A method for adaptive extraction and evaluation of fault shock features of a reciprocating engine

Abstract

The application provides a reciprocating engine fault impact feature adaptive extraction and evaluation method, comprising: processing vibration signals and crankshaft key signals of each cylinder of the reciprocating engine by using MSADE-OC joint analysis technology to obtain a phase-compensated MSADE-OC joint diagram and a multi-channel vibration envelope signal, and saving the multi-channel vibration envelope signal to a matrix Z'; sliding a sliding window W along the horizontal axis of the matrix Z' to obtain an intercepted vibration signal; calculating the average amplitude a[i] and the average RMS value b[i] of each channel vibration signal; according to a[i] and b[i], calculating the overall average peak value and the overall average RMS value of each cylinder of the reciprocating engine; when a[i] is greater than and b[i] is greater than, it is determined that a certain key component has a potential fault; otherwise, it is determined that a certain key component is in a normal state. The application fuses the engine component motion phase characteristics and the sliding window technology to solve the problem of inaccurate analysis results in the extraction and quantitative evaluation of the impact features in the engine vibration signals.

Description

Technical Field

[0001] This application belongs to the field of reciprocating engine fault diagnosis technology, specifically relating to an adaptive extraction and evaluation method for fault impact features of reciprocating engines. Background Technology

[0002] Reciprocating engines are highly efficient power units that play a vital role in transportation, power generation, and construction machinery. Monitoring and evaluating their operational status is therefore crucial. When a reciprocating engine malfunctions or its operating conditions change, its vibration signals contain rich information about the equipment's condition and fault characteristics. Analyzing these vibration signals can effectively identify the engine's operating status and fault type. However, the highly complex structure of reciprocating engines results in strong non-stationarity and non-periodicity in the impact characteristics of their vibration signals. This makes adaptive extraction of impact features significantly difficult, impacting the accuracy of quantifying and evaluating the equipment's operational status.

[0003] Currently, the mainstream methods for extracting and quantifying impact features from engine vibration signals focus on vibration signals as the core research object, with conventional processes mainly revolving around signal acquisition, decomposition, and impact feature extraction. The main steps are: first, vibration signals from key engine components are acquired using accelerometers, and preprocessed using methods such as filtering and noise reduction; then, Hilbert demodulation and energy operators are used to extract all impacts within the cycle; finally, the engine's health status is assessed and faults are identified by manually observing the spectrum and comparing characteristic indicators. However, these conventional methods have two significant limitations: in terms of feature quantification, existing methods struggle to effectively separate impact signals, making it impossible to assess the operating status of key engine components. Furthermore, traditional methods rely on manual analysis of spectra and characteristic indicators, lacking the ability to adaptively extract and quantify impact features; in terms of signal processing, conventional methods are limited to periodic samples within a finite observation period, while the vibration signals of reciprocating engines typically exhibit non-stationary and non-periodic characteristics, leading to inaccurate analysis results due to insufficient observation periods. Summary of the Invention

[0004] In view of this, this application provides an adaptive extraction and evaluation method for the impact features of reciprocating engine faults. By integrating the motion phase characteristics of engine components with sliding window technology, the method achieves adaptive extraction and quantitative evaluation of impact features, thereby improving the efficiency and accuracy of reciprocating engine fault diagnosis. This solves the technical problem of inaccurate analysis results caused by the non-stationary and non-periodic nature of the impact features in the reciprocating engine vibration signal in the existing extraction and quantitative evaluation of impact features in engine vibration signals.

[0005] The first aspect of this application provides an adaptive extraction and evaluation method for fault impact features of a reciprocating engine, which includes the following steps.

[0006] Step S1: The vibration signals of each cylinder of the reciprocating engine and the crankshaft key phase signal are processed in real time using the multi-source angular domain envelope-operating characteristic joint analysis technology to obtain the phase-compensated multi-source angular domain envelope-operating characteristic joint diagram. The multi-channel vibration envelope signal is obtained from the phase-compensated multi-source angular domain envelope-operating characteristic joint diagram and saved into matrix Z'.

