CN114235424B - Method for detecting faults of fuel filter of gas turbine - Google Patents
Method for detecting faults of fuel filter of gas turbine Download PDFInfo
- Publication number
- CN114235424B CN114235424B CN202111519924.9A CN202111519924A CN114235424B CN 114235424 B CN114235424 B CN 114235424B CN 202111519924 A CN202111519924 A CN 202111519924A CN 114235424 B CN114235424 B CN 114235424B
- Authority
- CN
- China
- Prior art keywords
- fuel filter
- gas turbine
- differential pressure
- fuel
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 230000005856 abnormality Effects 0.000 claims abstract description 4
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000003908 quality control method Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 2
- 239000002828 fuel tank Substances 0.000 claims description 2
- 230000009191 jumping Effects 0.000 claims description 2
- 239000007788 liquid Substances 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 description 6
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
Abstract
The invention aims to provide a method for detecting faults of a fuel filter of a gas turbine, which comprises the following steps of: selecting a fuel engine operation parameter, and establishing a normal operation fuel engine power, a rotating speed and a fuel filter differential pressure model by using historical data of the fuel engine, wherein the normal operation fuel engine power, the rotating speed and the fuel filter differential pressure model comprise an upper boundary, a lower boundary and a control center line; collecting power parameters in the actual operation process of the gas turbine to construct a to-be-detected sequence a, constructing a rotating speed parameter to construct a to-be-detected sequence b, and constructing a fuel filter differential pressure parameter to construct a to-be-detected sequence c; different SPC criterion combinations are selected to perform abnormality detection on the series a, b and the series c, and the fuel filter state is judged. The invention can update in real time and ensure the accuracy of the condition of the fuel filter.
Description
Technical Field
The invention relates to a gas turbine detection method, in particular to a gas turbine filter detection method.
Background
The gas turbine is used as an important power machine, and has the characteristics of compact structure, stable operation, higher thermal efficiency and the like, and the application range is wider. The gas turbine has high safe and reliable working requirements, and in order to avoid or timely process large faults, the health monitoring and abnormality detection of unit key indexes and key subsystems should be carried out.
The fuel system is a critical subsystem of the gas turbine, and its health has a significant impact on the efficiency of the unit. The most common form of failure of a fuel system is clogging of the fuel filter. In engineering applications, the clogging condition of the fuel filter is usually characterized by monitoring the pressure difference before and after the fuel filter, since the performance parameters of the fuel filter only provide initial parameters and cannot be updated in real time.
Disclosure of Invention
The invention aims to provide a method for detecting faults of a fuel filter of a gas turbine, which can be updated in real time.
The purpose of the invention is realized in the following way:
the invention relates to a method for detecting faults of a fuel filter of a gas turbine, which is characterized by comprising the following steps of:
(1) Calculating a fuel filter differential pressure model of the fuel system of the gas turbine under different working conditions according to the historical operation data of the unit;
(2) Constructing a fuel filter differential pressure array A, and calculating standard deviation D and mean value S under different working conditions;
(3) Taking multiples n.D and-n.D of the standard deviation D calculated in the step (2) to construct an upper boundary and a lower boundary of a differential pressure model of the fuel filter;
(4) Taking the average value S obtained by calculation in the step (2) as a control center line of the differential pressure model of the fuel filter;
(5) Collecting the power, the rotating speed and the differential pressure parameters of a fuel filter of the gas turbine in the actual operation process;
(6) According to the operation experience of the gas turbine and the differential pressure characteristic of the fuel filter, selecting one or more corresponding detection rules based on a quality control diagram theory, and carrying out abnormality detection on the power and the fuel tank liquid level;
(7) If the power and rotation speed detection result is stable and the fuel filter pressure difference detection result is abnormal, giving a corresponding alarm, and jumping to the step (9);
(8) Turning to the step (5) to carry out data acquisition and detection again;
(9) Giving an alarm and finishing detection.
The invention may further include:
1. The quality control map theory is based on the following SPC criteria list:
the invention has the advantages that: the invention can update in real time and ensure the accuracy of the condition of the fuel filter.
Drawings
FIG. 1 is a graph of fuel filter differential pressure change rate for various conditions during normal operation of a gas turbine;
FIG. 2 is a flow chart of fuel filter differential pressure status identification during operation of a gas turbine;
FIG. 3 is a flow chart of gas turbine fuel filter anomaly detection.
