A vacuum pump fault monitoring method and system

By extracting and analyzing the characteristics of vacuum pump failure data, the fault frequency and severity index of the functional module are calculated, and the failure risk index is determined, which can accurately locate and quickly deal with vacuum pump failures, and solve the efficiency of vacuum pump failure monitoring in the existing technology and The accuracy issue improves the stability and production efficiency of the production line.

CN118375603BActive Publication Date: 2024-11-29SHANDONG YINING ENVIRONMENTAL PROTECTION TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410824817.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-25
Publication Date
2024-11-29
Estimated Expiration
2044-06-25

AI Technical Summary

Technical Problem

The prior art is difficult to detect and accurately deal with when monitoring and positioning vacuum pump failures, especially when complex failures involving multiple functional modules, which affects the stable operation and production efficiency of the production line.

Method used

By obtaining vacuum pump failure data, extracting parameters, analyzing failure modes, calculating the failure frequency and severity index of the functional module, determining the failure risk index, calculating the weight of each functional module, analyzing the failure module and cause, determining the troubleshooting path, and realizing the failure Accurate positioning and fast processing.

Benefits of technology

Improve the efficiency and accuracy of fault detection, reasonably arrange maintenance plans, reduce overall failure rate, save maintenance costs and time, improve the operating reliability and stability of vacuum pumps, and reduce the risk of production interruptions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118375603B_ABST
    Figure CN118375603B_ABST
Patent Text Reader

Abstract

The present invention provides a vacuum pump fault monitoring method and system, which relates to the field of artificial intelligence technology. The method includes: analyzing the failure mode in the vacuum pump fault data according to the vacuum pump parameters to calculate the frequency and severity index of each functional module failure; determining the failure risk index of each functional module according to the frequency and severity index of each functional module failure; calculating the weight corresponding to each functional module according to the failure risk index; analyzing the failure risk index of each functional module to determine the vacuum pump fault module; analyzing the historical failure risk index and operation log of the vacuum pump fault module to determine the cause of the vacuum pump failure; determining the troubleshooting path that ultimately leads to the vacuum pump failure according to the cause of the vacuum pump failure. The present invention can monitor the operating status of the vacuum pump in real time, discover and handle faults in time, and improve the accuracy and efficiency of fault troubleshooting.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a vacuum pump fault monitoring method and system. Background Art

[0002] On the production line of a large manufacturing company, a vacuum pump device is responsible for providing the necessary vacuum environment for the process. In order to ensure the stable operation of the equipment, the company has long adopted traditional manual inspections and regular maintenance strategies.

[0003] However, during a production process, the operator noticed that the vacuum pump's exhaust efficiency had decreased, but the specific cause was not immediately identified. During the subsequent regular inspections, the technicians were unable to accurately find the fault point and only performed some routine inspections and adjustments. A few days later, the performance of the vacuum pump further deteriorated, directly affecting the stable operation of the production line. At this time, it was decided to conduct in-depth inspections and repairs. After a series of investigations, it was found that the fault involved multiple functional modules of the vacuum pump, including the sealing system, cooling system, and exhaust system.

[0004] Therefore, although manual inspection and regular maintenance can prevent certain failures to a certain extent, the limitations of this method are revealed when facing complex equipment such as vacuum pumps. It may not be able to detect and handle some potential complex failures involving multiple functional modules in a timely manner. In addition, when a failure actually occurs, traditional methods may find it difficult to accurately and quickly locate the specific cause, thus affecting the stable operation of the production line and the production efficiency of the enterprise. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a vacuum pump fault monitoring method and system, which can monitor the operating status of the vacuum pump in real time, discover and handle faults in time, and improve the accuracy and efficiency of fault detection.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] In a first aspect, a vacuum pump fault monitoring method is provided, the method comprising:

[0008] Acquire vacuum pump fault data, and perform feature extraction on the vacuum pump fault data to extract vacuum pump parameters;

[0009] According to the vacuum pump parameters, the failure modes in the vacuum pump fault data are analyzed to calculate the frequency and severity index of the failure of each functional module;

[0010] Determine the failure risk index of each functional module based on the frequency and severity index of failures in each functional module;

[0011] According to the failure risk index, calculate the weight corresponding to each functional module;

[0012] Analyze the failure risk index of each functional module to determine the vacuum pump failure module;

[0013] According to the vacuum pump failure module, analyze its historical failure risk index and operation log to determine the cause of the vacuum pump failure;

[0014] According to the cause of the vacuum pump failure, determine the troubleshooting path that ultimately leads to the vacuum pump failure.