[0007] Step S2: Traverse the matrix The first M-1 rows of data are processed using a sliding window W along the matrix. The horizontal axis is slipped, and the vibration signal obtained after slipping k times is denoted as a matrix. Where: k=1,2,3,…,R, R=floor(N / N) T The function `floor` represents rounding down. `M` represents the signal row number, and `N` represents the signal sampling length. The average sampling length over one period. The step size of the sliding window W, ∆L = 2 × N. T The center position corresponds to the phase angle θ at the moment of action of a key component, and the length is L1 = round(∆θ / ∆φ). The function round represents rounding according to the rounding rules. The angular sampling interval is the range covered by the sliding window W in the angular domain. The timing of the operation of a critical component includes any one of the following: combustion timing, intake valve opening timing, intake valve closing timing, exhaust valve opening timing, and exhaust valve closing timing.

[0008] Step S3: Based on the matrix The amplitude and RMS value of each line signal are used to calculate the average amplitude a of the vibration signal in each channel. and average RMS value b Average amplitude a This represents the average amplitude of each line of the signal. The average RMS value is b. is the mean RMS value of each row of signals. i is the row number of the vibration signal.

[0009] Step S4: Based on the average amplitude a of the vibration signals from each channel and average RMS value b Calculate the overall average peak value of each cylinder in the reciprocating engine. Compared with the overall average RMS value ,in, , The function mean represents the average value.

[0010] Step S5, when a Greater than And b Greater than If the condition is not met, a critical component is determined to have a potential fault; otherwise, a critical component is determined to be in normal condition.

[0011] In one specific embodiment of this application, before step S1, the adaptive extraction and evaluation method for fault impact features of the reciprocating engine further includes step S10.

[0012] Step S10: Real-time acquisition of vibration signals from each cylinder of the reciprocating engine and crankshaft key phase signals, and storage of these signals in matrix U. M×N In the matrix U M×N The first M-1 rows of signals are all vibration signals, and the Mth row of signals are crankshaft key phase signals.

[0013] In one specific embodiment of this application, after step S1 and before step S2, the adaptive extraction and evaluation method for fault impact characteristics of reciprocating engine further includes step S20.

[0014] Step S20: Extract the impact characteristics of a key component in the reciprocating engine at the moment of its action according to the analysis requirements, and analyze and evaluate them to obtain the phase angle θ corresponding to the moment of action of the key component.

[0015] In one specific embodiment of this application, after step S1 and before step S2, the adaptive extraction and evaluation method for fault impact characteristics of reciprocating engine further includes step S30.

[0016] Step S30: Obtain the step size, center position, and length of the sliding window W.

[0017] In one specific embodiment of this application, the area covered by the sliding window W in the corner region during step S2 is... The value range is 15°~25°.

[0018] In one specific embodiment of this application, steps S31 and S32 are a specific implementation of step S3.

[0019] Step S51: Calculate the matrix The amplitude and RMS value of each row of the signal are recorded in the matrix. and middle.

[0020] Step S52: Calculate the matrix and The mean of each row vector is used to obtain the average amplitude 'a' of the vibration signal in each channel. and average RMS value b , where: a b The function mean represents the average value. Indicates the channel number.

[0021] A second aspect of this application provides a computer device including a processor and a memory. The processor is used to execute the adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to the first aspect of this application. The memory is used to store executable instructions of the processor.

[0022] A third aspect of this application provides a computer-readable storage medium storing executable instructions for a computer. When executed by a processor, the executable instructions implement the adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to the first aspect of this application.

[0023] The fourth aspect of this application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to the first aspect of this application.

