A method and system for early warning of discharge voltage failure of an engine ignition electrode

Abstract

The application discloses an engine ignition electrode discharge voltage fault early warning method and system, comprising: obtaining sampling data of ignition electrode discharge, the sampling data comprising voltage signals and current signals; carrying out denoising processing on the sampling data according to a set filtering rule, the set filtering rule comprising: adopting a set transfer function to carry out low-pass filtering or band-pass filtering processing on the sampling data through a multiplication and accumulation operation mode; analyzing and processing the data after the denoising processing to obtain various spark performance parameters, the various spark performance parameters comprising spark energy, ignition voltage and ignition frequency; and carrying out fault early warning of the ignition electrode through a fault prediction model according to the various spark performance parameters. The voltage signals and the current signals of the ignition electrode discharge are analyzed and processed to obtain various spark performance parameters, and the fault early warning of the ignition electrode is carried out according to the various spark performance parameters, so that the test and fault early warning of various spark performances of the ignition electrode are solved.

Description

Technical Field

[0001] This invention belongs to the field of aero-engine fault detection technology, specifically relating to a method and system for early warning of engine ignition nozzle discharge voltage faults. Background Technology

[0002] In the field of engines, the ignition electrode is a crucial component of the engine ignition system, used to generate an electric spark. The performance of the ignition electrode directly affects the success of ignition. The discharge voltage of the ignition electrode is a vital parameter for evaluating its performance; it refers to the minimum input voltage required to break down the ignition electrode and generate a spark. Currently, the devices for detecting the discharge voltage of aero-engine ignition electrodes are simple voltage detectors and cannot perform tests on various spark performance characteristics or fault analysis. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for early warning of discharge voltage faults of engine ignition nozzles, which solves the problems of testing and fault warning of various spark performance of ignition nozzles.

[0004] This invention is achieved through the following technical solution:

[0005] A method for early warning of discharge voltage faults in engine ignition electrode terminals includes:

[0006] Acquire sampling data of the ignition nozzle discharge, including voltage and current signals;

[0007] The sampled data is denoised according to the set filtering rules, which include: using the set transfer function to perform low-pass or band-pass filtering on the sampled data through multiplication and accumulation operations;

[0008] The data after noise reduction is analyzed and processed to obtain various spark performance parameters, including spark energy, ignition voltage, and ignition frequency.

[0009] Each spark performance parameter is used to provide early warning of ignition nozzle faults through a fault prediction model.

[0010] In some embodiments, the transfer function used when performing low-pass filtering includes:

[0011] y(k)=ay(k-1)+bx(k)-bx(kN).

[0012] In some embodiments, the transfer function used when performing bandpass filtering includes:

[0013] y(k)=ay(k-1)+bx(k)+bx(kN).

[0014] In some embodiments, training the fault prediction model includes:

[0015] A large number of various spark performance parameters are input into the machine learning model;

[0016] The first loss function is constructed using the performance data of each spark output by the machine learning model and historical failure data.

[0017] The first loss function iteratively updates the parameters of the initial machine learning model until the preset conditions are met, thus obtaining the fault prediction model.

[0018] In some embodiments, the fault warning mechanism includes audio signals, visual signals, and control panel warnings.

[0019] This invention also relates to an engine ignition electrode discharge voltage fault early warning system, comprising:

[0020] The sampling data acquisition module is used to acquire sampling data of the ignition nozzle discharge. The sampling data includes voltage signals and current signals.

[0021] The data processing module is used to denoise the sampled data according to the set filtering rules;

[0022] The data transmission module is used to send the denoised sampled data to the computing control module via the bus;

[0023] The calculation and control module is used to analyze and process the denoised sampled data to obtain various spark performance parameters. The sampled data is denoised according to a set filtering rule, and the denoised data is analyzed and processed to obtain various spark performance parameters. The set filtering rule includes: using a set transfer function to perform low-pass filtering or band-pass filtering on the sampled data through multiplication and accumulation operations. The various spark performance parameters include spark energy, ignition voltage, and ignition frequency.

[0024] The fault warning module is used to provide fault warnings for the ignition nozzle based on the fault prediction model for various spark performance parameters.

[0025] In some embodiments, the sampling data acquisition module includes an opto-isolated probe.

[0026] In some embodiments, the sampling data acquisition module further includes a Rogowski current measurement coil.

[0027] In some embodiments, the data transmission module uses a multi-channel data acquisition card.

[0028] In some embodiments, the calculation control module is a PLC module.

[0029] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0030] 1. The voltage and current signals of the ignition nozzle discharge are acquired and analyzed to obtain various spark performance parameters. These spark performance parameters are then used to provide early warning of ignition nozzle faults through a fault prediction model, ensuring the performance of the ignition nozzle and improving its safety.

