Method and system for predicting residual service life of filter element of gas inlet filter of gas turbine
By preprocessing and feature extraction of the operating data and environmental data of the gas intake filter of the gas engine, inputting it into the trained filter element life prediction model for prediction, it solves the problem that the filter element replacement timing cannot be accurately grasped in the prior art, and realizes accurate prediction of the filter element service life and efficient utilization of resources.
Patent Information
- Application Number
- CN202411834985.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-03-21
AI Technical Summary
The prior art is difficult to accurately and timely reflect the deterioration status of the gas intake filter element of the gas engine, and it is impossible to accurately grasp the timing of the filter element replacement, resulting in the impact of the service life.
By obtaining the operating data and environmental data of the gas intake filter of the gas engine, performing data cleaning and feature extraction, inputting it into the trained filter element life prediction model for residual service life prediction, and determining the timing of filter element replacement.
It realizes accurate prediction of the remaining service life of the gas intake filter element of the gas engine, maximizes the working capacity of the filter, reduces maintenance costs, reduces resource waste, and provides a decision-making basis for predictive maintenance.
Smart Images
Figure CN119670035A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of fuel engine filter maintenance, and in particular to a method and system for predicting the remaining service life of a fuel engine air intake filter element. Background Art
[0002] The gas turbine air intake filter is an important device for gas turbine protection and a guarantee for the efficient operation of the gas turbine. Its filtering accuracy and efficiency are very important. At present, the filtering efficiency of the filter element can usually only be tested in the laboratory, and is not tested in the power plant. This often makes it difficult to accurately and timely reflect the deterioration state of the filter element in actual operation, and it is impossible to provide accurate data support for the maintenance of the filter element, and thus it is impossible to accurately grasp the timing of replacing the air intake filter element, which affects the service life of the filter element. Summary of the invention
[0003] The purpose of the present invention is to provide a method and system for predicting the remaining service life of a gas engine air intake filter element in order to solve at least one of the above technical problems.
[0004] In the first aspect, an embodiment of the present invention provides a method for predicting the remaining service life of a filter element of an air intake filter of a fuel engine, comprising: obtaining operating data of the fuel engine air intake filter and environmental data of a filter element to be predicted of the fuel engine air intake filter; performing data cleaning and feature extraction on the operating data and the environmental data to obtain preprocessed data; inputting the preprocessed data into a trained filter element life prediction model to perform remaining service life prediction to obtain the remaining service life of the filter element to be predicted.
[0005] Furthermore, the method further includes: determining a replacement timing of the filter element to be predicted based on the remaining service life.
[0006] Furthermore, the operating data includes: the inlet and outlet pressure difference, flow, temperature, humidity and engine load, operating time, and start and stop times of the engine air intake filter; the environmental data includes: air quality, air humidity, and air temperature.
[0007] Furthermore, the method also includes: training a preset learning model based on a preset training set to obtain the trained filter element life prediction model.
[0008] Furthermore, the preset learning model includes any one of the following: a linear regression model, a support vector regression model.
[0009] In the second aspect, an embodiment of the present invention also provides a system for predicting the remaining service life of a gas engine air intake filter element, comprising: an acquisition module, a preprocessing module and a prediction module; wherein the acquisition module is used to acquire the operating data of the gas engine air intake filter and the environmental data of the filter element to be predicted of the gas engine air intake filter; the preprocessing module is used to perform data cleaning and feature extraction on the operating data and the environmental data to obtain the preprocessed data; the prediction module is used to input the preprocessed data into a trained filter element life prediction model to perform remaining service life prediction to obtain the remaining service life of the filter element to be predicted.
[0010] Furthermore, it also includes: a determination module, which is used to determine the replacement time of the filter element to be predicted based on the remaining service life.
[0011] Furthermore, it also includes: a training module, which is used to train the preset learning model based on the preset training set to obtain the trained filter element life prediction model.
[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the embodiment of the present invention when executing the computer program.
[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.
