A novel multi-information decision fusion based on improved random forests in HVCB fault detection application

2022 ◽  
Author(s):  
Suliang Ma ◽  
Jianlin Li ◽  
Yiwen Wu ◽  
Chao Xin ◽  
Yaxin Li ◽  
...  
Keyword(s):  
Evidence Theory ◽  
Research Direction ◽  
Decision Fusion ◽  
Fault Identification ◽  
Circuit Breakers ◽  
Accurate Identification ◽  
Current Time ◽  
Fault Type ◽  
Fault Recognition ◽  
The Common

Abstract Evaluating the mechanical state of high-voltage circuit breakers (HVCBs) based on vibration information has currently become an important research direction. In contrast to the unicity of the travel–time and current–time curves, the vibration information from the different positions is diverse. These differences are often overlooked in HVCB fault identification applications. Additionally, the fault recognition results based on different location information often vary, and conflicting diagnosis results directly cause the accurate identification of the fault type to fail. Therefore, in this paper, a novel multi-information decision fusion approach is proposed based on the improved random forest (RF) and Dempster-Shafer evidence theory. In the proposed method, the diagnostic distribution of all classification regression trees (CART) in the RF is considered to solve the conflicts among the multi-information diagnosis results. Experimental results show that the proposed method eases the contradiction of multi-position diagnostic results and improves the accuracy of fault identification. Furthermore, compared to the common classifiers and probability generation methods, the effectiveness and superiority of the proposed method are verified.

A comparative study of data-driven and physics-based gas turbine fault recognition approaches

2021 ◽  
pp. 1748006X2198964
Author(s):  
Juan Luis Pérez-Ruiz ◽  
Igor Loboda ◽  
Iván González-Castillo ◽  
Víctor Manuel Pineda-Molina ◽  
Karen Anaid Rendón-Cortés ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Gas Turbine ◽  
Recognition Accuracy ◽  
Data Driven ◽  
Fault Identification ◽  
Fault Recognition ◽  
Data Driven Approach ◽  
Diagnostic Approaches ◽  
Artificial Neural Network Ann ◽  
Two Stages

The present paper compares the fault recognition capabilities of two gas turbine diagnostic approaches: data-driven and physics-based (a.k.a. gas path analysis, GPA). The comparison takes into consideration two differences between the approaches, the type of diagnostic space and diagnostic decision rule. To that end, two stages are proposed. In the first one, a data-driven approach with an artificial neural network (ANN) that recognizes faults in the space of measurement deviations is compared with a hybrid GPA approach that employs the same type of ANN to recognize faults in the space of estimated fault parameter. Different case studies for both anomaly detection and fault identification are proposed to evaluate the diagnostic spaces. They are formed by varying the classification, type of diagnostic analysis, and deviation noise scheme. In the second stage, the original GPA is reconstructed replacing the ANN with a tolerance-based rule to make diagnostic decisions. Here, two aspects are under analysis: the comparison of GPA classification rules and whole approaches. The results reveal that for simple classifications both spaces are equally accurate for anomaly detection and fault identification. However, for complex scenarios, the data-driven approach provides on average slightly better results for fault identification. The use of a hybrid GPA with ANN for a full classification instead of an original GPA with tolerance-based rule causes an increase of 12.49% in recognition accuracy for fault identification and up to 54.39% for anomaly detection. As for the whole approach comparison, the application of a data-driven approach instead of the original GPA can lead to an improvement of 12.14% and 53.26% in recognition accuracy for fault identification and anomaly detection, respectively.

scholarly journals A Complex Fault Diagnostic Approach of Active Distribution Network Based on SBS-SFS Optimized Multi-SVM

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Keyan Liu ◽  
Weijie Dong ◽  
Huanyu Dong ◽  
Jia Wei ◽  
Shiwu Xiao
Keyword(s):  
Fault Diagnosis ◽  
Distribution Networks ◽  
Operating Conditions ◽  
Superior Performance ◽  
Diagnostic Approach ◽  
Fault Identification ◽  
Support Vector ◽  
Distributed Power ◽  
Fault Type ◽  
Fault Diagnostic