[0031] 2. Noise reduction is performed using predefined filtering rules to enhance the effective components of the signal, reduce errors caused by environmental factors, and improve the accuracy of fault warnings.

[0032] 3. Employ multiple early warning mechanisms to provide fault warnings and provide comprehensive fault warnings, thereby accelerating the speed at which staff can detect fault characteristics, reducing the failure rate of ignition nozzles, lowering maintenance costs, and improving safety.

[0033] 4. Using an opto-isolated probe to acquire voltage signals can greatly reduce coupling interference and improve the accuracy of voltage signals.

[0034] 5. Using a Rogowski current measuring coil to acquire current signals can avoid direct contact with the circuit under test, greatly reducing electromagnetic interference and improving the accuracy of the current signal. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart of the engine ignition nozzle discharge voltage fault early warning method in an embodiment of the present invention.

[0037] Figure 2 This is a schematic diagram of the engine ignition nozzle discharge voltage fault early warning system in an embodiment of the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0039] Example 1

[0040] Reference Figure 1 In some embodiments, a method for early warning of discharge voltage faults in engine ignition nozzles includes:

[0041] Acquire sampling data of the ignition nozzle discharge, including voltage and current signals;

[0042] The sampled data is denoised according to the set filtering rules, which include: using the set transfer function to perform low-pass or band-pass filtering on the sampled data through multiplication and accumulation operations;

[0043] The data after noise reduction is analyzed and processed to obtain various spark performance parameters, including spark energy, ignition voltage, and ignition frequency.

[0044] Each spark performance parameter is used to provide early warning of ignition nozzle faults through a fault prediction model.

[0045] Spark energy is an important indicator for measuring the ignition capability of an ignition nozzle. For example, if the spark energy produced by the ignition nozzle is less than 0.05, it indicates that the ignition capability of the nozzle is relatively weak.

[0046] Voltage requirements: a spark can only be generated when the voltage of the ignition nozzle reaches a preset threshold. For example, when the voltage of the ignition nozzle reaches 10kV to 18kV, the gas insulation layer between the electrodes breaks down, generating the electric arc required for ignition.

[0047] Ignition frequency is also an important performance parameter. For example, a spark frequency of 3.5Hz indicates that the ignition nozzle can generate sparks multiple times in a short period of time, which can improve ignition efficiency and reliability.

[0048] The voltage and current signals of the ignition nozzle discharge are acquired and analyzed to obtain various spark performance parameters. These spark performance parameters are then used to provide early warning of ignition nozzle faults through a fault prediction model, ensuring the performance and safety of the ignition nozzle.

[0049] In some embodiments, the transfer function used when performing low-pass filtering includes: y(k) =

[0050] ay(k-1)+bx(k)-bx(kN).

[0051] In some embodiments, the transfer function used when performing bandpass filtering includes: y(k) =

[0052] ay(k-1)+bx(k)+bx(kN).

[0053] The noise reduction process uses predefined filtering rules to enhance the effective components of the signal, reduce errors caused by environmental factors, and improve the accuracy of fault warning.

[0054] In some embodiments, the fault prediction model includes a machine learning model.

[0055] In some embodiments, training the fault prediction model includes:

[0056] A large number of various spark performance parameters are input into the machine learning model;

[0057] The first loss function is constructed using the performance data of each spark output by the machine learning model and historical failure data.

[0058] The first loss function iteratively updates the parameters of the initial machine learning model until the preset conditions are met, thus obtaining the fault prediction model.

[0059] In some embodiments, the fault warning mechanism includes audio signals, visual signals, and control panel warnings.

[0060] Audio signal refers to the sound warning prompt provided by the preset audio when the fault prediction model outputs that the ignition nozzle is faulty.

[0061] Visual signals refer to the visual warning provided by continuously flashing a preset red light when the fault prediction model outputs that the ignition nozzle is faulty.

[0062] Control panel warning refers to the system that displays fault information on the control panel to alert staff when the fault prediction model outputs a fault in the ignition nozzle.

[0063] Employing multiple early warning mechanisms provides comprehensive fault warnings, enabling staff to quickly identify fault characteristics. By analyzing these characteristics, timely adjustments and maintenance of the ignition system can be made, reducing the failure rate of ignition nozzles, lowering maintenance costs, and improving safety.

[0064] This invention also relates to an engine ignition electrode discharge voltage fault early warning system, referring to... Figure 2 ,include:

[0065] The sampling data acquisition module is used to acquire sampling data of the ignition nozzle discharge. The sampling data includes voltage signals and current signals.

