Fault Diagnosis Method and System for Auxiliary Power Station Equipment in Smart Factory

Abstract

This application relates to the technical field of electrical performance testing, and specifically relates to a fault diagnosis method and system for auxiliary power station equipment in a smart factory. The method includes: obtaining the current sequence, power sequence, and vibration sequence of the boiler feed pump; equally dividing the acquisition duration into multiple time periods, and determining the vibration anomaly values of the boiler feed pump within each time period; determining the trend noise significance of the power sequence and current sequence within each time period; based on the trend noise significance, as well as the correlation between the current sequence and power sequence within each time period and the distribution of power data, determining the current-power influence value for each time period; based on the degree of dispersion of the difference between the vibration anomaly value and the current-power influence value, and the distribution range of the vibration anomaly value, determining the load vibration difference of the boiler feed pump, and performing fault diagnosis on the boiler feed pump. The purpose of this application is to improve the accuracy of fault diagnosis for the boiler feed pump.

Description

Technical Field

[0001] The present application relates to the technical field of electrical performance testing, and particularly to a fault diagnosis method and system for auxiliary power station equipment for intelligent factories. Background Art

[0002] Auxiliary power station equipment is an important part of power station production equipment and is crucial for the normal operation of power station equipment. There are various types of auxiliary power station equipment. In a narrow sense, auxiliary power station equipment specifically refers to coal mills, forced draft fans, induced draft fans, boiler feed pumps, and high-pressure heaters. These devices are called the five major auxiliary equipment due to their high reliability requirements, large manufacturing difficulty, and direct impact on unit efficiency.

[0003] Among them, the boiler feed pump plays a crucial role in the intelligent power distribution system, mainly including transporting water, boosting pressure, stabilizing the boiler water level, etc., to ensure the normal operation and thermal efficiency of the boiler. Therefore, it is necessary to monitor the operating state of the boiler feed pump in real time. Existing methods mainly perform fault diagnosis based on the abnormal vibration characteristics of the boiler feed pump, usually ignoring the phenomenon that the vibration characteristic forms of the boiler feed pump are different under the influence of the dynamic change of the operating load of the power station unit during normal operation, resulting in low accuracy of fault diagnosis for the boiler feed pump. Summary of the Invention

[0004] In view of the above, it is necessary to provide a fault diagnosis method and system for auxiliary power station equipment for intelligent factories, which improves the accuracy of fault diagnosis for boiler feed pumps compared with traditional fault diagnosis methods for auxiliary power station equipment:

[0005] In a first aspect, an embodiment of the present application provides a fault diagnosis method for auxiliary power station equipment for intelligent factories, and the method includes the following steps:

[0006] Collect current data, power data, and vibration data of the boiler feed pump at each acquisition moment, and respectively form a current sequence, a power sequence, and a vibration sequence according to the time sequence;

[0007] Divide the acquisition duration into multiple time periods equally, and use a signal decomposition algorithm to obtain each modal component of the vibration sequence in each time period. Based on the difference between the frequencies corresponding to the maximum amplitudes in the spectrograms of the vibration sequence and its respective modal components in each time period, determine the basic signal of the vibration sequence in each time period;

[0008] Based on the correlation between the vibration signal and its basic signal in each time period, and the distribution of the neighboring amplitudes of all peak points in the spectrograms of all modal components except the basic signal, determine the vibration abnormal value of the boiler feed pump in each time period;

[0009] Determine the trend noise significance of the power sequence and current sequence in each time period respectively based on the change trends of the trend components and the autocorrelation of the residual components of the power sequence and current sequence in each time period;

[0010] Based on the trend noise significance, as well as the correlation between the current sequence and the power sequence in each time period and the distribution of power data, determine the current-power influence value in each time period;

[0011] Based on the degree of dispersion of the difference between the vibration outliers and the current-power influence value, as well as the distribution range of the vibration outliers, determine the load vibration difference of the boiler feed pump and perform fault diagnosis on the boiler feed pump.

[0012] In one embodiment, the determination process of the basic signal is as follows:

[0013] Respectively take the frequencies corresponding to the maximum amplitudes in the spectrograms of the vibration sequences and each modal component in each time period as the main frequencies of the vibration sequences and the main frequencies of each modal component in each time period;

[0014] Among all the modal components of the vibration sequence in any time period, take the modal component with the smallest difference in the main frequency from the vibration sequence in the any time period as the basic signal of the vibration sequence in the any time period.