[0014] The present invention provides a method and system for predicting the remaining service life of a gas turbine air intake filter element. Through long-term data collection and analysis, the atmospheric environment in which the filter is located and operating data are organically integrated to achieve accurate prediction of the remaining service life of the filter element. This can maximize the use of the filter's working capacity, reduce maintenance costs and unnecessary waste of resources, provide a decision-making basis for predictive maintenance, and alleviate the technical problem in the prior art that it is impossible to accurately grasp the timing of replacing the air intake filter element. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0016] Figure 1A flow chart of a method for predicting the remaining service life of a gas engine air intake filter element provided by an embodiment of the present invention;
[0017] Figure 2 A schematic diagram of a system for predicting the remaining useful life of a gas engine air intake filter element provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0019] Embodiment 1
[0020] Figure 1 1 is a flow chart of a method for predicting the remaining service life of a gas engine air intake filter element according to an embodiment of the present invention. Figure 1 As shown, the method specifically comprises the following steps:
[0021] Step S102, obtaining the operating data of the gas engine air intake filter and the environmental data of the filter element to be predicted of the gas engine air intake filter.
[0022] Preferably, the operation data includes: the inlet and outlet pressure difference, flow rate, temperature, humidity and engine load, operation time, and start and stop times of the engine air intake filter;
[0023] Environmental data includes: air quality (such as PM2.5 concentration), air humidity, and air temperature.
[0024] Step S104, performing data cleaning and feature extraction on the operation data and the environment data to obtain pre-processed data.
[0025] Preferably, data cleaning includes denoising and data interpolation, wherein denoising is to eliminate data noise, and data interpolation is to fill in missing values caused by sensor failure or data loss.
[0026] Optional. Data interpolation includes linear interpolation and spline interpolation.
[0027] In an optional implementation provided by an embodiment of the present invention, feature extraction includes: filter pressure difference change rate (trend feature), influence factor of environmental pollution index on pressure difference change, influence weight of system disclosure on filter element wear rate, etc.
[0028] Step S106, inputting the preprocessed data into the trained filter element life prediction model to perform remaining service life prediction, and obtaining the remaining service life of the filter element to be predicted.
[0029] Specifically, before step S106, the method provided by the embodiment of the present invention further includes: training a preset learning model based on a preset training set to obtain a trained filter element life prediction model.
[0030] Preferably, the preset learning model includes any one of the following: a linear regression model, a support vector regression model.
[0031] Specifically, the method provided in the embodiment of the present invention uses thermodynamic theory, signal processing and artificial intelligence algorithm to establish a filter element life prediction model, wherein the signal processing process includes spectrum analysis and wavelet analysis.
[0032] Specifically, spectrum analysis uses fast Fourier transform (FFT) to analyze the spectrum characteristics in the intake system pressure signal to determine the filter element blockage characteristics; wavelet analysis identifies the mutation points or long-term change trends in the pressure difference signal.
[0033] In an optional implementation provided by an embodiment of the present invention, after step S106, the following step is also included: based on the remaining service life, determining the replacement timing of the filter element to be predicted.
[0034] Specifically, first determine the key technical and economic limitations of replacing the filter element based on the equipment operating specifications and actual working conditions:
[0035] 1. Key technical restrictions:
[0036] Maximum allowable pressure differential: When the filter element pressure differential reaches or approaches the upper limit of the gas turbine's operating specifications, the filter element needs to be replaced.
[0037] Filtration efficiency: When the filtration efficiency of the filter element drops to the point where it can no longer effectively filter pollutants in the air, it should be replaced even if the pressure difference does not exceed the standard.
[0038] 2. Economic limitations:
[0039] Loss of operating efficiency: Increased pressure differential results in reduced gas turbine efficiency and increased fuel consumption.
[0040] Failure risk cost: Excessive pressure differential may cause intake system failure, resulting in higher repair costs.
[0041] Filter element replacement cost: includes material and labor costs.
[0042] Then, based on the remaining service life, determine when to replace the filter element to be tested:
[0043] 1. Safety margin setting:
[0044] To prevent prediction errors or operating fluctuations, set a safety margin:
[0045] A replacement decision is triggered when the remaining service life is less than or equal to the safety margin.
[0046] 2. Dynamically adjust the replacement plan:
[0047] Remaining service life is decreasing rapidly: If the filter element deteriorates rapidly (such as in a highly polluted environment), arrange for replacement in advance.
[0048] Low-load environment: If the operating conditions are good and the remaining service life is long, the replacement time can be appropriately postponed to save costs.
[0049] 3. Combined with real-time monitoring operation data, dynamically evaluate the status of the filter element:
[0050] By monitoring the filter element pressure difference over time, the time when it approaches the maximum allowable pressure difference can be predicted: if the time is less than the planned maintenance cycle, replacement needs to be arranged in advance.