Detailed Description
The invention is described in more detail below, by way of example, with reference to the accompanying drawings:
With reference to fig. 1-3, the practice of the present invention includes the steps of:
establishing a pressure drop change rate model of the fuel filter under each working condition when the unit normally operates:
and selecting parameters which can represent the working condition and sum of the unit as abscissa, calculating the pressure drop change rate of the fuel filter under different working conditions by using the history data of the normal operation of the fuel engine, and establishing a normal pressure drop change rate curve comprising an upper boundary and a control center line.
1) The abscissa parameter can be the rotation speed (N') or the power (N) of the combustion engine;
2) The rate of change of pressure drop was calculated as
(ΔP02-ΔP01)/t
Wherein t is a calculation period; Δp 01、ΔP02 represents the fuel filter differential pressure values of the two calculation nodes, respectively. Considering the instability of the actual monitoring values, Δp 01、ΔP02 is selected from the arithmetic average or median of all the differential pressure monitoring values in the computing node neighborhood, which contains several monitoring values before or after the computing node.
3) The pressure drop change rate curve comprises an upper boundary and a control center line, and a trend curve which changes along with working conditions. The control center line is the average value (geometric average value, arithmetic average value or other weighted average value) of the pressure difference change rate curve of the fuel filter in each working condition and the like in the history normal operation, and the upper boundary is the control center line plus n times of standard deviation counted according to the history data. And the value of n is adjusted according to the actual data. This process may be performed off-line.
Detecting the real-time state of the power, the rotating speed and the differential pressure parameters of the fuel filter of the gas turbine:
(1) Collecting the power, the rotating speed and the differential pressure parameters of a fuel filter of the gas turbine in the actual operation process of the gas turbine;
(2) Preprocessing the collected unit operation data, and calculating corresponding power, rotating speed and fuel filter pressure difference;
(3) According to historical experience, selecting a data state detection rule in a quality control chart theory (SPC rule), and monitoring the real-time change state of the power, the rotating speed and the pressure difference of a fuel filter of the gas turbine of the unit.
Determining whether a gas turbine fuel filter is abnormal:
and (3) judging condition rules aiming at abnormal alarm of a fuel supply system of the gas turbine. And when the pressure difference of the fuel filter rises and the unit power and the rotation speed are stable or rise meets the detection rule, judging that the fuel supply system of the gas turbine is abnormal.
The SPC criteria list of the present invention is as follows:
Claims (2)
1. A method for detecting faults of a fuel filter of a gas turbine is characterized by comprising the following steps:
(1) Calculating a fuel filter differential pressure model of the fuel system of the gas turbine under different working conditions according to the historical operation data of the unit;
(2) Constructing a fuel filter differential pressure array A, and calculating standard deviation D and mean value S under different working conditions;
(3) Taking multiples n.D and-n.D of the standard deviation D calculated in the step (2) to construct an upper boundary and a lower boundary of a differential pressure model of the fuel filter;
(4) Taking the average value S obtained by calculation in the step (2) as a control center line of the differential pressure model of the fuel filter;
(5) Collecting the power, the rotating speed and the differential pressure parameters of a fuel filter of the gas turbine in the actual operation process;
(6) According to the operation experience of the gas turbine and the differential pressure characteristic of the fuel filter, selecting one or more corresponding detection rules based on a quality control diagram theory, and carrying out abnormality detection on the power and the fuel tank liquid level;
(7) If the power and rotation speed detection result is stable and the fuel filter pressure difference detection result is abnormal, giving a corresponding alarm, and jumping to the step (9);
(8) Turning to the step (5) to carry out data acquisition and detection again;
(9) Giving an alarm and finishing detection.
