scholarly journals Multiresolution analysis of vibration signals acquired from locomotive Diesel engine for classification of engine states basing on signal statistical parameters

2017 ◽  
Vol 168 (1) ◽  
pp. 68-72
Author(s):  
Piotr BOGUŚ ◽  
Mateusz CIESZYŃSKI ◽  
Jerzy MERKISZ
Keyword(s):  
Diesel Engine ◽  
Complex Analysis ◽  
Statistical Parameters ◽  
Vibration Signals ◽  
Time Frequency ◽  
Significant Difference ◽  
Before And After ◽  
On Line ◽  
Locomotive Diesel

The paper presents a method of classification of locomotive Diesel engine states basing on vibration signals taken from an engine body and using chosen statistical parameters calculated for the original signal and it wavelet multiresolution components. The researches presented in the paper concern estimation of an engine states before and after a general repair. The target application of the presented researches is an on-line diagnostic system which can complement standard OBD systems. To this purpose the applied methods should not base on complex analysis of some spectral, time-frequency or scalogram plots but rather on choosing single diagnostic parameters which are suitable for the fast on-line diagnostic. The results have showed the significant difference in distinguishing of engine work before and after a general repair using some chosen statistical parameters applied to vibration signals.

Detection of Roller Bearing Conditions Using Mechatronics Approach

1999 ◽  
Author(s):  
T. I. Liu ◽  
F. Ordukhani
Keyword(s):  
Neural Networks ◽  
Roller Bearing ◽  
Diagnostic System ◽  
Feature Selection Technique ◽  
Vibration Signals ◽  
Selection Technique ◽  
On Line ◽  
Line Classification ◽  
Nonlinear Pattern

Abstract An on-line monitoring and diagnostic system is needed to detect faulty bearings. In this work, by applying the feature selection technique to the data obtained from vibration signals, six indices were selected. Artificial neural networks were used for nonlinear pattern recognition. An attempt was made to distinguish between normal and defective bearings. Counterpropagation neural networks with various network sizes were trained for these tasks. The counterpropagation neural networks were able to recognize a normal from a defective bearing with the success rate between 88.3% to 100%. The best results were obtained when all the six indices were used for the on-line classification of roller bearings.

Character Strengths Before and After September 11

2003 ◽  
Vol 14 (4) ◽  
pp. 381-384 ◽  
Author(s):  
Christopher Peterson ◽  
Martin E.P. Seligman
Keyword(s):  
Character Strengths ◽  
September 11 ◽  
Self Report ◽  
Terrorist Attacks ◽  
Action Classification ◽  
Before And After ◽  
On Line ◽  
September 11 Terrorist Attacks ◽  
Positive Traits

Did Americans change following the September 11 terrorist attacks? We provide a tentative answer with respect to the positive traits included in the Values in Action Classification of Strengths and measured with a self-report questionnaire available on-line and completed by 4,817 respondents. When scores for individuals completing the survey in the 2 months immediately after September 11 were compared with scores for those individuals who completed the survey before September 11, seven character strengths showed increases: gratitude, hope, kindness, leadership, love, spirituality, and teamwork. Ten months after September 11, these character strengths were still elevated, although to a somewhat lesser degree than immediately following the attacks.

scholarly journals PELATIHAN TAKSONOMI NUMERIK SEBAGAI STRATEGI UNTUK MENINGKATKAN TECHNOLOGICAL PEDAGOGICAL CONTENT KNOWLEDGE GURU BIOLOGI

2020 ◽  
Vol 7 (2) ◽  
pp. 64-78
Author(s):  
Amalianneisha Rafadewi Andhanatami Putri ◽  
Topik Hidayat ◽  
Widi Purwianingsih
Keyword(s):  
Learning Strategies ◽  
Numerical Taxonomy ◽  
Biology Teachers ◽  
Average Percentage ◽  
Technology And Learning ◽  
Living Things ◽  
Significant Difference ◽  
Before And After ◽  
Post Test