[0015] In one embodiment, the determination process of the vibration outliers is as follows:

[0016] Calculate the absolute value of the correlation between the vibration sequence and its basic signal in each time period;

[0017] For the remaining modal components except the basic signal in each time period, calculate the mean value of all amplitudes in a preset-sized local area centered on each peak point in the spectrogram of each modal component;

[0018] Calculate the sum of all the means corresponding to all the modal components except the basic signal in each time period;

[0019] Based on the absolute value of the correlation between the vibration sequence and its basic signal in each time period and the sum corresponding to each time period, determine the vibration outliers of the boiler feed pump in each time period.

[0020] In one embodiment, the expression of the vibration outliers is:

[0021] In the formula, D i represents the vibration outliers of the boiler feed pump in the i-th time period; C i represents the sum corresponding to the i-th time period; A irepresents the absolute value of the correlation between the vibration sequence and its base signal within the \(i\)-th time period, and \(\alpha\) represents a preset value greater than 0.

[0022] In one embodiment, the process of determining the trend noise significance is as follows:

[0023] Obtain the first-order difference sequence of the trend component of the power sequence within each time period, and use the cumulative value of the absolute values of all data in the first-order difference sequence as the trend change amount of the power sequence within each time period;

[0024] Use the autocorrelation function to calculate the autocorrelation coefficient of the residual component of the power sequence within each time period at each preset time delay; calculate the absolute value of the mean of the autocorrelation functions of the power sequence within each time period corresponding to all preset time delays, denoted as the autocorrelation mean;

[0025] Based on the trend change amount and the autocorrelation mean, obtain the trend noise significance of the power sequence within each time period;

[0026] For the current sequence within each time period, calculate the trend noise significance of the current sequence within each time period according to the same calculation steps as the trend noise significance of the power sequence within each time period.

[0027] In one embodiment, the trend noise significance of the power sequence within each time period is the ratio of the trend change amount to the autocorrelation mean.

[0028] In one embodiment, the expression of the current power influence value is:

[0029] where \(M\) i represents the current power influence value of the \(i\)-th time period; \(G\) i represents the trend noise significance of the power sequence within the \(i\)-th time period; \(H\) i represents the trend noise significance of the current sequence within the \(i\)-th time period; \(\mu\) i represents the mean of the normalized values of all data in the power sequence within the \(i\)-th time period; \(L\) i represents the Spearman correlation coefficient between the current sequence and the power sequence within the \(i\)-th time period; \(\beta\) represents a preset value greater than 0.

[0030] In one embodiment, the process of determining the load vibration difference of the boiler feed pump is as follows:

[0031] Calculate the difference between the vibration anomaly value corresponding to each time period and the current power influence value, denoted as the comprehensive difference;

[0032] The degree of dispersion of the comprehensive differences in all time periods and the fusion result of the range of vibration outliers corresponding to all time periods are used as the load vibration difference of the boiler feed pump.

[0033] In one embodiment, the method for fault diagnosis of the boiler feed pump is as follows:

[0034] When the normalized value of the load vibration difference of the boiler feed pump is greater than the preset fault anomaly threshold, it is determined that the boiler feed pump has a fault; otherwise, there is no fault.

[0035] In a second aspect, the embodiments of the present application also provide a fault diagnosis system for power station auxiliary equipment for a smart factory, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned fault diagnosis method for power station auxiliary equipment for a smart factory are implemented.

[0036] The present application has at least the following beneficial effects:

[0037] By analyzing the content of abnormal vibration frequencies in the vibration sequence and the degree of deviation of the vibration sequence from the basic signal, the vibration outliers of the boiler feed pump in each time period are determined, improving the accuracy of analyzing the possibility of the presence of abnormal vibration characteristics in each time period;

[0038] Furthermore, by analyzing the trend changes and noise characteristics of the current and power data of the boiler feed pump, and combining the correlation between the current sequence and the power sequence, the current power influence values in each time period are determined. Then, based on the difference characteristics between the vibration outliers and the current power influence values, and combining the distribution range of the vibration outliers, the load vibration difference is determined, and by combining the correlation between the vibration change and the load change, the accuracy of extracting the abnormal operation characteristics of the boiler feed pump is improved, and further the accuracy of fault diagnosis of the boiler feed pump is improved. Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is a flowchart of the steps of the fault diagnosis method for power station auxiliary equipment for a smart factory provided by an embodiment of the present application;

