Double-acting spool valve acoustic monitoring method, device, readable storage medium and electronic equipment

Abstract

This invention provides an acoustic monitoring method, device, readable storage medium, and electronic device for a double-acting spool valve, belonging to the field of acoustic monitoring technology. The method includes: acquiring acoustic signals of the double-acting spool valve during a certain operating time; performing data preprocessing on the acoustic signals to obtain processed acoustic signals; determining the degree of damage to the double-acting spool valve during the operating time based on the processed acoustic signals; and determining the operating state of the double-acting spool valve during the operating time based on the degree of damage. The acoustic monitoring method for the double-acting spool valve of this invention has the advantage of accurately determining the operating state of the double-acting spool valve based on its degree of damage, thereby guiding the adjustment of process parameters and providing a basis for production operations, enabling the double-acting spool valve to maintain stable production.

Description

Technical Field

[0001] This invention relates to the field of acoustic monitoring technology, specifically to a method for acoustic monitoring of a double-acting slide valve, an acoustic monitoring device for a double-acting slide valve, a readable storage medium, and an electronic device. Background Technology

[0002] The double-acting slide valve in the regenerator regulates the valve opening and flue gas outlet flow through an actuator to control the regeneration pressure. Inside the valve are two valve plates that move in opposite directions. The opening degree controls the regenerator pressure, maintaining a stable pressure difference between the regenerator and the reactor. Its proper operation directly affects the safety and stability of the entire system. During operation, the double-acting slide valve is prone to guide rail bolt breakage, leading to guide rail detachment or tilting, valve plate separation, and valve stem bending deformation, causing unplanned shutdowns and seriously affecting safe production.

[0003] Currently, the diagnosis of double-acting spool valve malfunctions relies on the display panel to observe system faults. When a component malfunctions, the display panel will show alarm signals such as low oil pressure, motor overload, and high oil temperature. A low oil pressure alarm indicates the system is in a pressurization state; the alarm signal disappears when the system pressure reaches the set value. If the alarm persists, the pressurization system needs to be checked, with particular attention to the variable pump and oil circuit. A motor overload alarm indicates an abnormality in system pressure holding, requiring careful inspection of the accumulator, oil circuit, and other components for leaks. A high oil temperature alarm indicates the hydraulic oil temperature exceeds the normal range. Failure to cool it down promptly can lead to decreased oil viscosity, changes in oil quality, and, over time, aging of seals. Typically, the ideal oil temperature for hydraulic equipment is 35–60°C. When a high oil temperature alarm occurs, the cooling water lines should be checked for blockages. However, there is a lack of methods for monitoring double-acting spool valve bolt breakage, making it impossible to monitor the operating status of the double-acting spool valve. Summary of the Invention

[0004] The purpose of this invention is to provide an acoustic monitoring method for a double-acting spool valve, which solves the problem in the prior art that there is no method for monitoring bolt breakage faults in double-acting spool valves and therefore the operating status of double-acting spool valves cannot be monitored.

[0005] To achieve the above objectives, embodiments of the present invention provide an acoustic monitoring method for a dual-acting slide valve, the method comprising:

[0006] Acquire the acoustic signal of the double-acting slide valve during a certain operating time;

[0007] The acoustic signal is preprocessed to obtain the processed acoustic signal;

[0008] Based on the processed acoustic signals, the degree of damage to the double-acting slide valve during this operating period is determined.

[0009] Based on the degree of damage to the double-acting slide valve, the operating status of the double-acting slide valve during this operating period is determined.

[0010] Optionally, the acoustic signal includes ringing count parameters, energy parameters, and frequency parameters of the dual-acting slide valve during a certain operating time;

[0011] The acoustic signal is preprocessed to obtain a processed acoustic signal, including:

[0012] Acoustic signals with energy values ​​greater than a first energy threshold and peak frequencies greater than a first frequency threshold are defined as first valid signals.

[0013] The first effective signal is corrected using clustering algorithms, quartile method, Laida criterion and cross-validation to obtain the processed acoustic signal.

[0014] Optionally, the first effective signal is corrected using clustering algorithms, quartile methods, the Laida criterion, and cross-validation to obtain the processed acoustic signal, including:

[0015] The energy parameters of the first effective parameter are corrected using C-means clustering, quartile method, Laida criterion and K-fold cross-validation to obtain the second effective parameter;

[0016] The frequency parameters of the first effective parameter were corrected using the C-means clustering algorithm, quartile method, Laida criterion and K-fold cross-validation to obtain the third effective parameter;

[0017] The second effective parameter and the third effective parameter are used as the processed acoustic signal.

[0018] Optionally, the energy parameters of the first effective parameter are corrected using C-means clustering, quartile method, Laida criterion, and K-fold cross-validation to obtain the second effective parameter, including:

[0019] Using the C-means clustering algorithm, the energy parameters of the first effective parameter are classified to obtain a first class of energy parameters and a second class of energy parameters, wherein the energy value of each energy parameter in the first class of energy parameters is greater than the energy parameter with the largest energy value in the second class of energy parameters;

[0020] Based on the first type of energy parameters, the second energy threshold is determined using the quartile method;

[0021] Based on the energy parameters of the first effective parameter, the third energy threshold is determined using the Laida criterion;

[0022] Energy parameters with energy values ​​greater than the second and third energy thresholds in the first category of energy parameters are removed, and the remaining energy parameters are used as the first acoustic feature parameters.