[0015] Furthermore, vacuum pump fault data is obtained, and feature extraction is performed on the vacuum pump fault data to extract vacuum pump parameters, including:

[0016] Obtain vacuum pump fault data of the vacuum pump;

[0017] Preprocessing the vacuum pump fault data to obtain preprocessed data;

[0018] According to the preprocessed data, the number of clusters k is determined, and k data points are randomly determined as the initial cluster centers;

[0019] Calculate the distance between each data point and each cluster center, and assign the data point to the corresponding cluster center. For each cluster, calculate the average value of all data points within it, and set the average value as the new cluster center.

[0020] Repeat the steps until the preset number of iterations is reached to obtain the cluster analysis results;

[0021] According to the cluster analysis results, the data in each cluster is analyzed to extract the vacuum pump parameters related to vacuum pump failure. The vacuum pump parameters include temperature, pressure and vibration frequency.

[0022] Further, the vacuum pump fault data is preprocessed to obtain preprocessed data, including:

[0023] The number of wavelet transform layers is determined by Fourier transform; according to the number of wavelet transform layers, the vacuum pump fault data is convolved with the wavelet basis function to obtain a series of wavelet coefficients, and the wavelet transform is repeated until the number of wavelet transform layers is reached, and each iteration will generate new approximate coefficients and detail coefficients;

[0024] Threshold processing is performed on all the obtained new approximate coefficients and detail coefficients to obtain processed wavelet coefficients;

[0025] Perform wavelet reconstruction on the processed wavelet coefficients to obtain the denoised signal;

[0026] According to the original value of the denoised signal, it is proportionally converted into a value within the target range to obtain preprocessed data.

[0027] Furthermore, according to the vacuum pump parameters, the failure modes in the vacuum pump fault data are analyzed to calculate the frequency and severity index of the failure of each functional module, including:

[0028] Based on the vacuum pump failure data, the failure modes are classified to divide the equipment into different functional modules;

[0029] For each functional module, determining the number of times a failure occurs in the vacuum pump failure data, and calculating the failure frequency of each functional module;

[0030] According to the failure frequency of each functional module, Calculate the corresponding severity index, where is the severity index, is the fault frequency, It’s downtime; is the maintenance cost; is the failure recovery time; is the probability of failure occurring; is the maximum acceptable downtime; is the maximum acceptable repair cost; is the maximum acceptable fault recovery time; is the maximum acceptable probability of failure.

[0031] Furthermore, according to the frequency and severity index of failure of each functional module, the failure risk index of each functional module is determined, including:

[0032] According to the frequency and severity index of failure of each functional module, Calculate the failure risk index of each functional module, where: is the failure risk index; is the weight coefficient of the i-th influencing factor; is the value of the i-th influencing factor; n is the number of influencing factors, and the summation symbol It means to sum all items from i=1 to i=n, ​​where i is the index.

[0033] Furthermore, according to the failure risk index, the weight corresponding to each functional module is calculated, including:

[0034] According to the failure risk index, Calculate the weights corresponding to each functional module, where: Represents the weight of the jth functional module; represents the failure risk index of the jth functional module; Represents the criticality coefficient of the jth functional module; Represents the usage frequency coefficient of the jth functional module; Indicates the total number of functional modules; Represents the sum of the adjusted failure risk indexes of all functional modules, j and k are index variables; the summation symbol express Change from 1 to , the adjustment failure risk index of all functional modules is accumulated.

[0035] Furthermore, the failure risk index of each functional module is analyzed to determine the vacuum pump failure module, including:

[0036] Compare and analyze the failure risk index of each functional module, and obtain the change trend of the failure risk index by comparing the failure risk index of different modules;

[0037] According to the changing trend of the failure risk index, a comprehensive evaluation is conducted on the functional modules to determine the vacuum pump fault module.