[0024] The beneficial effects of the technical solution of this application are as follows: by combining the phase characteristics of the impact signal, the adaptive extraction of the working impact characteristics of each component is realized by using a sliding window, which makes up for the shortcomings of the existing methods in terms of limited analysis range and inability to adaptively extract impact characteristics; at the same time, the embodiments of this application automatically calculate the average amplitude and average RMS value of the working impact signal of each component, and construct a statistical histogram of impact characteristic values ​​(including the average amplitude a[i] and average RMS value b[i] of the vibration signal of each channel), thereby realizing the adaptive extraction and evaluation of vibration impact characteristics of key engine components. Attached Figure Description

[0025] Figure 1 The diagram shown is a flowchart illustrating an adaptive extraction and evaluation method for fault impact features of a reciprocating engine provided in an embodiment of this application.

[0026] Figure 2 The diagram shown is a layout of vibration measuring points and key phase measuring points for a reciprocating engine cylinder head according to an embodiment of this application.

[0027] Figure 3 The figure shown is a combined diagram of the multi-source angular domain envelope and operating characteristics after phase compensation, provided in an embodiment of this application.

[0028] Figure 4 The diagram shown is a schematic diagram of the sliding process of the first row of data provided in an embodiment of this application.

[0029] Figure 5 The image shown is a histogram of the average amplitude of the intake valve seating time of each cylinder in a reciprocating engine according to an embodiment of this application.

[0030] Figure 6 The image shown is a histogram of the average RMS values ​​of the intake valves of each cylinder in a reciprocating engine according to an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] It should be noted that, as an example, the reciprocating engine in this embodiment has a rated power of 1767KW, a design speed of 1000 rpm, and is equipped with 8 cylinders (cylinder numbers 1, 2, 3, 4, 5, 6, 7, and 8). Figure 2 This invention relates to the vibration measurement point arrangement and key phase measurement point arrangement of a reciprocating engine (hereinafter referred to as the engine), wherein: the letter "K" indicates the key phase sensor position, the letter "H" indicates the horizontal direction, "V" indicates the vertical direction, and "A" indicates the axial direction. The vibration measurement point arrangement of the reciprocating engine is as follows: one vibration measurement point is arranged on the intake side of each of the eight cylinder heads of the reciprocating engine, numbered sequentially from J1 to J8. The key phase measurement point arrangement of the reciprocating engine is as follows: when the engine is rotated to the top dead center of the compression stroke of cylinder number 1, reflective tape is attached to the surface of the coupling at the engine drive end, and the photoelectric sensor is aligned with the reflective tape to collect the key phase signal; during the data acquisition process, the operating speed of the reciprocating engine is stabilized at 950 rpm. The following uses the measured data of this reciprocating engine as an example to illustrate the implementation method of this application.

[0033] At least one embodiment of this application provides an adaptive extraction and evaluation method for fault impact features of a reciprocating engine, which includes the following steps.

[0034] Step S1: Process the vibration signals of each cylinder and the crankshaft key phase signal of the reciprocating engine acquired in real time using multi-source angular domain envelope-operating characteristic joint analysis technology to obtain a phase-compensated multi-source angular domain envelope-operating characteristic joint diagram. Obtain the multi-channel vibration envelope signal from the phase-compensated multi-source angular domain envelope-operating characteristic joint diagram and save the multi-channel vibration envelope signal to a matrix. middle.

[0035] It should be noted that vibration signals can also be called vibration acceleration signals or vibration impact signals. The multi-source angular domain envelope-operating characteristic joint analysis technique can employ the analysis technique mentioned in patent CN120213464A, which can be abbreviated as MSADE-OC joint analysis technique. The multi-source angular domain envelope-operating characteristic joint diagram can be abbreviated as MSADE-OC joint diagram.