[0051] Combined with external air quality (such as PM2.5 concentration) and humidity, adjust the remaining service life prediction value and optimize the replacement plan:
[0052] Highly polluted environment: The remaining life prediction curve may show nonlinear accelerated degradation and should be replaced in advance.
[0053] Good environment: Appropriately extend the service life of the filter element.
[0054] From the above description, it can be seen that the present invention provides a method for predicting the remaining service life of a gas turbine air intake filter element. Through long-term data collection and analysis, the atmospheric environment and operating data of the filter are organically integrated to achieve accurate prediction of the remaining service life of the filter element. This can maximize the use of the filter's working capacity, reduce maintenance costs and unnecessary waste of resources, provide a decision-making basis for predictive maintenance, and alleviate the technical problem of the prior art that it is impossible to accurately grasp the timing of replacing the air intake filter element.
[0055] Embodiment 2
[0056] Figure 2 Schematic diagram of a system for predicting the remaining service life of a gas engine air intake filter element according to an embodiment of the present invention. Figure 2 As shown, the system includes: an acquisition module 10, a preprocessing module 20 and a prediction module 30.
[0057] Specifically, the acquisition module 10 is used to acquire the operating data of the gas engine air intake filter and the environmental data of the filter element to be predicted of the gas engine air intake filter.
[0058] Preferably, the operating data include: the inlet and outlet pressure difference, flow, temperature, humidity of the gas turbine air intake filter and the gas turbine load, operating time, start and stop times; the environmental data include: air quality, air humidity, and air temperature.
[0059] The preprocessing module 20 is used to perform data cleaning and feature extraction on the operation data and the environment data to obtain preprocessed data.
[0060] The prediction module 30 is used to input the pre-processed data into the trained filter element life prediction model to perform remaining service life prediction and obtain the remaining service life of the filter element to be predicted.
[0061] Specifically, Figure 2 As shown, the system further includes: a determination module 40, for determining a replacement timing of the filter element to be predicted based on the remaining service life.
[0062] Specifically, Figure 2 As shown, the system also includes: a training module 50, which is used to train a preset learning model based on a preset training set to obtain a trained filter element life prediction model.
[0063] Preferably, the preset learning model includes any one of the following: a linear regression model, a support vector regression model.
[0064] The present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the embodiment of the present invention when executing the computer program.
[0065] The present invention also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.
[0066] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
[0067] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.
Claims
1. A method for predicting the remaining service life of a gas turbine air intake filter element, characterized in that: include: Acquiring operating data of a gas engine air intake filter and environmental data of a filter element to be predicted of the gas engine air intake filter; Performing data cleaning and feature extraction on the operation data and the environment data to obtain pre-processed data; The pre-processed data is input into a trained filter element life prediction model to perform remaining service life prediction, thereby obtaining the remaining service life of the filter element to be predicted.
2. The method according to claim 1, characterized in that: The method further includes: determining a replacement timing of the filter element to be predicted based on the remaining service life.
3. The method according to claim 1, characterized in that: The operation data includes: the inlet and outlet pressure difference, flow rate, temperature, humidity and engine load, operation time, and start and stop times of the engine air intake filter; The environmental data include: air quality, air humidity, and air temperature.
4. The method according to claim 1, characterized in that: The method further includes: training a preset learning model based on a preset training set to obtain the trained filter element life prediction model.
5. The method according to claim 4, characterized in that: The preset learning model includes any one of the following: a linear regression model, a support vector regression model.
6. A system for predicting the remaining service life of a gas turbine air intake filter element, characterized in that: include: Acquisition module, preprocessing module and prediction module; among them, The acquisition module is used to acquire the operating data of the gas engine air intake filter and the environmental data of the filter element to be predicted of the gas engine air intake filter; The preprocessing module is used to perform data cleaning and feature extraction on the operation data and the environment data to obtain preprocessed data; The prediction module is used to input the pre-processed data into a trained filter element life prediction model to perform remaining service life prediction, so as to obtain the remaining service life of the filter element to be predicted.
7. The system according to claim 6, characterized in that: Also includes: A determination module is used to determine the replacement timing of the filter element to be predicted based on the remaining service life.
8. The system according to claim 6, characterized in that: Also includes: The training module is used to train the preset learning model based on the preset training set to obtain the trained filter element life prediction model.
9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.