A method for predicting dust accumulation trend of rotating machinery blades based on PCFC algorithm

Abstract

The application discloses a rotating machinery blade dust accumulation trend prediction method based on a PCFC algorithm, relates to the field of mechanical equipment, and solves the problem of poor prediction effect of the rotating machinery blade dust accumulation trend prediction method, and comprises the following steps: S1, vibration monitoring is performed on the rotating machinery blade in each historical monitoring period, and blade vibration monitoring values corresponding to each historical monitoring period are acquired to obtain blade vibration monitoring data; S2, blade dust accumulation monitoring is performed on the rotating machinery blade in each historical monitoring period, blade dust accumulation index values corresponding to each historical monitoring period are acquired according to monitoring results to obtain blade dust accumulation monitoring data; and S3, real-time dust accumulation prediction is performed on the rotating machinery blade according to the blade dust accumulation monitoring data and the blade vibration monitoring data, and dust accumulation early warning is issued according to a prediction result, and the application improves the accuracy of the rotating machinery blade dust accumulation trend prediction result.

Description

Technical Field

[0001] This invention belongs to the field of machinery and relates to image recognition technology, specifically a method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm. Background Technology

[0002] Existing methods for early warning of dust accumulation on rotating machinery blades have the following specific shortcomings when monitoring dust accumulation on rotating machinery blades:

[0003] 1. Existing methods for early warning of dust accumulation on rotating machinery blades require the installation of high-precision probes and the combination of spectrum analysis to determine the vibration type, which increases equipment maintenance costs and exacerbates the business burden on enterprises.

[0004] 2. Existing methods for early warning of dust accumulation on rotating machinery blades cannot predict dust accumulation on rotating machinery blades in real time based on historical dust accumulation monitoring data and blade vibration monitoring data, and cannot issue dust accumulation warnings based on the prediction results, resulting in a lag in the warning process.

[0005] To address this, we propose a method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm. Summary of the Invention

[0006] To address the shortcomings of existing technologies, the purpose of this invention is to provide a method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm. This invention aims to improve the timeliness of dust accumulation early warning for rotating machinery blades and reduce equipment operation and maintenance costs.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm, comprising the following specific steps:

[0008] Step S1: Obtain historical vibration data of rotating machinery blades, select several historical monitoring periods from the obtained historical vibration data of rotating machinery blades, perform vibration monitoring on rotating machinery blades in each historical monitoring period, and obtain the blade vibration monitoring value corresponding to each historical monitoring period to obtain blade vibration monitoring data.

[0009] Step S2: Based on the blade vibration monitoring data, perform blade dust accumulation monitoring on the rotating machinery blades during each historical monitoring period, obtain the blade dust accumulation index value corresponding to each historical monitoring period based on the monitoring results, and obtain blade dust accumulation monitoring data.

[0010] Step S3: Based on the blade dust accumulation monitoring data and blade vibration monitoring data, perform real-time dust accumulation prediction on the rotating machinery blades, and issue dust accumulation warnings based on the prediction results.

[0011] Furthermore, step S1 also includes the following specific steps:

[0012] Step S11: Acquire the blade vibration monitoring data corresponding to the rotating machinery blade to obtain the historical vibration data of the rotating machinery blade, and mark it as a blade vibration history cycle based on the historical vibration data of the rotating machinery blade;

[0013] Step S12: Divide the blade vibration history period into several historical monitoring periods, and mark the divided historical monitoring periods as L1 historical monitoring period to La historical monitoring period in chronological order;

[0014] Step S13: Monitor the historical vibration index of the rotating machinery blades during the L1 historical monitoring period, obtain the blade vibration monitoring value corresponding to the L1 historical monitoring period based on the monitoring results, and name it the L1 blade vibration monitoring value.

[0015] Step S14: Obtain the vibration monitoring values ​​of blades L2 to La respectively;

[0016] Step S15: Define the blade vibration monitoring values ​​from L1 to La and the historical monitoring period from L1 to La as blade vibration monitoring data.

[0017] Furthermore, step S13 also includes the following specific steps:

[0018] Step S131: Divide the historical monitoring period of L1 into several consecutive blade vibration time points, and mark the marked blade vibration time points in chronological order as Z1 blade vibration time point to Zb blade vibration time point.

[0019] Step S132: Obtain the blade vibration values ​​corresponding to the vibration time points from Z1 to Zb of the rotating mechanical blades using vibration sensors, and obtain the vibration values ​​from Z1 to Zb.