[0023] The original acoustic signal corresponding to the second type of energy parameter is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining energy parameters, which are used as the second acoustic feature parameters.

[0024] The first acoustic feature parameter and the second acoustic feature parameter are used as the second effective parameter.

[0025] Optionally, the frequency parameters of the first effective parameter are corrected using C-means clustering, quartile method, Laida criterion, and K-fold cross-validation to obtain the third effective parameter, including:

[0026] Using the C-means clustering algorithm, the frequency parameters of the first effective parameter are classified to obtain a first class of frequency parameters and a second class of frequency parameters, wherein the peak frequency of each frequency parameter in the first class of frequency parameters is greater than the frequency parameter with the largest peak frequency in the second class of frequency parameters.

[0027] Based on the first type of frequency parameters, the second frequency threshold is determined using the quartile method;

[0028] Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion;

[0029] Eliminate the energy parameters in the first category of frequency parameters whose energy values ​​are greater than the second and third frequency thresholds, and use the remaining frequency parameters as the third acoustic signal;

[0030] The original acoustic signal corresponding to the second type of frequency parameters is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining frequency parameters, which are used as the fourth acoustic feature parameters.

[0031] The third acoustic feature parameter and the fourth acoustic feature parameter are used as the third effective parameter.

[0032] Optionally, based on the first type of energy parameters, a second energy threshold is determined using the quartile method, including:

[0033] All energy parameters in the first category of energy parameters are sorted in ascending order of energy value to form a box plot. The energy values ​​of the energy parameters at the 25th percentile of the box plot are taken as the upper quartiles, and the energy values ​​of the energy parameters at the 75th percentile of the box plot are taken as the lower quartiles.

[0034] The upper threshold value is calculated using the following formula and used as the second energy threshold:

[0035] E2 = Q3′ + 1.5(Q3′ - Q1′)

[0036] Where Q3′ is the upper quartile; Q1′ is the lower quartile;

[0037] Based on the energy parameters of the first effective parameter, the third energy threshold is determined using the Laida criterion, including:

[0038] Obtain the mean energy and standard deviation of all energy parameters in the first valid parameters;

[0039] The third energy threshold is calculated using the following formula:

[0040] E3=μ1+3σ1

[0041] Where E3 is the third energy threshold; μ1 is the energy mean of all energy parameters in the first effective parameters; and σ1 is the energy standard deviation of all energy parameters in the first effective parameters.

[0042] Optionally, based on the first type of frequency parameters, a second frequency threshold is determined using the quartile method, including:

[0043] All frequency parameters in the first category of frequency parameters are sorted in ascending order of peak frequency value to form a box plot. The peak frequency value of the frequency parameter located at 25% of the box plot is taken as the upper quartile, and the peak frequency value of the frequency parameter located at 75% of the box plot is taken as the lower quartile.

[0044] The upper threshold value is calculated using the following formula and used as the second frequency threshold:

[0045] f2 = Q3″ + 1.5(Q3″ - Q1″)

[0046] Where Q3″ is the upper quartile; Q1″ is the lower quartile;

[0047] Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion, including:

[0048] Obtain the mean peak frequency and standard deviation of peak frequency for all frequency parameters in the first valid parameters;

[0049] The third frequency threshold is calculated using the following formula:

[0050] f3=μ2+3σ2

[0051] Where f3 is the third frequency threshold; μ2 is the mean peak frequency of all frequency parameters in the first effective parameters; and σ2 is the standard deviation of the peak frequency of all frequency parameters in the first effective parameters.

[0052] Optionally, based on the processed acoustic signal, the degree of damage to the double-acting spool valve during this operating period can be determined, including:

[0053] Based on the processed acoustic signal, the crack length of the double-acting slide valve during this operating period is determined;

[0054] The degree of damage to the double-acting spool valve is determined based on the crack length.

[0055] Optionally, the crack length of the double-acting spool valve can be calculated using the following formula:

[0056]

[0057] Where a is the crack length; p is the fitting constant; C is the proportional constant; and N is the sum of the ringing count parameters in the processed acoustic signal.

[0058] Optionally, the degree of damage to the double-acting spool valve can be determined based on crack length, including:

[0059] If the crack length is less than or equal to the first preset value, then it is determined that the double-acting slide valve is undamaged during this operating period.

[0060] If the crack length is greater than the first preset value and less than or equal to the second preset threshold, the damage level of the double-acting slide valve during this operating period is determined to be low damage.

[0061] If the crack length is greater than the second preset value and less than or equal to the third preset threshold, the damage degree of the double-acting slide valve during this operating period is determined to be medium damage.

[0062] If the crack length is greater than the third preset value, the damage level of the double-acting slide valve during this operating period is determined to be high damage;

[0063] The first preset value is less than the second preset value, and the second preset value is less than the third preset value.

[0064] A second aspect of the present invention provides an acoustic monitoring device for a dual-acting slide valve, the device comprising:

[0065] The data acquisition module is used to acquire the acoustic signal of the double-acting slide valve during a certain operating time.

