Oscillation combustion fault detection method based on synchronous compression transformation

Abstract

The invention relates to the technical field of signal processing and fault diagnosis, and the method comprises the steps: collecting a flame chemiluminescence signal, and carrying out the adaptive filtering noise reduction processing; comprehensive combustion characteristic information is obtained by using an improved intrinsic orthogonal decomposition method and a high-order mode; developing a real-time synchronous compression transformation algorithm to perform time-frequency analysis on the data, and updating energy distribution in real time; sensor data are combined, multi-parameter conjoint analysis is conducted, combustion state evaluation is obtained, flame images are obtained from different angles through a plurality of high-speed cameras, the three-dimensional flame form is reconstructed through the computer vision technology, and fault detection information is provided; and a fault prediction model is constructed, and early warning of combustion faults is realized. The method realizes lossless and rapid detection of oscillation combustion faults, retains rich information of flame images, reflects the overall pulsation characteristics of flames, improves the detection speed and accuracy, and makes up for the disadvantage of low frequency resolution of a traditional time-frequency analysis method.

Description

Technical Field

[0001] The invention relates to the technical field of signal processing and fault diagnosis, and in particular to an oscillation combustion fault detection method based on synchronous compression transformation. Background Art

[0002] As a highly efficient energy conversion device, gas turbines are widely used in power generation, ship propulsion, mechanical power and other fields. However, the operating stability of its combustion chamber has a decisive influence on the performance and safety of the entire system. The gas turbine combustion chamber usually adopts a lean premixed swirl combustion method. Although this method can reduce the combustion temperature and NOx emissions, it is very easy to induce oscillating combustion failures. This failure will seriously affect the operating efficiency and combustion efficiency of the gas turbine and its combined cycle, and may also cause fluctuations in important parameters such as combustion chamber temperature and NOx concentration, posing a threat to equipment and personnel safety. During the operation of the gas turbine, combustion instability may occur, such as oscillating combustion, which will lead to a decrease in equipment performance and may even cause equipment damage. Therefore, the rapid detection and diagnosis of gas turbine oscillating combustion failures is particularly important.

[0003] The traditional oscillating combustion fault monitoring method mainly relies on the pressure sensor to perform frequency domain analysis on the combustion chamber time domain pressure signal. However, this method has some obvious shortcomings. First, since the installation position of the sensor is usually far away from the flame, there is an error between the actual combustion chamber pressure and the sensor measured pressure, resulting in deviation and lag in data monitoring. Secondly, due to the limitation of sensor response speed, the diagnosis and identification of fault phenomena are not timely, and the fault is often discovered only after serious losses have occurred, which is extremely unfavorable for actual production.

[0004] Existing gas turbine oscillation combustion fault detection technologies usually use methods such as acoustic detection and pressure fluctuation analysis. These methods can detect combustion oscillation to a certain extent, but have the following shortcomings:

[0005] Low sensitivity: Since methods such as acoustic detection and pressure fluctuation analysis are affected by environmental noise and mechanical vibration, they are not effective in detecting weak combustion oscillation signals and are prone to false alarms or missed alarms.

[0006] Difficulty in positioning: Existing detection technologies are difficult to accurately locate the specific location of combustion oscillations and cannot provide accurate information for troubleshooting.

[0007] Poor timeliness: Traditional detection methods require a long time for signal acquisition and processing, and cannot achieve real-time monitoring and rapid diagnosis. Summary of the invention

[0008] In view of the above existing problems, the present invention is proposed.

[0009] Therefore, the present invention provides an oscillating combustion fault detection method based on synchronous compression transformation, which can reduce the time cost of fault detection, improve the accuracy of fault detection, and reduce the false alarm rate.

[0010] To solve the above technical problems, the present invention provides the following technical solutions: an oscillating combustion fault detection method based on synchronous compression transformation, comprising: collecting flame chemiluminescence signals, and performing adaptive filtering and noise reduction processing on the collected flame chemiluminescence signals; using an improved intrinsic orthogonal decomposition method to extract the first-order modal time coefficient of the flame image, and using high-order modes to obtain comprehensive combustion characteristic information; developing a real-time synchronous compression transformation algorithm to perform time-frequency analysis on the data, and update the energy distribution in real time to respond to slight changes in the combustion state; combining sensor data to perform multi-parameter joint analysis to obtain a combustion state evaluation, using multiple high-speed cameras to obtain flame images from different angles, and reconstructing the three-dimensional flame morphology through computer vision technology to provide fault detection information; constructing a fault prediction model to automatically complete the entire fault detection process and achieve early warning of combustion faults.