[0020] Step S133: Create a line graph of blade vibration time periods using the vibration values ​​of blade Z1 to blade Zb and the vibration time points of blade Z1 to blade Zb.

[0021] Furthermore, step S13 also includes the following specific steps:

[0022] Step S134: In the line graph of the blade vibration period, mark the maximum vertical axis value as the first blade vibration peak value, mark the vertical axis value that is only less than the first blade vibration peak value as the second blade vibration peak value, mark the minimum vertical axis value as the first blade vibration valley value, and mark the vertical axis value that is only greater than the first blade vibration valley value as the second blade vibration valley value.

[0023] Step S135: Calculate the average value of the vibration values ​​of blade Z1 to blade Zb to obtain the average vibration value for the time period;

[0024] Step S136: Calculate the vibration monitoring value of blade L1 by taking the vibration peak value of the first blade, the vibration peak value of the second blade, the vibration trough value of the first blade, the vibration trough value of the second blade, and the average vibration value over the time period.

[0025] The vibration monitoring values ​​of L1 blade were calculated.

[0026] Furthermore, step S133 also includes the following specific steps:

[0027] In the existing Cartesian coordinate system, a Cartesian coordinate system for blade vibration is created by taking the time point of blade vibration as the abscissa and the blade vibration value as the ordinate.

[0028] In the rectangular coordinate system of the blade vibration plane, the coordinate point with the vibration time point of blade Z1 as the abscissa and the vibration value of blade Z1 as the ordinate is marked as the Z1 vibration coordinate point. The coordinate point with the vibration time point of blade Z2 as the abscissa and the vibration value of blade Z2 as the ordinate is marked as the Z2 vibration coordinate point. And so on, the coordinate point with the vibration time point of blade Zb as the abscissa and the vibration value of blade Zb as the ordinate is marked as the Zb vibration coordinate point. Connecting the vibration coordinate points from Z1 to Zb in sequence, we obtain a line graph of the blade vibration period.

[0029] Furthermore, step S2 also includes the following specific steps:

[0030] Step S21: Obtain leaf dust accumulation monitoring data, and obtain historical monitoring periods from L1 to La based on the leaf dust accumulation monitoring data;

[0031] Step S22: Acquire frontal images of the rotating machinery blades during the L1 historical monitoring period to the La historical monitoring period to obtain frontal images of the blades during the L1 period to the La period.

[0032] Step S23: Acquire side images of the rotating machinery blades during the L1 historical monitoring period to the La historical monitoring period to obtain the side images of the blades during the L1 period to the La period.

[0033] Step S24: Analyze the area of ​​dust accumulation on the front image of the leaf during time period L1, and obtain the dust ratio of the front area of ​​the L1 leaf based on the analysis results;

[0034] Step S25: Perform ash accumulation area analysis on the frontal images of the leaves from L2 time period to La time period to obtain the ash ratio of the frontal area of ​​the leaves from L2 to La time period.

[0035] Step S26: Analyze the ash accumulation thickness of the blade side image in time period L1, and obtain the ash accumulation thickness of the blade side in time period L1 based on the analysis results;

[0036] Step S27: Analyze the ash accumulation thickness of the blade side images from L2 time period to La time period to obtain the ash accumulation thickness of the blade side image from L2 time period to La time period.

[0037] Step S28: Calculate the product of the side surface dust thickness of L1 blade and the front surface dust ratio of L1 blade to obtain the dust accumulation index value of L1 blade. Calculate the product of the side surface dust thickness of L2 blade and the front surface dust ratio of L2 blade to obtain the dust accumulation index value of L2 blade. And so on, calculate the product of the side surface dust thickness of La blade and the front surface dust ratio of La blade to obtain the dust accumulation index value of La blade.

[0038] Step S29: Define the L1 leaf ash accumulation index value to the La leaf ash accumulation index value as leaf ash accumulation monitoring data.

[0039] Furthermore, step S24 also includes the following specific steps:

[0040] The frontal image of the leaf during the L1 time period is acquired. An image recognition algorithm is used to identify the dusty areas in the frontal image of the leaf during the L1 time period to obtain the first image feature region. The non-dusty areas in the frontal image of the leaf during the L1 time period are marked as the second image feature region.

[0041] The area values ​​of the first image feature region and the second image feature region are obtained respectively.

[0042] The area gray ratio of leaf L1 is obtained by calculating the area values ​​of the first and second image regions.