[0066] The data processing module is used to preprocess the acoustic signal to obtain the processed acoustic signal;

[0067] The damage determination module is used to determine the damage level of the double-acting slide valve during the operating time based on the processed acoustic signal.

[0068] The operating status determination module is used to determine the operating status of the double-acting spool valve during a certain operating time based on the degree of damage to the double-acting spool valve.

[0069] A third aspect of the present invention provides a machine-readable storage medium storing instructions that cause a machine to perform the acoustic monitoring method for a dual-acting slide valve described above.

[0070] On the other hand, the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described acoustic monitoring method for a dual-acting slide valve.

[0071] This technical solution acquires acoustic signals from the regenerator's double-acting slide valve over a certain operating period. The acoustic signals are then processed to ensure accuracy. Based on the processed signals, the degree of damage to the double-acting slide valve during that operating period is determined, thus establishing its operational status. This information guides the adjustment of the double-acting slide valve's process parameters, providing a basis for production operations and ensuring stable and safe production.

[0072] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0073] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0074] Figure 1 This is a flowchart of the acoustic monitoring method for a dual-acting slide valve provided by the present invention;

[0075] Figure 2 This is an overall principle block diagram of the acoustic monitoring method for dual-acting slide valves provided by the present invention;

[0076] Figure 3 This is a schematic diagram of the box plot division position provided by the present invention;

[0077] Figure 4 This is a schematic diagram of the acoustic monitoring device for the operating status of a catalytic cracking unit provided by the present invention.

[0078] Explanation of reference numerals in the attached figures

[0079] 10 - Data acquisition module; 20 - Data processing module;

[0080] 30 - Damage Determination Module; 40 - Operating Status Determination Module. Detailed Implementation

[0081] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0082] In the embodiments of the present invention, unless otherwise stated, directional terms such as "up," "down," "left," and "right" generally refer to the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use.

[0083] The terms “first,” “second,” “third,” etc., are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0084] The terms "parallel" and "perpendicular" do not mean that the components must be absolutely parallel or perpendicular, but rather that they can be slightly tilted. For example, "parallel" simply means that its direction is more parallel than "perpendicular," not that the structure must be completely parallel, but that it can be slightly tilted.

[0085] The terms "horizontal," "vertical," and "sag" do not imply that a component must be absolutely horizontal, vertical, or sagging, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," not that the structure must be completely horizontal, but can be slightly tilted.

[0086] Furthermore, terms like "roughly" and "basically" are used to indicate that the content does not require absolute precision, but rather allows for a certain degree of deviation. For example, "roughly equal" does not simply mean absolute equality; in actual production and operation, achieving absolute "equality" is difficult, and a certain degree of deviation is generally present. Therefore, besides absolute equality, "roughly equal to" also includes the aforementioned situation where a certain degree of deviation exists. Using this as an example, in other cases, unless otherwise specified, terms like "roughly" and "basically" have similar meanings.

[0087] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0088] Figure 1 This is a flowchart of the acoustic monitoring method for a dual-acting slide valve provided by the present invention; Figure 2 This is an overall principle block diagram of the acoustic monitoring method for dual-acting slide valves provided by the present invention; Figure 3 This is a schematic diagram of the box plot division position provided by the present invention; Figure 4 This is a schematic diagram of the acoustic monitoring device for the operating status of a catalytic cracking unit provided by the present invention.

[0089] Example 1

[0090] like Figure 1 As shown, this embodiment of the invention provides an acoustic monitoring method for a dual-acting slide valve, the method comprising:

[0091] Step 101: Acquire the acoustic signal of the double-acting slide valve during a certain operating time;

[0092] Step 102: Perform data preprocessing on the acoustic signal to obtain the processed acoustic signal;

[0093] Step 103: Based on the processed acoustic signal, determine the degree of damage to the double-acting slide valve during this operating period;

[0094] Step 104: Based on the degree of damage to the double-acting slide valve, determine the operating status of the double-acting slide valve during this operating period.

[0095] Specifically, a double-acting slide valve is installed in the regenerator of the catalytic cracking unit. This valve, through an actuator, adjusts the valve opening to regulate the flue gas outlet flow rate, thereby controlling the regeneration pressure. The valve contains two valve plates that move in opposite directions, controlling the regenerator pressure by adjusting the opening degree, maintaining a stable pressure difference between the regenerator and the reactor. Its normal operation directly affects the safety and stability of the entire unit. During operation, the double-acting slide valve is prone to guide rail bolt breakage, leading to guide rail detachment or tilting, valve plate disengagement, and valve stem bending deformation, causing unplanned shutdowns and seriously affecting safe production. Because the double-acting slide valve is located inside the regenerator, current technology lacks real-time monitoring methods for its operating status, thus failing to provide accurate guidance for subsequent processes such as feed rate. Therefore, this invention provides an acoustic monitoring method for a double-acting spool valve. First, the acoustic signal of the double-acting spool valve is acquired during a certain operating time. The acoustic signal is then preprocessed to obtain a processed acoustic signal. Based on the processed acoustic signal, the degree of damage to the double-acting spool valve during that operating time is determined. Based on the degree of damage to the double-acting spool valve, the operating state of the double-acting spool valve during that operating time is determined. The sensor is arranged at the extended end of the guide rail, and a waveguide rod can be added as needed.

