scholarly journals Cost-Sensitive LightGBM-Based Online Fault Detection Method for Wind Turbine Gearboxes

2021 ◽  
Vol 9 ◽  
Author(s):  
Mingzhu Tang ◽  
Qi Zhao ◽  
Huawei Wu ◽  
Zimin Wang
Keyword(s):  
Fault Detection ◽  
False Alarm ◽  
Wind Turbine ◽  
False Alarm Rate ◽  
Detection Rate ◽  
Rank Correlation ◽  
Spearman Rank Correlation ◽  
Misclassification Cost ◽  
Spearman Rank ◽  
The Cost

In practice, faulty samples of wind turbine (WT) gearboxes are far smaller than normal samples during operation, and most of the existing fault diagnosis methods for WT gearboxes only focus on the improvement of classification accuracy and ignore the decrease of missed alarms and the reduction of the average cost. To this end, a new framework is proposed through combining the Spearman rank correlation feature extraction and cost-sensitive LightGBM algorithm for WT gearbox’s fault detection. In this article, features from wind turbine supervisory control and data acquisition (SCADA) systems are firstly extracted. Then, the feature selection is employed by using the expert experience and Spearman rank correlation coefficient to analyze the correlation between the big data of WT gearboxes. Moreover, the cost-sensitive LightGBM fault detection framework is established by optimizing the misclassification cost. The false alarm rate and the missed detection rate of the WT gearbox under different working conditions are finally obtained. Experiments have verified that the proposed method can significantly improve the fault detection accuracy. Meanwhile, the proposed method can consistently outperform traditional classifiers such as AdaCost, cost-sensitive GBDT, and cost-sensitive XGBoost in terms of low false alarm rate and missed detection rate. Owing to its high Matthews correlation coefficient scores and low average misclassification cost, the cost-sensitive LightGBM (CS LightGBM) method is preferred for imbalanced WT gearbox fault detection in practice.

A Novel Markov Model and its Application to BIT System

2012 ◽  
Vol 239-240 ◽  
pp. 721-725
Author(s):  
Wen Rong Zheng ◽  
Shu Zong Wang
Keyword(s):  
Complex System ◽  
Fault Diagnosis ◽  
Fault Detection ◽  
Markov Model ◽  
False Alarm ◽  
False Alarm Rate ◽  
Detection Rate ◽  
Intermittent Fault ◽  
System A ◽  
Main Factor

Intermittent fault is the main factor for the raise of false alarm during the process of the detection in built-in test (BIT). Two-state Markov model and three-state Markov model for test is built for system fault diagnosis with BIT. According to the application of BIT in some complex system, a comparison of the false alarm rate between two-state Markov model and three-state Markov model is present, which shows we can reduce the false alarm rate (FAR) and improve fault detection rate by using three-state Markov model in BIT.

scholarly journals Cost-Sensitive Extremely Randomized Trees Algorithm for Online Fault Detection of Wind Turbine Generators

2021 ◽  
Vol 9 ◽  
Author(s):  
Mingzhu Tang ◽  
Yutao Chen ◽  
Huawei Wu ◽  
Qi Zhao ◽  
Wen Long ◽  
...  
Keyword(s):  
Fault Detection ◽  
Wind Turbine ◽  
Feature Selection Method ◽  
Misclassification Cost ◽  
Imbalanced Classification ◽  
Extremely Randomized Trees ◽  
Turbine Generators ◽  
Wind Turbine Generators ◽  
Doubly Fed ◽  
The Cost

The number of normal samples of wind turbine generators is much larger than the number of fault samples. To solve the problem of imbalanced classification in wind turbine generator fault detection, a cost-sensitive extremely randomized trees (CS-ERT) algorithm is proposed in this paper, in which the cost-sensitive learning method is introduced into an extremely randomized trees (ERT) algorithm. Based on the classification misclassification cost and class distribution, the misclassification cost gain (MCG) is proposed as the score measure of the CS-ERT model growth process to improve the classification accuracy of minority classes. The Hilbert-Schmidt independence criterion lasso (HSICLasso) feature selection method is used to select strongly correlated non-redundant features of doubly-fed wind turbine generators. The effectiveness of the method was verified by experiments on four different failure datasets of wind turbine generators. The experiment results show that average missing detection rate, average misclassification cost and gMean of the improved algorithm better than those of the ERT algorithm. In addition, compared with the CSForest, AdaCost and MetaCost methods, the proposed method has better real-time fault detection performance.

scholarly journals Fault Detection for Pitch System of Wind Turbine-Driven Doubly Fed Based on IHHO-LightGBM