[0036] For example, vibration signals from each cylinder and crankshaft key phase signals are collected in a reciprocating engine, and these signals are stored in matrix U. M×N In the diagram, the first eight rows of signals are vibration signals, and the ninth row is the crankshaft key phase signal. Here, M=9 represents the ninth row of signals, and N=256000 represents the signal sampling length. The vibration signal U is analyzed using a multi-source angular domain envelope-operating characteristic joint analysis technique. M×N The process yields the phase-compensated multi-source angular domain envelope-operating characteristic joint diagram and the corresponding multi-channel vibration envelope signal. The multi-channel vibration envelope signal is then saved to a matrix. middle, Figure 3 This is a combined envelope-operating characteristic plot of the multi-source angular domain after phase compensation. The horizontal axis represents crankshaft rotation angle (abbreviated as angle, unit: ). The vertical axis represents the signal envelope amplitude (abbreviated as amplitude, unit: m / s). 2 The matrix is ​​arranged from top to bottom along the vertical axis. The waveforms of each signal are arranged at equal intervals along the horizontal axis. The combined envelope-operating characteristic diagram of the multi-source angular domain after phase compensation eliminates the phase difference between various impact signals, ensuring consistency in the operating states of each cylinder corresponding to the vibration signals at each measuring point. This lays the foundation for subsequently determining the phase angles at the action moments of each key component. It should be noted that... Figure 3 In the figure, H1, H2...H8 represent the vibration signal of each channel.

[0037] Step S2: Traverse the matrix The first M-1 rows of data are processed using a sliding window W along the matrix. The horizontal axis is slipped, and the vibration signal obtained after slipping k times is denoted as a matrix. Where: k=1,2,3,…,R, R=floor(N / N) T The function `floor` represents rounding down. `M` represents the signal row number, and `N` represents the signal sampling length. The average sampling length over one period. The step size of the sliding window W. The center position is the phase angle θ corresponding to the moment a key component moves, and the length is... The function `round` rounds the integer part according to the rounding rules. The angular sampling interval is the range covered by the sliding window W in the angular domain. The timing of the operation of a critical component includes any one of the following: combustion timing, intake valve opening timing, intake valve closing timing, exhaust valve opening timing, and exhaust valve closing timing.

[0038] For example, using a sliding window to segment and extract vibration signals: traversing the matrix The first 8 rows of data are processed using a sliding window W along the matrix. The horizontal axis is slipped, and the vibration signal obtained after slipping k times is denoted as a matrix. Where: k=1,2,3,…,299, R=floor(256000 / 854)=299, the function floor represents rounding down. Figure 4 This is a schematic diagram illustrating the process of using a sliding window to capture the first line of signal. The window length of the sliding window is... The sliding step size is 47. The value is 1708. The first solid box represents the initial sliding window. The first, second, and third dashed boxes represent the positions of the sliding window after sliding 1, 2, and 3 times from the initial position, respectively. The positions of other sliding windows can be deduced in the same way. After 299 sliding interceptions, the first row of signals is divided into 300 groups of signals with a length of 47.

[0039] Step S3: Based on the matrix The amplitude and RMS value of each line signal are used to calculate the average amplitude a of the vibration signal in each channel. and average RMS value b Average amplitude a This represents the average amplitude of each line of the signal. The average RMS value is b. is the mean RMS value of each row of signals. i is the row number of the vibration signal.

[0040] For example, the average amplitude and average RMS value of the vibration signal for each channel are shown in Table 1 below.

[0041] Table 1. Average amplitude and average RMS value of vibration signals for each channel. Step S4: Based on the average amplitude a of the vibration signals from each channel and average RMS value b Calculate the overall average peak value of each cylinder in the reciprocating engine. Compared with the overall average RMS value ,in, , The function mean represents the average value.

[0042] For example, the average amplitude 'a' of the vibration signal for each channel can be plotted using the data in Table 1 above. and average RMS value b The histogram was obtained, and the overall average peak value of each cylinder of the reciprocating engine was calculated separately. Compared with the overall average RMS value ,in: , The histogram of the magnitudes is shown below. Figure 5 As shown, the histogram of RMS values ​​is plotted as follows: Figure 6 As shown. Figure 5 The horizontal axis represents the cylinder number, and the vertical axis represents the average amplitude a[i] of each cylinder. Figure 6 The horizontal axis represents the cylinder number, and the vertical axis represents the average RMS value b for each cylinder. .

[0043] Step S5, when a Greater than And b Greater than If the condition is not met, a critical component is determined to have a potential fault; otherwise, a critical component is determined to be in normal condition.