After renewable energy distributed generator (DG) is connected to the power grid, traditional diverse-electric-information-based fault diagnosis approaches are not suitable for an active distributed network (ADN) due to the weak characteristics of fault current. Thus, this paper proposes a comprehensive nonformula fault diagnostic approach of ADN using only voltage as input. In the preprocess, sequential forward selection (SFS) and sequential backward selection (SBS) are utilized to optimize the input feature matrix of the sample in order to reduce the information redundancy of multiple measuring points in ADN. Then, a single “1-a-1” support vector machine (SVM) classifier is used for fault identification, and a multi-SVM, with radial basis function (RBF) as the kernel function, is applied to identify the location and fault type. To prove the proposed method is adaptable for ADN, two direct drive fans are used as a DG to test the IEEE 33 node model at every 10% of the line under three operating conditions that include all cases of distributed power generation in ADN. Results comparing real-time and historical data show that the proposed multi-SVM model reaches an average fault type diagnosis accuracy of 97.27%, with a fault identification accuracy of 96%. A backpropagation neural network is then compared to the proposed model. The results show the superior performance of the SBS-SFS optimized multi-SVM. This model can be usefully applied to the fault diagnosis of new energy sources with distributed power access to distribution networks.

scholarly journals RGB-D Object Recognition Using Multi-Modal Deep Neural Network and DS Evidence Theory

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 529 ◽  
Author(s):  
Hui Zeng ◽  
Bin Yang ◽  
Xiuqing Wang ◽  
Jiwei Liu ◽  
Dongmei Fu
Keyword(s):  
Neural Network ◽  
Object Recognition ◽  
Deep Neural Network ◽  
Low Cost ◽  
Evidence Theory ◽  
Feature Learning ◽  
Decision Fusion ◽  
Support Vector ◽  
Depth Sensors ◽  
Depth Images

With the development of low-cost RGB-D (Red Green Blue-Depth) sensors, RGB-D object recognition has attracted more and more researchers’ attention in recent years. The deep learning technique has become popular in the field of image analysis and has achieved competitive results. To make full use of the effective identification information in the RGB and depth images, we propose a multi-modal deep neural network and a DS (Dempster Shafer) evidence theory based RGB-D object recognition method. First, the RGB and depth images are preprocessed and two convolutional neural networks are trained, respectively. Next, we perform multi-modal feature learning using the proposed quadruplet samples based objective function to fine-tune the network parameters. Then, two probability classification results are obtained using two sigmoid SVMs (Support Vector Machines) with the learned RGB and depth features. Finally, the DS evidence theory based decision fusion method is used for integrating the two classification results. Compared with other RGB-D object recognition methods, our proposed method adopts two fusion strategies: Multi-modal feature learning and DS decision fusion. Both the discriminative information of each modality and the correlation information between the two modalities are exploited. Extensive experimental results have validated the effectiveness of the proposed method.

scholarly journals Wavelet packet energy–based damage identification of wood utility poles using support vector machine multi-classifier and evidence theory

2018 ◽  
Vol 18 (1) ◽  
pp. 123-142 ◽  
Author(s):  
Yang Yu ◽  
Ulrike Dackermann ◽  
Jianchun Li ◽  
Ernst Niederleithinger
Keyword(s):  
Support Vector Machine ◽  
Wavelet Packet ◽  
Evidence Theory ◽  
Sensor Data ◽  
Support Vector ◽  
Final Decision ◽  
Accurate Identification ◽  
Band Frequency ◽  
Utility Poles ◽  
Damage Condition

This article presents a novel assessment framework to identify the health condition of wood utility poles. The innovative approach is based on the integration of data mining and machine learning methods and combines advanced signal processing, multi-sensor data fusion and decision ensembles to classify different damage condition types of wood poles. In the proposed framework, wavelet packet analysis is employed to transform captured multi-channel stress wave signals into energy information, which is consequently compressed by principal component analysis to extract a feature vector. Furthermore, support vector machine multi-classifier, optimized by genetic algorithm, is designed to identify the pole condition type. Finally, evidence theory is applied to fuse different assessment results from different sensors for a final decision. For validation of the proposed approach, the wood pole specimens with three common damage condition types are tested using a novel multi-sensor narrow-band frequency-excitation non-destructive testing system in the laboratory. The final experimental analysis results confirm that the proposed approach is capable of making full use of multi-sensor information and providing an effective and accurate identification on types of conditions in wood poles.