[0011] As a preferred solution of the oscillation combustion fault detection method based on synchronous compression transformation described in the present invention, wherein: the adaptive filtering noise reduction processing includes, when performing oscillation combustion fault detection, distinguishing noise from actual combustion oscillation signals, selecting an adaptive filter based on the steepest descent method, and combining the filter with noise estimation and signal enhancement;

[0012] The adaptive filter update rule is as follows:

[0013]

[0014] Where w(n) represents the filter weight vector, n represents the discrete time step, represents the noise power estimate at the nth moment, ∈ represents a constant, x(n) represents the input flame signal at the nth moment, e(n) represents the error signal at the nth moment, and α represents the forgetting factor.

[0015] As a preferred solution of the oscillating combustion fault detection method based on synchronous compression transformation described in the present invention, the improved intrinsic orthogonal decomposition method includes: performing POD analysis on the flame image set after filter processing to obtain eigenmodes and eigenvalues, and selecting M eigenmodes with the highest energy according to the size of the eigenvalues ​​to form a new mode set, which represents the most significant spatial features in the data;

[0016] For each selected mode, the time coefficient is calculated. The time coefficient represents the change of the projection of the flame image on each eigenmode over time. The calculation formula is as follows:

[0017]

[0018] Among them, c i (m) represents the time coefficient, I(m) represents the mth flame image frame, represents the mean of the image set, φ i (x, y) represents the intrinsic mode of the flame image, i is the index of the mode;

[0019] Store the calculated time coefficients in a collection:

[0020]

[0021] in, represents an ensemble of higher-order modal time coefficients that reveal subtle fluctuations in the combustion process and early signs of failure.

[0022] As a preferred solution of the oscillation combustion fault detection method based on synchronous compression transformation described in the present invention, the development of the real-time synchronous compression transformation algorithm includes rearranging the coefficients of the time-frequency transformation through the synchronous compression operator, moving the time-frequency coefficients of the signal at any point in the time-frequency plane to the center of gravity of the energy, enhancing the energy concentration of the instantaneous frequency, applying a window function on the basis of Fourier transformation, dividing the signal time domain, and obtaining the frequency distribution under the window at different time points by sliding the window function, and then arranging these short-time spectra in time sequence to describe the time-varying law of the signal frequency components;

[0023] For a certain time-varying signal The short-time Fourier transform window function is g(t), which is transformed by STFT:

[0024] G(t,f)=∫ R s(τ)g(τ-t)e -i2πf(τ-t) dτ

[0025] Wherein, G(t, f) represents the result of Fourier transform, s(τ) represents the original signal, τ represents the time variable of the original signal, g(τ-t) represents, t represents the time variable, f represents the frequency variable, and i represents the imaginary unit;

[0026] Perform Fourier transform on the time-varying harmonic signal and the window function signal to obtain the estimated result of the instantaneous frequency in the STFT time-frequency representation, which is expressed as:

[0027]

[0028] Among them, θ(t, ω) represents the instantaneous frequency, ω represents the frequency variable, arg(G(t, f)) represents the argument, and Re represents the real part. represents the partial derivative with respect to time t;

[0029] The instantaneous frequency estimation results are used to collect STFT coefficients with the same frequency. According to the properties of the Dirac function, the synchronous compression operator function ∫ R δ(η-ω0(t,ω)), we get the synchronous compression transformation, which is expressed as:

[0030] T s (t, η) = ∫ R G(t,f)δ(η-θ(t,ω))dω

[0031] Among them, T s (t, η) represents the instantaneous frequency signal, δ(η-θ(t, ω)) represents the Dirac function, η represents the instantaneous frequency variable, and the time-frequency coefficients are redistributed and arranged in the frequency direction. The synchronous compression transformation process at time t, that is, the frequency points are redistributed and go through all moments.

