)的异常探测算法.首先估计原始数据的虚拟维(VD)以确定要分离的独立成分个数,在此基础上进行快速独立成分分析(FastICA),然后基于平均局部奇异度选择含异常信息较多的独立成分,最后使用丰度量化算法得到异常目标的丰度图像...     

Intelligent Fault Diagnosis of Industrial Robot Based on Multiclass Mahalanobis-Taguchi System for Imbalanced Data

One of the biggest challenges for the fault diagnosis research of industrial robots is that the normal data is far more than the fault data; that is, the data is imbalanced. The traditional diagnosis approaches of industrial robots are more biased toward the majority categories, which makes the diagnosis accuracy of the minority categories decrease. To solve the imbalanced problem, the traditional algorithm is improved by using cost-sensitive learning, single-class learning and other approaches. However, these algorithms also have a series of problems. For instance, it is difficult to estimate the true misclassification cost, overfitting, and long computation time. Therefore, a fault diagnosis approach for industrial robots, based on the Multiclass Mahalanobis-Taguchi system (MMTS), is proposed in this article. It can be classified the categories by measuring the deviation degree from the sample to the reference space, which is more suitable for classifying imbalanced data. The accuracy, G-mean and F-measure are used to verify the effectiveness of the proposed approach on an industrial robot platform. The experimental results show that the proposed approach’s accuracy, F-measure and G-mean improves by an average of 20.74%, 12.85% and 21.68%, compared with the other five traditional approaches when the imbalance ratio is 9. With the increase in the imbalance ratio, the proposed approach has better stability than the traditional algorithms.     

基于高斯马尔科夫模型的高光谱异常目标检测算法研究

随着光谱成像技术的发展,高光谱异常检测在遥感图像处理中的应用越来越广泛。传统RX异常检测算法忽略影像空间相关性,而且由于没有经过有效数据降维,运算耗费大,对于高光谱数据有效性不高。高光谱影像在空间和光谱上符合高斯-马尔科夫模型。通过建立马尔科夫参数能够直接计算协方差矩阵的逆矩阵,避免了高光谱海量数据的庞大计算。提出一种基于三维高斯-马尔科夫随机场模型的改进RX异常检测算法。该方法用高斯-马尔科夫随机场模型模拟高光谱影像数据,用最大似然近似法估计高斯-马尔科夫随机场参数,由高斯-马尔科夫随机场参数直接构造检测算子,并以待检测像元为中心设置局部优化窗口,称为马尔科夫检测窗。取窗口内数据计算均值向量和协方差逆矩阵,得到中心像元的异常度,通过移动窗口进行逐像元检测。应用AVIRIS高光谱数据对传统RX算法、高斯-马尔科夫模型背景假设异常检测算法和该算法进行了仿真实验对比。结果表明,该算法能够有效提高高光谱异常检测效率,降低虚警率。运行时间较传统RX算法提高了45.2%,体现出更好的计算效率。     

A Visual Fault Detection Method for Induction Motors Based on a Zero-Sequence Current and an Improved Symmetrized Dot Pattern

Motor faults, especially mechanical faults, reflect eminently faint characteristic amplitudes in the stator current. In order to solve the issue of the motor current lacking effective and direct signal representation, this paper introduces a visual fault detection method for an induction motor based on zero-sequence current and an improved symmetric dot matrix pattern. Empirical mode decomposition (EMD) is used to eliminate the power frequency in the zero-sequence current derived from the original signal. A local symmetrized dot pattern (LSDP) method is proposed to solve the adaptive problem of classical symmetric lattice patterns with outliers. The LSDP approach maps the zero-sequence current to the ultimate coordinate and obtains a more intuitive two-dimensional image representation than the time–frequency image. Kernel density estimation (KDE) is used to complete the information about the density distribution of the image further to enhance the visual difference between the normal and fault samples. This method mines fault features in the current signals, which avoids the need to deploy additional sensors to collect vibration signals. The test results show that the fault detection accuracy of the LSDP can reach 96.85%, indicating that two-dimensional image representation can be effectively applied to current-based motor fault detection.     