Comparison of five automated urine sediment analyzers with manual microscopy for accurate identification of urine sediment

2019 ◽  
Vol 57 (11) ◽  
pp. 1744-1753 ◽  
Author(s):  
Jooyoung Cho ◽  
Kyeong Jin Oh ◽  
Beom Chan Jeon ◽  
Sang-Guk Lee ◽  
Jeong-Ho Kim
Keyword(s):  
Blood Cells ◽  
White Blood Cells ◽  
Turnaround Time ◽  
Accurate Identification ◽  
Urine Sediment ◽  
Detection Rates ◽  
Manual Processing ◽  
The Common ◽  
Distinct Features ◽  
Clinical Algorithms

Abstract Background While the introduction of automated urine analyzers is expected to reduce the labor involved, turnaround time and potential assay variations, microscopic examination remains the “gold standard” for the analysis of urine sediments. In this study, we evaluated the analytical and diagnostic performance of five recently introduced automated urine sediment analyzers. Methods A total of 1016 samples were examined using five automated urine sediment analyzers and manual microscopy. Concordance of results from each automated analyzer and manual microscopy were evaluated. In addition, image and microscopic review rates of each system were investigated. Results The proportional bias for red blood cells (RBCs), white blood cells (WBCs) and squamous epithelial cells in the automated urine sediment analyzers were within ±20% of values obtained using the manual microscope, except in the cases of RBCs and WBCs analyzed using URiSCAN PlusScope and Iris iQ200SPRINT, respectively. The sensitivities of Roche Cobas® u 701 and Siemens UAS800 for pathologic casts (73.6% and 81.1%, respectively) and crystals (62.2% and 49.5%, respectively) were high, along with high image review rates (24.6% and 25.2%, respectively). The detection rates for crystals, casts and review rates can be changed for the Sysmex UF-5000 platform according to cut-off thresholds. Conclusions Each automated urine sediment analyzer has certain distinct features, in addition to the common advantages of reducing the burden of manual processing. Therefore, laboratory physicians are encouraged to understand these features, and to utilize each system in appropriate ways, considering clinical algorithms and laboratory workflow.

scholarly journals Fault Diagnosis of Motor Bearings Based on a One-Dimensional Fusion Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (1) ◽  
pp. 122 ◽  
Author(s):  
Xianzhong Jian ◽  
Wenlong Li ◽  
Xuguang Guo ◽  
Ruzhi Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
Evidence Theory ◽  
Variable Load ◽  
One Dimensional ◽  
Fault Recognition ◽  
Vibration Time ◽  
Load Conditions ◽  
Motor Bearing

Deep learning has been an important topic in fault diagnosis of motor bearings, which can avoid the need for extensive domain expertise and cumbersome artificial feature extraction. However, existing neural networks have low fault recognition rates and low adaptability under variable load conditions. In order to solve these problems, we propose a one-dimensional fusion neural network (OFNN), which combines Adaptive one-dimensional Convolution Neural Networks with Wide Kernel (ACNN-W) and Dempster-Shafer (D-S) evidence theory. Firstly, the original vibration time-domain signals of a motor bearing acquired by two sensors are resampled. Then, four frameworks of ACNN-W optimized by RMSprop are utilized to learn features adaptively and pre-classify them with Softmax classifiers. Finally, the D-S evidence theory is used to comprehensively determine the class vector output by the Softmax classifiers to achieve fault detection of the bearing. The proposed method adapts to different load conditions by incorporating complementary or conflicting evidences from different sensors through experiments on the Case Western Reserve University (CWRU) motor bearing database. Experimental results show that the proposed method can effectively enhance the cross-domain adaptive ability of the model and has a better diagnostic accuracy than other existing experimental methods.

Performance Test Functions of Genetic Algorithm

2013 ◽  
Vol 278-280 ◽  
pp. 1334-1337
Author(s):  
Wen Xia Yun ◽  
Yong Jie Ma ◽  
Ying Chen
Keyword(s):  
Genetic Algorithm ◽  
Performance Test ◽  
Research Direction ◽  
Test Functions ◽  
Selection Algorithm ◽  
Test Function ◽  
The Common ◽  
Test Algorithm ◽  
Performance Of Algorithm ◽  
Important Research Direction

Due to the disadvantages of genetic algorithm such as the weaker ability for local search, premature convergence, random walk and problems related, and so on , the design and improvement of the algorithm is an important research direction of genetic algorithm. And evaluating the performance of algorithm systematically and scientifically is the key to test algorithm whether good or bad .The common method used to evaluate algorithm is test function, however, the existing literature on the optimization algorithm has different methods to evaluate the performance of algorithm, and there is no uniform test criteria. As for those questions above, This paper studies test functions of genetic algorithm, and analyses characteristics of the main test functions, which can be used as the basis of selection algorithm test functions.