[0038] In a second aspect, a vacuum pump fault monitoring system includes:

[0039] An acquisition module is used to acquire vacuum pump fault data and perform feature extraction on the vacuum pump fault data to extract vacuum pump parameters; analyze failure modes in the vacuum pump fault data according to the vacuum pump parameters to calculate the frequency and severity index of failure of each functional module; determine the failure risk index of each functional module according to the frequency and severity index of failure of each functional module;

[0040] The processing module is used to calculate the weight corresponding to each functional module according to the failure risk index; analyze the failure risk index of each functional module to determine the vacuum pump failure module; analyze the historical failure risk index and operation log of the vacuum pump failure module to determine the cause of the vacuum pump failure; and determine the troubleshooting path that ultimately leads to the vacuum pump failure according to the cause of the vacuum pump failure.

[0041] According to a third aspect, a computing device includes:

[0042] one or more processors;

[0043] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0044] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0045] The above solution of the present invention includes at least the following beneficial effects:

[0046] By extracting and analyzing the features of vacuum pump fault data, this method can quickly identify the faulty module, thereby greatly improving the efficiency and accuracy of fault detection. By calculating the frequency and severity index of failures in each functional module, potential faults can be discovered in a timely manner. According to the failure risk index and the weight of the functional module, the company can arrange maintenance plans more reasonably, give priority to high-risk modules, and reduce the overall failure rate. By accurately locating the faulty module and the cause, unnecessary comprehensive overhauls are avoided, saving maintenance costs and time. Through continuous monitoring and timely troubleshooting, the operating reliability and stability of the vacuum pump can be significantly improved, and the risk of production interruptions can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of a vacuum pump fault monitoring method provided by an embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of a vacuum pump fault monitoring system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in a form and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0050] like Figure 1 As shown, an embodiment of the present invention provides a vacuum pump fault monitoring method, the method comprising the following steps:

[0051] Step 11, acquiring vacuum pump fault data, and performing feature extraction on the vacuum pump fault data to extract vacuum pump parameters;

[0052] Step 12, analyzing the failure modes in the vacuum pump fault data according to the vacuum pump parameters to calculate the frequency and severity index of the failure of each functional module;

[0053] Step 13, determining the failure risk index of each functional module according to the frequency and severity index of failure of each functional module;

[0054] Step 14, calculating the weight corresponding to each functional module according to the failure risk index;

[0055] Step 15, analyzing the failure risk index of each functional module to determine the vacuum pump fault module;

[0056] Step 16, analyzing the historical failure risk index and operation log of the vacuum pump failure module to determine the cause of the vacuum pump failure;

[0057] Step 17, according to the cause of the vacuum pump failure, determine the troubleshooting path that ultimately causes the vacuum pump failure.

[0058] In the embodiment of the present invention, step 11 can collect comprehensive and specific fault data, and through feature extraction, the key parameters related to the performance and status of the vacuum pump can be accurately identified. Step 12, through the analysis of the failure mode, the fault conditions of each functional module can be deeply understood, and the calculation of the fault frequency and severity index is helpful to quantitatively evaluate the impact of the fault. Step 13, the determination of the failure risk index can help enterprises more intuitively understand the risk of failure of each functional module. Step 14, by calculating the weight, the importance of each functional module in the overall equipment operation can be clarified. Step 15, the module that may fail can be quickly and accurately located, which improves the efficiency and accuracy of troubleshooting and shortens the equipment downtime. Step 16, through the analysis of historical data and operation logs, the root cause of the fault can be deeply understood. Step 17, determining the troubleshooting path can help maintenance personnel quickly and accurately find and solve the problem, improve maintenance efficiency, reduce maintenance costs, and also help prevent similar faults from happening again.

[0059] In a preferred embodiment of the present invention, the above step 11 may include:

[0060] Step 111, obtaining vacuum pump fault data of the vacuum pump;

[0061] Step 112, preprocessing the vacuum pump fault data to obtain preprocessed data;

[0062] Step 113, determining the number of clusters k based on the preprocessed data, and randomly determining k data points as initial cluster centers;

[0063] Step 114, calculating the distance between each data point and each cluster center, and assigning the data point to the corresponding cluster center. For each cluster, calculating the average value of all data points within it, and setting the average value as the new cluster center;

[0064] Step 115, repeat the steps until a preset number of iterations is reached to obtain a cluster analysis result;

[0065] Step 116, according to the cluster analysis result, analyze the data in each cluster, extract the vacuum pump parameters related to the vacuum pump failure, the vacuum pump parameters include temperature, pressure and vibration frequency, through cluster analysis, it is possible to identify the parameters closely related to the failure.