TPACK is the ability to integrate knowledges of content, pedagogical, and technology that must be possessed by teachers in facing the era of education in the 21st century. To improve TPACK can be done with training strategies, in this study numerical taxonomy training is a training program for biology teachers about TPACK and CoRes, and content which is related to concepts, technology, and learning strategies for classification of living things that discuss about numerical taxonomy, as a strategy to improve TPACK biology teachers in classifying living things learning. The method used was pre-experimental one group pre-post test design. The data about teachers’ TPACK was gained from CoReS and lesson plans prepared by teachers, and teachers’ prespective on TPACK was gained from responses toward questionnaires. The result showed after training,  analysis of CoRes reveals that 80% of Biology teachers’ is on the Growing TPACK, and 20% is on the Pre TPACK category. The average percentage of N-gain TPACK ability of teachers is 60% in the medium category, the result of significant test (t test) indicates t score t table (16.88 2.13), it showed a significant difference in the TPACK ability of biology teachers before and after numerical taxonomy training. Teachers’ prespective on TPACK in classification of living things learning have a positive changes, teachers starts to be able to determine the technology, strategy, and understanding the content of living things learning especially the numerical taxonomy. It can be concluded that numerical taxonomy training can improve TPACK’s ability.

Application of S transform and morphological pattern spectrum for gear fault diagnosis

2011 ◽  
Vol 225 (12) ◽  
pp. 2963-2972 ◽  
Author(s):  
B Li ◽  
P-L Zhang ◽  
Z-J Wang ◽  
S-S Mi ◽  
D-S Liu
Keyword(s):  
Fault Diagnosis ◽  
Wavelet Transforms ◽  
Morphological Pattern ◽  
Vibration Signals ◽  
Pattern Spectrum ◽  
Time Frequency ◽  
S Transform ◽  
Gear Fault ◽  
Gear Fault Diagnosis

Time–frequency representations (TFR) have been intensively employed for analysing vibration signals in gear fault diagnosis. However, in many applications, TFR are simply utilized as a visual aid to detect gear defects. An attractive issue is to utilize the TFR for automatic classification of faults. A key step for this study is to extract discriminative features from TFR as input feature vector for classifiers. This article contributes to this ongoing investigation by applying morphological pattern spectrum (MPS) to characterize the TFR for gear fault diagnosis. The S transform, which combines the separate strengths of the short-time Fourier transform and wavelet transforms, is chosen to perform the time–frequency analysis of vibration signals from gear. Then, the MPS scheme is applied to extract the discriminative features from the TFR. The promise of MPS is illustrated by performing our procedure on vibration signals measured from a gearbox with five operating states. Experiment results demonstrate the MPS to be a satisfactory scheme for characterizing TFRs for an accurate classification of gear faults.

scholarly journals Intelligent Fault Diagnosis of Diesel Engines via Extreme Gradient Boosting and High-Accuracy Time–Frequency Information of Vibration Signals

Sensors ◽  
2019 ◽  
Vol 19 (15) ◽  
pp. 3280 ◽  
Author(s):  
Jianfeng Tao ◽  
Chengjin Qin ◽  
Weixing Li ◽  
Chengliang Liu
Keyword(s):  
Fault Diagnosis ◽  
Diesel Engine ◽  
Time Domain ◽  
Classification Accuracy ◽  
High Accuracy ◽  
Gradient Boosting ◽  
Vibration Signals ◽  
Time Frequency ◽  
Frequency Information ◽  
Extreme Gradient Boosting

Accurate and timely misfire fault diagnosis is of vital significance for diesel engines. However, existing algorithms are prone to fall into model over-fitting and adopt low energy-concentrated features. This paper presents a novel extreme gradient boosting-based misfire fault diagnosis approach utilizing the high-accuracy time–frequency information of vibration signals. First, diesel engine misfire tests were conducted under different spindle speeds, and the corresponding vibration signals were acquired via a triaxial accelerometer. The time-domain features of signals were extracted by using a time-domain statistics method, while the high-accuracy time–frequency domain features were obtained via the high-resolution multisynchrosqueezing transform. Thereafter, considering the nonlinearity and high dimensionality of the original characteristic data sets, the locally linear embedding method was employed for feature dimensionality reduction. Eventually, to avoid model overfitting, the extreme gradient boosting algorithm was utilized for diesel engine misfire fault diagnosis. Experiments under different spindle speeds and comprehensive comparisons with other evaluation methods were conducted to demonstrate the effectiveness of the proposed extreme gradient boosting-based misfire diagnosis method. The results verify that the highest classification accuracy of the proposed extreme gradient boosting-based algorithm is up to 99.93%. Simultaneously, the classification accuracy of the presented approach is approximately 24.63% higher on average than those of algorithms that use wavelet packet-based features. Moreover, it is shown that it obtains the minimum root mean squared error and can effectively prevent the model from falling into overfitting.