[0041] Figure 2 It is a comparison diagram of the vibration signal spectra in the normal state and the abnormal state;

[0042] Figure 3 It is a schematic diagram of the acquisition process of vibration abnormal values;

[0043] Figure 4 It is a schematic diagram of the acquisition process of the significance of the trend noise of the power sequence;

[0044] Figure 5 It is a schematic diagram of the current power in the normal state;

[0045] Figure 6 It is a schematic diagram of the current power in the abnormal state. Specific implementation manners

[0046] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example", etc. are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Exactly speaking, the use of words such as "exemplary", "or", "for example", etc. is intended to present related concepts in a specific manner.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used in this application are only for the purpose of describing specific embodiments, and are not intended to limit this application. It should be understood that unless otherwise specified in this application, " / " means "or".

[0048] In addition, it should be noted that the terms "first" and "second" in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0049] The following specifically describes the specific solutions of the power station auxiliary fault diagnosis method and system for smart factories provided by this application in conjunction with the drawings.

[0050] Please refer to Figure 1 , which shows the step flow chart of the power station auxiliary fault diagnosis method for smart factories provided by an embodiment of this application. The method includes the following steps:

[0051] Step 1, collect the current data, power data and vibration data of the boiler feed pump at each acquisition moment, and respectively form a current sequence, a power sequence and a vibration sequence according to the time sequence.

[0052] Auxiliary power station equipment includes many devices in the power station production process. In this embodiment, fault diagnosis is performed on the boiler feed pump among them. When an abnormality occurs inside the boiler feed pump, it is usually accompanied by an increase in vibration and a change in working performance. Therefore, a digital power meter is used to collect the current data and power data of the boiler feed pump motor. A displacement sensor is used to collect the vibration data at the pump body position. The collected current data, power data, and vibration data are respectively arranged in time series to form a current sequence, a power sequence, and a vibration sequence.

[0053] In this embodiment, when using a digital power meter and a displacement sensor to collect data, the collection time interval is 0.01 seconds, and the collection duration is 1 minute. The values of the time interval and the collection duration are preset manually, and the implementer can set them by himself / herself. This application does not have special restrictions.

[0054] Step 2: Based on the content of the abnormal vibration frequency in the vibration sequence of the boiler feed pump and the offset degree of the vibration sequence relative to the base signal, determine the vibration abnormal value of the boiler feed pump; by analyzing the trend changes and noise characteristics of the current and power data of the boiler feed pump, and combining the correlation between the current sequence and the power sequence, determine the current-power influence value for each time period; further determine the load vibration difference.

[0055] In the boiler system, the water in the boiler is heated and then turned into steam and discharged, providing power for the steam turbine. In order to meet the requirements of the water level and steam pressure in the boiler, the boiler feed pump needs to continuously supply water to the boiler. The boiler feed pump operates in a high-temperature and high-pressure environment for a long time, and it has a very high rotational speed during operation. Therefore, the boiler feed pump is prone to failure. Common failure types include internal leakage of the feed pump, filter clogging, and abnormal vibration of the feed pump. These failures will affect various parameters of the boiler feed pump. Among them, the vibration parameter is relatively easy to measure and is an important characteristic representing the operating state of the boiler feed pump. Many mechanical failures of the boiler feed pump can be reflected in the form of abnormal vibration, such as rotor imbalance, impeller corrosion, and bearing damage.