[0032] As a preferred solution of the oscillating combustion fault detection method based on synchronous compression transformation described in the present invention, wherein: the multi-parameter joint analysis includes analyzing the data collected by the sensor to understand the distribution and characteristics, adjusting the parameters through the optimization algorithm, and finding the best parameter combination after multiple iterations;

[0033] Substitute the parameter combination into the multi-parameter joint analysis formula to calculate the weighted contribution of each sensor. The weight takes into account the different sensitivities of the sensors to angle, speed, and light intensity, and applies a normalization function to ensure the comparability of data from different sensors. The specific formula is:

[0034]

[0035] Among them, G(θ, v, I) represents the main function of multi-parameter joint analysis, θ represents the flame inclination angle, v represents the flame burning speed, I represents the flame radiation intensity, n represents the number of sensors, Ω i represents the effective measurement domain of the i-th sensor, f i (θ i , v i , I i ) represents the weighted contribution, α i represents the angle parameter of the i-th sensor, θ i Represents the angle value measured by the i-th sensor, θ 0i represents the reference angle value of the i-th sensor, β i represents the adjustment coefficient of the speed parameter of the i-th sensor, γ i represents the adjustment coefficient of the light intensity parameter of the i-th sensor, denote the mean and standard deviation of the angle measurement values ​​of the i-th sensor, respectively. denote the mean and standard deviation of the velocity measurements of the i-th sensor, respectively.

[0036] As a preferred solution of the oscillating combustion fault detection method based on synchronous compression transformation described in the present invention, wherein: the reconstruction of the three-dimensional flame morphology includes combining the results of multi-parameter joint analysis and using a computer vision algorithm to reconstruct the three-dimensional morphology of the flame;

[0037] By considering the change of flame over time through the time correlation function, a dynamic three-dimensional flame model is obtained:

[0038] F(x, y, z, t) = ∫ Ω G(θ,v,I)·h(t)dt

[0039] h(t)=sin(ωt+φ)·e- λt

[0040] Among them, x, y, z represent the coordinate axes of the three-dimensional space, h(t) represents the function of the flame changing with time, Ω represents the spatial domain of integration, φ represents the phase offset, and λ represents the attenuation coefficient; the three-dimensional flame model gives the complete form of the flame in the three-dimensional space, including its changes with time.

[0041] As a preferred solution of the oscillating combustion fault detection method based on synchronous compression transformation described in the present invention, wherein: the fault prediction model includes comparing the calculated flame state and flame morphology with the normal behavior threshold, and if the calculated result exceeds the preset threshold range, it is considered that abnormal behavior exists;

[0042] When the flame temperature is lower than 1000K or higher than 2500K, the abnormal behavior is considered to be incomplete combustion and burner blockage. The solution is to adjust the oxygen / fuel ratio of the burner and check and clean the carbon deposits and sediments inside the burner;

[0043] When the flame oscillation frequency is lower than 0.5Hz or higher than 2Hz, and the flame shape is lower than 0.5 or higher than 1.5, the abnormal behavior is considered to be caused by damage to the internal structure of the burner and unstable fuel supply. The solution is to check the fuel supply system to keep the fuel flow stable; check whether the burner nozzle and combustion chamber are blocked, and check whether the internal structure is damaged;

[0044] When the contrast of the flame image is lower than 0.6 or higher than 1.5, it is considered that the abnormal behavior is caused by improper camera settings or the characteristics of the flame itself. The solution is to adjust the camera parameters to improve the image quality, check whether the camera lens is contaminated or damaged; check the brightness and color characteristics of the flame;

[0045] The detected abnormal behaviors and causes are summarized as fault detection information and recorded in the database for subsequent analysis and reporting. Fault detection reports are generated regularly to monitor the health and performance of the combustion process.

[0046] Another object of the present invention is to provide an oscillating combustion fault detection system based on synchronous compression transformation, which can improve the fault detection accuracy and diagnosis speed through the oscillating combustion fault detection algorithm.

[0047] As a preferred solution of the oscillating combustion fault detection system based on synchronous compression transformation described in the present invention, it includes: a data acquisition module, an intrinsic orthogonal decomposition method module, a synchronous compression transformation module, a multi-parameter joint analysis module, a three-dimensional flame morphology reconstruction module, and a fault detection module;

[0048] The data acquisition module uses a highly sensitive flame chemiluminescence sensor to accurately capture the light signal generated by the chemical reaction in the flame. The sensor array is arranged at different positions of the burner to obtain the overall chemiluminescence characteristics of the flame;

[0049] The intrinsic orthogonal decomposition method module accurately predicts faults by analyzing and identifying the change pattern during the combustion process;

[0050] The synchronous compression transformation module performs time-frequency analysis on sensor data through real-time SCT algorithm, captures instantaneous changes in the combustion process, reflects subtle changes in the combustion state, and improves the sensitivity of fault detection;

[0051] The multi-parameter joint analysis module uses a multi-parameter joint analysis algorithm in combination with the result of synchronous compression transformation to evaluate the flame state;

[0052] The three-dimensional flame shape reconstruction module uses computer vision technology to reconstruct the three-dimensional flame shape from flame images acquired from different angles;

[0053] The fault detection module analyzes the results of multi-parameter joint analysis and three-dimensional flame morphology reconstruction to detect abnormal behavior of the flame.