[0096] Furthermore, the acoustic signals are the ringing count parameters, energy parameters, and frequency parameters of the double-acting slide valve during a certain operating time.

[0097] Specifically, in this embodiment, the damage and cracking signal of bolt fracture was found to be a high-frequency, high-energy burst signal with a peak frequency of 150-200kHz; the guide rail friction signal was a low-frequency, low-energy continuous signal with a peak frequency of ≤75kHz; the background noise signal was a low-frequency, low-energy signal with a certain regularity, which was submerged in the acoustic signal monitored during the normal operation of the slide valve; there may also be abnormal signals mixed in with the damage and cracking signal. Therefore, by including the ringing count parameter, energy parameter, and frequency parameter in the acoustic signal, it is easy to distinguish the damage and cracking of the double-acting slide valve during its operation, as these parameters have obvious characteristics.

[0098] Further, the acoustic signal is preprocessed to obtain a processed acoustic signal, including:

[0099] Acoustic signals with energy values ​​greater than a first energy threshold and peak frequencies greater than a first frequency threshold are defined as first valid signals.

[0100] The first effective signal is corrected using clustering algorithms, quartile method, Laida criterion and cross-validation to obtain the processed acoustic signal.

[0101] Specifically, by performing preliminary statistical analysis on the collected data, a suitable energy threshold can be obtained as the first energy threshold, and a suitable frequency threshold can be obtained as the first frequency threshold. The combination of the first energy threshold and the first frequency threshold can filter out the carpet background noise signal in the energy distribution. Because the settling tank generates strong background noise during production and is in a fully enclosed state, coupled with the influence of the waveguide rod on sound wave propagation, it is impossible to obtain the background noise signal and the valve cover opening / closing signal reflecting the flow state of the double-acting slide valve. If wavelet denoising is used, the wavelet node coefficients can only be set to the same value, which is equivalent to treating the noise as white noise with a certain energy and performing full-band noise reduction processing. Therefore, by performing statistical analysis on the collected signals, a suitable threshold is defined, which can filter out the carpet background noise signal in the energy distribution, achieving a filtering effect.

[0102] In this embodiment, for a certain dual-acting slide valve, the energy values ​​of all acquired acoustic signals are sorted in descending order, and the peak frequencies of all signals are sorted in descending order. There are 50 signals that meet the condition that the energy value is greater than a first energy threshold and the peak frequency is greater than a first frequency threshold. This allows background noise signals with energy values ​​lower than the first energy threshold to be filtered out. These 50 signals are determined as the first effective parameters. The first energy threshold and the first frequency threshold can adaptively separate the effective signals from the carpet-like background noise at the bottom under different environments, different acquisition parameters, and different sampling times.

[0103] Simultaneously, anomalous acoustic emission signals were removed using statistical and clustering methods. The energy value was 3.4838 × 10⁻⁶. -4 The signal belongs to an abnormal state signal, which can be regarded as being generated due to some unexpected impact during the production process. As a singular value, it is judged as an abnormal valid signal. In order to remove the influence of the singular value, clustering algorithm, quartile method, Laida criterion and cross-validation are used to correct the first valid signal to obtain the processed acoustic signal.

[0104] Furthermore, the first effective signal is corrected using clustering algorithms, quartile methods, the Laida criterion, and cross-validation to obtain the processed acoustic signal, including:

[0105] The energy parameters of the first effective parameter are corrected using C-means clustering, quartile method, Laida criterion and K-fold cross-validation to obtain the second effective parameter;

[0106] The frequency parameters of the first effective parameter were corrected using the C-means clustering algorithm, quartile method, Laida criterion and K-fold cross-validation to obtain the third effective parameter;

[0107] The second effective parameter and the third effective parameter are used as the processed acoustic signal.

[0108] Specifically, since the acoustic signal in this embodiment is the energy parameter and frequency parameter of the double-acting slide valve during a certain operating time, the data of the energy parameter and frequency parameter are corrected respectively to improve the accuracy of the data.

[0109] Furthermore, using C-means clustering, quartile method, Laida criterion, and K-fold cross-validation, the energy parameters of the first effective parameter are corrected to obtain the second effective parameter, including:

[0110] Using the C-means clustering algorithm, the energy parameters of the first effective parameter are classified to obtain a first class of energy parameters and a second class of energy parameters, wherein the energy value of each energy parameter in the first class of energy parameters is greater than the energy parameter with the largest energy value in the second class of energy parameters;

[0111] Based on the first type of energy parameters, the second energy threshold is determined using the quartile method;

[0112] Based on the energy parameters of the first effective parameter, the third energy threshold is determined using the Laida criterion;

[0113] Energy parameters with energy values ​​greater than the second and third energy thresholds in the first category of energy parameters are removed, and the remaining energy parameters are used as the first acoustic feature parameters.

[0114] The original acoustic signal corresponding to the second type of energy parameter is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining energy parameters, which are used as the second acoustic feature parameters.

[0115] The first acoustic feature parameter and the second acoustic feature parameter are used as the second effective parameter.