[0056] The boiler feed pump will generate a uniform and fixed-frequency vibration signal during normal operation, and the vibration frequency under the normal operation state is used as the base frequency. When rotor imbalance or bearing damage occurs, the vibration sequence will show significant amplitude changes, and the abnormal signals detected in the low-frequency range will increase. When the impeller corrosion fault occurs, it may cause uneven mass distribution of the impeller. This mass offset will cause additional vibration when the pump rotates at high speed, resulting in an increase in vibration intensity and easily introducing high-frequency vibration. Based on the above characteristics, a preliminary assessment of the operating vibration state of the boiler feed pump in the auxiliary power station equipment can be made. The spectrum comparison diagram of the vibration signals in the normal state and the abnormal state is as Figure 2As shown in the figure, the abscissa is the frequency and the ordinate is the amplitude. When the boiler feed pump is operating normally, the data in the frequency spectrum diagram of its vibration sequence is mainly concentrated in a certain frequency domain range. Taking 50HZ as an example, in the normal signal frequency spectrum diagram, the amplitudes of the frequencies adjacent to 50HZ are relatively large, while the amplitudes of other frequencies are relatively small; the abnormal state signal frequency spectrum diagram (a) is the frequency spectrum diagram of the vibration signal with an abnormal increase in low frequencies when the rotor is unbalanced or the bearing is damaged. Compared with the normal signal frequency spectrum diagram, the amplitudes of the frequencies adjacent to 100HZ, 150HZ, and 200HZ become larger; the abnormal state signal frequency spectrum diagram (b) is the frequency spectrum diagram of the vibration signal introducing high-frequency vibration signals when there is an impeller fault. Compared with the normal signal frequency spectrum diagram, the amplitudes of the frequencies adjacent to 400HZ and 600HZ in the figure become larger.

[0057] Step 2.1: Divide the acquisition duration into multiple time periods equally, and use the signal decomposition algorithm to obtain the modal components of the vibration sequence in each time period. Based on the difference in the frequencies corresponding to the maximum amplitudes in the frequency spectrum diagrams between the vibration sequence in each time period and its modal components, determine the basic signal of the vibration sequence in each time period.

[0058] Since the abnormal operation of the boiler feed pump is highly random, the abnormal characteristics in different time periods may vary significantly. In order to accurately analyze the operation state in the short term, the acquisition duration is divided into a preset number of time periods equally.

[0059] In this embodiment, the value of the preset number is 10. The value of the preset number is preset manually, and the implementer can set it by himself / herself. This application does not make special restrictions.

[0060] This application uses the signal decomposition algorithm to extract vibration fault characteristics. The signal decomposition algorithm is used to perform modal decomposition on the vibration sequence in each time period to obtain the modal components of the vibration sequence in each time period. Among them, each modal component is also a discrete sequence, representing the frequency components in the vibration sequence in each time period.

[0061] In this embodiment, the ensemble empirical mode decomposition (EEMD) method is used for modal decomposition. As other implementation manners, on the basis of being able to perform modal decomposition on the vibration sequence, the implementer can use other existing technologies for modal decomposition, such as the empirical mode decomposition method, the complementary ensemble empirical mode decomposition method, etc. This application does not make special restrictions.

[0062] When the boiler feed pump is operating normally, the data in the frequency spectrum diagram of its vibration sequence is mainly concentrated in a certain frequency range. Taking 50HZ as an example, 50HZ is used as the base frequency. When a fault occurs in the boiler feed pump, in addition to the 50HZ base frequency data with the largest content in the vibration sequence, the vibration sequence also contains data of other abnormal frequencies, such as 100HZ and 150HZ data at low frequencies, and 350HZ data at high frequencies. The higher the amplitude of these abnormal frequencies, the greater the possibility that the boiler feed pump has a fault.

[0063] Perform a discrete Fourier transform on the vibration sequences in each time period to obtain the frequency spectrum diagrams of the vibration sequences in each time period. The frequency corresponding to the maximum amplitude in the frequency spectrum diagram of the vibration sequence in each time period is used as the main frequency of the vibration sequence in each time period; for each modal component, the main frequency of each modal component is obtained according to the same acquisition method as the main frequency of the vibration sequence in each time period.

[0064] Among all the modal components of the vibration sequence in any time period, the modal component with the smallest difference in the main frequency from the vibration sequence in the any time period is used as the base signal of the vibration sequence in the any time period.

[0065] Step 2.2: Based on the correlation between the vibration signals and their base signals in each time period, and the distribution of the neighboring amplitudes of all peak points in the frequency spectrum diagrams of all modal components except the base signal, determine the vibration outliers of the boiler feed pump in each time period.

[0066] Taking the i-th time period as an example, calculate the absolute value of the correlation between the vibration sequence and its base signal in the i-th time period. The smaller the absolute value of the correlation, the greater the difference between the vibration sequence and the decomposed base signal in the i-th time period, that is, the greater the deviation of the actual vibration signal from the vibration signal with a uniform and fixed frequency under normal operating conditions.