[0054] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of an oscillation combustion fault detection method based on synchronous compression transformation.

[0055] A computer-readable storage medium stores a computer program thereon, characterized in that when the computer program is executed by a processor, the computer program implements the steps of an oscillating combustion fault detection method based on synchronous compression transformation.

[0056] The beneficial effects of the present invention are as follows: in terms of data acquisition, the present invention utilizes high-speed photography technology to acquire flame images, thereby avoiding the data lag problem caused by traditional pressure monitoring methods, and can achieve non-destructive and rapid detection of oscillating combustion faults; the intrinsic orthogonal decomposition can perform data dimension reduction and feature extraction on the flame image, retain the rich information of the flame image, reflect the overall pulsation characteristics of the flame, and improve the detection speed and accuracy; the synchronous compression transformation performs energy rearrangement and instantaneous concentration through the synchronous compression operator, thereby making up for the disadvantage of low frequency resolution of traditional time-frequency analysis methods, and achieving accurate diagnosis and rapid detection of oscillating combustion faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0058] Figure 1 A schematic flow chart of an oscillating combustion fault detection method based on synchronous compression transformation is provided for one embodiment of the present invention.

[0059] Figure 2 The present invention provides a detection result of an oscillating combustion fault detection method based on synchronous compression transformation according to an embodiment of the present invention.

[0060] Figure 3 A pressure signal SST result diagram under two working conditions of flame oscillation and stability of an oscillating combustion fault detection method based on synchronous compression transformation provided by an embodiment of the present invention. Figure 4 A schematic diagram of working modules of an oscillating combustion fault detection system based on synchronous compression transformation is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0063] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0064] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0065] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0066] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0067] Example 1

[0068] Reference Figure 1 , which is the first embodiment of the present invention, provides an oscillation combustion fault detection method based on synchronous compression transformation, comprising:

[0069] S1: Collect flame chemiluminescence signals and perform adaptive filtering and noise reduction processing on the collected flame chemiluminescence signals.

[0070] Furthermore, the adaptive filtering noise reduction process includes, when performing oscillation combustion fault detection, distinguishing between noise and actual combustion oscillation signals, selecting an adaptive filter based on the steepest descent method, the filter combining noise estimation and signal enhancement;

[0071] The adaptive filter update rule is as follows:

[0072]

[0073] Where w(n) represents the filter weight vector, n represents the discrete time step, represents the noise power estimate at the nth moment, ∈ represents a constant, x(n) represents the input flame signal at the nth moment, e(n) represents the error signal at the nth moment, and α represents the forgetting factor.

[0074] S2: The improved intrinsic orthogonal decomposition method is used to extract the first-order modal time coefficient of the flame image, and the high-order modes are used to obtain comprehensive combustion characteristic information.

[0075] Furthermore, the improved intrinsic orthogonal decomposition method includes performing POD analysis on the flame image set after filter processing to obtain eigenmodes and eigenvalues, and selecting M eigenmodes with the highest energy according to the magnitude of the eigenvalues ​​to form a new mode set representing the most significant spatial features in the data;

[0076] For each selected mode, the time coefficient is calculated. The time coefficient represents the change of the projection of the flame image on each eigenmode over time. The calculation formula is as follows:

[0077]

[0078] Among them, c i (m) represents the time coefficient, I(m) represents the mth flame image frame, represents the mean of the image set, φ i (x, y) represents the intrinsic mode of the flame image, i is the index of the mode;

[0079] Store the calculated time coefficients in a collection:

[0080]

[0081] in, represents an ensemble of higher-order modal time coefficients that reveal subtle fluctuations in the combustion process and early signs of failure.

[0082] S3: Develop a real-time synchronous compression transform algorithm to perform time-frequency analysis on the data and update the energy allocation in real time in response to small changes in the combustion state.