2021 ◽  
Vol 11 (17) ◽  
pp. 8030
Author(s):  
Mingzhu Tang ◽  
Zhonghui Peng ◽  
Huawei Wu
Keyword(s):  
Experimental Data ◽  
Control System ◽  
Fault Detection ◽  
False Alarm ◽  
Wind Turbine ◽  
False Alarm Rate ◽  
Optimization Algorithm ◽  
Pitch Control ◽  
Detection Model ◽  
Light Gradient

To address the issue of a large calculation and difficult optimization for the traditional fault detection of a wind turbine-based pitch control system, a fault detection model, based on LightGBM by the improved Harris Hawks optimization algorithm (light gradient boosting machine by the improved Harris Hawks optimization,IHHO-LightGBM) for the wind turbine-based pitch control system, is proposed in this article. Firstly, a trigonometric function model is introduced by IHHO to update the prey escape energy, to balance the global exploration ability and local development ability of the algorithm. In this model, the fault detection false alarm rate is used as the fitness function, and the two parameters are used as the optimization objects of the improved Harris Hawks optimization algorithm, to optimize the parameters, so as to achieve the global optimal parameters to improve the performance of the fault detection model. Three different fault data of the pitch control system in actual operations of domestic wind farms are used as the experimental data, the Pearson correlation analysis method is introduced, and the wind turbine power output is taken as the main state parameter, to analyze the correlation degree of all the characteristic variables of the data and screen the important characteristic variables out, so as to achieve the effective dimensionality reduction process of the data, by using the feature selection method. Three established fault detection models are selected and compared with the proposed method, to verify its feasibility. The experimental data indicate that compared with other algorithms, the fault detecting ability of the proposed model is improved in all aspects, and the false alarm rate and false negative rate are lower.

scholarly journals Integrated design of observer based fault detection for a class of uncertain nonlinear systems

2011 ◽  
Vol 21 (3) ◽  
pp. 423-430 ◽  
Author(s):  
Wei Chen ◽  
Abdul Khan ◽  
Muhammmad Abid ◽  
Steven Ding
Keyword(s):  
Nonlinear Systems ◽  
Fault Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Detection Rate ◽  
Design Method ◽  
Integrated Design ◽  
Uncertain Nonlinear Systems ◽  
Trade Off ◽  
Residual Generator

Integrated design of observer based fault detection for a class of uncertain nonlinear systems Integrated design of observer based Fault Detection (FD) for a class of uncertain nonlinear systems with Lipschitz nonlinearities is studied. In the context of norm based residual evaluation, the residual generator and evaluator are designed together in an integrated form, and, based on it, a trade-off FD system is finally achieved in the sense that, for a given Fault Detection Rate (FDR), the False Alarm Rate (FAR) is minimized. A numerical example is given to illustrate the effectiveness of the proposed design method.

HUBUNGAN BEBAN KERJA PERAWAT DENGAN KELENGKAPAN PENGISIAN DOKUMENTASI ASUHAN KEPERAWATAN

2020 ◽  
Vol 5 (2) ◽  
pp. 588
Author(s):  
Etlida Wati ◽  
Ulva Arini
Keyword(s):  
Nursing Care ◽  
Rank Correlation ◽  
Bivariate Analysis ◽  
Spearman Rank Correlation ◽  
Cross Sectional ◽  
Weight Category ◽  
Spearman Rank ◽  
Hospital Room ◽  
Analysis Technique ◽  
Nurse Workload

<p>Documentation is an activity of recording, reporting or recording an event and activities carried out in the form of providing services that are considered important and valuable. One factor that can influence documentation is the nurse's workload. The purpose of this study is to identify the relationship between nurses' workload and the application of documentation in the Hj. Anna Lasmanah Banjarnegara. This  research is quantitative with a cross sectional approach descriptive correlation design. Samples were taken with a total sampling of 65 nurses. Instruments to measure documentation using observation sheets. While the nurse workload instrument uses a questionnaire sheet. The analysis technique uses Spearman Rank correlation. Based on the research results of the workload of a nurse in the hospital room , most of them are in the weight category, as many as 46 respondents (70.8%). Application of nursing care documentation in the hospital room Hj. Anna Lasmanah Banjarnegara, most of them are respondents in the incomplete category as many as 63 respondents (96.9%). There is a significant relationship between nurse workload with the application of documentation, this is evidenced by the results of the Spearman Rank correlation bivariate analysis, which is r = 0.688 with p = 0.000 &lt;0.05. It is hoped that management will motivate nurses to complete the documentation of nursing care</p>

Multiple faults detection and isolation approach applied to a kraft recovery boiler

