scholarly journals Subway Gearbox Fault Diagnosis Algorithm Based on Adaptive Spline Impact Suppression

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 660
Author(s):  
Zhongshuo Hu ◽  
Jianwei Yang ◽  
Dechen Yao ◽  
Jinhai Wang ◽  
Yongliang Bai
Keyword(s):  
Fault Diagnosis ◽  
Spline Interpolation ◽  
Reference Value ◽  
High Amplitude ◽  
Engineering Practice ◽  
Negative Effects ◽  
Short Term ◽  
Time Domain Signal ◽  
Gearbox Vibration ◽  
Long Time

In the signal processing of real subway vehicles, impacts between wheelsets and rail joint gaps have significant negative effects on the spectrum. This introduces great difficulties for the fault diagnosis of gearboxes. To solve this problem, this paper proposes an adaptive time-domain signal segmentation method that envelopes the original signal using a cubic spline interpolation. The peak values of the rail joint gap impacts are extracted to realize the adaptive segmentation of gearbox fault signals when the vehicle was moving at a uniform speed. A long-time and unsteady signal affected by wheel–rail impacts is segmented into multiple short-term, steady-state signals, which can suppress the high amplitude of the shock response signal. Finally, on this basis, multiple short-term sample signals are analyzed by time- and frequency-domain analyses and compared with the nonfaulty results. The results showed that the method can efficiently suppress the high-amplitude components of subway gearbox vibration signals and effectively extract the characteristics of weak faults due to uniform wear of the gearbox in the time and frequency domains. This provides reference value for the gearbox fault diagnosis in engineering practice.

scholarly journals Fault diagnosis and maintenance of automobile engine cooling system

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Chunmei Chen
Keyword(s):  
Fault Diagnosis ◽  
Cooling System ◽  
Reference Value ◽  
Mechanical Equipment ◽  
Automobile Engine ◽  
Engine Cooling ◽  
Economic Level ◽  
Long Time ◽  
Further Development

With the further development of the society, the economic level of Chinese residents is gradually improving. Under such circumstances, the number of automobiles and their usage are increasing as well. As a kind of mechanical equipment, there will be many application faults of the automobile after long-term use. Only by solving the faults can automobiles be restarted and run stably for a long time. Based on this, this paper focuses on automobile maintenance, analyzes the principle of engine cooling system, and studies the diagnosis and maintenance methods of this kind of fault, trying to provide some reference value for the further discussion and research in this field.

scholarly journals Aircraft Gearbox Fault Diagnosis System: An Approach based on Deep Learning Techniques

2020 ◽  
Vol 30 (1) ◽  
pp. 258-272
Author(s):  
P B Mallikarjuna ◽  
M Sreenatha ◽  
S Manjunath ◽  
Niranjan C Kundur
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Frequency Domain ◽  
Short Term Memory ◽  
Aircraft Engine ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Gearbox Vibration ◽  
Long Short Term Memory

Abstract Gearbox is one of the vital components in aircraft engines. If any small damage to gearbox, it can cause the breakdown of aircraft engine. Thus it is significant to study fault diagnosis in gearbox system. In this paper, two deep learning models (Long short term memory (LSTM) and Bi-directional long short term memory (BLSTM)) are proposed to classify the condition of gearbox into good or bad. These models are applied on aircraft gearbox vibration data in both time and frequency domain. A publicly available aircraft gearbox vibration dataset is used to evaluate the performance of proposed models. The results proved that accuracy achieved by LSTM and BLSTM are highly reliable and applicable in health monitoring of aircraft gearbox system in time domain as compared to frequency domain. Also, to show the superiority of proposed models for aircraft gearbox fault diagnosis, performance is compared with classical machine learning models.

Time Window from Visual Images to Visual Short-Term Memory: Consolidation or Integration?