[0083] Furthermore, the development of the real-time synchronous compression transformation algorithm includes rearranging the coefficients of the time-frequency transformation through the synchronous compression operator, moving the time-frequency coefficients of the signal at any point in the time-frequency plane to the center of gravity of the energy, enhancing the energy concentration of the instantaneous frequency, applying a window function on the basis of Fourier transform, dividing the signal time domain, obtaining the frequency distribution under the window at different time points by sliding the window function, and then arranging these short-time spectra in time sequence to describe the time-varying law of the signal frequency components;

[0084] For a certain time-varying signal The short-time Fourier transform window function is g(t), which is transformed by STFT:

[0085] G(t,f)=∫ R s(τ)g(τ-t)e -i2πf(T-t) dτ

[0086] Wherein, G(t, f) represents the result of Fourier transform, s(τ) represents the original signal, τ represents the time variable of the original signal, g(τ-t) represents, t represents the time variable, f represents the frequency variable, and i represents the imaginary unit;

[0087] Perform Fourier transform on the time-varying harmonic signal and the window function signal to obtain the estimated result of the instantaneous frequency in the STFT time-frequency representation, which is expressed as:

[0088]

[0089] Among them, θ(t, ω) represents the instantaneous frequency, ω represents the frequency variable, arg(G(t, f)) represents the argument, and Re represents the real part. represents the partial derivative with respect to time t;

[0090] The instantaneous frequency estimation results are used to collect STFT coefficients with the same frequency. According to the properties of the Dirac function, the synchronous compression operator function ∫ R δ(η-ω0(t,ω)), we get the synchronous compression transformation, which is expressed as:

[0091] T s (t, η) = ∫ R G(t,f)δ(η-θ(t,ω))dω

[0092] Among them, T s (t, η) represents the instantaneous frequency signal, δ(η-θ(t, ω)) represents the Dirac function, η represents the instantaneous frequency variable, and the time-frequency coefficients are redistributed and arranged in the frequency direction. The synchronous compression transformation process at time t, that is, the frequency points are redistributed and go through all moments.

[0093] S4: Combine sensor data to conduct multi-parameter joint analysis to obtain combustion status evaluation, use multiple high-speed cameras to obtain flame images from different angles, reconstruct the three-dimensional flame morphology through computer vision technology, and provide fault detection information.

[0094] Furthermore, the multi-parameter joint analysis includes analyzing the data collected by the sensors to understand the distribution and characteristics, adjusting the parameters through an optimization algorithm, and finding the best parameter combination after multiple iterations;

[0095] Substitute the parameter combination into the multi-parameter joint analysis formula to calculate the weighted contribution of each sensor. The weight takes into account the different sensitivities of the sensors to angle, speed, and light intensity, and applies a normalization function to ensure the comparability of data from different sensors. The specific formula is:

[0096]

[0097] Among them, G(θ, v, I) represents the main function of multi-parameter joint analysis, θ represents the flame inclination angle, v represents the flame burning speed, I represents the flame radiation intensity, n represents the number of sensors, Ω i represents the effective measurement domain of the i-th sensor, f i (θ i , v i , I i ) represents the weighted contribution, α i represents the angle parameter of the i-th sensor, θ i Represents the angle value measured by the i-th sensor, θ 0i represents the reference angle value of the i-th sensor, β i represents the adjustment coefficient of the speed parameter of the i-th sensor, γ i represents the adjustment coefficient of the light intensity parameter of the i-th sensor, denote the mean and standard deviation of the angle measurement values ​​of the i-th sensor, respectively. denote the mean and standard deviation of the velocity measurements of the i-th sensor, respectively.

[0098] Furthermore, the reconstructing the three-dimensional flame shape includes reconstructing the three-dimensional flame shape using a computer vision algorithm in combination with the result of multi-parameter joint analysis;

[0099] By considering the change of flame over time through the time correlation function, a dynamic three-dimensional flame model is obtained:

[0100] F(x, y, z, t) = ∫ Ω G(θ,v,I)·h(t)dt

[0101] h(t)=sin(ωt+φ)·e -λt

[0102] Among them, x, y, z represent the coordinate axes of the three-dimensional space, h(t) represents the function of the flame changing with time, Ω represents the spatial domain of integration, φ represents the phase offset, and λ represents the attenuation coefficient; the three-dimensional flame model gives the complete form of the flame in the three-dimensional space, including its changes with time.

[0103] S5: Build a fault prediction model to automatically complete the entire fault detection process and achieve early warning of combustion failures.