DA-LSTM-VAE: Dual-Stage Attention-Based LSTM-VAE for KPI Anomaly Detection

To ensure the normal operation of the system, the enterprise’s operations engineer will monitor the system through the KPI (key performance indicator). For example, web page visits, server memory utilization, etc. KPI anomaly detection is a core technology, which is of great significance for rapid fault detection and repair. This paper proposes a novel dual-stage attention-based LSTM-VAE (DA-LSTM-VAE) model for KPI anomaly detection. Firstly, in order to capture time correlation in KPI data, long–short-term memory (LSTM) units are used to replace traditional neurons in the variational autoencoder (VAE). Then, in order to improve the effect of KPI anomaly detection, an attention mechanism is introduced into the input stage of the encoder and decoder, respectively. During the input stage of the encoder, a time attention mechanism is adopted to assign different weights to different time points, which can adaptively select important input sequences to avoid the influence of noise in the data. During the input stage of the decoder, a feature attention mechanism is adopted to adaptively select important latent variable representations, which can capture the long-term dependence of time series better. In addition, this paper proposes an adaptive threshold method based on anomaly scores measured by reconstruction probability, which can minimize false positives and false negatives and avoid adjustment of the threshold manually. Experimental results in a public dataset show that the proposed method in this paper outperforms other baseline methods.     

On-line conveyor belts inspection based on machine vision

Under the background that mining conveyor belts are prone to failure in operation, the on-line fault detection technique based on machine vision for conveyor belts is investigated. High-brightness linear light sources arranged to a vaulted shape provide light for a line-array CCD camera to capture high-quality belt images. A fast image segmentation algorithm is proposed to deal belt images on-line. The algorithm for detecting longitudinal rip and belt deviation which are serious threat to the mine safety production from binary belt images is presented. Then, an on-line visual belt inspection system is developed. The laboratory testing results testify the validity of the visual inspection system.     

SpaceWire冗余网络故障检测恢复技术实现

为提高SapceWire网络可靠性,基于SpaceWire-D提出了一种应用于SpaceWire冗余网络的故障检测恢复技术。网络节点通过比较主、备份端口收到的时间码来判断链路故障状态,在确认主链路发生故障后,节点自动启用备份端口工作。通过引入时间码抖动容限参数,提高了节点对故障判断的准确性,避免了故障误判。测试结果表明,即使故障链路未与节点直接连接,节点也能够在一个时间槽长度内检测到链路故障并自动切换至备份链路。此技术保证了网络故障情况下的数据正确传输,提高了SpaceWire网络的可靠性,是一种稳定可靠的故障检测恢复技术。     

Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics

De-noising and extraction of the weak signature are crucial to fault prognostics in which case features are often very weak and masked by noise. The wavelet transform has been widely used in signal de-noising due to its extraordinary time-frequency representation capability. In this paper, the performance of wavelet decomposition-based de-noising and wavelet filter-based de-noising methods are compared based on signals from mechanical defects. The comparison result reveals that wavelet filter is more suitable and reliable to detect a weak signature of mechanical impulse-like defect signals, whereas the wavelet decomposition de-noising method can achieve satisfactory results on smooth signal detection. In order to select optimal parameters for the wavelet filter, a two-step optimization process is proposed. Minimal Shannon entropy is used to optimize the Morlet wavelet shape factor. A periodicity detection method based on singular value decomposition (SVD) is used to choose the appropriate scale for the wavelet transform. The signal de-noising results from both simulated signals and experimental data are presented and both support the proposed method.     

