Short-Time Wavelet Entropy Integrating Improved LSTM for Fault Diagnosis of Modular Multilevel Converter
IEEE Transactions on Cybernetics
|January 5, 2021
Summary
This study introduces a new fault diagnosis method for modular multilevel converters (MMCs) in high-voltage direct current (HVDC) systems. The technique uses short-time wavelet entropy with LSTM and SVM for improved accuracy and efficiency in detecting faults.
Area of Science:
- Electrical Engineering
- Power Systems
- Control Systems
Background:
- Modular multilevel converters (MMCs) are crucial components in high-voltage direct current (HVDC) transmission systems.
- Faults in MMC bridge arm inductance and submodule IGBTs significantly degrade transmission quality.
- Existing fault diagnosis methods often require extensive data and struggle with adaptability.
Purpose of the Study:
- To develop a novel, robust, and accurate fault diagnosis method for MMC-HVDC systems.
- To enhance the efficiency of fault detection by reducing the number of required electrical signal samples.
- To enable the diagnosis of multiple fault types using a single signal.
Main Methods:
- A new fault diagnosis approach integrating short-time wavelet entropy, Long Short-Term Memory (LSTM) networks, and Support Vector Machines (SVM).
- Extraction of fault information using a proposed short-time wavelet entropy calculation method with an optimized calculation period.
- Processing of wavelet entropy fault information in the time dimension using an improved LSTM topology.
- Adaptive classification of faults using SVM, with LSTM output as input.
Main Results:
- Experimental validation on a double-ended MMC-HVDC transmission system confirmed the method's effectiveness.
- The proposed method demonstrated superior robustness, adaptability, and accuracy compared to traditional techniques.
- Significant reduction in the number of electrical signal samples needed for diagnosis was achieved.
- Successful diagnosis of multiple fault types from a single collected signal.
Conclusions:
- The developed fault diagnosis method offers a significant advancement for MMC-HVDC systems.
- The integration of short-time wavelet entropy, LSTM, and SVM provides a powerful tool for reliable and efficient fault detection.
- This approach paves the way for more resilient and cost-effective HVDC transmission infrastructure.
Related Concept Videos
01:21Energy Losses in Transformers
1.1K
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality, the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be the high resistance of the...
There are four main reasons for energy losses in transformers.
The first cause can be the high resistance of the...
1.1K
01:25Multimachine Stability
299
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
299
01:21Power System Three-Phase Short Circuits
396
Determining the subtransient fault current in a power system involves representing transformers by their leakage reactances, transmission lines by their equivalent series reactances, and synchronous machines as constant voltage sources behind their subtransient reactances. In this analysis, certain elements are excluded, such as winding resistances, series resistances, shunt admittances, delta-Y phase shifts, armature resistance, saturation, saliency, non-rotating impedance loads, and small...
396
01:21Three-Phase Short Circuit—Unloaded Synchronous Machine
512
Conducting a three-phase short circuit test on an unloaded synchronous machine helps understand its impact on the system. The AC fault current's oscillogram, with the DC offset removed, reveals that the waveform amplitude decreases from an initially high value to a steady-state level for one phase of the machine.
This behavior occurs due to the magnetic flux produced by the short-circuit armature currents. Initially, these currents follow high-reluctance paths but eventually shift to...
This behavior occurs due to the magnetic flux produced by the short-circuit armature currents. Initially, these currents follow high-reluctance paths but eventually shift to...
512
01:23Linear time-invariant Systems
691
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
691
01:20Power Factor Correction
360
The power transmission to a factory involves the transfer of apparent power, a combination of active and reactive power. The power factor measures how effectively electrical power is converted into useful work output. The ratio of the real power (KW) that does the work to the apparent power (KVA) supplied to the circuit.
360