scholarly journals Wind Turbine Multi-Fault Detection based on SCADA Data via an AutoEncoder

2021 ◽  
Vol 19 ◽  
pp. 487-492
Author(s):  
Á Encalada-Dávila ◽  
◽  
C. Tutivén ◽  
B. Puruncajas ◽  
Y. Vidal ◽  
...  
Keyword(s):  
Renewable Energy ◽  
Fault Detection ◽  
Wind Turbine ◽  
Sampling Rate ◽  
Prediction Errors ◽  
National Renewable Energy Laboratory ◽  
Different Types ◽  
Detection Strategies ◽  
Types Of Faults

Nowadays, wind turbine fault detection strategies are settled as a meaningful pipeline to achieve required levels of efficiency, availability, and reliability, considering there is an increasing installation of this kind of machinery, both in onshore and offshore configuration. In this work, it has been applied a strategy that makes use of SCADA data with an increased sampling rate. The employed wind turbine in this study is based on an advanced benchmark, established by the National Renewable Energy Laboratory (NREL) of USA. Different types of faults on several actuators and sensed by certain installed sensors have been studied. The proposed strategy is based on a normality model by means of an autoencoder. As of this, faulty data are used for testing from which prediction errors were computed to detect if those raise a fault alert according to a defined metric which establishes a threshold on which a wind turbine works securely. The obtained results determine that the proposed strategy is successful since the model detects the considered three types of faults. Finally, even when prediction errors are small, the model is able to detect the faults without problems.

scholarly journals Analysis on the Force and Life of Gearbox in Double-Rotor Wind Turbine

Energies ◽  
2019 ◽  
Vol 12 (21) ◽  
pp. 4220 ◽  
Author(s):  
Yaru Yang ◽  
Hua Li ◽  
Jin Yao ◽  
Wenxiang Gao ◽  
Haiyan Peng
Keyword(s):  
Renewable Energy ◽  
Life Span ◽  
Wind Turbine ◽  
Structural Parameters ◽  
Total Power ◽  
National Renewable Energy Laboratory ◽  
Ring Gear ◽  
Fixed Ring ◽  
Planet Gear ◽  
Planetary Transmission

In order to study the force and life of the key components in the gearbox of an existing double-rotor wind turbine, the design and structural parameters of the gearbox in the traditional National Renewable Energy Laboratory (NREL) 5 MW single-rotor wind turbine are adopted, and the fixed ring gear of the first planetary stage transmission is released to form a differential gearbox suitable for a double-rotor wind turbine with two inputs. The double input is used to connect the double rotor. Subsequently, the characteristics of the gearbox in a double-rotor wind turbine are discussed. On the basis of the constant rated power of the whole wind turbine, the total power is divided into two parts, which are allocated to the double rotors, then two rotational speeds of the two inputs are given according to different power ratios by complying with the matching principle of force and moment. Furthermore, the force acting on the pitch circle of the planet gear, as well as the force and life of the planet bearing of the two-stage planetary transmission are calculated and compared with a single-rotor wind turbine. The results show that the structural advantages of a double-rotor wind turbine can reduce the stress of key components of the gearbox and increase the life span of the planet bearing, thereby the life of the whole gearbox is improved and the downtime of the whole wind turbine is reduced.

scholarly journals Fault detection technique for test cases in software engineering

2018 ◽  
Vol 7 (1) ◽  
pp. 53
Author(s):  
Jagatjot Singh ◽  
Sumit Sharma
Keyword(s):  
Software Engineering ◽  
Fault Detection ◽  
Back Propagation ◽  
Test Case ◽  
Test Cases ◽  
Engineering Process ◽  
Different Types ◽  
Software Engineering Process ◽  
Propagation Technique ◽  
Types Of Faults

The processing of software and performing various operations on it is known as a software engineering process. The application of test cases for detecting the faults within the software is done through the testing process. There are various types of faults that occur within a software or test case which are to be identified and preventive approaches are to be applied to prevent them. In this paper, the Learn-to-rank algorithm is utilized which helps in detecting the faults from the software. The Back-Propagation technique is included with the LRA approach for enhancing its performance and improving the detection of fault rate. 10 test cases of different types are used for running various experiments and the MATLAB tool is utilized for performing various simulations. It is seen through the various simulation results that the fault detection rate is increased as well as the execution time is minimized with the help of this approach. 

Modal Current and Cumulative Sum Based Fault Detection Approach in Transmission Lines

2018 ◽  
Vol 19 (6) ◽  
Author(s):  
Mohammad Amin Jarrahi ◽  
Haidar Samet
Keyword(s):  
Fault Detection ◽  
Transmission Lines ◽  
Fault Analysis ◽  
Cumulative Sum ◽  
Efficiency Assessment ◽  
Fast Approach ◽  
Detection Approach ◽  
Three Phase ◽  
Different Types ◽  
Types Of Faults

AbstractIn this paper, a simple and fast approach is suggested for fault detection in transmission lines. The proposed technique utilizes a modified cumulative sum approach for a modal current to identify faults. The modal current is derived by proper linear mixing of three-phase currents. Since different types of faults may occur in transmission lines, all three-phase currents should be considered during fault analysis. By converting three-phase currents to a modal current, the processing time is reduced and less memory is needed. In this paper, a modal current is processed instead of three-phase currents. The modified cumulative sum approach presented in this paper is capable of decreasing computational burdens on the digital relay and accelerating the fault detection procedure. The proposed fault detection technique is evaluated in four different systems. Moreover, some real recorded field data were deliberated in the efficiency assessment of the proposed method. The results denote high accuracy and quickness of the proposed approach. Furthermore, the performance of the proposed methodology is compared with some other similar methods from different aspects.