[0066] In the embodiment of the present invention, step 111 collects data from sensors installed on the vacuum pump, and the sensor readings include temperature, pressure, vibration and other parameters. Step 112 denoises the vacuum pump fault data, and then normalizes the data to make the numerical ranges of different parameters consistent. Step 113 sets a cluster number range, for example, from 2 to a certain upper limit value (this upper limit value can be set according to the characteristics of the data and actual needs); for each k value in the range, perform the following operations:

[0067] Use the k-means algorithm to cluster the data, calculate and record the degree of distortion of each cluster (that is, the sum of the distances from each data point to the center of the cluster to which it belongs), and draw a curve chart of the k value and the corresponding degree of distortion; observe the curve chart and find the "elbow" position, that is, the point where the rate of change of the degree of distortion begins to decrease significantly. The k value corresponding to this point is usually considered to be the optimal number of clusters; randomly select k data points from the preprocessed data as the initial cluster centers:

[0068] After determining the optimal number of clusters k, randomly select k different data points from the preprocessed data set, ensure that these k data points are not repeated, and are distributed as much as possible in the entire data space to improve the initial quality of clustering, and set these k data points as the initial cluster centers. Step 114, traverse each data point in the data set, for each data point, use the Euclidean distance formula to calculate its distance from all current cluster centers; find the cluster center closest to the data point, and assign the data point to that cluster; for each cluster, collect all the data points assigned to the cluster, calculate the average value of these data points in each dimension, this average value will become the new cluster center coordinates, and update the center of the cluster to the calculated new average value. Step 115, set an iteration counter and a change threshold (used to detect whether the change of the cluster center is less than a preset value), start iteration, and perform the operations in step 114 (calculate distance, assign data points, update cluster center) in each iteration. After each iteration, compare the difference between the current cluster center and the cluster center in the previous iteration. If the difference is less than the preset change threshold or the preset maximum number of iterations is reached, stop the iteration. Step 116, for each cluster, examine the common features and differences of the data points therein, analyze how these features are associated with the failure mode of the vacuum pump, observe which parameters show significant changes or outliers in a specific cluster based on the data points in the cluster, and identify the parameters most related to the vacuum pump failure, including temperature, pressure, and vibration frequency; from each cluster related to the failure, extract those parameters that have changed significantly as key parameters.

[0069] In a preferred embodiment of the present invention, the above step 112 may include:

[0070] Step 1121, determine the number of wavelet transform layers by Fourier transform; according to the number of wavelet transform layers, convolve the vacuum pump fault data with the wavelet basis function to obtain a series of wavelet coefficients, and repeat the wavelet transform until the number of wavelet transform layers is reached. Each iteration will generate new approximate coefficients and detail coefficients, specifically including: Perform Fourier transform to analyze its frequency components. Fourier transform converts time domain signals into frequency domain signals. , to obtain the different frequency components and their amplitudes in the signal. The specific calculation formula is:

[0071] ;

[0072] in, ,in, is an imaginary unit, is a frequency variable, and is the amplitude, and is the angular frequency, and is the initial phase, is the attenuation coefficient; It is a time variable, representing the value of the signal at different time points;

[0073] By observing the frequency domain signal , we can determine the main frequency components in the signal. If the signal mainly contains low-frequency components, select fewer wavelet transform layers L; if the signal contains rich high-frequency information, more wavelet transform layers L are needed to capture these details; set the initial wavelet transform layer number ( l =1), and obtain vacuum pump fault data in discrete form ,in, Represents the sampling points, for each layer l , do the following:

[0074] Using wavelet basis functions Discrete form of vacuum pump fault data Perform convolution and extract and location The calculation formula is as follows:

[0075] ;

[0076] In discrete form, this formula performs the corresponding summation operation, where It is in l Layers and Positions The wavelet coefficients at represents the conjugate of the wavelet basis function, is the scale parameter.