[0067] In this embodiment, the correlation between the vibration sequence and its base signal is the Pearson correlation coefficient. As other implementation manners, on the basis of being able to measure the correlation between the vibration sequence and its base signal, the implementer can use other existing technologies to measure the correlation between the vibration sequence and its base signal, such as the Spearman correlation coefficient, the Kendall rank correlation coefficient, etc. This application does not make special restrictions.

[0068] The magnitude of the absolute value of the correlation analyzes the possibility of anomalies in the vibration sequence from the time domain perspective, and it is necessary to further analyze the possibility of faults in combination with the magnitude of the abnormal frequency signal. For the spectrograms of other modal components except the basic signal, the present application uses the findpeaks function in matalb to extract peaks, calculates the mean value of all amplitudes within a local region with a preset radius centered on each peak point, calculates the sum of the means of all peak points in the spectrograms of all modal components except the basic signal, and a large value of the sum indicates that the vibration sequence contains more abnormal frequencies in the i-th time period. Among them, when the local region constructed centered on a peak point in a certain spectrogram exceeds the range of the spectrogram, data filling is performed on the exceeded part according to the spectrogram.

[0069] In this embodiment, the value of the preset radius is 10, and the value of the preset radius is preset by humans. The implementer can set it by himself, and the present application does not make special restrictions.

[0070] In this embodiment, the mean filling method is used for data filling. As other implementation manners, on the basis of being able to achieve data filling, the implementer can use other existing technologies for data filling, such as the median filling method, the interpolation method, etc., and the present application does not make special restrictions.

[0071] Based on the above analysis, based on the absolute value of the correlation between the vibration sequence and its basic signal in each time period, and the sum corresponding to each time period, the vibration anomaly value of the boiler feed pump in each time period is determined, and the expression is:

[0072] In the formula, D i represents the vibration anomaly value of the boiler feed pump in the i-th time period; C i represents the sum corresponding to the i-th time period; A i represents the absolute value of the correlation between the vibration sequence and its basic signal in the i-th time period, and α represents a preset value greater than 0, the purpose is to avoid the denominator being 0, and the value of α is preset by humans. The implementer can set it by himself. In this embodiment, the value of α is 0.01.

[0073] It should be noted that: the larger the value of the vibration anomaly value D i , the greater the possibility that the boiler feed pump has a vibration fault in the i-th time period. The schematic diagram of the acquisition process of the vibration anomaly value is as Figure 3 shown.

[0074] Step 2.3 respectively determines the trend noise significance of the power sequence and the current sequence in each time period based on the change trend of the trend component and the autocorrelation of the residual component of the power sequence and the current sequence in each time period.

[0075] During the actual operation of power station units, the operating load is dynamic, which causes the current and power required by the boiler feed pump to change accordingly. The changes in current and power will affect the rotation speed of the internal components of the boiler feed pump, and then lead to changes in vibration characteristics. In addition, under a certain load condition, the current and power of the boiler feed pump are not smooth and stable, and there may be noise or fluctuations due to factors such as poor heat dissipation. Further analyze the overall change trend of current and power and the noise content. Taking the power data as an example, the STL (Seasonal and Trend decomposition using Loess) algorithm is used to decompose the power sequence in each time period, and the trend component, seasonal component and residual component are obtained.

[0076] Among them, the trend component represents the trend state of the power data changing with the load in each time period. Obtain the first-order difference sequence of the trend component of the power sequence in each time period, and take the cumulative value of the absolute values of all data in the first-order difference sequence as the trend change amount of the power sequence in each time period; if the value of the trend change amount is larger, it means that the trend characteristics of the power change in each time period are more significant. If there is more noise in the collected power sequence, there will be more random fluctuations in the obtained residual component and weaker autocorrelation. Therefore, the autocorrelation function is used to calculate the autocorrelation coefficient of the residual component of the power sequence in each time period at each preset time delay, and calculate the absolute value of the mean of the autocorrelation functions of the power sequence in each time period corresponding to all preset time delays, which is denoted as the autocorrelation mean. If the autocorrelation mean is smaller, it indicates that the autocorrelation of the residual component is weaker and the power sequence contains more noise.