[0043] The surface area ash ratio of L1 blade is calculated.

[0044] Furthermore, step S26 also includes the following specific steps:

[0045] Image recognition algorithms were used to identify the blade edges in the side images of the blades during the L1 time period. Several edge feature points were selected from the blade edges, and one sample edge feature point was randomly selected from the multiple edge feature points obtained.

[0046] Draw a straight line perpendicular to the blade edge through the sample edge feature point to obtain the blade side marking line. Identify the dust accumulation area in the blade side marking line to obtain the dust accumulation area of ​​the marking line. Obtain the length value of the line segment area occupied by the dust accumulation area of ​​the marking line in the blade side marking line to obtain the dust accumulation thickness value of the area corresponding to the sample edge feature point.

[0047] The ash thickness value of the region corresponding to each edge feature point is obtained, and the average value of the obtained ash thickness values ​​of multiple regions is calculated to obtain the ash thickness of the L1 blade side.

[0048] Furthermore, step S3 also includes the following specific steps:

[0049] Step S31: Obtain blade vibration monitoring data, and obtain the L1 blade vibration monitoring value to the La blade vibration monitoring value based on the blade vibration monitoring data;

[0050] Step S32: Obtain leaf dust accumulation monitoring data, and obtain the L1 leaf dust accumulation index value to the La leaf dust accumulation index value based on the leaf dust accumulation monitoring data;

[0051] Step S33: Perform polynomial fitting based on the vibration monitoring values ​​of L1 blade to La blade and the dust accumulation index values ​​of L1 blade to La blade, and create a dust accumulation prediction model based on the fitting results.

[0052] Step S34: Mark the time point corresponding to the current moment as the end time point of the time period to mark a real-time prediction period for blade dust accumulation, and obtain the blade vibration monitoring value corresponding to the real-time prediction period for blade dust accumulation to obtain the real-time blade vibration monitoring value. Substitute the real-time blade vibration monitoring value into the dust accumulation prediction model, obtain the blade dust accumulation index value output by the dust accumulation prediction model, and obtain the real-time blade dust accumulation index value.

[0053] Step S35: Obtain the benchmark range of leaf dust accumulation index. If the real-time leaf dust accumulation index value is within the benchmark range, there is no need to issue a leaf dust removal warning. If the real-time leaf dust accumulation index value is not within the benchmark range, then issue a leaf dust removal warning.

[0054] Furthermore, step S33 also includes the following specific steps:

[0055] A polynomial fitting function was established to compare the vibration monitoring values ​​of L1 blade with those of La blade and the dust accumulation index values ​​of L1 blade with those of La blade.

[0056] Substitute the vibration monitoring values ​​of L1 blade to La blade and the dust accumulation index values ​​of L1 blade to La blade into the polynomial fitting function respectively to calculate the residual sum of squares (RSS) function of the dust accumulation index values ​​of the blades.

[0057] The coefficients a0 to a10 of the polynomial fitting function in the residual sum of squares (RSS) function are respectively... n By taking partial derivatives, we obtain n unknowns a0 to a10. n The function expression, and n unknowns a0 to a n By combining the function expressions, we obtain n sets containing a0 to a n The system of equations is obtained, and the system of equations is solved to obtain a0 to a n The specific value;

[0058] From a0 to a n The specific numerical values ​​are substituted back into the polynomial fitting function to obtain the ash accumulation prediction model.

[0059] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0060] 1. This invention creates a dust accumulation prediction model by analyzing historical data to provide early warning of dust accumulation in mechanical equipment. It eliminates the need to use multiple high-precision probes to analyze blade vibration spectrum data, thus efficiently saving equipment operation and maintenance costs.

[0061] 2. This invention uses historical blade dust accumulation monitoring data and blade vibration monitoring data to predict dust accumulation on rotating machinery blades in real time, and issues dust accumulation warnings based on the prediction results, thereby improving the timeliness of the warning process. Attached Figure Description

[0062] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0063] Figure 1 This is a diagram illustrating the implementation steps of the present invention;

[0064] Figure 2 This is a line graph showing the vibration period of the blade in this invention. Detailed Implementation

[0065] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0066] Example 1

[0067] Please see Figure 1 The blade dust accumulation monitoring device of this invention belongs to image recognition technology in computer vision. A technical solution is provided: a method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm, comprising the following specific steps:

[0068] Step S1: Obtain historical vibration data of rotating machinery blades, select several historical monitoring periods from the obtained historical vibration data of rotating machinery blades, perform vibration monitoring on rotating machinery blades in each historical monitoring period, and obtain the blade vibration monitoring value corresponding to each historical monitoring period to obtain blade vibration monitoring data.