Optimization of Diesel Engine: Synchronous Alternator Group

Joint Rail ◽  
2004 ◽  
Author(s):  
Gelu F. Giˆrda ◽  
Abdemusa Moosajee
Keyword(s):  
Diesel Engine ◽  
Electrical Power ◽  
Close Collaboration ◽  
Group Efficiency ◽  
Line Measurement ◽  
Three Phase ◽  
Power Group ◽  
Measurement Control ◽  
Before And After ◽  
On Line

The paper describes the findings of an experiment that is a result of close collaboration among four companies. The paper discusses the experiment on one locomotive by using a microprocessor-based relay, Multiple Function Relay (MFR) SEL-701, for on-line measurement, control and optimization of a HEP (Head End Power) group. The HEP has a Diesel engine, 810 HP/908 HP, 1800 rpm, and a double wound three-phase self excited synchronous alternator, 625 kVA, 575 V. The HEP group is installed on the locomotive and supplies the electrical hotel power to the train’s coaches. The relay SEL-701 (Schweitzer Engineering Laboratories) measures the Diesel engine temperatures on 7 different points and the winding temperatures at 3 internal points, one per each phase. The SEL-701 monitors alternator output currents and voltages and controls one (or both) train lines when the Diesel engine’s hottest temperature equals the maximum admissible temperature. Amongst others the paper highlights the benefits derived by use of on-line measurements of the Diesel engine before and after relocation of a pre-existent engine shutdown temperature probe. In addition, the paper discusses the decrease in the numbers of Diesel engine shut downs due to the modified mode of protection and the increase in available electrical power supplied to the train lines together with the comparison of the HEP group efficiency before and after modification.

scholarly journals Two-Dimensional Impact Reconstruction Method for Rail Defect Inspection

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Jie Zhao ◽  
Jianhui Lin ◽  
Jinbao Yao ◽  
Jianming Ding
Keyword(s):  
Vertical Vibration ◽  
Reconstruction Method ◽  
Two Dimensional ◽  
Analysis Method ◽  
Defect Inspection ◽  
Inspection Method ◽  
Vibration Signals ◽  
Time Frequency ◽  
On Line ◽  
The Impact

The safety of train operating is seriously menaced by the rail defects, so it is of great significance to inspect rail defects dynamically while the train is operating. This paper presents a two-dimensional impact reconstruction method to realize the on-line inspection of rail defects. The proposed method utilizes preprocessing technology to convert time domain vertical vibration signals acquired by wireless sensor network to space signals. The modern time-frequency analysis method is improved to reconstruct the obtained multisensor information. Then, the image fusion processing technology based on spectrum threshold processing and node color labeling is proposed to reduce the noise, and blank the periodic impact signal caused by rail joints and locomotive running gear. This method can convert the aperiodic impact signals caused by rail defects to partial periodic impact signals, and locate the rail defects. An application indicates that the two-dimensional impact reconstruction method could display the impact caused by rail defects obviously, and is an effective on-line rail defects inspection method.

Classification-Based Fuel Injection Fault Detection of a Trainset Diesel Engine Using Vibration Signature Analysis

2020 ◽  
Vol 142 (5) ◽  
Author(s):  
Moosa Ayati ◽  
Farzad A. Shirazi ◽  
Saeed Ansari-Rad ◽  
Alireza Zabihihesari
Keyword(s):  
Diesel Engine ◽  
Fault Detection ◽  
Diesel Engines ◽  
Nearest Neighbor ◽  
Fuel Injection ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Vibration Signals ◽  
Feature Extraction Method ◽  
Time Frequency

Abstract Diesel engines are crucial components of trainsets. Automated fault detection of diesel engines can play an important role for increasing reliability of passenger trains. In this research, vibration-based fuel injection fault detection of a high-power 12-cylinder trainset diesel engine is studied. Vibration signals are analyzed in frequency and time-frequency domains to obtain possible patterns of faults. Fast Fourier transform (FFT) and wavelet packet transform (WPT) of vibration signals are used to extract several uncorrelated features. These features are chosen to increase the ability of classifiers to separate healthy and faulty engine sides, automatically. Different classification methods including multilayer perception (MLP), support vector machines (SVM), K-nearest neighbor (KNN), and local linear model tree (LOLIMOT) are used to process captured features; these methods are utilized in both “Single-sensor condition monitoring” and “Classification and fault detection” sections. It is shown that KNN networks are practical tools in the proposed fault detection procedure. The main novelty of this work comes from introducing a rich feature-extraction method based on a combination of FFT and db4 features. In addition, the complexity of computations and average running-time decrease while classification accuracy in the fuel injection fault detection procedure increases.

Sign in / Sign up

Export Citation Format

Share Document