[0077] Through wavelet transform, the signal is decomposed into approximate coefficients and detail factor , the calculation formula is:

[0078] ;

[0079] ;

[0080] Among them, among them, and are the low-pass and high-pass filter coefficients, respectively; is an index that traverses the wavelet coefficient position; if the current layer number l If it is less than the predetermined number of layers L, then increase l (Right now l = l+1), and use the approximate coefficient of the previous layer As input data for the next layer , repeat the above wavelet transform steps until the predetermined number of layers L is reached. Finally, a series of wavelet coefficients will be obtained, including the approximate coefficients of each layer. and detail factor ;

[0081] Step 1122, threshold processing is performed on all the obtained new approximation coefficients and detail coefficients to obtain processed wavelet coefficients, specifically including: for the approximation coefficients and detail coefficients at each scale, their sizes are checked one by one, if the absolute value of a wavelet coefficient is lower than the set threshold, it is set to zero (hard threshold processing), if the absolute value of the wavelet coefficient is higher than or equal to the threshold, the original value is retained (hard threshold); the new wavelet coefficients after threshold processing are saved;

[0082] Step 1123, performing wavelet reconstruction on the processed wavelet coefficients to obtain the denoised signal, specifically including: starting from the approximate coefficients of the highest layer (or the coarsest scale), reconstructing layer by layer, at each layer, using the detail coefficients of the corresponding layer and the approximate signal of the previous layer to restore the signal of a finer scale; upsampling the approximate signal of the previous layer (i.e., inserting zeros or interpolating between every two samples); using the same wavelet basis function as that used in the decomposition The corresponding reconstruction filter performs a convolution operation on the upsampled approximate signal, adds the convolution-operated approximate signal to the detail coefficient of the current layer, and obtains the reconstructed signal of the current scale. The above process is repeated until the finest scale (that is, the scale of the original signal) is reached. After reaching the finest scale, a reconstructed signal with the same length as the original signal is obtained.

[0083] Step 1124, according to the original numerical value of the denoised signal, convert it into a numerical value within the target range in proportion to obtain preprocessed data, specifically including: traversing the denoised signal data, checking the value of each data point, and recording the maximum and minimum values ​​encountered during the traversal process, which will represent the original numerical range of the denoised signal; setting a target numerical range according to application requirements or subsequent processing requirements, such as [0, 1], [-1, 1]; using the maximum and minimum values ​​found, calculating the size of the original numerical range (maximum value, minimum value); determining the size of the target range (target maximum value, target minimum value); dividing the target range size by the original range size to obtain a conversion ratio, which will be used to map the original data points into the target range; traversing the denoised signal data again, for each data point, first subtracting the minimum value, then multiplying it by the conversion ratio, and finally adding the minimum value of the target range, so that the original data point can be converted into the target range.

[0084] In an embodiment of the present invention, the noise components in the vacuum pump fault data can be effectively removed by wavelet transform and threshold processing. Noise often interferes with data analysis and affects the extraction and identification of fault features. This process can significantly improve the signal-to-noise ratio of the signal, making subsequent data analysis more accurate. Wavelet transform can decompose the signal into components of different frequencies and scales, and show the rough outline and detailed changes of the signal through approximate coefficients and detail coefficients; wavelet transform has excellent data compression performance. By thresholding the wavelet coefficients, those coefficients that have little effect on signal reconstruction can be removed, and data compression storage can be achieved, storage space can be saved, and data processing efficiency can be improved. The number of layers of wavelet transform can be adjusted according to actual needs, so as to analyze signals at different scales. The data conversion operation in step 1124 can convert the denoised signal value into the target range in proportion to achieve data standardization.

[0085] In a preferred embodiment of the present invention, the above step 12 may include:

[0086] Step 121, classifying the failure modes according to the vacuum pump failure data to divide the equipment into different functional modules;

[0087] Step 122, for each functional module, determining the number of times a fault occurs in the vacuum pump fault data, and calculating the fault frequency of each functional module;

[0088] Step 123, according to the failure frequency of each functional module, Calculate the corresponding severity index, where is the severity index, is the fault frequency, It’s downtime; is the maintenance cost; is the failure recovery time; is the probability of failure occurring; is the maximum acceptable downtime; is the maximum acceptable repair cost; is the maximum acceptable fault recovery time; is the maximum acceptable probability of failure.