[0069] Step S1 further includes the following specific steps:

[0070] The vibration monitoring data of the rotating machinery blades is acquired to obtain the historical vibration data of the rotating machinery blades, and the historical vibration data of the rotating machinery blades is marked as a blade vibration history cycle.

[0071] It should be noted here that:

[0072] In this application, the duration of the blade vibration history cycle referred to herein is specifically three months.

[0073] The blade vibration history period was divided into several historical monitoring periods, and these historical monitoring periods were marked in chronological order as L1 historical monitoring period to La historical monitoring period;

[0074] It should be noted here that:

[0075] In this application, L refers to the symbol corresponding to the historical monitoring period, and a refers to the quantity value corresponding to the historical monitoring period, and a is an integer greater than 0.

[0076] In this application, the durations corresponding to the historical monitoring periods from L1 to La are equal, and each duration is 24 hours.

[0077] Historical vibration index monitoring was conducted on rotating machinery blades during the L1 historical monitoring period. Based on the monitoring results, the blade vibration monitoring value corresponding to the L1 historical monitoring period was obtained and named the L1 blade vibration monitoring value.

[0078] Specifically as follows:

[0079] The historical monitoring period of L1 was divided into several consecutive blade vibration time points, and the marked blade vibration time points were marked in chronological order as Z1 blade vibration time point to Zb blade vibration time point.

[0080] It should be noted here that:

[0081] In this application, Z is the symbol corresponding to the blade vibration time point, b is the quantity value corresponding to the blade vibration time point, and b is an integer greater than 0.

[0082] The vibration values ​​of the rotating mechanical blades at vibration time points Z1 to Zb are obtained by using vibration sensors.

[0083] In the existing Cartesian coordinate system, a Cartesian coordinate system for blade vibration is created by taking the time point of blade vibration as the abscissa and the blade vibration value as the ordinate.

[0084] Please see Figure 2 In the rectangular coordinate system of the blade vibration plane, the coordinate point with the vibration time point of blade Z1 as the abscissa and the vibration value of blade Z1 as the ordinate is marked as the Z1 vibration coordinate point. The coordinate point with the vibration time point of blade Z2 as the abscissa and the vibration value of blade Z2 as the ordinate is marked as the Z2 vibration coordinate point. And so on, the coordinate point with the vibration time point of blade Zb as the abscissa and the vibration value of blade Zb as the ordinate is marked as the Zb vibration coordinate point. Connecting the vibration coordinate points from Z1 to Zb in sequence, we get a line graph of the blade vibration period.

[0085] In the line graph of the blade vibration period, the maximum vertical axis value is marked as the first blade vibration peak value, the vertical axis value that is only less than the first blade vibration peak value is marked as the second blade vibration peak value, the minimum vertical axis value is marked as the first blade vibration valley value, and the vertical axis value that is only greater than the first blade vibration valley value is marked as the second blade vibration valley value.

[0086] It should be noted here that:

[0087] In this application, the vibration values ​​referred to herein are specifically vibration frequency values.

[0088] The average vibration values ​​of blade Z1 to blade Zb are calculated to obtain the average vibration value for the time period.

[0089] The vibration monitoring value of blade L1 is obtained by calculating the peak vibration value of the first blade, the peak vibration value of the second blade, the trough vibration value of the first blade, the trough vibration value of the second blade, and the average vibration value over a period of time.

[0090] The vibration monitoring values ​​of blade L1 are calculated using the following formula:

[0091] ;

[0092] Wherein, Zjl1 is the vibration monitoring value of L1 blade, Zf1 is the vibration peak value of the first blade, Zf2 is the vibration peak value of the second blade, Zg1 is the vibration valley value of the first blade, Zg2 is the vibration valley value of the second blade, and Zzp is the average vibration value over the period.

[0093] Repeat the process of acquiring the blade vibration monitoring values ​​corresponding to the historical monitoring period of L1, and acquire the blade vibration monitoring values ​​from L2 to La respectively;

[0094] The blade vibration monitoring values ​​from L1 to La, and the historical monitoring period from L1 to La, are defined as blade vibration monitoring data.