[0077] In this embodiment, the value range of the preset time delay is an integer in [1, N - 1], where N represents the length of the residual component. The value range of the preset time delay is preset manually, and the implementer can set it by himself. This application does not make special restrictions.

[0078] Take the ratio of the trend change amount of the power sequence in each time period to the corresponding autocorrelation mean as the trend noise significance of the power sequence in each time period. If the value of the trend noise significance is larger, it indicates that the trend change of the power in each time period is more obvious and the noise content is more. The schematic diagram of the acquisition process of the trend noise significance of the power sequence is as Figure 4 shown.

[0079] For the current data, calculate the trend noise significance of the current sequence in each time period according to the same calculation method as the trend noise significance of the power sequence in each time period. If the value of the trend noise significance is larger, it indicates that the trend change of the current in each time period is more obvious and the noise content is more.

[0080] Step 2.4: Determine the current-power influence value for each time period based on the trend noise significance, the correlation between the current sequence and the power sequence within each time period, and the distribution of power data.

[0081] Since the current and power of the boiler feed pump are positively correlated under good conditions, during the process of load change, when the current increases, the power also increases. However, if it is interfered by factors such as loose motor terminal connections, it will lead to a decrease in the correlation degree between the current and the power, thereby affecting the rotation speed of the boiler feed pump and easily causing faults. The schematic diagram of the current-power under normal conditions is as Figure 5 shown. Under normal conditions, the current and power are positively correlated. The schematic diagram of the current-power under abnormal conditions is as Figure 6 shown. Under abnormal conditions, the correlation degree between the current and the power decreases.

[0082] Calculate the Spearman correlation coefficient between the current sequence and the power sequence within each time period. If the value of the Spearman correlation coefficient is smaller, it indicates that the positive correlation degree between the current and the power is lower, and the power supply state of the boiler feed pump is more unstable.

[0083] Based on the trend noise significance of the power sequence, the trend noise significance of the current sequence, and the Spearman correlation coefficient between the current sequence and the power sequence within each time period, combined with the distribution of power data within each time period, determine the current-power influence value for each time period. The expression is:

[0084] In the formula, M i represents the current-power influence value of the i-th time period; G i represents the trend noise significance of the power sequence within the i-th time period; H i represents the trend noise significance of the current sequence within the i-th time period; μ i represents the mean of the normalized values of all data in the power sequence within the i-th time period; L i represents the Spearman correlation coefficient between the current sequence and the power sequence within the i-th time period; β represents a preset value greater than 0, aiming to avoid the denominator being 0. The value of β is preset manually, and the implementer can set it by himself. In this embodiment, the value of β is 0.01.

[0085] It should be noted that: the larger the current-power influence value M i , the greater the operating load of the boiler feed pump in the i-th time period, and the greater the degree of influence of the boiler feed pump on the changes in current and power in the i-th time period.

[0086] Step 2.5, determine the load vibration difference of the boiler feed pump based on the discreteness of the difference between the vibration outlier and the current power influence value, as well as the distribution range of the vibration outlier, and perform fault diagnosis on the boiler feed pump.

[0087] Under different load conditions of power station units, there are certain differences in the vibration characteristics of the boiler feed pump. For example, when the boiler feed pump operates at high load, due to more demanding operating conditions of the boiler feed pump at high load, more mechanical stress or hydrodynamic problems are caused, resulting in increased vibration. Therefore, the calculated vibration outlier is relatively large; when the boiler feed pump operates at low load, the operation of the boiler feed pump is more stable, the vibration sources are reduced, and the calculated vibration outlier is relatively small. Therefore, the diagnostic result of only diagnosing faults based on the magnitude of the vibration outlier is not accurate enough. Combining the above characteristics, calculate the load vibration difference of the boiler feed pump.

[0088] Calculate the difference between the vibration outlier and the current power influence value corresponding to each time period, denoted as the comprehensive difference. Calculate the discreteness of the comprehensive differences of all time periods. If the discreteness is greater, it indicates that the difference between the vibration change and the load change of the boiler feed pump is greater. Under good operating conditions, although the load fluctuates, the vibration outlier of the boiler feed pump usually does not change significantly. Therefore, calculate the range of the vibration outliers of the boiler feed pump within all time periods. If the range is greater, it indicates that the degree of change in the vibration characteristics is greater.