[0116] Specifically, taking a double-acting spool valve as an example: First, for the energy parameters of the 50 first effective parameters of the double-acting spool valve, the C-means clustering algorithm is used, set into two groups, automatically clustering the signals into high-energy and low-energy parts. The high-energy part corresponds to the first type of energy parameters, and the low-energy part corresponds to the second type of energy parameters. Since abnormal signals are generated by sudden events such as impact and crack propagation, and the energy values ​​are relatively large, abnormal signal detection is only performed on the high-energy clusters formed by C-means clustering. For the high-energy clusters formed by clustering, the quantiles of the high-energy cluster data are used to identify the outliers. All energy values ​​are arranged from smallest to largest and divided into four equal parts (rounded up if less than the minimum), and a box plot is drawn, as shown below. Figure 3As shown, the upper whisker value is determined in the box plot as the second energy threshold. When the energy value in a cluster is greater than the upper whisker value in the box plot, such data points can be considered as suspected outliers. Simultaneously, to avoid errors caused by the randomness of the C-means clustering algorithm, the Raida criterion in statistics is used to verify the outlier signals. Based on the energy parameters of the first effective parameter, the Raida criterion is used to determine the third energy threshold. Energy parameters in the first class of energy parameters whose energy values ​​are all greater than the second and third energy thresholds are identified as outliers and removed. The remaining energy parameters in the first class of energy parameters are used as the first acoustic feature parameters. The original acoustic signals corresponding to the second class of energy parameters are divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. Subsets with reconstruction errors greater than a set threshold after testing are deleted, resulting in the remaining energy parameters, which are used as the second acoustic feature parameters. Finally, the first and second acoustic feature parameters are used as the second effective parameters.

[0117] Similarly, a similar approach is used to process the data for frequency parameters, including:

[0118] Using C-means clustering, quartile method, Laida criterion, and K-fold cross-validation, the frequency parameters of the first effective parameter are corrected to obtain the third effective parameter, including:

[0119] Using the C-means clustering algorithm, the frequency parameters of the first effective parameter are classified to obtain a first class of frequency parameters and a second class of frequency parameters, wherein the peak frequency of each frequency parameter in the first class of frequency parameters is greater than the frequency parameter with the largest peak frequency in the second class of frequency parameters.

[0120] Based on the first type of frequency parameters, the second frequency threshold is determined using the quartile method;

[0121] Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion;

[0122] Eliminate the energy parameters in the first category of frequency parameters whose energy values ​​are greater than the second and third frequency thresholds, and use the remaining frequency parameters as the third acoustic feature parameters;

[0123] The original acoustic signal corresponding to the second type of frequency parameters is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining frequency parameters, which are used as the fourth acoustic feature parameters.

[0124] The third and fourth acoustic feature parameters are used as the third effective parameters.

[0125] Finally, the obtained second and third effective parameters are used as the processed acoustic signals. In order to ensure that the number of effective signals in each channel is the same, the number of signals m that are removed needs to be recorded, and the m signals with the largest energy values ​​in the background noise are selected to supplement the effective signals.

[0126] Furthermore, all energy parameters in the first category of energy parameters are sorted in ascending order of energy value to form a box plot. The energy values ​​of the energy parameters at the 25th percentile of the box plot are taken as the upper quartiles, and the energy values ​​of the energy parameters at the 75th percentile of the box plot are taken as the lower quartiles.

[0127] The upper threshold value is calculated using the following formula and used as the second energy threshold:

[0128] E2 = Q3′ + 1.5(Q3′ - Q1′)

[0129] Where Q3′ is the upper quartile; Q1′ is the lower quartile;

[0130] Based on the energy parameters of the first effective parameter, the third energy threshold is determined using the Laida criterion, including:

[0131] Obtain the mean energy and standard deviation of all energy parameters in the first valid parameters;

[0132] The third energy threshold is calculated using the following formula:

[0133] E3=μ1+3σ1

[0134] Where E3 is the third energy threshold; μ1 is the energy mean of all energy parameters in the first effective parameter; and σ1 is the energy standard deviation of all energy parameters in the first effective parameter.

[0135] Furthermore, the frequency parameters of the first effective parameter are classified using the C-means clustering algorithm to obtain a first class of frequency parameters and a second class of frequency parameters, wherein the peak frequency of each frequency parameter in the first class of frequency parameters is greater than the frequency parameter with the largest peak frequency in the second class of frequency parameters.

[0136] Based on the first type of frequency parameters, the second frequency threshold is determined using the quartile method;

[0137] Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion;

[0138] The frequency parameters that are greater than the second frequency threshold and the third frequency threshold in the first type of frequency parameters are used as the second valid parameters.

[0139] Furthermore, based on the first type of frequency parameters, the second frequency threshold is determined using the quartile method, including:

[0140] All frequency parameters in the first category of frequency parameters are sorted in ascending order of peak frequency value to form a box plot. The peak frequency value of the frequency parameter located at 25% of the box plot is taken as the upper quartile, and the peak frequency value of the frequency parameter located at 75% of the box plot is taken as the lower quartile.