[0095] Step S2: Based on the blade vibration monitoring data, perform blade dust accumulation monitoring on the rotating machinery blades during each historical monitoring period, obtain the blade dust accumulation index value corresponding to each historical monitoring period based on the monitoring results, and obtain blade dust accumulation monitoring data.

[0096] Step S2 further includes the following specific steps:

[0097] Acquire leaf dust accumulation monitoring data, and obtain historical monitoring periods from L1 to La based on the leaf dust accumulation monitoring data;

[0098] Frontal images of rotating machinery blades from the L1 historical monitoring period to the La historical monitoring period were acquired, resulting in frontal images of the blades from the L1 period to the La period.

[0099] Side images of rotating machinery blades during historical monitoring periods L1 to La were acquired, resulting in side images of the blades during periods L1 to La.

[0100] It should be noted here that:

[0101] In this application, the frontal images of the leaves from L1 to La are all frontal images of the leaves collected from the historical monitoring period of L1 to the end of the historical monitoring period of La, and the frontal images of the leaves from L1 to La are all side images of the leaves collected from the historical monitoring period of L1 to the end of the historical monitoring period of La.

[0102] In this application, the image shooting parameters corresponding to the frontal image of the blade in the L1 time period to the frontal image of the blade in the La time period are the same, and the image shooting parameters corresponding to the side image of the blade in the L1 time period to the side image of the blade in the La time period are the same. The image shooting parameters involved here include, but are not limited to, shooting angle, shooting focal length and image resolution.

[0103] The area of ​​ash accumulation on the front images of the leaves in the L1 time period was analyzed, and the ash ratio of the front area of ​​the L1 leaves was obtained based on the analysis results.

[0104] Specifically as follows:

[0105] The frontal image of the leaf during the L1 time period is acquired. An image recognition algorithm is used to identify the dusty areas in the frontal image of the leaf during the L1 time period to obtain the first image feature region. The non-dusty areas in the frontal image of the leaf during the L1 time period are marked as the second image feature region.

[0106] The area values ​​of the first image feature region and the second image feature region are obtained respectively.

[0107] The area gray ratio of leaf L1 is obtained by calculating the area values ​​of the first and second image regions.

[0108] The specific formula for calculating the surface dust ratio of the L1 blade is as follows:

[0109] ;

[0110] Where Jmb1 is the gray ratio of the positive area of ​​L1 leaf, Mj1 is the area value of the first image region, and Mj2 is the area value of the second image region.

[0111] Repeat the process of obtaining the gray area ratio of the front area of ​​L1 leaf, and perform gray area analysis on the front images of the front of the leaf from L2 time period to La time period to obtain the gray area ratio of the front area of ​​L2 leaf to La leaf.

[0112] The dust accumulation thickness of the blade side image in time L1 was analyzed, and the dust accumulation thickness of the L1 blade side was obtained based on the analysis results.

[0113] Specifically as follows:

[0114] Image recognition algorithms were used to identify the blade edges in the side images of the blades during the L1 time period. Several edge feature points were selected from the blade edges, and one sample edge feature point was randomly selected from the multiple edge feature points obtained.

[0115] Draw a straight line perpendicular to the blade edge through the sample edge feature point to obtain the blade side marking line. Identify the dust accumulation area in the blade side marking line to obtain the dust accumulation area of ​​the marking line. Obtain the length value of the line segment area occupied by the dust accumulation area of ​​the marking line in the blade side marking line to obtain the dust accumulation thickness value of the area corresponding to the sample edge feature point.

[0116] Repeat the process of obtaining the ash thickness value of the area corresponding to the sample edge feature point, obtain the ash thickness value of the area corresponding to each edge feature point, and calculate the average value of the obtained ash thickness values ​​of multiple areas to obtain the ash thickness of the L1 blade side.

[0117] Repeat the process of obtaining the ash accumulation thickness on the side of the L1 blade, and analyze the ash accumulation thickness on the side images of the blade from the L2 time period to the La time period to obtain the ash accumulation thickness on the side of the L2 blade to the La blade.

[0118] Calculate the product of the ash thickness on the side surface of blade L1 and the ash ratio on the front surface of blade L1 to obtain the ash accumulation index value of blade L1. Calculate the product of the ash thickness on the side surface of blade L2 and the ash ratio on the front surface of blade L2 to obtain the ash accumulation index value of blade L2. And so on, calculate the product of the ash thickness on the side surface of blade La and the ash ratio on the front surface of blade La to obtain the ash accumulation index value of blade La.