[0104] Furthermore, the fault prediction model includes comparing the calculated flame state and flame morphology with a normal behavior threshold, and if the calculated result exceeds a preset threshold range, it is considered that abnormal behavior exists;

[0105] When the flame temperature is lower than 1000K or higher than 2500K, the abnormal behavior is considered to be incomplete combustion and burner blockage. The solution is to adjust the oxygen / fuel ratio of the burner and check and clean the carbon deposits and sediments inside the burner;

[0106] When the flame oscillation frequency is lower than 0.5Hz or higher than 2Hz, and the flame shape is lower than 0.5 or higher than 1.5, the abnormal behavior is considered to be caused by damage to the internal structure of the burner and unstable fuel supply. The solution is to check the fuel supply system to keep the fuel flow stable; check whether the burner nozzle and combustion chamber are blocked, and check whether the internal structure is damaged;

[0107] When the contrast of the flame image is lower than 0.6 or higher than 1.5, it is considered that the abnormal behavior is caused by improper camera settings or the characteristics of the flame itself. The solution is to adjust the camera parameters to improve the image quality, check whether the camera lens is contaminated or damaged; check the brightness and color characteristics of the flame;

[0108] The detected abnormal behaviors and causes are summarized as fault detection information and recorded in the database for subsequent analysis and reporting. Fault detection reports are generated regularly to monitor the health and performance of the combustion process.

[0109] Example 2

[0110] Reference Figure 2 and Figure 3 , which is an embodiment of the present invention, provides an oscillation combustion fault detection method based on synchronous compression transformation. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0111] Figure 2For the two verification conditions involved in the embodiments of the present invention, the pressure signals of the oscillation and stable conditions of the experimental bench used for verification were first collected, and STFT analysis was performed on them. In the oscillation condition, an obvious oscillation main frequency was identified near t=0.75s, but the frequency resolution was poor; for the stable condition, no obvious oscillation main frequency appeared. Figure 3 The results of synchronous compression transformation analysis of pressure signals under two working conditions are shown in Figure 2. For the oscillating working condition, the synchronous compression transformation concentrates the energy of the measured signal, superimposes the spectrum in the pseudo-frequency interval, concentrates the energy on the actual instantaneous frequency, improves the time-frequency aggregation, and greatly improves the frequency resolution. The STFT analysis results of the flame CH* light intensity signal under two working conditions show that the oscillating working condition shows an obvious main frequency response near t=0.2s, and no oscillating main frequency appears under the stable working condition. The flame CH* light intensity signal shows an obvious time advantage over the pressure signal in terms of diagnostic speed. The results of synchronous compression transformation analysis of the flame CH* light intensity signal under two working conditions show that the frequency domain resolution of the time-frequency analysis results is greatly improved through synchronous compression transformation analysis. The flame image is subjected to data dimension reduction and feature extraction by using the intrinsic orthogonal decomposition method, and the first-order modal time coefficient is obtained, which is used as the data input of STFT for oscillation combustion fault diagnosis again. The first-order modal time coefficient of intrinsic orthogonal decomposition is used as the input of STFT, and an obvious main frequency response appears at t=0.01s, which greatly improves the diagnosis speed; like the pressure signal and CH* light intensity signal, there is also the problem of low frequency resolution. Through synchronous compression transform analysis, the frequency resolution of the spectrum is greatly improved, and the frequency positioning is more accurate.

[0112] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0113] Example 3

[0114] The third embodiment of the present invention is different from the first two embodiments in that:

[0115] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0116] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0117] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0118] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0119] Example 4

[0120] Reference Figure 4 , which is an embodiment of the present invention, provides an oscillating combustion fault detection system based on synchronous compression transformation, which is characterized by: including a data acquisition module, an intrinsic orthogonal decomposition method module, a synchronous compression transformation module, a multi-parameter joint analysis module, a three-dimensional flame morphology reconstruction module, and a fault detection module.

[0121] The data acquisition module uses a highly sensitive flame chemiluminescence sensor to accurately capture the light signal generated by the chemical reaction in the flame. The sensor array is arranged at different positions of the burner to obtain the overall chemiluminescence characteristics of the flame.

[0122] The intrinsic orthogonal decomposition method module accurately predicts faults by analyzing and identifying the changing patterns in the combustion process.

[0123] The synchronous compression transform module uses the real-time SCT algorithm to perform time-frequency analysis on sensor data, capture instantaneous changes in the combustion process, reflect subtle changes in the combustion state, and improve the sensitivity of fault detection;

[0124] The multi-parameter joint analysis module combines the results of synchronous compression transformation and uses a multi-parameter joint analysis algorithm to evaluate the flame state.

[0125] The three-dimensional flame shape reconstruction module uses computer vision technology to reconstruct the three-dimensional flame shape from flame images acquired from different angles.