2004 ◽  
Vol 51 (1) ◽  
pp. 45-51 ◽  
Author(s):  
Yuhong Jiang
Keyword(s):  
Short Term Memory ◽  
Time Window ◽  
Short Interval ◽  
Visual Images ◽  
Short Term ◽  
Temporal Window ◽  
Term Memory ◽  
Visual Short Term Memory ◽  
Probe Task ◽  
Long Time

Abstract. When two dot arrays are briefly presented, separated by a short interval of time, visual short-term memory of the first array is disrupted if the interval between arrays is shorter than 1300-1500 ms ( Brockmole, Wang, & Irwin, 2002 ). Here we investigated whether such a time window was triggered by the necessity to integrate arrays. Using a probe task we removed the need for integration but retained the requirement to represent the images. We found that a long time window was needed for performance to reach asymptote even when integration across images was not required. Furthermore, such window was lengthened if subjects had to remember the locations of the second array, but not if they only conducted a visual search among it. We suggest that a temporal window is required for consolidation of the first array, which is vulnerable to disruption by subsequent images that also need to be memorized.

scholarly journals Catchment water quality in the year preceding and immediately following restoration of a drained afforested blanket bog

2021 ◽  
Author(s):  
Paul P. J. Gaffney ◽  
Mark H. Hancock ◽  
Mark A. Taggart ◽  
Roxane Andersen
Keyword(s):  
Water Quality ◽  
Nutrient Release ◽  
Pass Rate ◽  
Future Research ◽  
Negative Effects ◽  
Short Term ◽  
Peatland Restoration ◽  
Blanket Bog ◽  
Quality Threshold ◽  
Policy Incentives

AbstractThe restoration of drained afforested peatlands, through drain blocking and tree removal, is increasing in response to peatland restoration targets and policy incentives. In the short term, these intensive restoration operations may affect receiving watercourses and the biota that depend upon them. This study assessed the immediate effect of ‘forest-to-bog’ restoration by measuring stream and river water quality for a 15 month period pre- and post-restoration, in the Flow Country peatlands of northern Scotland. We found that the chemistry of streams draining restoration areas differed from that of control streams following restoration, with phosphate concentrations significantly higher (1.7–6.2 fold, mean 4.4) in restoration streams compared to the pre-restoration period. This led to a decrease in the pass rate (from 100 to 75%) for the target “good” quality threshold (based on EU Water Framework Directive guidelines) in rivers in this immediate post-restoration period, when compared to unaffected river baseline sites (which fell from 100 to 90% post-restoration). While overall increases in turbidity, dissolved organic carbon, iron, potassium and manganese were not significant post-restoration, they exhibited an exaggerated seasonal cycle, peaking in summer months in restoration streams. We attribute these relatively limited, minor short-term impacts to the fact that relatively small percentages of the catchment area (3–23%), in our study catchments were felled, and that drain blocking and silt traps, put in place as part of restoration management, were likely effective in mitigating negative effects. Looking ahead, we suggest that future research should investigate longer term water quality effects and compare different ways of potentially controlling nutrient release.

scholarly journals Characterization of Short-Term Heat Stress in Holstein Dairy Cows Using Altered Indicators of Metabolomics, Blood Parameters, Milk MicroRNA-216 and Characteristics

Animals ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 722
Author(s):  
Jang-Hoon Jo ◽  
Jalil Ghassemi Nejad ◽  
Dong-Qiao Peng ◽  
Hye-Ran Kim ◽  
Sang-Ho Kim ◽  
...  
Keyword(s):  
Heat Stress ◽  
Dairy Cows ◽  
Milk Yield ◽  
Milk Fat ◽  
Blood Parameters ◽  
Negative Effects ◽  
Short Term ◽  
Lactating Cows ◽  
Humidity Index ◽  
Holstein Dairy Cows

