Abstract The remaining useful life (RUL) estimation of bearings is critical for ensuring the reliability of mechanical systems. Owing to the rapid development of deep learning methods, a multitude of data-driven RUL estimation approaches have been proposed recently. However, the following problems remain in existing methods: 1) Most network models use raw data or statistical features as input, which renders it difficult to extract complex fault-related information hidden in signals; 2) for current observations, the dependence between current states is emphasized, but their complex dependence on previous states is often disregarded; 3) the output of neural networks is directly used as the estimated RUL in most studies, resulting in extremely volatile prediction results that lack robustness. Hence, a novel prognostics approach is proposed based on a time–frequency representation (TFR) subsequence, three-dimensional convolutional neural network (3DCNN), and Gaussian process regression (GPR). The approach primarily comprises two aspects: construction of a health indicator (HI) using the TFR-subsequence–3DCNN model, and RUL estimation based on the GPR model. The raw signals of the bearings are converted into TFR-subsequences by continuous wavelet transform and a dislocated overlapping strategy. Subsequently, the 3DCNN is applied to extract the hidden spatiotemporal features from the TFR-subsequences and construct HIs. Finally, the RUL of the bearings is estimated using the GPR model, which can also define the probability distribution of the potential function and prediction confidence. Experiments on the PRONOSTIA platform demonstrate the superiority of the proposed TFR-subsequence–3DCNN–GPR approach. The use of degradation-related spatiotemporal features in signals is proposed herein to achieve a highly accurate bearing RUL prediction with uncertainty quantification.
The failure mechanisms of the three kinds of crossing structures (aqueducts,inverted siphons,culverts) are analyzed and the failure modes are decomposed into integrated structure failure,water leakage and crack. Based on the failure mode,the reason for failure is analyzed as uneven settlement of foundation,excess load of structure material,water seal damage and so on. At last the risk factors are summarized as flood,earthquake,frozen disasters and inappropriate action in design,construction and operation. This research is the basis for the further risk assessment and provides the engineers with a reference in design and construction.
Aiming at the fracture problem of the square plansifter with 8 cells,the calculation for nature frequency and dynamic response of this structure is completed.Two improving projects of the structure were proposed based on the calculation results.Two projects of improving the structure are verified by finite element analysis.The first improving project was put into running.The practice use shows that dynamic finite element model and the first improving project is feasible.
Analysing vibration signal is an effective important method for diesel engine fault diagnosis, and its key techniques are feature extraction and pattern recognition. In this paper, wavelet packet decomposition algorithm as an effective method for fault feature extraction is used to decompose the vibration signals, and its percentage of energy band wavelet packet and wavelet packet energy spectrum entropy are regarded as diagnostic feature vectors. At the same time, in the process of pattern recognition, a mixed neural network training algorithm-GA-BP algorithm was used to recognize the fault pattern in fault diagnosis of valve gap abnormal fault. This method can effectively and reliably be used in the fault diagnosis of valve gap abnormal fault by comparing the two algorithms and analyzing the results of real examples. This method can also effectively be used in other fields.
Model-based methods utilize atmospheric scattering model to effectively dehaze images but introduce unwanted artifacts. By contrast, recent model-free methods directly restore dehazed images by an end-to-end network and avoid artificial errors. However, their dehazing ability is limited. To address this problem, we combine the advantages of supervised and unsupervised learning and propose a semisupervised knowledge distillation network for single image dehazing named SSKDN. Specially, we respectively build a supervised learning branch and an unsupervised learning branch by four attention-guided feature extraction blocks. In the supervised learning branch, the network is optimized by synthetic images. In the unsupervised learning branch, we dehaze real-world images by dark channel prior and refine dehazing network (RefineDNet) (another dehazing method) and use these dehazed images as fake ground truths to optimize network using prior information and knowledge distillation. Experimental results on synthetic and real-world images demonstrate that the proposed SSKDN performs better than state-of-the-art methods and owns powerful generalization ability.
Anomaly detection (AD) is an important technique for hyperspectral image processing and analysis. Typically, it is accomplished by extracting knowledge from the background and distinguishing anomalies and background using the difference between them. However, it is almost impossible to obtain "pure" background to achieve an ideal detection because of anomaly contamination. The low-rank and sparse matrix decomposition (LRaSMD) technique has been proved to have the potential to solve the aforementioned problem. But the accuracy and time consumption need to be further improved. Thus we propose a local hyperspectral AD method based on LRaSMD with an optimization algorithm for better performance. The LRaSMD technique is first implemented with semisoft Go decomposition (GoDec) rather than GoDec to quickly and accurately set the background apart from the anomalies. Then the low-rank prior knowledge of the background is fully explored to compute the background statistics. After that, the local Mahalanobis distance of pixels is calculated with the sliding dual-window strategy to detect the probable anomalies. The proposed method is validated using four real hyperspectral data sets with ground-truth information. Our experimental results indicate that the proposed method achieves better detection performance as compared with the comparison algorithms.
An adaptive shadow detection algorithm is proposed to eliminate interference on object detection from the shadow. The algorithm uses three components in YUV colour space to identify shadow pixels from the candidate foreground. An adaptive threshold estimator is designed to improve shadow detection accuracy and adaptive capacity in various lighting conditions. This estimator uses edge detection method to obtain global texture, as well statistical calculations to obtain the thresholds. Algorithm has the characteristic of low complexity and little restraint; hence it is suitable for real time‐moving shadow detection in various lighting conditions. Experiment results show that this algorithm can obtain a high detection accuracy and the time‐assume is greatly shortened compared with other algorithms with similar accuracy.
According to modulation characteristics of roller bearing fault vibration signals and limitation of traditional envelope analysis,a roller bearing fault diagnosis method using improved envelope analysis based on empirical mode decomposition(EMD) and spectrum kurtosis(SK) was proposed here.Firstly,roller bearing fault vibration signals were decomposed into a finite number of intrinsic mode functions(IMFs).Secondly,FFT transformation was used to make each IMF into a spectral signal and calculate their absolute values,then spectrum kurtosis values were calculated using each IMF spectral absolute value square envelope.Finally,using the filtering function of the spectrum kurtosis,the best frequency band for demodulation was automatically chosen with the criterion of IMFs spectrum kurtosis.The proposed method was applied to simulated signals and actual signals,the analysis results demonstrated the effectiveness of the proposed method.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