[0126] The fault detection module analyzes the results of multi-parameter joint analysis and three-dimensional flame morphology reconstruction to detect abnormal flame behavior.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting oscillating combustion faults based on synchronous compression transformation, characterized in that: include, Collecting flame chemiluminescence signals, and performing adaptive filtering and noise reduction processing on the collected flame chemiluminescence signals; The improved intrinsic orthogonal decomposition method is used to extract the first-order modal time coefficient of the flame image, and the high-order modes are used to obtain comprehensive combustion characteristic information; Develop a real-time synchronous compression transform algorithm to perform time-frequency analysis on the data and update the energy allocation in real time in response to small changes in the combustion state; Combined with sensor data, multi-parameter joint analysis is performed to obtain combustion status evaluation, flame images are acquired from different angles using multiple high-speed cameras, and three-dimensional flame morphology is reconstructed through computer vision technology to provide fault detection information; Build a fault prediction model to automatically complete the entire fault detection process and achieve early warning of combustion failures.

2. The oscillating combustion fault detection method based on synchronous compression transformation according to claim 1 is characterized in that: The adaptive filtering and noise reduction processing includes, when performing oscillation combustion fault detection, distinguishing between noise and actual combustion oscillation signals, selecting an adaptive filter based on the steepest descent method, and combining the filter with noise estimation and signal enhancement; The adaptive filter update rule is as follows: Where w(n) represents the filter weight vector, n represents the discrete time step, represents the noise power estimate at the nth moment, ∈ represents a constant, x(n) represents the input flame signal at the nth moment, e(n) represents the error signal at the nth moment, and α represents the forgetting factor.

3. The oscillating combustion fault detection method based on synchronous compression transformation according to claim 2 is characterized in that: The improved intrinsic orthogonal decomposition method includes performing POD analysis on the flame image set after filter processing to obtain eigenmodes and eigenvalues, and selecting M eigenmodes with the highest energy according to the size of the eigenvalues ​​to form a new mode set representing the most significant spatial features in the data; For each selected mode, the time coefficient is calculated. The time coefficient represents the change of the projection of the flame image on each eigenmode over time. The calculation formula is as follows: Among them, c i (m) represents the time coefficient, I(m) represents the mth flame image frame, represents the mean of the image set, φ i (x, y) represents the intrinsic mode of the flame image, i is the index of the mode; Store the calculated time coefficients in a collection: in, represents an ensemble of higher-order modal time coefficients that reveal subtle fluctuations in the combustion process and early signs of failure.

4. The oscillating combustion fault detection method based on synchronous compression transformation according to claim 3 is characterized in that: The development of the real-time synchronous compression transformation algorithm includes rearranging the coefficients of the time-frequency transformation through the synchronous compression operator, moving the time-frequency coefficients of the signal at any point in the time-frequency plane to the center of gravity of the energy, enhancing the energy concentration of the instantaneous frequency, applying a window function on the basis of Fourier transformation, dividing the signal time domain, obtaining the frequency distribution under the window at different time points through sliding the window function, and then arranging these short-time spectra in time sequence to describe the time-varying law of the signal frequency components; For a certain time-varying signal The short-time Fourier transform window function is g(t), which is transformed by STFT: G(t,f)=∫ R s(τ)g(τ-t)e -i2πf(τ-t) dτ Where G(t,f) represents the result of Fourier transform, s(τ) represents the original signal, τ represents the time variable of the original signal, g(τ-t) represents, t represents the time variable, f represents the frequency variable, and i represents the imaginary unit; Perform Fourier transform on the time-varying harmonic signal and the window function signal to obtain the estimated result of the instantaneous frequency in the STFT time-frequency representation, which is expressed as: Among them, θ(t,ω) represents the instantaneous frequency, ω represents the frequency variable, arg(G(t,f)) represents the argument, and Re represents the real part. represents the partial derivative with respect to time t; The instantaneous frequency estimation results are used to collect STFT coefficients with the same frequency. According to the properties of the Dirac function, the synchronous compression operator function ∫ R δ(′-ω0(t,ω)), we get the synchronous compression transformation, which is expressed as: T s (t,η)=∫ R G(t,f)δ(η-θ(t,ω))dω Among them, T s (t,η) represents the instantaneous frequency signal, δ(η-θ(t,ω)) represents the Dirac function, η represents the instantaneous frequency variable, and the time-frequency coefficients are redistributed and arranged in the frequency direction. The synchronous compression transformation process at time t means that the frequency points are redistributed and go through all moments.