[0044] For example, comparing a and b and The relative relationships between these components are used to assess the operating status of specified key engine components. Figure 5 and Figure 6 The dashed line represents the average value of the corresponding feature. , Solid-color filled bars indicate that the characteristic value of the corresponding cylinder is less than its average value, while grid-filled bars indicate that the characteristic value of the corresponding cylinder is greater than its average value; compare a and b and The relative relationships between them are used to evaluate the operating status of specified key components of the engine, specifically the average amplitude 'a' of the intake valve closing moment of cylinders 5, 7, and 8. All were significantly higher than the overall average peak value. ( 482m / s 2 The average RMS value was significantly higher than the overall average RMS value. 155m / s 2 This indicates that there may be significant abnormalities in the intake valve components of these cylinders.

[0045] To verify the effectiveness of the above analysis, the engine cylinder head was disassembled and inspected. The valve stem protrusion data of each cylinder's intake valve are shown in Table 2. Most cylinders' intake valves showed a certain degree of wear, with an average wear amount of approximately 0.015-0.036 inch. Among them, cylinder number 8 had the largest intake valve wear, reaching 0.036 inch; cylinders number 5 and 7 were next, with wear amounts of 0.030 inch each. The on-site inspection results were largely consistent with the analysis conclusions, verifying the effectiveness of the proposed method for adaptive extraction and evaluation of engine impact characteristics.

[0046] Table 2. Intake valve stem protrusion test results (unit: inch) The technical solution provided in this application combines the phase characteristics of the impact signal (such as the moment of action of a key component) and uses a sliding window to adaptively extract the working impact characteristics of each component (such as the vibration signal intercepted in step S2), thus overcoming the shortcomings of existing methods in terms of limited analysis range and inability to adaptively extract impact characteristics. Simultaneously, this application embodiment automatically calculates the average amplitude and average RMS value of the working impact signal of each component to construct impact characteristic values ​​(including the average amplitude a of the vibration signal from each channel). and average RMS value b The statistical histogram of the engine was used to achieve adaptive extraction and evaluation of vibration and impact characteristics of key engine components.

[0047] In at least one embodiment of this application, prior to step S1, the adaptive extraction and evaluation method for fault impact features of the reciprocating engine further includes step S10.

[0048] Step S10: Real-time acquisition of vibration signals from each cylinder of the reciprocating engine and crankshaft key phase signals, and storage of these signals in matrix U. M×N In the matrix U M×N The first M-1 rows of signals are all vibration signals, and the Mth row of signals are crankshaft key phase signals.

[0049] In at least one embodiment of this application, after step S1 and before step S2, the adaptive extraction and evaluation method for fault impact features of reciprocating engine further includes step S20.

[0050] Step S20: Extract the impact characteristics of a key component's operating moment in the reciprocating engine according to the analysis requirements, analyze and evaluate them, and obtain the corresponding phase angle θ at the operating moment of the key component. The operating moment of the key component includes the combustion moment, the intake valve opening moment, the intake valve closing moment, the exhaust valve opening moment, or the exhaust valve closing moment.

[0051] Specifically, the peak value and RMS value of the impact at a certain moment in the vibration signal of each cylinder are calculated, and the relationship between each cylinder and the average value is analyzed and evaluated. The phase angle is obtained by converting the time domain to the angular domain. In the multi-source angular domain envelope-operating characteristic joint graph analysis technology, the signal has been converted from the time domain to the angular domain, so the crankshaft rotation angle, i.e., the phase angle, has been obtained.

[0052] It should be noted that the phase angle of each key component's operation can be determined based on the engine's operating cycle characteristics. Impact characteristics are derived from the vibration signal U... M×N The characteristics of the peak value and RMS value are extracted, and then analyzed and evaluated based on the characteristics of the peak value and RMS value.

[0053] For example, the moment a critical component operates is the moment the intake valve closes. According to the analysis requirements, the impact characteristics of the moment the intake valve closes in a reciprocating engine are extracted for analysis and evaluation, and the corresponding phase angle is marked as θ=70°.