[0089] In this embodiment, the difference between the vibration outlier and the current power influence value is the absolute value of the difference. As other implementation manners, on the basis of being able to measure the difference between the vibration outlier and the current power influence value, the implementer can use other calculation methods to measure the difference between the vibration outlier and the current power influence value, such as ratio, square of the difference, etc. This application does not make special restrictions.

[0090] In this embodiment, the discreteness is the coefficient of variation. As other implementation manners, on the basis of being able to measure the uneven distribution degree of the comprehensive differences, the implementer can use other statistics to measure the uneven distribution degree of the comprehensive differences, such as standard deviation, variance, etc. This application does not make special restrictions.

[0091] Take the fusion result of the discreteness of the comprehensive differences of all time periods and the range of the vibration outliers corresponding to all time periods as the load vibration difference of the boiler feed pump.

[0092] It should be understood that: Fusion refers to combining multiple independent variables in a way that enhances the overall effect, such as multiplicative relationship, additive relationship, etc. The implementer can make limitations according to the actual situation.

[0093] In this embodiment, the product of the degree of dispersion of the comprehensive differences in all time periods and the range of the vibration outliers corresponding to all time periods is used as the load vibration difference of the boiler feed pump.

[0094] In another embodiment, the sum of the degree of dispersion of the comprehensive differences in all time periods and the range of the vibration outliers corresponding to all time periods is used as the load vibration difference of the boiler feed pump.

[0095] It should be noted that: the greater the load vibration difference R of the boiler feed pump, the greater the possibility that the boiler feed pump has a fault.

[0096] Normalize the load vibration difference of the boiler feed pump. The expression is: S = 1 - exp(-R); where S represents the normalized value of the load vibration difference of the boiler feed pump, exp() is the exponential function with the natural constant as the base, and R represents the load vibration difference of the boiler feed pump.

[0097] Furthermore, set a fault anomaly threshold. When the normalized value of the load vibration difference of the boiler feed pump is greater than the fault anomaly threshold, it is determined that the boiler feed pump has a fault; otherwise, it is determined that the boiler feed pump is in good operating condition and has no fault.

[0098] In this embodiment, the value of the fault anomaly threshold is 0.7. The value of the fault anomaly threshold is preset manually, and the implementer can set it by himself / herself. This application does not make special restrictions.

[0099] Based on the same inventive concept as the above method, the embodiment of this application also provides a fault diagnosis system for power station auxiliary equipment for a smart factory, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods for fault diagnosis of power station auxiliary equipment for a smart factory.

[0100] To sum up, this application determines the vibration outliers of the boiler feed pump in each time period by analyzing the content of abnormal vibration frequencies in the vibration sequence and the offset degree of the vibration sequence relative to the base signal, improving the accuracy of analyzing the possibility of abnormal vibration characteristics in each time period;

[0101] Furthermore, by analyzing the trend changes and noise characteristics of the current and power data of the boiler feed pump, combining the correlation between the current sequence and the power sequence, the current-power influence value for each time period is determined. Then, based on the difference characteristics between the vibration anomaly value and the current-power influence value, and combining the distribution range of the vibration anomaly value, the load vibration difference is determined. By combining the correlation between the vibration change and the load change, the accuracy of extracting the abnormal operation characteristics of the boiler feed pump is improved, and thus the accuracy of fault diagnosis for the boiler feed pump is enhanced.