5. The oscillating combustion fault detection method based on synchronous compression transformation according to claim 4 is characterized in that: The multi-parameter joint analysis includes analyzing the data collected by the sensors to understand the distribution and characteristics, adjusting the parameters through the optimization algorithm, and finding the best parameter combination after multiple iterations; Substitute the parameter combination into the multi-parameter joint analysis formula to calculate the weighted contribution of each sensor. The weight takes into account the different sensitivities of the sensors to angle, speed, and light intensity, and applies a normalization function to ensure the comparability of data from different sensors. The specific formula is: Among them, G(θ,v,I) represents the main function of multi-parameter joint analysis, θ represents the flame inclination angle, v represents the flame burning speed, I represents the flame radiation intensity, n represents the number of sensors, Ω i represents the effective measurement domain of the i-th sensor, f i (θ i ,v i ,I i ) represents the weighted contribution, α i represents the angle parameter of the i-th sensor, θ i Represents the angle value measured by the i-th sensor, θ 0i represents the reference angle value of the i-th sensor, β i represents the adjustment coefficient of the speed parameter of the i-th sensor, γ i represents the adjustment coefficient of the light intensity parameter of the i-th sensor, denote the mean and standard deviation of the angle measurement values ​​of the i-th sensor, respectively. denote the mean and standard deviation of the velocity measurements of the i-th sensor, respectively.

6. The oscillating combustion fault detection method based on synchronous compression transformation according to claim 5, characterized in that: The reconstructing of the three-dimensional flame shape includes combining the results of multi-parameter joint analysis and using a computer vision algorithm to reconstruct the three-dimensional shape of the flame; By considering the change of flame over time through the time correlation function, a dynamic three-dimensional flame model is obtained: F(x,y,z,t)=∫ Ω G(θ,v,I)·h(t)dt h(t)=sin(ωt+φ)·e -λt Among them, x, y, z represent the coordinate axes of the three-dimensional space, h(t) represents the function of the flame changing with time, Ω represents the spatial domain of integration, φ represents the phase offset, and λ represents the attenuation coefficient; the three-dimensional flame model gives the complete form of the flame in the three-dimensional space, including its changes with time.

7. The oscillating combustion fault detection method based on synchronous compression transformation according to claim 6 is characterized in that: The fault prediction model includes comparing the calculated flame state and flame morphology with normal behavior thresholds, and if the calculated result exceeds a preset threshold range, it is considered that abnormal behavior exists; When the flame temperature is lower than 1000K or higher than 2500K, the abnormal behavior is considered to be incomplete combustion and burner blockage. The solution is to adjust the oxygen / fuel ratio of the burner and check and clean the carbon deposits and sediments inside the burner; When the flame oscillation frequency is lower than 0.5Hz or higher than 2Hz, and the flame shape is lower than 0.5 or higher than 1.5, the abnormal behavior is considered to be caused by damage to the internal structure of the burner and unstable fuel supply. The solution is to check the fuel supply system to keep the fuel flow stable; check whether the burner nozzle and combustion chamber are blocked, and check whether the internal structure is damaged; When the contrast of the flame image is lower than 0.6 or higher than 1.5, it is considered that the abnormal behavior is caused by improper camera settings or the characteristics of the flame itself. The solution is to adjust the camera parameters to improve the image quality, check whether the camera lens is contaminated or damaged; check the brightness and color characteristics of the flame; The detected abnormal behaviors and causes are summarized as fault detection information and recorded in the database for subsequent analysis and reporting. Fault detection reports are generated regularly to monitor the health and performance of the combustion process.

8. A system using an oscillating combustion fault detection method based on synchronous compression transformation as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition module, intrinsic orthogonal decomposition method module, synchronous compression transformation module, multi-parameter joint analysis module, three-dimensional flame morphology reconstruction module, and fault detection module; The data acquisition module uses a highly sensitive flame chemiluminescence sensor to accurately capture the light signal generated by the chemical reaction in the flame. The sensor array is arranged at different positions of the burner to obtain the overall chemiluminescence characteristics of the flame; The intrinsic orthogonal decomposition method module accurately predicts faults by analyzing and identifying the change pattern during the combustion process; The synchronous compression transformation module performs time-frequency analysis on sensor data through real-time SCT algorithm, captures instantaneous changes in the combustion process, reflects subtle changes in the combustion state, and improves the sensitivity of fault detection; The multi-parameter joint analysis module uses a multi-parameter joint analysis algorithm in combination with the result of synchronous compression transformation to evaluate the flame state; The three-dimensional flame shape reconstruction module uses computer vision technology to reconstruct the three-dimensional flame shape from flame images acquired from different angles; The fault detection module analyzes the results of multi-parameter joint analysis and three-dimensional flame morphology reconstruction to detect abnormal behavior of the flame.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images