scholarly journals Fault Detection and Diagnosis in Multi-Robot Systems: A Survey

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 4019 ◽  
Author(s):  
Eliahu Khalastchi ◽  
Meir Kalech
Keyword(s):  
Fault Detection ◽  
Fault Detection And Diagnosis ◽  
Research Opportunities ◽  
The World ◽  
Different Types ◽  
Robot Systems ◽  
Detection And Diagnosis ◽  
Types Of Faults ◽  
Multi Robot

The use of robots has increased significantly in the recent years; rapidly expending to numerous applications. These sophisticated machines are susceptible to different types of faults that might endanger the robot or its surroundings. These faults must be detected and diagnosed in time to allow continual operation. The field of Fault Detection and Diagnosis (FDD) has been studied for many years. This research has given birth to many approaches that are applicable to different types of physical machines. However, the domain of robotics poses unique requirements that challenge traditional FDD approaches. The study of FDD for robotics is relatively new; only few surveys were presented. These surveys have focused on the single robot scenario. To the best of our knowledge, there is no survey that focuses on FDD for Multi-Robot Systems (MRS). In this paper we set out to fill this gap. This paper provides detailed insights to the world of FDD for MRS. We first describe how different attributes of MRS pose different challenges for FDD. With respect to these challenges, we survey different FDD approaches applicable for MRS. We conclude with a description of research opportunities in this field. With these contributions it is the authors’ intention to provide detailed insights to the world of FDD for MRS.

scholarly journals Fault Model for UML Behavioral Activity and Sequence Diagrams

2019 ◽  
Vol 9 (1) ◽  
pp. 6926-6929
Keyword(s):  
Fault Detection ◽  
Software Testing ◽  
Fault Model ◽  
Behavioral Activity ◽  
Sequence Diagrams ◽  
Coverage Criteria ◽  
Testing Methodology ◽  
Different Types ◽  
Uml Diagrams ◽  
Types Of Faults

In software testing, the fault detection in any software construct is very important factor to check how efficiently testing process is carried out. While testing software, it is required to take some coverage criteria to check the testing methodology. The paper shows a way for fault detection for UML behavioral diagrams. Different types of faults which can occur in UML diagrams are discussed and a fault model is proposed for combinational diagram made by integrating UML behavioral diagram such as activity and sequence diagrams. The percentage of fault detected in software is calculated using fault model and to prove how efficient is the software testing process.

scholarly journals PLC AND HMI FOR CONVEYOR MONITORING AND FAULT DETECTION

2021 ◽  
Vol 9 (5) ◽  
pp. 34-38
Author(s):  
Mrunal Deshkar ◽  
◽  
Dipanjali Padhi ◽  
Keyword(s):  
Fault Detection ◽  
Fire Safety ◽  
Programmable Logic Controller ◽  
New Method ◽  
Programmable Logic ◽  
Different Types ◽  
Types Of Faults

The conveyor is usually used in industries to transport the commodity from one end to another, and can use it anywhere. As the occurrence of faults can affect the entire generation of power, the monitoring and security of these conveyors is important. Using relay logic methods, which have many drawbacks, the safety of the conveyors is carried out, and a new method is therefore required. This paper focuses on the monitoring, control, and safety of conveyors against different types of conveyor faults using a programmable logic controller (plc). This work considers four significant types of faults that commonly occur in conveyors, such as belt sway fault, pull chord fault, zero speed fault, and fire safety.

scholarly journals A New Acoustic Emission Sensor Based Gear Fault Detection Approach

2020 ◽  
Vol 4 (3) ◽  
Author(s):  
Yongzhi Qu ◽  
Eric Bechhoefer ◽  
David He ◽  
Junda Zhu
Keyword(s):  
Acoustic Emission ◽  
Fault Detection ◽  
Wind Turbine ◽  
Gear Tooth ◽  
Sampling Rate ◽  
Signal Frequency ◽  
Maintenance Cost ◽  
Detection Approach ◽  
Gear Fault ◽  
Ae Signal

In order to reduce wind energy costs, prognostics and health management (PHM) of wind turbine is needed to reduce operations and maintenance cost of wind turbines. The major cost on wind turbine repairs is due to gearbox failure. Therefore, developing effective gearbox fault detection tools is important in the PHM of wind turbine. PHM system allows less costly maintenance because it can inform operators of needed repairs before a fault causes collateral damage happens to the gearbox. In this paper, a new acoustic emission (AE) sensor based gear fault detection approach is presented. This approach combines a heterodyne based frequency reduction technique with time synchronous average (TSA) and spectral kurtosis (SK) toprocess AE sensor signals and extract features as condition indictors for gear fault detection. Heterodyne techniques commonly used in communication are used to preprocess the AE signals before sampling. By heterodyning, the AE signal frequency is down shifted from MHz to below 50 kHz. This reduced AE signal sampling rate is comparable to that of vibration signals. The presented approach is validated using seeded gear tooth crack fault tests on a notational split torque gearbox. The approach presented in this paper is physics based and the validation results have showed that it could effectively detect the gear faults.

Sign in / Sign up

Export Citation Format

Share Document