[0141] The upper threshold value is calculated using the following formula and used as the second frequency threshold:

[0142] f2 = Q3″ + 1.5(Q3″ - Q1″)

[0143] Where Q3″ is the upper quartile; Q1″ is the lower quartile;

[0144] Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion, including:

[0145] Obtain the mean peak frequency and standard deviation of peak frequency for all frequency parameters in the first valid parameters;

[0146] The third frequency threshold is calculated using the following formula:

[0147] f3=μ2+3σ2

[0148] Where f3 is the third energy threshold; μ2 is the mean peak frequency of all frequency parameters in the first effective parameters; and σ2 is the standard deviation of the peak frequency of all frequency parameters in the first effective parameters.

[0149] Specifically, the processing steps for the first type of frequency parameter are the same as those for the first type of energy parameter, and will not be repeated here.

[0150] Furthermore, based on the processed acoustic signals, the degree of damage to the double-acting spool valve during this operating period is determined, including:

[0151] Based on the processed acoustic signal, the crack length of the double-acting slide valve during this operating period is determined;

[0152] The degree of damage to the double-acting spool valve is determined based on the crack length.

[0153] Furthermore, the crack length of the double-acting slide valve is calculated using the following formula:

[0154]

[0155] Where a is the crack length; p is the fitting constant (related to material properties and test conditions); C is the proportionality constant; and N is the sum of the ringing count parameters in the processed acoustic signal.

[0156] Furthermore, based on the crack length, the degree of damage to the double-acting spool valve is determined, including:

[0157] If the crack length is less than or equal to the first preset value, then it is determined that the double-acting slide valve is undamaged during this operating period.

[0158] If the crack length is greater than the first preset value and less than or equal to the second preset value, the damage level of the double-acting slide valve during this operating period is determined to be low damage.

[0159] If the crack length is greater than the second preset value and less than or equal to the third preset value, the damage level of the double-acting slide valve during this operating period is determined to be medium damage.

[0160] If the crack length is greater than the third preset value, the damage level of the double-acting slide valve during this operating period is determined to be high damage;

[0161] The first preset value is less than the second preset value, and the second preset value is less than the third preset value.

[0162] Specifically, if the damage to the double-acting spool valve is determined to be low, observation operation should be adopted. If the number of processed acoustic signals increases during the observation operation, the operation speed should be reduced. If an increasing trend is observed, work should be stopped immediately for maintenance. If the damage to the double-acting spool valve is determined to be medium, the operation speed should be reduced and maintenance should be carried out at an opportune time. If the number of processed acoustic signals increases during this process, work should be stopped immediately for maintenance as soon as an increasing trend is observed. If the damage to the double-acting spool valve is determined to be high, work should be stopped immediately for maintenance and a comprehensive overhaul of the double-acting spool valve should be carried out.

[0163] In another implementation, if the acoustic signal generating component is the same as the double-acting slide valve in working principle, the above-mentioned scheme can also be used for fault analysis, identification and diagnosis, so as to obtain the operating status of the component with the same working principle as the double-acting slide valve.

[0164] Example 2

[0165] like Figure 4 As shown, the present invention provides an acoustic monitoring device for a dual-acting slide valve, the device comprising:

[0166] The data acquisition module 10 is used to acquire the acoustic signal of the double-acting slide valve during a certain operating time.

[0167] Data processing module 20 is used to preprocess the acoustic signal to obtain the processed acoustic signal;

[0168] The damage determination module 30 is used to determine the damage degree of the double-acting slide valve during the operating time based on the processed acoustic signal.

[0169] The operating status determination module 40 is used to determine the operating status of the double-acting slide valve during the operating time period based on the degree of damage to the double-acting slide valve.

[0170] Example 3

[0171] The present invention provides a readable storage medium storing instructions for causing a machine to execute the acoustic monitoring method for a dual-acting slide valve described above.

[0172] Example 4

[0173] The present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described acoustic monitoring method for a dual-acting slide valve.

[0174] Example 5

[0175] In this embodiment, taking the No. 1 double-acting slide valve in a catalytic cracking unit as an example, the appropriate sampling parameters were determined as follows: a threshold value of 49 dB, a sampling point count of 4096, a peak positioning time (PDT) of 200, an end definition time (HDT) of 3800 μs, a system lock-up time of 300 μs, and a maximum duration of 1000 ms. Acoustic signal acquisition was performed on the double-acting slide valve. This channel continuously acquired data for 1928 seconds, collecting a total of 28324 acoustic emission signals.

[0176] The acquired parameters were cleaned, and abnormal acoustic emission signals were removed using statistical and clustering methods to obtain 50 first effective parameters. For these 50 first effective parameters, the C-means clustering algorithm (C-means) was used, with C=2, to automatically cluster the energy parameters of the first effective parameters into two parts: high energy (first type of energy parameters) and low energy (second type of energy parameters).

[0177] For the first type of energy parameters, all energy parameters in the first type are sorted by energy from smallest to largest to form a box plot. The upper threshold value is determined from the box plot and used as the second energy threshold. The Raida criterion in statistics is used to verify abnormal signals. Based on the energy parameters of the first effective parameter, the Raida criterion is used to determine the third energy threshold. The signal with the largest energy value in the background noise is selected as the effective parameter. Finally, the upper and lower threshold values ​​of the effective parameter energy for the No. 1 double-acting slide valve are 2.1237 × 10⁻⁶. -4 and 1.1577×10 -4 and will be located at 2.5493×10-4 and 1.3697×10 -4 The energy parameters between them are selected as the first acoustic characteristic parameters;

[0178] In addition, for the second type of energy parameters, the original acoustic signal corresponding to the second type of energy parameters is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining energy parameters, which are used as the second acoustic feature parameters.