Identification of multiple transient faults based on the adaptive spectral kurtosis method

This paper proposes a multi-fault detection method based on the adaptive spectral kurtosis (ASK) analysis of the vibration signal from single sensor. A theoretical model of multiple bearing faults is established in this paper. Compared with the kurtogram and protrugram techniques, the proposed method can more effectively extract signatures of multiple bearing faults even in the presence of strong background noise. The performance of the proposed method in fault detection of the rolling element bearings is validated using simulation data and experimental signals from a bearing with multiple faults and two faulty bearings.     

Radon anomalies along faults in North of Jordan

Radon emanation was sampled in five locations in a limestone quarry area using SSNTDs CR-39. Radon levels in the soil air at four different well-known traceable fault planes were measured along a traverse line perpendicular to each of these faults. Radon levels at the fault were higher by a factor of 3–10 than away from the faults. However, some sites have broader shoulders than the others. The method was applied along a fifth inferred fault zone. The results show anomalous radon level in the sampled station near the fault zone, which gave a radon value higher by three times than background. This study draws its importance from the fact that in Jordan many cities and villages have been established over an intensive faulted land. Also, our study has considerable implications for the future radon mapping. Moreover, radon gas is proved to be a good tool for fault zones detection.     

Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern failure prevention systems. Therefore, many machine learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. This work shows a framework that incorporates neuroevolution methods to boost the anomaly detection scores of new and already known models. The presented approach adapts evolution strategies for evolving an ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimize the architecture and hyperparameters such as the window size, the number of layers, and the layer depths. The proposed framework shows that it is possible to boost most anomaly detection deep learning models in a reasonable time and a fully automated mode. We ran tests on the SWAT and WADI datasets. To the best of our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.     

Roller bearing acoustic signature extraction by wavelet packet transform,applications in fault detection and size estimation

Continuous online monitoring of rotating machines is necessary to assess real-time health conditions so as to enable early detection of operation problems and thus reduce the possibility of downtime. Rolling element bearings are crucial parts of many machines and there has been an increasing demand to find effective and reliable health monitoring technique and advanced signal processing to detect and diagnose the size and location of incipient defects. Condition monitoring of rolling element bearings, comprises four main stages which are, statistical analysis, fault diagnostics, defect size calculation, and prognostics. In this paper the effect of defect size, operating speed, and loading conditions on statistical parameters of acoustic emission (AE) signals, using design of experiment method (DOE), have been investigated to select the most sensitive parameters for diagnosing incipient faults and defect growth on rolling element bearings. A modified and effective signal processing algorithm is designed to diagnose localized defects on rolling element bearings components under different operating speeds, loadings, and defect sizes. The algorithm is based on optimizing the ratio of Kurtosis and Shannon entropy to obtain the optimal band pass filter utilizing wavelet packet transform (WPT) and envelope detection. Results show the superiority of the developed algorithm and its effectiveness in extracting bearing characteristic frequencies from the raw acoustic emission signals masked by background noise under different operating conditions. To experimentally measure the defect size on rolling element bearings using acoustic emission technique, the proposed method along with spectrum of squared Hilbert transform are performed under different rotating speeds, loading conditions, and defect sizes to measure the time difference between the double AE impulses. Measurement results show the power of the proposed method for experimentally measuring size of different fault shapes using acoustic emission signals.     

Development of an on-line diagnosis system for rotor vibration via model-based intelligent inference

An on-line fault detection and isolation technique is proposed for the diagnosis of rotating machinery. The architecture of the system consists of a feature generation module and a fault inference module. Lateral vibration data are used for calculating the system features. Both continuous-time and discrete-time parameter estimation algorithms are employed for generating the features. A neural fuzzy network is exploited for intelligent inference of faults based on the extracted features. The proposed method is implemented on a digital signal processor. Experiments carried out for a rotor kit and a centrifugal fan indicate the potential of the proposed techniques in predictive maintenance.     