TAPPI Journal ◽  
2014 ◽  
Vol 13 (1) ◽  
pp. 33-41
Author(s):  
YVON THARRAULT ◽  
MOULOUD AMAZOUZ
Keyword(s):  
Fault Detection ◽  
Early Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Principal Component ◽  
Fault Isolation ◽  
Fault Detection And Isolation ◽  
Detection Scheme ◽  
Multiple Faults ◽  
Recovery Boiler

Recovery boilers play a key role in chemical pulp mills. Early detection of defects, such as water leaks, in a recovery boiler is critical to the prevention of explosions, which can occur when water reaches the molten smelt bed of the boiler. Early detection is difficult to achieve because of the complexity and the multitude of recovery boiler operating parameters. Multiple faults can occur in multiple components of the boiler simultaneously, and an efficient and robust fault isolation method is needed. In this paper, we present a new fault detection and isolation scheme for multiple faults. The proposed approach is based on principal component analysis (PCA), a popular fault detection technique. For fault detection, the Mahalanobis distance with an exponentially weighted moving average filter to reduce the false alarm rate is used. This filter is used to adapt the sensitivity of the fault detection scheme versus false alarm rate. For fault isolation, the reconstruction-based contribution is used. To avoid a combinatorial excess of faulty scenarios related to multiple faults, an iterative approach is used. This new method was validated using real data from a pulp and paper mill in Canada. The results demonstrate that the proposed method can effectively detect sensor faults and water leakage.

scholarly journals Infrared small target detection based on region proposal and CNN classifier

2021 ◽  
Author(s):  
Mingming Fan ◽  
Shaoqing Tian ◽  
Kai Liu ◽  
Jiaxin Zhao ◽  
Yunsong Li
Keyword(s):  
Neural Network ◽  
False Alarm ◽  
False Alarm Rate ◽  
Target Detection ◽  
Detection Rate ◽  
Corner Detection ◽  
Small Target ◽  
Small Target Detection ◽  
Potential Target ◽  
Infrared Small Target

AbstractInfrared small target detection has been a challenging task due to the weak radiation intensity of targets and the complexity of the background. Traditional methods using hand-designed features are usually effective for specific background and have the problems of low detection rate and high false alarm rate in complex infrared scene. In order to fully exploit the features of infrared image, this paper proposes an infrared small target detection method based on region proposal and convolution neural network. Firstly, the small target intensity is enhanced according to the local intensity characteristics. Then, potential target regions are proposed by corner detection to ensure high detection rate of the method. Finally, the potential target regions are fed into the classifier based on convolutional neural network to eliminate the non-target regions, which can effectively suppress the complex background clutter. Extensive experiments demonstrate that the proposed method can effectively reduce the false alarm rate, and outperform other state-of-the-art methods in terms of subjective visual impression and quantitative evaluation metrics.

scholarly journals Security of Things Intrusion Detection System for Smart Healthcare

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1375
Author(s):  
Celestine Iwendi ◽  
Joseph Henry Anajemba ◽  
Cresantus Biamba ◽  
Desire Ngabo
Keyword(s):  
Genetic Algorithm ◽  
Intrusion Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Detection Rate ◽  
Web Security ◽  
Intrusion Detection Systems ◽  
High Detection Rate ◽  
Detection Systems ◽  
Smart Healthcare

Web security plays a very crucial role in the Security of Things (SoT) paradigm for smart healthcare and will continue to be impactful in medical infrastructures in the near future. This paper addressed a key component of security-intrusion detection systems due to the number of web security attacks, which have increased dramatically in recent years in healthcare, as well as the privacy issues. Various intrusion-detection systems have been proposed in different works to detect cyber threats in smart healthcare and to identify network-based attacks and privacy violations. This study was carried out as a result of the limitations of the intrusion detection systems in responding to attacks and challenges and in implementing privacy control and attacks in the smart healthcare industry. The research proposed a machine learning support system that combined a Random Forest (RF) and a genetic algorithm: a feature optimization method that built new intrusion detection systems with a high detection rate and a more accurate false alarm rate. To optimize the functionality of our approach, a weighted genetic algorithm and RF were combined to generate the best subset of functionality that achieved a high detection rate and a low false alarm rate. This study used the NSL-KDD dataset to simultaneously classify RF, Naive Bayes (NB) and logistic regression classifiers for machine learning. The results confirmed the importance of optimizing functionality, which gave better results in terms of the false alarm rate, precision, detection rate, recall and F1 metrics. The combination of our genetic algorithm and RF models achieved a detection rate of 98.81% and a false alarm rate of 0.8%. This research raised awareness of privacy and authentication in the smart healthcare domain, wireless communications and privacy control and developed the necessary intelligent and efficient web system. Furthermore, the proposed algorithm was applied to examine the F1-score and precisionperformance as compared to the NSL-KDD and CSE-CIC-IDS2018 datasets using different scaling factors. The results showed that the proposed GA was greatly optimized, for which the average precision was optimized by 5.65% and the average F1-score by 8.2%.