[0054] In at least one embodiment of this application, after step S1 and before step S2, the adaptive extraction and evaluation method for fault impact features of reciprocating engine further includes step S30.

[0055] Step S30: Obtain the step size, center position, and length of the sliding window W. Step size The center position is the phase angle θ, and the length is , The average sampling length over one period is given by the function `round`, which rounds the data to the nearest integer according to the rounding rules. The angular sampling interval is the range covered by the sliding window W in the angular domain. .

[0056] For example, design a sliding window W with a step size of... The center position is θ=70°, and the length is ,in: The average sampling length over one period is given by the function `round`, which rounds the data to the nearest integer according to the rounding rules. =20° is the range covered by the sliding window W in the angular domain, and the angular domain sampling interval is... .

[0057] In at least one embodiment of this application, the area covered by the sliding window W in the corner region during step S30 is... The value range is 15° to 25°. Therefore, if the value is below 15°, the sliding window may truncate impact information; if the value is above 25°, adjacent impacts may be easily mixed in. This is achieved by setting the coverage area of ​​the sliding window W in the angular domain. The value range is 15° to 25°, thereby reducing or avoiding the risk of the sliding window cutting off impact information and mixing in adjacent impacts.

[0058] In at least one embodiment of this application, steps S31 and S32 are a specific implementation of step S3.

[0059] Step S31: Calculate the matrix The amplitude and RMS value of each row of the signal are recorded in the matrix. and middle.

[0060] Step S32: Calculate the matrix and The mean of each row vector is used to obtain the average amplitude 'a' of the vibration signal in each channel. and average RMS value b , where: a b The function mean represents the average value. Indicates the channel number.

[0061] At least one embodiment of this application also provides a computer device, which includes a processor and a memory. The processor is used to execute the adaptive extraction and evaluation method for reciprocating engine fault impact features provided in any of the above embodiments of this application. The memory is used to store executable instructions of the processor, such as application programs. The number of processors can be one or more. The application programs stored in the memory can include one or more modules, each corresponding to a set of instructions. Furthermore, the processor is configured to execute instructions to perform the above-described adaptive extraction and evaluation method for reciprocating engine fault impact features.

[0062] The computer device may also include a power supply component configured for power management, a wired or wireless network interface configured to connect the computer device to a network, and an input / output (I / O) interface. The computer device can operate on an operating system stored in memory, such as Windows Server. TM Mac OSX TM Unix TM Linux TM FreeBSD TM Or similar.

[0063] At least one embodiment of this application also provides a computer-readable storage medium storing executable instructions for a computer. When executed by a processor, the executable instructions implement the adaptive extraction and evaluation method for fault impact features of a reciprocating engine provided in any of the above embodiments of this application.

[0064] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the computer device, enables the computer device to perform the adaptive extraction and evaluation method for reciprocating engine fault impact features. The adaptive extraction and evaluation method for reciprocating engine fault impact features is executed by a proxy program.

[0065] Those skilled in the art will recognize that the algorithmic steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0066] At least one embodiment of this application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the adaptive extraction and evaluation method for reciprocating engine fault impact features provided in any of the above embodiments of this application.

[0067] If the aforementioned functions are implemented as 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 this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a computer program product. This computer program product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the reciprocating engine fault impact feature adaptive extraction and evaluation method of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program verification codes, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0068] It should be noted that the combination of the technical features in the embodiments of this application is not limited to the combination methods described in the embodiments of this application or the combination methods described in specific embodiments. All technical features described in this application can be freely combined or combined in any way, unless there is a contradiction between them.