[0089] In an embodiment of the present invention, step 121 classifies the failure modes of the vacuum pump, which helps to more systematically understand and analyze the different types of failures of the equipment. Through the functional module division, the fault point can be located more specifically. Step 122 counts the number of failures of each functional module and calculates the failure frequency, which helps to identify which modules are more prone to failure. Step 123 can more comprehensively reflect the impact of failures of different functional modules on the overall operation and economic benefits of the equipment, allocate maintenance resources more accurately, and give priority to functional modules with high severity indexes, thereby reducing overall operational risks. It also helps to improve the overall operating efficiency and reliability of the equipment, reduce unexpected downtime, and ensure the stable operation of the production line.

[0090] In a preferred embodiment of the present invention, the above step 13 may include:

[0091] Step 131, according to the frequency and severity index of failure of each functional module, Calculate the failure risk index of each functional module, where: is the failure risk index; is the weight coefficient of the i-th influencing factor; is the value of the i-th influencing factor, such as temperature, pressure, vibration and other specific values; n is the number of influencing factors, and the summation symbol It means to sum all items from i=1 to i=n, ​​where i is the index.

[0092] In the embodiment of the present invention, the failure risk index comprehensively considers the failure frequency, severity index and multiple influencing factors, and provides a comprehensive and integrated evaluation index, which helps to more accurately evaluate the actual risk level of each functional module. By quantifying the failure risk of each functional module into a specific numerical value, the risk levels of different modules can be intuitively compared, which helps enterprises to more clearly understand the risk status of each part of the equipment; through the calculation of the failure risk index, high-risk functional modules can be identified, which helps to take corresponding measures before the failure occurs, reduce the probability and impact of the failure, and improve the reliability and stability of the equipment.

[0093] In a preferred embodiment of the present invention, the above step 14 may include:

[0094] Step 141, according to the failure risk index, Calculate the weights corresponding to each functional module, where: Represents the weight of the jth functional module; represents the failure risk index of the jth functional module; Represents the criticality coefficient of the jth functional module; Represents the usage frequency coefficient of the jth functional module; Indicates the total number of functional modules; represents the sum of the adjusted failure risk indexes of all functional modules, j and are all index variables; summation symbol express Change from 1 to , the adjustment failure risk index of all functional modules is accumulated.

[0095] In an embodiment of the present invention, by calculating the weight of each functional module, resources can be allocated to each module more accurately. Modules with high weights mean a greater impact on the overall performance of the equipment, so these modules can be given priority for maintenance or upgrades to ensure that resources are used most effectively. This process takes into account the failure risk index, criticality coefficient, and usage frequency coefficient, thereby comprehensively evaluating the importance of each functional module, which helps companies to more accurately understand the role of each module in equipment operation; for modules with higher weights, more frequent maintenance measures can be taken to reduce the possibility of failures; for modules with lower weights, the maintenance frequency can be appropriately reduced to save costs. By focusing on the maintenance of important modules, the overall reliability of the equipment can be significantly improved. This helps to reduce unexpected downtime and ensure the stable operation of the production line.

[0096] In a preferred embodiment of the present invention, the above step 15 may include:

[0097] Step 151, comparing and analyzing the failure risk index of each functional module, and obtaining a change trend of the failure risk index by comparing the failure risk indexes of different modules;

[0098] Step 152 : Comprehensively evaluate the functional modules according to the change trend of the failure risk index to determine the vacuum pump fault module.

[0099] In an embodiment of the present invention, step 151, obtain the failure risk index of each functional module from the previous step or record; use a chart tool (such as Excel, Tableau or other data analysis software) to create a comparison chart of the failure risk index, select an appropriate chart type, such as a bar chart, a line chart or a radar chart, so as to clearly display the failure risk index of different functional modules; compare the failure risk indexes of different functional modules on the chart to observe which modules have a higher failure risk index and which have a lower failure risk index. If there are multiple periods of data, they can be arranged in chronological order to observe the changing trend of the failure risk index, and by analyzing the data at consecutive time points, it is identified whether the failure risk index presents an upward, downward or stable trend. Step 152, based on the failure risk index and its changing trend, each functional module is evaluated, and through comprehensive evaluation, those functional modules with high failure risk index and an upward trend are identified. For example, assuming that there is a vacuum pump system, which includes three main functional modules: module A (intake system), module B (compression system) and module C (exhaust system). The failure risk index of each module has been obtained through previous analysis.