scholarly journals Does continuity in nursing staff matter? A pilot study on correlation of central line-associated bloodstream infections and employee turnover

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Thomas Scheier ◽  
Stefan P. Kuster ◽  
Mesida Dunic ◽  
Christian Falk ◽  
Hugo Sax ◽  
...  
Keyword(s):  
Nursing Staff ◽  
Employee Turnover ◽  
Rank Correlation ◽  
Bloodstream Infections ◽  
Central Line ◽  
Incidence Rates ◽  
Nursing Personnel ◽  
Care Hospital ◽  
Spearman Rank Correlation ◽  
Spearman Rank

Abstract Background Understaffing has been previously reported as a risk factor for central line-associated bloodstream infections (CLABSI). No previous study addressed the question whether fluctuations in staffing have an impact on CLABSI incidence. We analyzed prospectively collected CLABSI surveillance data and data on employee turnover of health care workers (HCW) to address this research question. Methods In January 2016, a semiautomatic surveillance system for CLABSI was implemented at the University Hospital Zurich, a 940 bed tertiary care hospital in Switzerland. Monthly incidence rates (CLABSI/1000 catheter days) were calculated and correlations with human resources management-derived data on employee turnover of HCWs (defined as number of leaving HCWs per month divided by the number of employed HCWs) investigated. Results Over a period of 24 months, we detected on the hospital level a positive correlation of CLABSI incidence rates and turnover of nursing personnel (Spearman rank correlation, r = 0.467, P = 0.022). In more detailed analyses on the professional training of nursing personnel, a correlation of CLABSI incidence rates and licensed practical nurses (Spearman rank correlation, r = 0.26, P = 0.038) or registered nurses (r = 0.471, P = 0.021) was found. Physician turnover did not correlate with CLABSI incidence (Spearman rank correlation, r =  −0.058, P = 0.787). Conclusions Prospectively determined CLABSI incidence correlated positively with the degree of turnover of nurses overall and nurses with advanced training, but not with the turnover of physicians. Efforts to maintain continuity in nursing staff might be helpful for sustained reduction in CLABSI rates.

scholarly journals In vivo calibration of the T2* cardiovascular magnetic resonance method at 1.5 T for estimation of cardiac iron in a minipig model of transfusional iron overload

2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Peter Diedrich Jensen ◽  
Asbjørn Haaning Nielsen ◽  
Carsten Wiberg Simonsen ◽  
Ulrik Thorngren Baandrup ◽  
Svend Eggert Jensen ◽  
...  
Keyword(s):  
Rank Correlation ◽  
Calibration Data ◽  
Iron Loading ◽  
Spearman Rank Correlation ◽  
Calibration Equation ◽  
Spearman Rank ◽  
Cardiac Iron ◽  
In Vivo Calibration ◽  
Spearman Rank Correlation Coefficient

Abstract Background Non-invasive estimation of the cardiac iron concentration (CIC) by T2* cardiovascular magnetic resonance (CMR) has been validated repeatedly and is in widespread clinical use. However, calibration data are limited, and mostly from post-mortem studies. In the present study, we performed an in vivo calibration in a dextran-iron loaded minipig model. Methods R2* (= 1/T2*) was assessed in vivo by 1.5 T CMR in the cardiac septum. Chemical CIC was assessed by inductively coupled plasma-optical emission spectroscopy in endomyocardial catheter biopsies (EMBs) from cardiac septum taken during follow up of 11 minipigs on dextran-iron loading, and also in full-wall biopsies from cardiac septum, taken post-mortem in another 16  minipigs, after completed iron loading. Results A strong correlation could be demonstrated between chemical CIC in 55 EMBs and parallel cardiac T2* (Spearman rank correlation coefficient 0.72, P < 0.001). Regression analysis led to [CIC] = (R2* − 17.16)/41.12 for the calibration equation with CIC in mg/g dry weight and R2* in Hz. An even stronger correlation was found, when chemical CIC was measured by full-wall biopsies from cardiac septum, taken immediately after euthanasia, in connection with the last CMR session after finished iron loading (Spearman rank correlation coefficient 0.95 (P < 0.001). Regression analysis led to the calibration equation [CIC] = (R2* − 17.2)/31.8. Conclusions Calibration of cardiac T2* by EMBs is possible in the minipig model but is less accurate than by full-wall biopsies. Likely explanations are sampling error, variable content of non-iron containing tissue and smaller biopsies, when using catheter biopsies. The results further validate the CMR T2* technique for estimation of cardiac iron in conditions with iron overload and add to the limited calibration data published earlier.

Sign in / Sign up

Export Citation Format

Share Document