[0179] Then, the first acoustic characteristic parameter and the second acoustic characteristic parameter are used as the second effective parameter.

[0180] Similarly, the acquired parameters are cleaned, and abnormal acoustic emission signals are removed using statistical and clustering methods to obtain 50 first effective parameters. For these 50 first effective parameters, the C-means clustering algorithm (C-means) is used, with C=2, to automatically cluster the frequency parameters of the first effective parameters into two parts: high energy (first type of frequency parameters) and low energy (second type of frequency parameters).

[0181] For the first type of frequency parameters, all frequency parameters in the first type are sorted by frequency from smallest to largest to form a box plot. The upper threshold value is determined from the box plot and used as the second frequency threshold. The Raida criterion in statistics is used to verify abnormal signals. Based on the frequency parameters of the first effective parameter, the Raida criterion is used to determine the third frequency threshold. The third frequency threshold is then obtained, and the signal with the highest energy value in the background noise is selected as an effective parameter. Finally, the upper and lower threshold values ​​of the effective parameter frequency for the No. 1 double-acting slide valve are 5.1577 × 10⁻⁶. 2 and 2.3171×10 2 and will be located at 5.3423×10 2 and 2.4622×10 2 The frequency parameters between them are selected as the third acoustic feature parameters;

[0182] The original acoustic signal corresponding to the second type of frequency parameters is then divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining frequency parameters, which are used as the fourth acoustic feature parameters.

[0183] The third and fourth acoustic characteristic parameters are used as the third effective parameters.

[0184] The second and third effective parameters are used as processed acoustic signals and subsequently used to determine the degree of damage, thereby obtaining the operating status of the double-acting slide valve during this period.

[0185] Example 6

[0186] To verify the effectiveness of damage monitoring for double-acting spool valves, 1200 sets of acoustic signals were collected. This proposed method and conventional recognition models were used to identify bolt fracture (400 sets), guide rail friction (400 sets), and noise signals (400 sets). Compared to conventional recognition models, such as the CNN model (86.50% accuracy) and the empirical database matching model (74.58% accuracy), the model in this proposed method achieved an accuracy of 97.08%.

[0187] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention.

[0188] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not describe the various possible combinations separately.

[0189] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0190] Furthermore, various different implementations of the present invention can be combined arbitrarily, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed in the present invention.

Claims

1. A dual-acting spool valve acoustic monitoring method, characterized by, The method includes: Acquire the acoustic signal of the double-acting slide valve during a certain operating time; The acoustic signal is preprocessed to obtain the processed acoustic signal; Based on the processed acoustic signals, the degree of damage to the double-acting slide valve during this operating period is determined. Based on the degree of damage to the double-acting slide valve, the operating status of the double-acting slide valve during this operating period is determined.

2. The method of claim 1, wherein, The acoustic signals include the ringing count parameters, energy parameters, and frequency parameters of the double-acting slide valve during a certain operating time; The acoustic signal is preprocessed to obtain a processed acoustic signal, including: Acoustic signals with energy values ​​greater than a first energy threshold and peak frequencies greater than a first frequency threshold are defined as first valid signals. The first effective signal is corrected using clustering algorithms, quartile method, Laida criterion and cross-validation to obtain the processed acoustic signal.

3. The method of claim 2, wherein, Using clustering algorithms, quartile method, Laida criterion, and cross-validation, the first effective signal is corrected to obtain the processed acoustic signal, including: The energy parameters of the first effective parameter are corrected using C-means clustering, quartile method, Laida criterion and K-fold cross-validation to obtain the second effective parameter; The frequency parameters of the first effective parameter were corrected using the C-means clustering algorithm, quartile method, Laida criterion and K-fold cross-validation to obtain the third effective parameter; The second effective parameter and the third effective parameter are used as the processed acoustic signal.

4. The method of claim 3, wherein, Using C-means clustering, quartile method, Laida criterion, and K-fold cross-validation, the energy parameters of the first effective parameter are corrected to obtain the second effective parameter, including: Using the C-means clustering algorithm, the energy parameters of the first effective parameter are classified to obtain a first class of energy parameters and a second class of energy parameters, wherein the energy value of each energy parameter in the first class of energy parameters is greater than the energy parameter with the largest energy value in the second class of energy parameters; Based on the first type of energy parameters, the second energy threshold is determined using the quartile method; Based on the energy parameters of the first effective parameter, the third energy threshold is determined using the Laida criterion; Energy parameters with energy values ​​greater than the second and third energy thresholds in the first category of energy parameters are removed, and the remaining energy parameters are used as the first acoustic feature parameters. The original acoustic signal corresponding to the second type of energy parameter is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining energy parameters, which are used as the second acoustic feature parameters. The first acoustic feature parameter and the second acoustic feature parameter are used as the second effective parameter.