[0069] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the term "comprising" only indicates the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0070] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An adaptive extraction and evaluation method for fault impact features of a reciprocating engine, characterized in that, include: Step S1: Use multi-source angular domain envelope-operating characteristic joint analysis technology to process the vibration signals of each cylinder of the reciprocating engine and the crankshaft key phase signal acquired in real time, obtain the multi-source angular domain envelope-operating characteristic joint diagram after phase compensation, obtain the multi-channel vibration envelope signal from the multi-source angular domain envelope-operating characteristic joint diagram after phase compensation, and save the multi-channel vibration envelope signal into matrix Z'. Step S2: Traverse the first M-1 rows of data in matrix Z', and use a sliding window W to slide along the horizontal axis of matrix Z'. After sliding k times, the intercepted vibration signal is denoted as matrix S2. Where: k=1,2,3,…,R, R=floor(N / N) T The function `floor` represents rounding down, `M` represents the signal row number, and `N` represents the signal sampling length. T The average sampling length over one period; the step size of the sliding window W, ∆L = 2 × N T The center position is the phase angle θ corresponding to the moment a key component moves, and the length is L1 = round(∆θ / ∆φ). The function round indicates rounding according to the rounding rules. ∆θ is the range covered by the sliding window W in the angular domain, and the angular domain sampling interval ∆φ = 360° / N. T The timing of the operation of a key component includes any one of the following: the combustion timing, the intake valve opening timing, the intake valve closing timing, the exhaust valve opening timing, and the exhaust valve closing timing. Step S3: Based on the matrix The amplitude and RMS value of each line of signal are calculated, and the average amplitude a[i] and average RMS value b[i] of the vibration signal of each channel are calculated. The average amplitude a[i] is the mean of the amplitude of each line of signal, and the average RMS value b[i] is the mean of the RMS value of each line of signal; i is the line number of the vibration signal. Step S4: Based on the average amplitude a[i] and average RMS value b[i] of the vibration signal of each channel, calculate the overall average peak value β1 and the overall average RMS value β2 of each cylinder of the reciprocating engine, where β1=mean(a[i]) and β2=mean(b[i]), and the function mean represents taking the average value. Step S5: When a[i] is greater than β1 and b[i] is greater than β2, it is determined that a key component has a potential fault; otherwise, it is determined that a key component is in normal condition.

2. The adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to claim 1, characterized in that, Before step S1, the following is also included: Step S10: Real-time acquisition of vibration signals from each cylinder of the reciprocating engine and crankshaft key phase signals, and storage of these signals in matrix U. M×N In the matrix U M×N The first M-1 rows of signals are all vibration signals, and the Mth row of signals are crankshaft key phase signals.

3. The adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to claim 1, characterized in that, After step S1 and before step S2, it also includes: Step S20: Extract the impact characteristics of a key component in the reciprocating engine at the moment of its action according to the analysis requirements, and analyze and evaluate them to obtain the phase angle θ corresponding to the moment of action of the key component.

4. The adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to claim 1, characterized in that, After step S1 and before step S2, it also includes: Step S30: Obtain the step size, center position, and length of the sliding window W.

5. The adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to claim 1, characterized in that, In step S2, the range of ∆θ covered by the sliding window W in the angular domain is 15°~25°.

6. The adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine according to any one of claims 1 to 5, characterized in that, Step S3 includes: Step S31: Calculate the matrix The amplitude and RMS value of each row of the signal are recorded in the matrix. and middle; Step S32: Calculate the matrix and The mean of each row vector is used to obtain the average amplitude a[i] and average RMS value b[i] of the vibration signal of each channel, where: a[i]=mean(A[i,:]), b[i]=mean(B[i,:]), the function mean means to take the average value, and i represents the channel number.

7. A computer device, characterized in that, include: A processor for executing the adaptive extraction and evaluation method for fault impact features of a reciprocating engine according to any one of claims 1 to 6; as well as Memory for storing the executable instructions of the processor.

8. A computer-readable storage medium having executable instructions stored thereon, characterized in that, When the executable instructions are executed by the processor, they implement the adaptive extraction and evaluation method for fault impact features of a reciprocating engine as described in any one of claims 1 to 6.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the adaptive extraction and evaluation method for fault impact characteristics of a reciprocating engine as described in any one of claims 1 to 6.

Images