Application of multi-scale chirplet path pursuit and fractional Fourier transform for gear fault detection in speed up and speed-down processes

Demodulation is very important for gear fault detection. However, the demodulation is substantially complicated by the non-stationary nature of the signal during the speed-up and speed-down processes. As such, we propose a new technique to detect gear faults under such conditions based on the multi-scale chirplet path pursuit (MSCPP) algorithm and the fractional Fourier transform (FrFT) method. With the MSCPP algorithm, the instantaneous frequency of the signal component with the largest energy in the multi-components gear vibration signal can be estimated. Then according to the estimated instantaneous frequency, the vibration signal segment whose instantaneous frequency curve approximated as either an ascending or descending linear segment can be obtained from the original gear vibration signal. In other words, the vibration signal segment that can be regarded as a multi-component linear frequency modulated (LFM) signal is extracted. As the FrFT is suitable for multi-component LFM signal analysis, it is then applied to demodulating this vibration signal segment and hence detecting local gear faults based on the revealed modulation phenomenon. The effectiveness of the proposed method has been demonstrated by both simulation and experimental data.     

Research on the Fastest Detection Method for Weak Trends under Noise Interference

Trend anomaly detection is the practice of comparing and analyzing current and historical data trends to detect real-time abnormalities in online industrial data-streams. It has the advantages of tracking a concept drift automatically and predicting trend changes in the shortest time, making it important both for algorithmic research and industry. However, industrial data streams contain considerable noise that interferes with detecting weak anomalies. In this paper, the fastest detection algorithm “sliding nesting” is adopted. It is based on calculating the data weight in each window by applying variable weights, while maintaining the method of trend-effective integration accumulation. The new algorithm changes the traditional calculation method of the trend anomaly detection score, which calculates the score in a short window. This algorithm, SNWFD–DS, can detect weak trend abnormalities in the presence of noise interference. Compared with other methods, it has significant advantages. An on-site oil drilling data test shows that this method can significantly reduce delays compared with other methods and can improve the detection accuracy of weak trend anomalies under noise interference.     

Complex signal analysis for wind turbine planetary gearbox fault diagnosis via iterative atomic decomposition thresholding

The vibration signals from complex structures such as wind turbine (WT) planetary gearboxes are intricate. Reliable analysis of such signals is the key to success in fault detection and diagnosis for complex structures. The recently proposed iterative atomic decomposition thresholding (IADT) method has shown to be effective in extracting true constituent components of complicated signals and in suppressing background noise interferences. In this study, such properties of the IADT are exploited to analyze and extract the target signal components from complex signals with a focus on WT planetary gearboxes under constant running conditions. Fault diagnosis for WT planetary gearboxes has been a very important yet challenging issue due to their harsh working conditions and complex structures. Planetary gearbox fault diagnosis relies on detecting the presence of gear characteristic frequencies or monitoring their magnitude changes. However, a planetary gearbox vibration signal is a mixture of multiple complex components due to the unique structure, complex kinetics and background noise. As such, the IADT is applied to enhance the gear characteristic frequencies of interest, and thereby diagnose gear faults. Considering the spectral properties of planetary gearbox vibration signals, we propose to use Fourier dictionary in the IADT so as to match the harmonic waves in frequency domain and pinpoint the gear fault characteristic frequency. To reduce computing time and better target at more relevant signal components, we also suggest a criterion to estimate the number of sparse components to be used by the IADT. The performance of the proposed approach in planetary gearbox fault diagnosis has been evaluated through analyzing the numerically simulated, lab experimental and on-site collected signals. The results show that both localized and distributed gear faults, both the sun and planet gear faults, can be diagnosed successfully.     

改进的无线射频识别阅读器定位算法

针对RFID故障频率较高而导致RFID阅读器定位准确性较低的问题,提出一种改进的RFID阅读器定位算法。首先对RFID阅读器的故障类型进行分析,然后基于识别区域几何知识和线性二阶锥形规划处理长时大范围故障,并且采用质量指数指标对定位结果进行评价,最后对算法进行仿真测试。仿真结果表明,相对于当前的RFID阅读器定位算法,本文算法不仅提高了定位精度,而且可以提供定位质量信息。