2. The method for detecting a failure of a fuel filter of a gas turbine according to claim 1, wherein: the quality control map theory is based on the following SPC criteria list:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111519924.9A CN114235424B (en) | 2021-12-13 | Method for detecting faults of fuel filter of gas turbine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111519924.9A CN114235424B (en) | 2021-12-13 | Method for detecting faults of fuel filter of gas turbine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114235424A CN114235424A (en) | 2022-03-25 |
| CN114235424B true CN114235424B (en) | 2024-06-28 |
Family
ID=
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114252216A (en) * | 2021-12-13 | 2022-03-29 | 中国船舶重工集团公司第七0三研究所 | Method for detecting leakage of lubricating oil of gas turbine |
| CN114252272A (en) * | 2021-12-13 | 2022-03-29 | 中国船舶重工集团公司第七0三研究所 | Method for detecting abnormal heat dissipation of gas turbine bearing |
| CN114252274A (en) * | 2021-12-13 | 2022-03-29 | 中国船舶重工集团公司第七0三研究所 | Online detection method for blockage of gas inlet filter of gas turbine |
| CN114323664A (en) * | 2021-12-13 | 2022-04-12 | 中国船舶重工集团公司第七0三研究所 | Method for detecting abnormal gas vibration of gas turbine |
| CN114323665A (en) * | 2021-12-13 | 2022-04-12 | 中国船舶重工集团公司第七0三研究所 | Method for detecting faults of fuel supply system of gas turbine |
| CN116735222A (en) * | 2023-05-17 | 2023-09-12 | 中国船舶集团有限公司第七〇三研究所 | Method for detecting fault of lubricating oil filter of gas turbine |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114252216A (en) * | 2021-12-13 | 2022-03-29 | 中国船舶重工集团公司第七0三研究所 | Method for detecting leakage of lubricating oil of gas turbine |
| CN114252272A (en) * | 2021-12-13 | 2022-03-29 | 中国船舶重工集团公司第七0三研究所 | Method for detecting abnormal heat dissipation of gas turbine bearing |
| CN114252274A (en) * | 2021-12-13 | 2022-03-29 | 中国船舶重工集团公司第七0三研究所 | Online detection method for blockage of gas inlet filter of gas turbine |
| CN114323664A (en) * | 2021-12-13 | 2022-04-12 | 中国船舶重工集团公司第七0三研究所 | Method for detecting abnormal gas vibration of gas turbine |
| CN114323665A (en) * | 2021-12-13 | 2022-04-12 | 中国船舶重工集团公司第七0三研究所 | Method for detecting faults of fuel supply system of gas turbine |
| CN116735222A (en) * | 2023-05-17 | 2023-09-12 | 中国船舶集团有限公司第七〇三研究所 | Method for detecting fault of lubricating oil filter of gas turbine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| US6587737B2 (en) | Method for the monitoring of a plant | |
| CN111522858B (en) | Multi-dimensional state vector-based pumping unit performance degradation early warning method | |
| CN111720296B (en) | Steam feed pump equipment abnormal state early warning method based on self-encoder | |
| CN110618610A (en) | Gas turbine NOx standard exceeding early warning method and device based on LSTM deep learning | |
| CN110469496B (en) | Intelligent early warning method and system for water pump | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN112124229A (en) | Remote real-time fault diagnosis method for emergency pump truck | |
| CN116735222A (en) | Method for detecting fault of lubricating oil filter of gas turbine | |
| CN114235424B (en) | Method for detecting faults of fuel filter of gas turbine | |
| CN109779938B (en) | Intelligent interlocking protection method for centrifugal compressor unit | |
| CN114252272A (en) | Method for detecting abnormal heat dissipation of gas turbine bearing | |
| CN111879522B (en) | Steam turbine operation monitoring and fault distinguishing method and system based on time sequence probability | |
| CN113446157B (en) | Fault early warning method and equipment for offshore wind generating set | |
| CN110821849B (en) | Cavitation monitoring method for fire pump | |
| CN112418306A (en) | Gas turbine compressor fault early warning method based on LSTM-SVM | |
| CN109840563B (en) | Fan fault diagnosis method based on three-dimensional membership function fuzzy logic system | |
| CN114252216B (en) | Detection method for lubricating oil leakage of gas turbine | |
| CN114235424A (en) | Method for detecting faults of fuel filter of gas turbine | |
| CN114662226B (en) | Rolling bearing residual service life prediction method based on time-varying Kalman filtering | |
| CN114323665B (en) | Method for detecting faults of fuel supply system of gas turbine | |
| CN114323664A (en) | Method for detecting abnormal gas vibration of gas turbine | |
| CN114239708A (en) | Combustion engine abnormity detection method based on quality control chart theory | |
| CN108983609B (en) | Load disturbance-based single-input single-output control loop PI controller optimization method | |
| CN114065990A (en) | Method for monitoring feed pump in thermal power plant, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |