A method and system for detecting abnormal engine tail flame based on spectral comparison

Abstract

The present invention relates to a method and system for detecting engine tail flame anomalies based on spectral comparison, the method comprising: simulating an ideal combustion process of an engine based on a radiation model, generating an ideal tail flame spectrum for reference, and extracting a reference spectrum intensity of a target substance; collecting an actual tail flame spectrum of the tail flame of the engine to be tested, and obtaining the actual spectrum intensity of the target substance; obtaining a dynamic feature for judging whether the engine to be tested is faulty based on the reference spectrum intensity and the actual spectrum intensity; constructing a dynamic threshold range for judging whether the dynamic feature is abnormal; judging whether the dynamic feature is abnormal based on the dynamic threshold range, wherein if the dynamic feature exceeds the dynamic threshold range, the dynamic feature is abnormal, and if the dynamic feature is within the dynamic threshold range, the dynamic feature is not abnormal. The present invention realizes an organic combination between simulation and actual monitoring, and can flexibly realize high-precision and real-time fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of engine tail flame detection, and in particular to a method and system for detecting engine tail flame abnormality based on spectral comparison. Background Art

[0002] When liquid rocket engines work for a long time under high temperature and high pressure, it is easy to cause ablation and corrosion of materials, especially during the combustion process, key components such as the engine nozzle and pipeline may experience abnormal wear. This wear not only affects the service life of the engine, but may also lead to unstable combustion and thrust reduction, and even cause failures in severe cases. Therefore, it is of great significance to monitor the composition of combustion products in the tail flame of liquid rocket engines in real time, especially to detect abnormal changes in material composition.

[0003] Although traditional fault detection systems based on parameters such as temperature, pressure and speed are effective in detecting some macroscopic fault modes (such as abnormal temperature or overall performance degradation), they are less sensitive to microscopic fault modes such as local ablation and friction. In addition, these traditional methods usually have the problem of delayed response, making it difficult to capture early abnormal signals in time, which can easily lead to failures not being discovered in time, which may lead to more serious damage. In contrast, spectral analysis based on engine tail flames has significant advantages. By real-time monitoring of the spectral characteristics of specific elements (such as sodium and potassium) in the tail flame, small changes in the combustion process can be detected with high sensitivity, so that fault modes such as local ablation or friction can be detected early. In addition, since spectral detection directly reflects the changes in the composition of combustion products, the warning time is longer, and abnormal signals can be sent to operators earlier, effectively improving the timeliness and accuracy of fault detection.

[0004] However, there is still a lack of a more accurate and effective spectral detection solution. Therefore, a new detection solution is urgently needed to improve its detection effectiveness. Summary of the invention

[0005] The object of the present invention is to provide a method and system for detecting engine tail flame abnormality based on spectral comparison.

[0006] To achieve the above-mentioned object of the invention, the present invention provides a method for detecting abnormal engine tail flame based on spectral comparison, comprising the following steps:

[0007] S1. Simulating an ideal combustion process of an engine based on a radiation model, generating an ideal tail flame spectrum for reference, and extracting a reference spectrum intensity of a target substance based on the ideal tail flame spectrum;

[0008] S2. Collecting the actual tail flame spectrum of the tail flame of the engine to be tested, and obtaining the actual spectral intensity of the target substance based on the actual tail flame spectrum;

[0009] S3. Based on the reference spectral intensity and the actual spectral intensity, a dynamic characteristic for determining whether the engine under test is faulty is obtained;

[0010] S4. Constructing a dynamic threshold range for determining whether the dynamic feature is abnormal;

[0011] S5. Determine whether the dynamic feature is abnormal based on the dynamic threshold range, wherein if the dynamic feature exceeds the dynamic threshold range, then the dynamic feature is abnormal, that is, it is determined that the engine to be tested has a fault; if the dynamic feature is within the dynamic threshold range, then the dynamic feature is not abnormal, that is, it is determined that the engine to be tested has no fault.

[0012] According to one aspect of the present invention, in step S1, in the step of extracting the reference spectrum intensity of the target substance based on the ideal tail flame spectrum, the target substance is a plurality of component elements contained in the structure of the engine;

[0013] The reference spectrum intensity is extracted based on the following method:

[0014] A characteristic absorption wavelength in the atomic absorption spectrum of the target substance is obtained, and a corresponding spectrum peak is extracted from the ideal tail flame spectrum based on the characteristic absorption wavelength to serve as the reference spectrum intensity.

[0015] According to one aspect of the present invention, in step S2, in the step of obtaining the actual spectrum intensity of the target substance based on the actual tail flame spectrum, the actual spectrum intensity is extracted based on the following method:

[0016] A characteristic absorption wavelength in the atomic absorption spectrum of the target substance is obtained, and a corresponding spectrum peak is extracted from the actual tail flame spectrum based on the characteristic absorption wavelength to serve as the actual spectrum intensity.

[0017] According to one aspect of the present invention, the target substance uses two component elements.

[0018] According to one aspect of the present invention, in step S3, in the step of obtaining dynamic features for determining whether the engine to be tested is faulty based on the reference spectrum intensity and the actual spectrum intensity, the dynamic features include: a spectrum intensity difference and a spectrum intensity ratio difference of the target substance;

[0019] The spectral intensity difference is obtained based on the same component element and is expressed as:

[0020] ;

[0021] ;

[0022] in, represents the actual spectral intensity, represents the reference spectrum intensity, subscript and They are flag bits, used to indicate different component elements;

[0023] The spectral intensity ratio difference is obtained based on different component elements and is expressed as:

[0024] ;

[0025] in, Indicates the actual spectral intensity ratio between different components. Indicates the reference spectral intensity ratio between different components. and They are flag bits, used to indicate different component elements.

[0026] According to one aspect of the present invention, in step S4, the step of constructing a dynamic threshold range for determining whether the dynamic feature is abnormal includes:

[0027] S41. Based on a sliding window method, obtaining the actual spectral intensity at a preset time, and calculating the mean and standard deviation of the actual spectral intensity;

[0028] S42. Construct the dynamic threshold range based on the mean and the standard deviation.

[0029] According to one aspect of the present invention, in step S41, in the step of calculating the mean and standard deviation of the actual spectral intensity, the mean includes: the mean of the actual spectral intensity of each of the component elements within the preset time, and the mean of the actual spectral intensity ratio between different component elements within the preset time; wherein the mean of the actual spectral intensity of each of the component elements within the preset time is respectively expressed as:

[0030] ;

[0031] ;

[0032] The average value of the actual spectral intensity ratio within the preset time is expressed as:

[0033] ;

[0034] ;

[0035] in, represents the number of data points of the actual spectral intensity / actual spectral intensity ratio collected within a preset time, with the subscript The flag bit representing the actual spectral intensity / actual spectral intensity ratio, i.e. Actual spectral intensity / actual spectral intensity ratio, subscript and They are flag bits, used to indicate different component elements;

[0036] The standard deviation includes: the standard deviation of the actual spectral intensity of each of the component elements within the preset time, and the standard deviation of the actual spectral intensity ratio between different component elements within the preset time; wherein the standard deviation of the actual spectral intensity of each of the component elements within the preset time is respectively expressed as:

[0037] ;

[0038] ;

[0039] The standard deviation of the actual spectral intensity ratio within the preset time is expressed as:

[0040] ;

[0041] ;

[0042] in, represents the number of data points of the actual spectral intensity / actual spectral intensity ratio collected within a preset time, with the subscript The flag bit representing the actual spectral intensity / actual spectral intensity ratio, i.e. Actual spectral intensity / actual spectral intensity ratio, subscript and They are flag bits, used to indicate different component elements;

[0043] In step S42, in the step of constructing the dynamic threshold range based on the mean and the standard deviation, the dynamic threshold range includes: a first dynamic threshold range, a second dynamic threshold range and a third dynamic threshold range;

[0044] The first dynamic threshold range is expressed as:

[0045] ;

[0046] in, represents the lower limit of the first dynamic threshold range, represents the upper limit of the first dynamic threshold range, Indicates the component elements aThe average value of the actual spectral intensity at the preset time, Indicates the component elements a The standard deviation of the actual spectral intensity at the preset time;

[0047] The second dynamic threshold range is expressed as:

[0048] ;

[0049] in, represents the lower limit of the second dynamic threshold range, represents the upper limit of the second dynamic threshold range, Indicates the component elements b The average value of the actual spectral intensity at the preset time, Indicates the component elements b The standard deviation of the actual spectral intensity at the preset time;

[0050] The third dynamic threshold range is expressed as:

[0051] ;

[0052] in, represents the lower limit of the third dynamic threshold range, represents the upper limit of the third dynamic threshold range, It represents the average value of the spectral intensity ratio difference at the preset time. Indicates the standard deviation of the spectral intensity ratio difference at the preset time.

[0053] According to one aspect of the present invention, in step S5, in the step of judging whether the dynamic feature is abnormal based on the dynamic threshold range, the judging condition adopted is:

[0054] like , then determine the component elements a Abnormal concentration;

[0055] like , then determine the component elements b Abnormal concentration;

[0056] like , then it is judged that the overall combustion conditions are abnormal;

[0057] In step S5, if the dynamic feature exceeds the dynamic threshold range, then the dynamic feature is abnormal, that is, in the step of determining whether the engine to be tested has a fault, if the number of times the dynamic feature exceeds the dynamic threshold range exceeds a preset threshold, an alarm is triggered, and the alarm signal is at least one of sound, image, and text.

[0058] According to one aspect of the present invention, the two component elements of the target substance are sodium and potassium, respectively.

[0059] To achieve the above-mentioned object of the invention, the present invention provides a system for the above-mentioned engine tail flame abnormality detection method, comprising:

[0060] An ideal combustion spectrum data module simulates an ideal combustion process of an engine based on a radiation model, generates an ideal tail flame spectrum for reference, and extracts a reference spectrum intensity of a target substance based on the ideal tail flame spectrum;

[0061] An actual spectrum data acquisition module, used to acquire an actual tail flame spectrum of the tail flame of the engine to be tested, and to obtain an actual spectrum intensity of the target substance based on the actual tail flame spectrum;

[0062] A data processing module, which acquires dynamic features for determining whether the engine to be tested is faulty based on the reference spectrum intensity and the actual spectrum intensity;

[0063] The dynamic threshold adjustment and state discrimination module is used to construct a dynamic threshold range for judging whether the dynamic feature is abnormal, and to judge whether the dynamic feature is abnormal based on the dynamic threshold range, wherein if the dynamic feature exceeds the dynamic threshold range, the dynamic feature is abnormal, that is, it is judged that the engine to be tested has a fault; if the dynamic feature is within the dynamic threshold range, the dynamic feature is not abnormal, that is, it is judged that the engine to be tested has no fault.

[0064] According to one scheme of the present invention, the present invention obtains reference spectral intensity based on simulation, and monitors the actual spectral intensity of the engine to be tested in real time based on a spectrometer, thereby achieving an organic combination of simulation and actual monitoring, and can flexibly implement high-precision and real-time fault diagnosis, effectively ensuring the timely and reliable prediction of engine faults.

[0065] According to one scheme of the present invention, the present invention can perform quantitative analysis on the concentration of each metal element by extracting the characteristic spectral lines of the corresponding elements. This multi-element monitoring capability effectively enhances the overall control over the combustion state and wake composition, and provides strong support for engine combustion optimization and wake pollution monitoring.

[0066] According to one solution of the present invention, the present invention can accurately determine whether abnormal ablation or corrosion occurs in key components of the engine by analyzing the changes in characteristic spectral lines. Early detection and alarm are performed for possible material ablation and structural damage, thereby achieving early prevention of faults, extending the life of engine components, and reducing maintenance frequency and costs.

[0067] According to one solution of the present invention, the fault detection method based on spectral analysis of the present invention, combined with a dynamic threshold adjustment mechanism, can reflect the combustion state of the engine in real time and has higher fault diagnosis sensitivity and real-time performance.

[0068] According to one solution of the present invention, by real-time monitoring of the spectral characteristics of sodium and potassium elements in the engine tail flame, the sensitivity of fault detection is significantly improved, and microscopic fault modes such as local ablation and friction can be detected at an early stage, thus making up for the shortcomings of traditional temperature, pressure and speed detection systems.

[0069] According to one solution of the present invention, the present invention can dynamically adjust the range of the detection threshold based on the sliding window method, and can calculate the mean and standard deviation of the dynamic characteristics according to the actual spectral intensity collected in real time, so that the detection process can adapt to different working conditions and environmental changes, and improve the accuracy and real-time performance of the detection. At the same time, spectral analysis can directly reflect the changes in the composition of the combustion products, so the warning time is longer, and the operator can obtain abnormal signals in time and take preventive measures to avoid the expansion of potential faults.

[0070] According to one solution of the present invention, the present invention can realize the functions of automatic status identification and abnormality reporting, automatically generate a status report when an abnormality is detected and send an alarm message to a monitoring platform or an operator, thereby reducing manual intervention and improving the efficiency of fault detection and management.

[0071] According to a solution of the present invention, the present invention not only enhances the real-time performance and sensitivity of fault detection, but also significantly improves the reliability and applicability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 It is a flowchart schematically showing a method for detecting abnormal engine tail flame according to an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments cannot be described one by one here, but the embodiments of the present invention are not therefore limited to the following embodiments.

[0074] like Figure 1 As shown, according to one embodiment of the present invention, a method for detecting abnormal engine tail flame based on spectral comparison of the present invention comprises the following steps:

[0075] S1. Simulate the ideal combustion process of the engine based on the radiation model, generate an ideal tail flame spectrum for reference, and extract the reference spectrum intensity of the target substance based on the ideal tail flame spectrum;

[0076] S2. Collecting the actual tail flame spectrum of the tail flame of the engine to be tested, and obtaining the actual spectral intensity of the target substance based on the actual tail flame spectrum;

[0077] S3. Based on the reference spectral intensity and the actual spectral intensity, dynamic characteristics are obtained for determining whether the engine under test is faulty;

[0078] S4. Constructing a dynamic threshold range for determining whether a dynamic feature is abnormal;

[0079] S5. Determine whether the dynamic characteristic is abnormal based on the dynamic threshold range, wherein if the dynamic characteristic exceeds the dynamic threshold range, the dynamic characteristic is abnormal, that is, it is determined that the engine to be tested has a fault; if the dynamic characteristic is within the dynamic threshold range, the dynamic characteristic is not abnormal, that is, it is determined that the engine to be tested has no fault.

[0080] According to one embodiment of the present invention, in step S1, in the step of simulating the ideal combustion process of the engine based on the radiation model, ANSYS Fluent simulation software is used to simulate the radiation model to obtain the corresponding ideal combustion process, thereby generating the corresponding ideal tail flame spectrum.

[0081] Furthermore, in step S1, in the step of extracting the reference spectrum intensity of the target substance based on the ideal tail flame spectrum, the target substance is a plurality of component elements contained in the structure of the engine; thus, the reference spectrum intensity is extracted based on the following method.

[0082] The characteristic absorption wavelength in the atomic absorption spectrum of the target substance is obtained, and the corresponding spectrum peak is extracted from the ideal tail flame spectrum based on the characteristic absorption wavelength as the reference spectrum intensity.

[0083] According to an embodiment of the present invention, in step S2, in the step of collecting the actual tail flame spectrum of the tail flame of the engine to be tested, an Ocean Optics USB2000+ spectrometer is used to collect the actual tail flame spectrum, wherein the sampling rate used is 1 Hz.

[0084] Furthermore, in step S2, in the step of obtaining the actual spectrum intensity of the target substance based on the actual tail flame spectrum, the actual spectrum intensity is extracted based on the following method.

[0085] The characteristic absorption wavelength in the atomic absorption spectrum of the target substance is obtained, and the corresponding spectrum peak is extracted from the actual tail flame spectrum based on the characteristic absorption wavelength as the actual spectrum intensity.

[0086] According to one embodiment of the present invention, the target substance adopts two component elements, for example, the two component elements are sodium (Na) and potassium (K). Therefore, in the process of obtaining the reference spectral intensity, the reference spectral intensity of the sodium (Na) element is obtained according to the spectral peak at the characteristic absorption wavelength of 589nm in the atomic absorption spectrum of the sodium (Na) element, and correspondingly, the reference spectral intensity of the potassium (K) element is obtained according to the spectral peak at the characteristic absorption wavelength of 766nm in the atomic absorption spectrum of the potassium (K) element; similarly, in the process of obtaining the actual spectral intensity, the actual spectral intensity of the sodium (Na) element is obtained according to the spectral peak at the characteristic absorption wavelength of 589nm in the atomic absorption spectrum of the sodium (Na) element, and correspondingly, the actual spectral intensity of the potassium (K) element is obtained according to the spectral peak at the characteristic absorption wavelength of 766nm in the atomic absorption spectrum of the potassium (K) element.

[0087] According to an embodiment of the present invention, in step S3, in the step of obtaining dynamic features for determining whether the engine to be tested is faulty based on the reference spectral intensity and the actual spectral intensity, the dynamic features include: spectral intensity difference and spectral intensity ratio difference of the target substance;

[0088] The spectral intensity difference is obtained based on the same component element and is expressed as:

[0089] ;

[0090] ;

[0091] in, represents the actual spectral intensity, represents the reference spectrum intensity, subscript and They are flag bits, used to indicate different component elements;

[0092] Specifically, when the target substances are sodium (Na) and potassium (K), the spectral intensity difference can be further expressed as:

[0093] Sodium (Na) spectral intensity difference:

[0094] ;

[0095] in, Indicates the actual spectral intensity of the sodium (Na) element. Represents the reference spectrum intensity of the sodium (Na) element;

[0096] Potassium (K) spectral intensity difference:

[0097] ;

[0098] in, Indicates the actual spectral intensity of potassium (K) element. Represents the reference spectrum intensity of potassium (K) element;

[0099] Furthermore, the spectral intensity ratio difference is obtained based on different component elements, which is expressed as:

[0100] ;

[0101] in, Indicates the actual spectral intensity ratio between different components. Indicates the reference spectral intensity ratio between different components. and They are flag bits, used to indicate different component elements.

[0102] Specifically, when the target substances are sodium (Na) and potassium (K), the spectral intensity ratio difference can be further expressed as:

[0103] .

[0104] According to an embodiment of the present invention, in step S4, the step of constructing a dynamic threshold range for determining whether a dynamic feature is abnormal includes:

[0105] S41. Based on the sliding window method, the actual spectral intensity within the preset time is obtained, and the mean and standard deviation of the actual spectral intensity are calculated; in this embodiment, in the sliding window method, the window size (WindowSize) involved defines the data duration used for each calculation of statistics (such as mean, standard deviation, threshold, etc.); wherein, it is further necessary to set the step size (Step Size), which defines the time interval for each window movement. Thus, the speed at which the window slides forward can be determined based on the step size, and usually a smaller step size can achieve more frequent updates. In this embodiment, the window size and step size are both 30 minutes, that is, based on the 30-minute window size, data is collected every 30 minutes, the mean and standard deviation within the 30-minute time period are calculated, and the threshold range is updated based on these statistics. Correspondingly, the step size means that it is recalculated and updated every 30 minutes, and the time interval for window sliding is 30 minutes. Therefore, in this embodiment, the selected preset time is the window size of 30 minutes.

[0106] Furthermore, the mean value includes: the mean value of the actual spectral intensity of various component elements within a preset time, and the mean value of the actual spectral intensity ratio between different component elements within a preset time; wherein the mean value of the actual spectral intensity of various component elements within a preset time is respectively expressed as:

[0107] ;

[0108] ;

[0109] Furthermore, the average value of the actual spectral intensity ratio within the preset time is expressed as:

[0110] ;

[0111] ;

[0112] in, Indicates the number of data points of the actual spectral intensity / actual spectral intensity ratio collected within the preset time. The flag bit indicating the ratio of actual spectral intensity to actual spectral intensity, i.e. Actual spectral intensity / actual spectral intensity ratio, subscript and They are flag bits, used to indicate different component elements;

[0113] Specifically, when the target substances are sodium (Na) and potassium (K), the mean value can be further expressed as:

[0114] ;

[0115] ;

[0116] ;

[0117] .

[0118] Furthermore, the standard deviation includes: the standard deviation of the actual spectral intensity of various component elements at a preset time, and the standard deviation of the actual spectral intensity ratio between different component elements at a preset time; wherein the standard deviation of the actual spectral intensity of various component elements at a preset time is respectively expressed as:

[0119] ;

[0120] ;

[0121] Furthermore, the standard deviation of the actual spectral intensity ratio at the preset time is expressed as:

[0122] ;

[0123] ;

[0124] in, Indicates the number of data points of the actual spectral intensity / actual spectral intensity ratio collected within the preset time. The flag bit indicating the ratio of actual spectral intensity to actual spectral intensity, i.e. Actual spectral intensity / actual spectral intensity ratio, subscript and They are flag bits, used to indicate different component elements;

[0125] Specifically, when the target substances are sodium (Na) and potassium (K), the standard deviation can be further expressed as:

[0126] ;

[0127] ;

[0128] ;

[0129] .

[0130] In this embodiment, the preset time can be set to 30 minutes. Of course, the setting value can be adaptively modified based on actual needs to achieve flexible setting of the sliding window, which will not be repeated here.

[0131] S42. A dynamic threshold range is constructed based on the mean and the standard deviation; in this embodiment, the dynamic threshold range includes: a first dynamic threshold range, a second dynamic threshold range and a third dynamic threshold range; wherein the first dynamic threshold range is represented as:

[0132] ;

[0133] in, represents the lower limit of the first dynamic threshold range, represents the upper limit of the first dynamic threshold range, Indicates the component elements a The average value of the actual spectral intensity at the preset time, Indicates the component elements a The standard deviation of the actual spectral intensity at the preset time;

[0134] In this embodiment, the first dynamic threshold range is used to determine whether the sodium (Na) spectral intensity difference is abnormal. Therefore, the first dynamic threshold range can be further expressed for the sodium (Na) element as:

[0135] .

[0136] Further, the second dynamic threshold range is expressed as:

[0137] ;

[0138] in, represents the lower limit of the second dynamic threshold range, represents the upper limit of the second dynamic threshold range, Indicates the component elements b The average value of the actual spectral intensity at the preset time, Indicates the component elements b The standard deviation of the actual spectral intensity at the preset time;

[0139] In this embodiment, the second dynamic threshold range is used to determine whether the potassium (K) spectral intensity difference is abnormal. Therefore, the second dynamic threshold range can be further expressed for the potassium (K) element as:

[0140] .

[0141] Further, the third dynamic threshold range is expressed as:

[0142] ;

[0143] in, represents the lower limit of the third dynamic threshold range, represents the upper limit of the third dynamic threshold range, It represents the average value of the spectral intensity ratio difference at the preset time. Indicates the standard deviation of the spectral intensity ratio difference at the preset time.

[0144] According to an embodiment of the present invention, in step S5, in the step of determining whether the dynamic feature is abnormal based on the dynamic threshold range, the determination condition adopted is:

[0145] like , then determine the component elements a Abnormal concentration, for the sodium (Na) element, the corresponding judgment condition can be expressed as: ;

[0146] like , then determine the component elements b Abnormal concentration, for potassium (K), the corresponding judgment condition can be expressed as: ;

[0147] like , then it is judged that the overall combustion conditions are abnormal;

[0148] Further, in step S5, if the dynamic feature exceeds the dynamic threshold range, then the dynamic feature is abnormal, that is, in the step of determining whether the engine under test has a fault, if the number of times the dynamic feature exceeds the dynamic threshold range exceeds a preset threshold, an alarm is triggered, and the alarm signal is at least one of sound, image, and text;

[0149] In this embodiment, based on the determined results, the dynamic characteristics of each abnormality and the corresponding dynamic threshold range can be further saved, so that they can be sent to relevant operators or monitoring platforms in the form of abnormal situation reports.

[0150] According to one embodiment of the present invention, the present invention provides a system for the above-mentioned engine tail flame abnormality detection method, comprising:

[0151] The ideal combustion spectrum data module simulates the ideal combustion process of the engine based on the radiation model, generates an ideal tail flame spectrum for reference, and extracts the reference spectrum intensity of the target substance based on the ideal tail flame spectrum;

[0152] An actual spectrum data acquisition module is used to acquire the actual tail flame spectrum of the tail flame of the engine to be tested, and obtain the actual spectrum intensity of the target substance based on the actual tail flame spectrum;

[0153] A data processing module, which obtains dynamic features for judging whether the engine to be tested is faulty based on the reference spectrum intensity and the actual spectrum intensity;

[0154] The dynamic threshold adjustment and state discrimination module is used to construct a dynamic threshold range for judging whether the dynamic characteristics are abnormal, and to judge whether the dynamic characteristics are abnormal based on the dynamic threshold range. If the dynamic characteristics exceed the dynamic threshold range, the dynamic characteristics are abnormal, that is, it is judged that the engine to be tested has a fault. If the dynamic characteristics are within the dynamic threshold range, the dynamic characteristics are not abnormal, that is, it is judged that the engine to be tested does not have a fault.

[0155] In this embodiment, the system may also include: an alarm module, wherein if the number of times the dynamic characteristics exceed the dynamic threshold range exceeds a preset threshold, the alarm module triggers an alarm, and the generated alarm signal is at least one of sound, image, and text; further, the alarm module can also save the dynamic characteristics of each abnormality and the corresponding dynamic threshold range, so that it can be sent to the relevant operator or monitoring platform in the form of an abnormal situation report.

[0156] The above contents are merely examples of specific solutions of the present invention. For devices and structures not described in detail therein, it should be understood that they can be implemented by adopting general devices and general methods available in the art.

[0157] The above is only one solution of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting abnormal engine tail flame based on spectral comparison, characterized in that: The following steps are involved: S1. Simulating an ideal combustion process of an engine based on a radiation model, generating an ideal tail flame spectrum for reference, and extracting a reference spectrum intensity of a target substance based on the ideal tail flame spectrum; S2. Collecting the actual tail flame spectrum of the tail flame of the engine to be tested, and obtaining the actual spectral intensity of the target substance based on the actual tail flame spectrum; S3. Based on the reference spectral intensity and the actual spectral intensity, a dynamic characteristic for determining whether the engine under test is faulty is obtained; S4. Constructing a dynamic threshold range for determining whether the dynamic feature is abnormal; S5. Determine whether the dynamic feature is abnormal based on the dynamic threshold range, wherein if the dynamic feature exceeds the dynamic threshold range, then the dynamic feature is abnormal, that is, it is determined that the engine to be tested has a fault; if the dynamic feature is within the dynamic threshold range, then the dynamic feature is not abnormal, that is, it is determined that the engine to be tested has no fault.

2. The engine tail flame abnormality detection method based on spectral comparison according to claim 1 is characterized in that: In step S1, in the step of extracting the reference spectrum intensity of the target substance based on the ideal tail flame spectrum, the target substance is a plurality of component elements contained in the structure of the engine; The reference spectrum intensity is extracted based on the following method: A characteristic absorption wavelength in the atomic absorption spectrum of the target substance is obtained, and a corresponding spectrum peak is extracted from the ideal tail flame spectrum based on the characteristic absorption wavelength to serve as the reference spectrum intensity.

3. The engine tail flame abnormality detection method based on spectral comparison according to claim 2 is characterized in that: In step S2, in the step of obtaining the actual spectrum intensity of the target substance based on the actual tail flame spectrum, the actual spectrum intensity is extracted based on the following method: A characteristic absorption wavelength in the atomic absorption spectrum of the target substance is obtained, and a corresponding spectrum peak is extracted from the actual tail flame spectrum based on the characteristic absorption wavelength to serve as the actual spectrum intensity.

4. The engine tail flame abnormality detection method based on spectral comparison according to claim 3 is characterized in that: The target substance uses two component elements.

5. The engine tail flame abnormality detection method based on spectral comparison according to claim 4 is characterized in that: In step S3, in the step of acquiring dynamic features for judging whether the engine to be tested is faulty based on the reference spectrum intensity and the actual spectrum intensity, the dynamic features include: a spectrum intensity difference and a spectrum intensity ratio difference of the target substance; The spectral intensity difference is obtained based on the same component element and is expressed as: in, represents the actual spectral intensity, represents the reference spectrum intensity, subscript and They are flag bits, used to indicate different component elements; The spectral intensity ratio difference is obtained based on different component elements and is expressed as: in, Indicates the actual spectral intensity ratio between different components. Indicates the reference spectral intensity ratio between different components. and They are flag bits, used to indicate different component elements.

6. The engine tail flame abnormality detection method based on spectral comparison according to claim 5 is characterized in that: In step S4, the step of constructing a dynamic threshold range for determining whether the dynamic feature is abnormal includes: S41. Based on the sliding window method, obtain the actual spectral intensity within a preset time, and calculate the mean and standard deviation of the actual spectral intensity; S42. Construct the dynamic threshold range based on the mean and the standard deviation.