[0119] The leaf ash accumulation index values ​​from L1 to La are defined as leaf ash accumulation monitoring data.

[0120] Step S3: Based on the blade dust accumulation monitoring data and blade vibration monitoring data, perform real-time dust accumulation prediction on the rotating machinery blades, and issue dust accumulation warnings based on the prediction results;

[0121] Step S3 further includes the following specific steps:

[0122] Acquire blade vibration monitoring data, and obtain L1 blade vibration monitoring value to La blade vibration monitoring value based on the blade vibration monitoring data;

[0123] Acquire leaf dust accumulation monitoring data, and obtain the L1 leaf dust accumulation index value to the La leaf dust accumulation index value based on the leaf dust accumulation monitoring data;

[0124] A polynomial fitting was performed based on the vibration monitoring values ​​of L1 blade to La blade and the dust accumulation index values ​​of L1 blade to La blade, and a dust accumulation prediction model was created based on the fitting results.

[0125] Specifically as follows:

[0126] A polynomial fitting function was established to compare the vibration monitoring values ​​of L1 blade with those of La blade and the dust accumulation index values ​​of L1 blade with those of La blade.

[0127] The polynomial fitting function is as follows:

[0128] ;

[0129] Where y is the blade dust accumulation index value, x is the blade vibration monitoring value, and a0 to a n The coefficients of the polynomial fitting function, where n is the order of the polynomial fitting function;

[0130] Substitute the vibration monitoring values ​​of L1 blade to La blade and the dust accumulation index values ​​of L1 blade to La blade into the polynomial fitting function respectively to calculate the residual sum of squares (RSS) function of the dust accumulation index values ​​of the blades.

[0131] The coefficients a0 to a10 of the polynomial fitting function in the residual sum of squares (RSS) function are respectively... n By taking partial derivatives, we obtain n unknowns a0 to a10. n The function expression, and n unknowns a0 to a n By combining the function expressions, we obtain n sets containing a0 to a n The system of equations is obtained, and the system of equations is solved to obtain a0 to a n The specific value;

[0132] From a0 to a n The specific numerical values ​​are substituted back into the polynomial fitting function to obtain the ash accumulation prediction model;

[0133] Mark the current time point as the end time point of the time period to form a real-time prediction period for blade dust accumulation. Obtain the blade vibration monitoring value corresponding to the real-time prediction period for blade dust accumulation to obtain the real-time blade vibration monitoring value. Substitute the real-time blade vibration monitoring value into the dust accumulation prediction model and obtain the blade dust accumulation index value output by the dust accumulation prediction model to obtain the real-time blade dust accumulation index value.

[0134] Obtain the benchmark range of leaf dust accumulation index. If the real-time leaf dust accumulation index value is within the benchmark range, there is no need to issue a leaf dust removal warning. If the real-time leaf dust accumulation index value is not within the benchmark range, a leaf dust removal warning needs to be issued.

[0135] It should be noted here that:

[0136] In this application, the situations in which the leaf dust removal warning is issued include situations where the real-time leaf dust accumulation index value is at the boundary of the leaf dust accumulation index benchmark range;

[0137] The baseline range for the leaf dust accumulation index was obtained as follows:

[0138] The lower limit of the benchmark interval for blade dust accumulation index involved here is 0, that is, there is no dust accumulation on the rotating machinery blades. Several historical monitoring periods for which blade dust removal early warning has been carried out are obtained, and the blade dust accumulation index value corresponding to each historical monitoring period is obtained. The blade dust accumulation index value with the smallest value is marked as the upper limit of the benchmark interval for blade dust accumulation index, thus obtaining the benchmark interval for blade dust accumulation index.

[0139] In this application, if a corresponding calculation formula appears, the above calculation formula is a dimensionless calculation. The weighting coefficient, proportional coefficient and other coefficients in the formula are set to quantify each parameter to obtain a result value. The size of the weighting coefficient and proportional coefficient is only required to not affect the proportional relationship between the parameter and the result value.