[0102] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the descriptions. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0103] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and without departing from the basic characteristics of the present application, the present application can be implemented in other specific forms. Therefore, from any perspective, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A fault diagnosis method for auxiliary power station equipment in the intelligent factory, characterized in that, The method includes the following steps: Collect the current data, power data, and vibration data of the boiler feed pump at each collection moment, and respectively form a current sequence, a power sequence, and a vibration sequence according to the time sequence; Divide the collection duration into multiple time periods equally, and use a signal decomposition algorithm to obtain each modal component of the vibration sequence within each time period; Respectively take the frequency corresponding to the maximum amplitude value in the spectrogram of the vibration sequence and each modal component within each time period as the main frequency of the vibration sequence and the main frequency of each modal component within each time period; Among all the modal components of the vibration sequence within any time period, take the modal component with the smallest difference in the main frequency from the vibration sequence within the said any time period as the basic signal of the vibration sequence within the said any time period; Based on the correlation between the vibration signal and its basic signal within each time period, and the distribution of the neighboring amplitudes of all peak points in the spectrograms of all modal components except the basic signal, determine the vibration anomaly value of the boiler feed pump within each time period; Obtain the first-order difference sequence of the trend component of the power sequence within each time period, and take the cumulative value of the absolute values of all data in the first-order difference sequence as the trend change amount of the power sequence within each time period; Use the autocorrelation function to calculate the autocorrelation coefficient of the residual component of the power sequence within each time period at each preset time delay; calculate the absolute value of the mean of the autocorrelation functions of the power sequence within each time period corresponding to all preset time delays, and denote it as the autocorrelation mean; Based on the trend change amount and the autocorrelation mean, obtain the trend noise significance of the power sequence within each time period; For the current sequence within each time period, calculate the trend noise significance of the current sequence within each time period according to the same calculation steps as the trend noise significance of the power sequence within each time period; Based on the trend noise significance, as well as the correlation between the current sequence and the power sequence within each time period and the distribution of the power data, determine the current-power influence value of each time period; Based on the dispersion degree of the difference between the vibration anomaly value and the current-power influence value, and the distribution range of the vibration anomaly value, determine the load vibration difference of the boiler feed pump, and perform fault diagnosis on the boiler feed pump.

2. The fault diagnosis method for auxiliary power station equipment oriented to intelligent factories according to claim 1, wherein, The determination process of the vibration anomaly value is as follows: Calculate the absolute value of the correlation between the vibration sequence and its basic signal within each time period; For the remaining modal components except the basic signal within each time period, calculate the mean value of all amplitudes within a preset size of the local area centered on each peak point in the spectrogram of each modal component; Calculate the cumulative sum of all the means corresponding to all modal components except the basic signal within each time period; Based on the absolute value of the correlation between the vibration sequence and its basic signal within each time period, and the cumulative sum corresponding to each time period, determine the vibration anomaly value of the boiler feed pump within each time period.

3. The fault diagnosis method for auxiliary power plant equipment for smart factories according to claim 2, wherein, The expression of the vibration anomaly value is: In the formula, D i represents the vibration anomaly value of the boiler feed pump in the i-th time period; C i represents the cumulative sum corresponding to the i-th time period; A i represents the absolute value of the correlation between the vibration sequence and its basic signal in the i-th time period, and α represents a preset value greater than 0.

4. The fault diagnosis method for auxiliary power station equipment oriented to intelligent factories according to claim 1, characterized in that, The trend noise significance of the power sequence within each time period is the ratio of the trend change amount to the autocorrelation mean.

5. The fault diagnosis method for auxiliary power station equipment in the intelligent factory according to claim 1, characterized in that, The expression of the current-power influence value is: Where M i represents the current power influence value in the i-th time period; G i represents the trend noise significance of the power sequence within the i-th time period; H i Indicates the trend noise significance of the current sequence within the i-th time period; μ i represents the mean of the normalized values of all data in the power sequence during the i-th time period; L i represents the Spearman correlation coefficient between the current sequence and the power sequence during the i-th time period; β represents a preset value greater than 0.

6. The fault diagnosis method for auxiliary power station equipment oriented to intelligent factories according to claim 1, characterized in that, The determination process of the load vibration difference of the boiler feed pump is: Calculate the difference between the vibration anomaly value and the current power influence value corresponding to each time period, which is denoted as the comprehensive difference; Take the fusion result of the dispersion degree of the comprehensive differences of all time periods and the range of the vibration anomaly values corresponding to all time periods as the load vibration difference of the boiler feed pump.

7. The fault diagnosis method for auxiliary power station equipment oriented to intelligent factories according to claim 1, characterized in that The method for fault diagnosis of the boiler feed pump is as follows: When the normalized value of the load vibration difference of the boiler feed pump is greater than the preset fault anomaly threshold, it is determined that the boiler feed pump has a fault; otherwise, there is no fault.

8. A power plant auxiliary equipment fault diagnosis system for an intelligent factory, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the fault diagnosis method for power station auxiliary equipment facing the intelligent factory according to any one of claims 1-7.

Images