5. The method of claim 3, wherein, Using C-means clustering, quartile method, Laida criterion, and K-fold cross-validation, the frequency parameters of the first effective parameter are corrected to obtain the third effective parameter, including: Using the C-means clustering algorithm, the frequency parameters of the first effective parameter are classified to obtain a first class of frequency parameters and a second class of frequency parameters, wherein the peak frequency of each frequency parameter in the first class of frequency parameters is greater than the frequency parameter with the largest peak frequency in the second class of frequency parameters. Based on the first type of frequency parameters, the second frequency threshold is determined using the quartile method; Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion; Eliminate the energy parameters in the first category of frequency parameters whose energy values ​​are greater than the second and third frequency thresholds, and use the remaining frequency parameters as the third acoustic feature parameters; The original acoustic signal corresponding to the second type of frequency parameters is divided into K subsets. Based on K-fold cross-validation, an autoencoder is used for training and testing. The subsets with reconstruction errors greater than a set threshold after testing are deleted to obtain the remaining frequency parameters, which are used as the fourth acoustic feature parameters. The third acoustic feature parameter and the fourth acoustic feature parameter are used as the third effective parameter.

6. The method according to claim 4, characterized in that, Based on the first type of energy parameters, the second energy threshold is determined using the quartile method, including: All energy parameters in the first category of energy parameters are sorted in ascending order of energy value to form a box plot. The energy values ​​of the energy parameters at the 25th percentile of the box plot are taken as the upper quartiles, and the energy values ​​of the energy parameters at the 75th percentile of the box plot are taken as the lower quartiles. The upper threshold value is calculated using the following formula and used as the second energy threshold: E2 = Q3′ + 1.5(Q3′ - Q1′) Where Q3′ is the upper quartile; Q1′ is the lower quartile; Based on the energy parameters of the first effective parameter, the third energy threshold is determined using the Laida criterion, including: Obtain the mean energy and standard deviation of all energy parameters in the first valid parameters; The third energy threshold is calculated using the following formula: E3=μ1+3σ1 Where E3 is the third energy threshold; μ1 is the energy mean of all energy parameters in the first effective parameters; and σ1 is the energy standard deviation of all energy parameters in the first effective parameters.

7. The method according to claim 5, characterized in that, Based on the first type of frequency parameters, the second frequency threshold is determined using the quartile method, including: All frequency parameters in the first category of frequency parameters are sorted in ascending order of peak frequency value to form a box plot. The peak frequency value of the frequency parameter located at 25% of the box plot is taken as the upper quartile, and the peak frequency value of the frequency parameter located at 75% of the box plot is taken as the lower quartile. The upper threshold value is calculated using the following formula and used as the second frequency threshold: f2 = Q3″ + 1.5(Q3″ - Q1″) Where Q3″ is the upper quartile; Q1″ is the lower quartile; Based on the frequency parameter of the first effective parameter, the third frequency threshold is determined using the Raida criterion, including: Obtain the mean peak frequency and standard deviation of peak frequency for all frequency parameters in the first valid parameters; The third frequency threshold is calculated using the following formula: f3=μ2+3σ2 Where f3 is the third frequency threshold; μ2 is the mean peak frequency of all frequency parameters in the first effective parameters; and σ2 is the standard deviation of the peak frequency of all frequency parameters in the first effective parameters.

8. The method according to claim 1, characterized in that, Based on the processed acoustic signals, the degree of damage to the double-acting spool valve during this operating period is determined, including: Based on the processed acoustic signal, the crack length of the double-acting slide valve during this operating period is determined; The degree of damage to the double-acting spool valve is determined based on the crack length.

9. The method according to claim 8, characterized in that, The crack length of the double-acting spool valve is calculated using the following formula: Where a is the crack length; p is the fitting constant; C is the proportional constant; and N is the sum of the ringing count parameters in the processed acoustic signal.

10. The method according to claim 8, characterized in that, The degree of damage to the double-acting spool valve is determined based on crack length, including: If the crack length is less than or equal to the first preset value, then it is determined that the double-acting slide valve is undamaged during this operating period. If the crack length is greater than the first preset value and less than or equal to the second preset value, the damage level of the double-acting slide valve during this operating period is determined to be low damage. If the crack length is greater than the second preset value and less than or equal to the third preset value, the damage level of the double-acting slide valve during this operating period is determined to be medium damage. If the crack length is greater than the third preset value, the damage level of the double-acting slide valve during this operating period is determined to be high damage; The first preset value is less than the second preset value, and the second preset value is less than the third preset value.

11. An acoustic monitoring device for a double-acting slide valve, characterized in that, The device includes: The data acquisition module is used to acquire the acoustic signal of the double-acting slide valve during a certain operating time. The data processing module is used to preprocess the acoustic signal to obtain the processed acoustic signal; The damage determination module is used to determine the damage level of the double-acting slide valve during the operating time based on the processed acoustic signal. The operating status determination module is used to determine the operating status of the double-acting spool valve during a certain operating time based on the degree of damage to the double-acting spool valve.

12. A readable storage medium storing instructions for causing a machine to perform the acoustic monitoring method for a dual-acting slide valve as described in any one of claims 1-10.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the acoustic monitoring method for a dual-acting slide valve as described in any one of claims 1-10.

Images