This study aims to characterize the influence of short-term heat stress (HS; 4 day) in early lactating Holstein dairy cows, in terms of triggering blood metabolomics and parameters, milk yield and composition, and milk microRNA expression. Eight cows (milk yield = 30 ± 1.5 kg/day, parity = 1.09 ± 0.05) were homogeneously housed in environmentally controlled chambers, assigned into two groups with respect to the temperature humidity index (THI) at two distinct levels: approximately ~71 (low-temperature, low-humidity; LTLH) and ~86 (high-temperature, high-humidity; HTHH). Average feed intake (FI) dropped about 10 kg in the HTHH group, compared with the LTLH group (p = 0.001), whereas water intake was only numerically higher (p = 0.183) in the HTHH group than in the LTLH group. Physiological parameters, including rectal temperature (p = 0.001) and heart rate (p = 0.038), were significantly higher in the HTHH group than in the LTLH group. Plasma cortisol and haptoglobin were higher (p < 0.05) in the HTHH group, compared to the LTLH group. Milk yield, milk fat yield, 3.5% fat-corrected milk (FCM), and energy-corrected milk (ECM) were lower (p < 0.05) in the HTHH group than in the LTLH group. Higher relative expression of milk miRNA-216 was observed in the HTHH group (p < 0.05). Valine, isoleucine, methionine, phenylalanine, tyrosine, tryptophan, lactic acid, 3-phenylpropionic acid, 1,5-anhydro-D-sorbitol, myo-inositol, and urea were decreased (p < 0.05). These results suggest that early lactating cows are more vulnerable to short-term (4 day) high THI levels—that is, HTHH conditions—compared with LTLH, considering the enormous negative effects observed in measured blood metabolomics and parameters, milk yield and compositions, and milk miRNA-216 expression.

scholarly journals Extraction of local and global features by a convolutional neural network–long short-term memory network for diagnosing bearing faults

2021 ◽  
pp. 095440622110165
Author(s):  
Zhang Chao ◽  
Wang Wei-zhi ◽  
Zhang Chen ◽  
Fan Bin ◽  
Wang Jian-guo ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Condition Monitoring ◽  
Short Term Memory ◽  
Vibration Signal ◽  
Short Term ◽  
Global Features ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Lstm Network

Accurate and reliable fault diagnosis is one of the key and difficult issues in mechanical condition monitoring. In recent years, Convolutional Neural Network (CNN) has been widely used in mechanical condition monitoring, which is also a great breakthrough in the field of bearing fault diagnosis. However, CNN can only extract local features of signals. The model accuracy and generalization of the original vibration signals are very low in the process of vibration signal processing only by CNN. Based on the above problems, this paper improves the traditional convolution layer of CNN, and builds the learning module (local feature learning block, LFLB) of the local characteristics. At the same time, the Long Short-Term Memory (LSTM) is introduced into the network, which is used to extract the global features. This paper proposes the new neural network—improved CNN-LSTM network. The extracted deep feature is used for fault classification. The improved CNN-LSTM network is applied to the processing of the vibration signal of the faulty bearing collected by the bearing failure laboratory of Inner Mongolia University of science and technology. The results show that the accuracy of the improved CNN-LSTM network on the same batch test set is 98.75%, which is about 24% higher than that of the traditional CNN. The proposed network is applied to the bearing data collection of Western Reserve University under the condition that the network parameters remain unchanged. The experiment shows that the improved CNN-LSTM network has better generalization than the traditional CNN.

Fault Diagnosis Method for a Network Control System with Long-Time Delay and Data Packet Loss Based on H∞ Filtering

2013 ◽  
Vol 846-847 ◽  
pp. 795-798
Author(s):  
Jiao Meng ◽  
Qi Hua Xu ◽  
Xiao Xiao
Keyword(s):  
Control System ◽  
Fault Diagnosis ◽  
Time Delay ◽  
Packet Loss ◽  
Estimation Error ◽  
Network Control ◽  
Data Packet ◽  
Practical Significance ◽  
Network Control System ◽  
Long Time

Improving network control system---NCS reliability and safety has important practical significance because NCS is a hot research subject in these years. Fault diagnosis methods are researched in this paper according to NCS with long-time delay and data packet loss. Firstly, given a NCS with long-time delay, a state observer is structured. Secondly, make the state estimation error equation equivalent to an asynchronous dynamical system having event incidence constraint according to whether the system having data packets loss. The problem of fault diagnosis is converted to filtering problem through structuring filtering residual system based on the observer, then giving a corresponding filter designing algorithm. The designed fault diagnosis filter system not only make sure the stability of the closed loop system but also make the residual systems norm less than given reduction level. Finally, the simulation results prove that the algorithm can diagnose faults effectively.

Sign in / Sign up

Export Citation Format

Share Document