A novel approach for online fault detection in HVDC converters

International audienceThis paper presents a methodology to design the services of smart actuators for machine tools. The smart actuators aim at replacing the traditional drives (spindles and feed-drives) and enable to add data processing abilities to implement monitoring and control tasks. Their data processing abilities are also exploited in order to create a new decision level at the machine level. The aim of this decision level is to react to disturbances that the monitoring tasks detect. The cooperation between the computational objects (the smart spindle, the smart feed-drives and the CNC unit) enables to carry out functions for accommodating or adapting to the disturbances. This leads to the extension of the notion of smart actuator with the notion of agent. In order to implement the services of the smart drives, a general design is presented describing the services as well as the behavior of the smart drive according to the object oriented approach. Requirements about the CNC unit are detailed. Eventually, an implementation of the smart drive services that involves a virtual lathe and a virtual turning operation is described. This description is part of the design methodology. Experimental results obtained thanks to the virtual machine are then presented

show abstract

“…Nevertheless, works dealing with fault detection of such equipment exist like the ones presented in [36,37].…”

Section: To Monitor Drivementioning

confidence: 99%

Design methodology for smart actuator services for machine tool and machining control and monitoring

Desforges

Habbadi

Archimède

2011

Robotics and Computer-Integrated Manufacturing

View full text Add to dashboard Cite

show abstract

“…Such techniques are appropriate when the conventional approaches do not appear as an effective solution. Most of them describe methods using a pre-processing stage coupled with a Multi Layer Perceptron (MLP) neural network [16] - [19], but significant variations on this theme exist, including using adaptive linear neurons [20], radial basis function neural networks [21] and ANNs optimized by the particle swarm theory [22]. Still considering MLP neural networks, a scheme to detect and classify faults in a HVDC line, presented in [23], should be highlighted.…”

Section: Introductionmentioning

confidence: 99%

“…In this situation, the ANN should change its output offering information about the HVDC system. Mathematically, the pre-processing step is presented in (1) -(4), where k is the latest sample, M is the data window size, i.e.,20 samples in this case, Va is the RMS phase A voltage at bus 1, a V is the normalized RMS phase A voltage, Vd is the mean voltage value of the DC line, d V is the normalized mean voltage value of the DC line, Id is the mean value of current through the DC line, and d I is the normalized mean value of current through the DC line. The normalization process considerably improves the ANN performance and is based on a suitable choice of base values as will be discussed in Subsection 3.4.…”

mentioning

confidence: 99%

A novel and comprehensive single terminal ANN based decision support for relaying of VSC based HVDC links

Santos

Blond

Coury

et al. 2016

Electric Power Systems Research

View full text Add to dashboard Cite

HVDC technology is increasingly important for long distance bulk power transmission, but existing protection relaying techniques for such a system are subject to limitations. This paper presents a novel Artificial Neural Network (ANN) based on an algorithm for fault detection, location and classification in VSC-HVDC systems. Taking advantage of the ability of ANNs to identify and classify patterns, the proposed algorithm is able to detect and correctly classify a fault occurring at either the rectifier substation on the DC line or at the inverter substation. Therefore, such a scheme can be used as a decision support tool or as a backup protection. Only local signals are used at the rectifier substation and no communication link is necessary, thus improving the system's protection reliability and reducing the overall cost of the hardware implementation. A detailed VSC-HVDC system is described and used to simulate a number of fault scenarios in the system. Using the resulting fault waveforms, a comprehensive decision support scheme is developed and described, paying particular attention to the signal processing chain and design of the specific ANNs for each relaying task. Finally, a detailed analysis of the influence of key fault parameters on the limits of the algorithm's performance is carried out.

show abstract

“…Fault classification and location of HVDC transmission system is currently afford by the function of repeater stations [12]. Reliable operation of HVDC transmission system depends on fast detection and clearing the fault [7]. An Artificial Neural Network (ANN) has been used for fault detection in HVDC system.…”

Section: Introductionmentioning

confidence: 99%

“…An Artificial Neural Network (ANN) has been used for fault detection in HVDC system. Only four types of faults including, short circuit in DC transmission system, single line to ground (SLG), double line to ground (DLG) & three phase fault in AC system has been detected [7]. Artificial Neural Networks (ANNs) is a mathematical model inspired by biological neural networks [15].…”

Section: Introductionmentioning

confidence: 99%

A Review on Different ANN Based Fault Detection Techniques for HVDC Systems

Nagar¹,

Shah²

2016

IJIREM

View full text Add to dashboard Cite

Neural Network has been one among few best choices for the detection of faults in electrical systems. HVDC transmission system has no doubt first choice for the long transmission of electricity all over the world. This paper presents a use of different artificial neural network for the fault detection & classification in HVDC transmission system. Here an attempt is made to cite the scholarly work done and available on renounced journals with excellent review on their work. The work is valuable and may be light house for beginners in the same field.

show abstract

A novel approach for online fault detection in HVDC converters

Cited by 19 publications

References 4 publications

Design methodology for smart actuator services for machine tool and machining control and monitoring

Design methodology for smart actuator services for machine tool and machining control and monitoring

A novel and comprehensive single terminal ANN based decision support for relaying of VSC based HVDC links

A Review on Different ANN Based Fault Detection Techniques for HVDC Systems

Contact Info

Product

Resources

About