State Classification of Reciprocating Compressor Valves using Event per Cycle Measurements

Kurt Pichler; Andrea Schrems; Matthias Huschenbett

State Classification of Reciprocating Compressor Valves using Event per Cycle Measurements

Kurt Pichler
, Andrea Schrems
, Matthias Huschenbett

Institute of Design and Control of Mechatronical Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

This paper presents a novel approach for diagnosing faults in reciprocating compressors using analysis of event information per cycle. Based on easily available system variables, selected event information of the valves is used to detect damaged valves. Then the discussed method tries to find an optimal combination of valve events to distinguish between normal and faulty operating conditions. Finally, the fault state of the valve is classified by applying pattern recognition techniques to the space of the valve events.

Original language	English
Title of host publication	Proceedings of the MFPT 2010
Number of pages	11
Publication status	Published - Jun 2010

Fields of science

203 Mechanical Engineering
202034 Control engineering
202012 Electrical measurement technology
206 Medical Engineering
202027 Mechatronics
202003 Automation
203027 Internal combustion engines
207109 Pollutant emission

JKU Focus areas

Mechatronics and Information Processing

Cite this

@inproceedings{c28c2ab793db4b4481092860eedce11f,

title = "State Classification of Reciprocating Compressor Valves using Event per Cycle Measurements",

abstract = "This paper presents a novel approach for diagnosing faults in reciprocating compressors using analysis of event information per cycle. Based on easily available system variables, selected event information of the valves is used to detect damaged valves. Then the discussed method tries to find an optimal combination of valve events to distinguish between normal and faulty operating conditions. Finally, the fault state of the valve is classified by applying pattern recognition techniques to the space of the valve events.",

author = "Kurt Pichler and Andrea Schrems and Matthias Huschenbett",

year = "2010",

month = jun,

language = "English",

booktitle = "Proceedings of the MFPT 2010",

}

TY - GEN

T1 - State Classification of Reciprocating Compressor Valves using Event per Cycle Measurements

AU - Pichler, Kurt

AU - Schrems, Andrea

AU - Huschenbett, Matthias

PY - 2010/6

Y1 - 2010/6

N2 - This paper presents a novel approach for diagnosing faults in reciprocating compressors using analysis of event information per cycle. Based on easily available system variables, selected event information of the valves is used to detect damaged valves. Then the discussed method tries to find an optimal combination of valve events to distinguish between normal and faulty operating conditions. Finally, the fault state of the valve is classified by applying pattern recognition techniques to the space of the valve events.

AB - This paper presents a novel approach for diagnosing faults in reciprocating compressors using analysis of event information per cycle. Based on easily available system variables, selected event information of the valves is used to detect damaged valves. Then the discussed method tries to find an optimal combination of valve events to distinguish between normal and faulty operating conditions. Finally, the fault state of the valve is classified by applying pattern recognition techniques to the space of the valve events.

M3 - Conference proceedings

BT - Proceedings of the MFPT 2010

ER -