[0066] The data processing module is used to denoise the sampled data according to the set filtering rules;

[0067] The data transmission module is used to send the denoised sampled data to the computing control module via the bus;

[0068] The calculation and control module is used to analyze and process the denoised sampled data to obtain various spark performance parameters. The sampled data is denoised according to a set filtering rule, and the denoised data is analyzed and processed to obtain various spark performance parameters. The set filtering rule includes: using a set transfer function to perform low-pass filtering or band-pass filtering on the sampled data through multiplication and accumulation operations. The various spark performance parameters include spark energy, ignition voltage, and ignition frequency.

[0069] The fault warning module is used to provide fault warnings for the ignition nozzle based on the fault prediction model for various spark performance parameters.

[0070] In some embodiments, the sampling data acquisition module includes an opto-isolated probe.

[0071] Using an opto-isolated probe to acquire voltage signals can greatly reduce coupling interference and improve the accuracy of voltage signals.

[0072] In some embodiments, the sampling data acquisition module further includes a Rogowski current measurement coil.

[0073] By using a Rogowski current measuring coil to acquire current signals, the circuit under test can be collected without direct contact, which greatly reduces electromagnetic interference and improves the accuracy of the current signal.

[0074] In some embodiments, the data transmission module uses a multi-channel data acquisition card.

[0075] In some embodiments, the calculation control module is a PLC module.

[0076] The working process of the engine ignition electrode discharge voltage fault warning system is as follows:

[0077] The engine ignition nozzle discharge voltage fault early warning system collects the voltage signal of the ignition nozzle discharge through an opto-isolated probe;

[0078] Meanwhile, the engine ignition nozzle discharge voltage fault warning system collects the current signal of the ignition nozzle discharge through the Rogowski current measurement coil;

[0079] The data processing module performs noise reduction processing on the acquired voltage and current signals according to the set filtering rules;

[0080] The multi-channel data acquisition card sends the denoised voltage and current signals to the PLC module via a bus;

[0081] The PLC module analyzes and processes the received voltage and current signals to obtain various spark performance parameters;

[0082] Each spark performance parameter is used to provide early warning of ignition nozzle faults through a fault prediction model.

[0083] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Any simple modifications or equivalent changes made to the above embodiments based on the technical essence of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for early warning of discharge voltage faults in engine ignition electrode terminals, characterized in that, include: Acquire sampling data of the discharge of the ignition nozzle, wherein the sampling data includes voltage signals and current signals; The sampled data is denoised according to a set filtering rule, which includes: using a set transfer function to perform low-pass or band-pass filtering on the sampled data through multiplication and accumulation; analyzing the denoised data to obtain various spark performance parameters, including spark energy, ignition voltage, and ignition frequency; and using a fault prediction model to provide fault warnings for the ignition nozzle based on these spark performance parameters. When performing low-pass filtering, the transfer function used includes: y(k) = ay(k-1) + bx(k) - bx(kN); when performing band-pass filtering, the transfer function used includes: y(k) = ay(k-1) + bx(k) + bx(kN).

2. The method for early warning of discharge voltage faults of engine ignition electrode according to claim 1, characterized in that, The training of the fault prediction model includes: inputting a large number of spark performance parameters into a machine learning model; constructing a first loss function from the spark performance data output by the machine learning model and historical fault data; iteratively updating the parameters of the initial machine learning model using the first loss function until a preset condition is met, thereby obtaining the fault prediction model.

3. The method for early warning of discharge voltage faults in engine ignition nozzles according to claim 1, characterized in that, The fault warning mechanism includes audio signals, visual signals, and control panel warnings.

4. A fault warning system for discharge voltage of an engine ignition electrode, characterized in that, include: The sampling data acquisition module is used to acquire sampling data of the ignition nozzle discharge, the sampling data including voltage signals and current signals; The data processing module is used to denoise the sampled data according to the set filtering rules; The data transmission module is used to send the denoised sampled data to the computing control module via the bus; The calculation and control module is used to analyze and process the denoised sampled data to obtain various spark performance parameters. The sampled data is denoised according to a set filtering rule, and the denoised data is analyzed and processed to obtain various spark performance parameters. The set filtering rule includes: using a set transfer function to perform low-pass filtering or band-pass filtering on the sampled data through multiplication and accumulation operations. The various spark performance parameters include spark energy, ignition voltage, and ignition frequency. The fault warning module is used to provide fault warnings for the ignition nozzle based on the fault prediction model for various spark performance parameters.

5. The engine ignition electrode discharge voltage fault early warning system according to claim 4, characterized in that: The sampling data acquisition module includes an opto-isolated probe.

6. The engine ignition nozzle discharge voltage fault early warning system according to claim 4, characterized in that: The sampling data acquisition module also includes a Rogowski current measurement coil.

7. The engine ignition electrode discharge voltage fault early warning system according to claim 4, characterized in that: The data transmission module uses a multi-channel data acquisition card.

8. The engine ignition nozzle discharge voltage fault early warning system according to claim 4, characterized in that: The calculation and control module adopts a PLC module.

Images