7. The engine tail flame abnormality detection method based on spectral comparison according to claim 6 is characterized in that: In step S41, in the step of calculating the mean and standard deviation of the actual spectral intensity, the mean includes: the mean of the actual spectral intensity of each of the component elements within the preset time, and the mean of the actual spectral intensity ratio between different component elements within the preset time; wherein the mean of the actual spectral intensity of each of the component elements within the preset time is respectively expressed as: ； The average value of the actual spectral intensity ratio within the preset time is expressed as: in, represents the number of data points of the actual spectral intensity / actual spectral intensity ratio collected within a preset time, with the subscript The flag bit representing the actual spectral intensity / actual spectral intensity ratio, i.e. Actual spectral intensity / actual spectral intensity ratio, subscript and They are flag bits, used to indicate different component elements; The standard deviation includes: the standard deviation of the actual spectral intensity of each of the component elements within the preset time, and the standard deviation of the actual spectral intensity ratio between different component elements within the preset time; wherein the standard deviation of the actual spectral intensity of each of the component elements within the preset time is respectively expressed as: ； The standard deviation of the actual spectral intensity ratio within the preset time is expressed as: in, represents the number of data points of the actual spectral intensity / actual spectral intensity ratio collected within a preset time, with the subscript The flag bit representing the actual spectral intensity / actual spectral intensity ratio, i.e. Actual spectral intensity / actual spectral intensity ratio, subscript and They are flag bits, used to indicate different component elements; In step S42, in the step of constructing the dynamic threshold range based on the mean and the standard deviation, the dynamic threshold range includes: a first dynamic threshold range, a second dynamic threshold range and a third dynamic threshold range; The first dynamic threshold range is expressed as: in, represents the lower limit of the first dynamic threshold range, represents the upper limit of the first dynamic threshold range, Indicates the component elements a The average value of the actual spectral intensity at the preset time, Indicates the component elements a The standard deviation of the actual spectral intensity at the preset time; The second dynamic threshold range is expressed as: in, represents the lower limit of the second dynamic threshold range, represents the upper limit of the second dynamic threshold range, Indicates the component elements b The average value of the actual spectral intensity at the preset time, Indicates the component elements b The standard deviation of the actual spectral intensity at the preset time; The third dynamic threshold range is expressed as: in, represents the lower limit of the third dynamic threshold range, represents the upper limit of the third dynamic threshold range, It represents the average value of the spectral intensity ratio difference at the preset time. Indicates the standard deviation of the spectral intensity ratio difference at the preset time.

8. The method for detecting abnormal engine tail flame based on spectral comparison according to claim 7, characterized in that: In step S5, in the step of judging whether the dynamic feature is abnormal based on the dynamic threshold range, the judgment condition adopted is: like , then determine the component elements a Abnormal concentration; like , then determine the component elements b Abnormal concentration; like , then it is judged that the overall combustion conditions are abnormal; In step S5, if the dynamic feature exceeds the dynamic threshold range, then the dynamic feature is abnormal, that is, in the step of determining whether the engine to be tested has a fault, if the number of times the dynamic feature exceeds the dynamic threshold range exceeds a preset threshold, an alarm is triggered, and the alarm signal is at least one of sound, image, and text.

9. The engine tail flame abnormality detection method based on spectral comparison according to claim 8 is characterized in that: The two component elements of the target substance are sodium and potassium.

10. A system for the engine tail flame abnormality detection method based on spectral comparison according to any one of claims 1 to 9, characterized in that: include: An ideal combustion spectrum data module simulates an ideal combustion process of an engine based on a radiation model, generates an ideal tail flame spectrum for reference, and extracts a reference spectrum intensity of a target substance based on the ideal tail flame spectrum; An actual spectrum data acquisition module, used to acquire an actual tail flame spectrum of the tail flame of the engine to be tested, and to obtain an actual spectrum intensity of the target substance based on the actual tail flame spectrum; A data processing module, which acquires dynamic features for determining whether the engine to be tested is faulty based on the reference spectrum intensity and the actual spectrum intensity; The dynamic threshold adjustment and state discrimination module is used to construct a dynamic threshold range for judging whether the dynamic feature is abnormal, and to judge whether the dynamic feature is abnormal based on the dynamic threshold range, wherein if the dynamic feature exceeds the dynamic threshold range, the dynamic feature is abnormal, that is, it is judged that the engine to be tested has a fault; if the dynamic feature is within the dynamic threshold range, the dynamic feature is not abnormal, that is, it is judged that the engine to be tested has no fault.

Images