[0140] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm, characterized in that, include: Step S1: Obtain historical vibration data of rotating machinery blades, and select several historical monitoring periods from the obtained historical vibration data of rotating machinery blades. Perform vibration monitoring on the rotating machinery blades in each historical monitoring period, obtain the blade vibration monitoring value corresponding to each historical monitoring period, and obtain blade vibration monitoring data. Step S2: Based on the blade vibration monitoring data, perform blade dust accumulation monitoring on the rotating machinery blades during each historical monitoring period, obtain the blade dust accumulation index value corresponding to each historical monitoring period based on the monitoring results, and obtain blade dust accumulation monitoring data. Step S3: Based on the blade dust accumulation monitoring data and blade vibration monitoring data, perform real-time dust accumulation prediction on the rotating machinery blades, and issue dust accumulation warnings based on the prediction results; Step S2 further includes the following specific steps: Step S21: Obtain leaf dust accumulation monitoring data, and obtain historical monitoring periods from L1 to La based on the leaf dust accumulation monitoring data; Step S22: Acquire frontal images of the rotating machinery blades during the L1 historical monitoring period to the La historical monitoring period to obtain frontal images of the blades during the L1 period to the La period. Step S23: Acquire side images of the rotating machinery blades during the L1 historical monitoring period to the La historical monitoring period to obtain the side images of the blades during the L1 period to the La period. Step S24: Analyze the area of ​​dust accumulation on the front image of the leaf during time period L1, and obtain the dust ratio of the front area of ​​the L1 leaf based on the analysis results; Step S25: Perform ash accumulation area analysis on the frontal images of the leaves from L2 time period to La time period to obtain the ash ratio of the frontal area of ​​the leaves from L2 to La time period. Step S26: Analyze the ash accumulation thickness of the blade side image in time period L1, and obtain the ash accumulation thickness of the blade side in time period L1 based on the analysis results; Step S27: Analyze the ash accumulation thickness of the blade side images from L2 time period to La time period to obtain the ash accumulation thickness of the blade side image from L2 time period to La time period. Step S28: Calculate the product of the ash thickness on the side surface of blade L1 and the ash ratio on the front surface of blade L1 to obtain the ash accumulation index value of blade L1. Similarly, calculate the product of the ash thickness on the side surface of blade La and the ash ratio on the front surface of blade La to obtain the ash accumulation index value of blade La. Step S29: Define the L1 leaf ash accumulation index value to the La leaf ash accumulation index value as leaf ash accumulation monitoring data.

2. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 1, characterized in that, Step S1 further includes the following specific steps: Step S11: Acquire the blade vibration monitoring data corresponding to the rotating machinery blade to obtain the historical vibration data of the rotating machinery blade, and mark it as a blade vibration history cycle based on the historical vibration data of the rotating machinery blade; Step S12: Divide the blade vibration history period into the L1 historical monitoring period to the La historical monitoring period; Step S13: Monitor the historical vibration index of the rotating machinery blades during the L1 historical monitoring period, and obtain the L1 blade vibration monitoring value based on the monitoring results; Step S14: Obtain the vibration monitoring values ​​of blades L2 to La respectively; Step S15: Define the blade vibration monitoring values ​​from L1 to La and the historical monitoring period from L1 to La as blade vibration monitoring data.

3. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 2, characterized in that, Step S13 further includes the following specific steps: Step S131: Divide the historical monitoring period of L1 into the blade vibration time point from Z1 to Zb. Step S132: Obtain the blade vibration values ​​corresponding to the vibration time points from blade Z1 to blade Zb of the rotating mechanical blade, and obtain the vibration values ​​from blade Z1 to blade Zb. Step S133: Create a line graph of blade vibration time periods using the vibration values ​​of blade Z1 to blade Zb and the vibration time points of blade Z1 to blade Zb.

4. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 2, characterized in that, Step S13 further includes the following specific steps: Step S134: In the line graph of the blade vibration period, mark the maximum vertical axis value as the first blade vibration peak value, mark the vertical axis value that is only less than the first blade vibration peak value as the second blade vibration peak value, mark the minimum vertical axis value as the first blade vibration valley value, and mark the vertical axis value that is only greater than the first blade vibration valley value as the second blade vibration valley value. Step S135: Calculate the average value of the vibration values ​​of blade Z1 to blade Zb to obtain the average vibration value Zzp for the time period; Step S136: The vibration monitoring value Zjl1 of blade L1 is obtained by calculating the vibration peak value Zf1 of the first blade, the vibration peak value Zf2 of the second blade, the vibration valley value Zg1 of the first blade, the vibration valley value Zg2 of the second blade, and the average vibration value Zzp over the time period.

5. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 3, characterized in that, Step S133 further includes the following specific steps: A Cartesian coordinate system for blade vibration is created by using the time points of blade vibration as the x-axis and the blade vibration values ​​as the y-axis. In the rectangular coordinate system of the blade vibration plane, the coordinate point with the vibration time point of blade Z1 as the abscissa and the vibration value of blade Z1 as the ordinate is marked as the Z1 vibration coordinate point. Similarly, the coordinate point with the vibration time point of blade Zb as the abscissa and the vibration value of blade Zb as the ordinate is marked as the Zb vibration coordinate point. Connecting the Z1 vibration coordinate point to the Zb vibration coordinate point in sequence yields a line graph of the blade vibration period.

6. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 1, characterized in that, Step S24 further includes the following specific steps: The frontal image of the leaf during the L1 time period is acquired. An image recognition algorithm is used to identify the dusty areas in the frontal image of the leaf during the L1 time period to obtain the first image feature region. The non-dusty areas in the frontal image of the leaf during the L1 time period are marked as the second image feature region. The area values ​​of the first image feature region and the second image feature region are obtained respectively to obtain the area value Mj1 of the first image region and the area value Mj2 of the second image region. The area value Mj1 of the first image region and the area value Mj2 of the second image region are used to calculate the gray ratio Jmb1 of the positive area of ​​leaf L1.

7. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 1, characterized in that, Step S26 further includes the following specific steps: Image recognition algorithms were used to identify the blade edges in the side images of the blades during the L1 time period. Several edge feature points were selected from the blade edges, and one sample edge feature point was randomly selected from the multiple edge feature points obtained. Draw a straight line perpendicular to the blade edge through the sample edge feature point to obtain the blade side marking line. Identify the dust accumulation area in the blade side marking line to obtain the dust accumulation area of ​​the marking line. Obtain the length value of the line segment area occupied by the dust accumulation area of ​​the marking line in the blade side marking line to obtain the dust accumulation thickness value of the area corresponding to the sample edge feature point. The ash thickness value of the region corresponding to each edge feature point is obtained, and the average value of the obtained ash thickness values ​​of multiple regions is calculated to obtain the ash thickness of the L1 blade side.

8. The method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 1, characterized in that, Step S3 further includes the following specific steps: Step S31: Obtain blade vibration monitoring data, and obtain the L1 blade vibration monitoring value to the La blade vibration monitoring value based on the blade vibration monitoring data; Step S32: Obtain leaf dust accumulation monitoring data, and obtain the L1 leaf dust accumulation index value to the La leaf dust accumulation index value based on the leaf dust accumulation monitoring data; Step S33: Perform polynomial fitting based on the vibration monitoring values ​​of L1 blade to La blade and the dust accumulation index values ​​of L1 blade to La blade, and create a dust accumulation prediction model based on the fitting results. Step S34: Mark the time point corresponding to the current moment as the end time point of the time period to mark a real-time prediction period for blade dust accumulation, and obtain the blade vibration monitoring value corresponding to the real-time prediction period for blade dust accumulation to obtain the real-time blade vibration monitoring value. Substitute the real-time blade vibration monitoring value into the dust accumulation prediction model, obtain the blade dust accumulation index value output by the dust accumulation prediction model, and obtain the real-time blade dust accumulation index value. Step S35: Obtain the benchmark range of leaf dust accumulation index. If the real-time leaf dust accumulation index value is within the benchmark range, there is no need to issue a leaf dust removal warning. If the real-time leaf dust accumulation index value is not within the benchmark range, then issue a leaf dust removal warning.

9. A method for predicting the dust accumulation trend of rotating machinery blades based on the PCFC algorithm according to claim 8, characterized in that, Step S33 further includes the following specific steps: A polynomial fitting function was established to compare the vibration monitoring values ​​of L1 blade with those of La blade and the dust accumulation index values ​​of L1 blade with those of La blade. Substitute the vibration monitoring values ​​of L1 blade to La blade and the dust accumulation index values ​​of L1 blade to La blade into the polynomial fitting function respectively to calculate the residual sum of squares (RSS) function of the dust accumulation index values ​​of the blades. The coefficients a0 to a10 of the polynomial fitting function in the residual sum of squares (RSS) function are respectively... n By taking partial derivatives, we obtain n unknowns a0 to a10. n The function expression, and n unknowns a0 to a n By combining the function expressions, we obtain n sets containing a0 to a n The system of equations is obtained, and the system of equations is solved to obtain a0 to a n The specific value; From a0 to a n The specific numerical values ​​are substituted back into the polynomial fitting function to obtain the ash accumulation prediction model.

Images