Synchro Phasor Measurement Based Fault Analysis of a Parallel Transmission Line

2014 ◽  
Vol 984-985 ◽  
pp. 996-1004
Author(s):  
D. Miruthula ◽  
Ramachandran Rajeswari
Keyword(s):  
Transmission Line ◽  
Transmission System ◽  
Fault Analysis ◽  
Operating Conditions ◽  
Measurement Unit ◽  
Fault Identification ◽  
Parallel Transmission ◽  
Inference System ◽  
Fault Type ◽  
Phasor Measurement

This paper presents a new method to classify transmission line shunt faults and determine the fault location using phasor data of the transmission system. Most algorithms employed for analyzing fault data require that the fault type to be classified. The older fault-type classification algorithms are inefficient because they are not effective under certain operating conditions of the power system and may not be able to accurately select the faulted transmission line if the same fault recorder monitors multiple lines. An intelligent techniques described in this paper is used to precisely detect all ten types of shunt faults that may occur in an electric power transmission system (double-circuit transmission lines) with the help of data obtained from phasor measurement unit. This method is virtually independent of the mutual coupling effect caused by the adjacent parallel circuit and insensitive to the variation of source impedance. Thousands of fault simulations by MATLAB have proved the accuracy and effectiveness of the proposed algorithm. This paper includes the analysis of fault identification techniques using Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System based protection schemes. The performances of the techniques are examined for different faults on the parallel transmission line and compared with the conventional relay scheme. The results obtained shows that ANFIS based fault identification gives better performance than other techniques.

scholarly journals Protection of wind park connected series capacitor compensated three-phase transmission line using RBWT

2020 ◽  
Vol 12 (2) ◽  
pp. 18-28
Author(s):  
Gaurav Kapoor
Keyword(s):  
Wavelet Transform ◽  
Transmission Line ◽  
Current Data ◽  
Fault Type ◽  
Fault Recognition ◽  
Single Side ◽  
Three Phase ◽  
Wind Park ◽  
Phase Transmission ◽  
Series Capacitor

This paper proposes the RBWT (reverse biorthogonal-1.5 wavelet transform)-based fault recognition and faulty phase categorization technique for the protection of wind park connected series capacitor compensated three-phase transmission line (WPCSCCTPTL). The single side captured fault currents of the WPCSCCTPTL are used to evaluate the amplitudes of RBWT coefficients at fifth level. To authorize the performance of the proposed technique, a widespread collection of simulation studies have been done thus varying fault type, location, resistance, and switching time. In this work, the performance of the RBWT has been investigated for the evolving faults, the position of fault for the close-in relay faults is varied from 5 km up to 9 km, the position of fault for the far-end relay faults is varied from 195 km up to 199 km, faults at two different positions, the position of fault around the series capacitors are changed and for the variation in wind-turbine units. The benefit of RBWT is that it correctly detects all types of faults in WPCSCCTPTL by employing one-side fault current data only. It is also investigated that the proposed technique is robust to the variation in the fault factors of WPCSCCTPTL. Keywords: fault recognition, faulty phase categorization, three-phase transmission line protection, reverse biorthogonal-1.5 wavelet transform.

scholarly journals BREEDING STRATEGIES FOR DEVELOPING DRY BEAN CULTIVARS RESISTANT TO BRUCHID WEEVILS

HortScience ◽  
1990 ◽  
Vol 25 (9) ◽  
pp. 1123d-1123 ◽  
Author(s):  
Fredrick A. Bliss
Keyword(s):  
Common Bean ◽  
Breeding Strategies ◽  
Near Isogenic Lines ◽  
Bean Weevil ◽  
Accurate Identification ◽  
Dry Bean ◽  
The Common ◽  
Single Seeds ◽  
Genotypic Mixtures ◽  
Seed Yields

The presence of arcelin protein in the seeds of common bean, Phaseolus vulgaris L., provides resistance to the Mexican bean weevil and to a lesser degree, the common bean weevil. Fast, accurate identification of single seeds containing arcelin facilitates the transfer of alleles for each of four different arcelin types through standard crossing procedures. Seed yields and other traits of near-isogenic lines that contain different alleles were comparable to the standard parent, Porrillo 70. Genotypic mixtures containing resistant and susceptible seeds produced seed yields comparable to Porrillo 70, which suggests that heterogeneous populations offer the potential for stable resistant cultivars.

Sign in / Sign up

Export Citation Format

Share Document