[0100] The failure risk index of module A has risen from 0.3 to 0.5 in the past three months; the failure risk index of module B has remained stable at around 0.2; and the failure risk index of module C has risen rapidly from 0.4 to 0.8. Comparing the failure risk indexes of the three modules, we can see that the index of module C is not only high, but also has a clear upward trend; although module A has risen, the current risk index is still at a medium level; the risk index of module B has remained at a low level and has been stable. Based on the above analysis, it can be determined that module C is the current high-risk module, which is likely to have a fault or is about to fail. Module A needs to continue to be monitored, but the current risk level has not reached an emergency state. Module B can continue to operate normally without special attention. For module C, immediately conduct detailed fault diagnosis, find out the specific reasons for the increase in failure risk, and take corresponding maintenance or repair measures. For module A, monitoring should be strengthened and regular inspections should be carried out to ensure its stable performance. For module B, routine maintenance can be carried out according to the normal plan.

[0101] In another preferred embodiment of the present invention, the above step 16 may include:

[0102] Step 161, starting from the previously determined vacuum pump fault module, collect the historical failure risk index data of the module. These data should include the risk index values ​​at different time points for time series analysis; at the same time, obtain the operation log of the module, which should include the start and stop time of the module, the operation status, any abnormal records, and possible error codes or warning information. The collected historical failure risk index data are sorted into a time series format, and the operation log is preprocessed to extract key information, such as the time, type, and frequency of abnormal occurrence, and remove information irrelevant to the fault analysis. Draw a time series graph of the historical failure risk index, observe the fluctuation of the risk index, especially pay attention to the time period when the risk index rises significantly; analyze the data characteristics of the stable period and the rising period before the risk index rises, and compare the index changes in different time periods to find possible triggering factors. Carefully read the operation log, especially the log records corresponding to the time period when the failure risk index rises, find and record all abnormal events, such as excessive temperature, abnormal pressure, current fluctuations, etc., which may be the direct cause of the fault, and analyze the correlation and frequency of occurrence between abnormal events to determine whether there is a certain pattern or periodic law. Combine the results of the failure risk index analysis and the operation log analysis to infer possible causes of failure. For example, if frequent current fluctuations occur before the failure risk index rises, then current instability may be one of the causes of module failure. Consider a variety of factors, such as equipment aging, improper maintenance, and changes in the external environment, to derive a comprehensive cause of failure. Organize the analysis results into a report that lists the faulty module, the trend of the failure risk index, key abnormal records in the operation log, and the inferred cause of failure.

[0103] In another preferred embodiment of the present invention, the above step 17 may include:

[0104] Step 171, from the list of vacuum pump failure causes analyzed in step 16, score each failure cause according to the likelihood and the degree of impact on the operation of the vacuum pump. For example, a scoring system of 1-10 may be used, where 10 represents the most likely and has the greatest impact, and 1 represents the least likely and has the least impact; based on the scoring results, sort the failure causes from high to low to ensure that the most likely and most impactful causes are dealt with first.

[0105] For the sorted fault causes, start to develop a preliminary troubleshooting plan. For each fault cause, list the possible troubleshooting directions and methods. For example, if the fault cause is unstable current, the preliminary plan may include: checking the integrity and connection of the power supply line, using a voltmeter and an ammeter to measure the actual voltage and current fluctuations, and evaluating whether the quality of the power supply meets the operating requirements of the vacuum pump. For each direction in the preliminary troubleshooting plan, design a specific troubleshooting path. Taking unstable current as an example, the detailed troubleshooting path is as follows:

[0106] First, turn off the vacuum pump and use a multimeter or special test tool to check the power line to confirm that the line is intact and the joints are tight. Next, start the vacuum pump and use a voltmeter and ammeter to monitor the changes in voltage and current in real time during operation, and record any abnormal fluctuations. If abnormal voltage or current is found, further evaluation of the power quality may require the use of a power quality analyzer to detect harmonics, voltage drops, and other problems in the power supply. For each troubleshooting path, determine the specific operations for each step. For example, when checking the power line, it is necessary to remove part of the casing to expose the line, or use a specific test probe for contact testing. Set the expected results for each step. For example, when checking the power line, the expected line should be intact and the joints should not be loose. Plan possible next steps. If the results of a step are not as expected, the next inspection or test content should be clarified.

[0107] Perform actual operations according to the detailed troubleshooting paths and steps designed. During the execution process, record the operation conditions, observed phenomena, and measured data of each step in detail, and compare the actual results with the expected results. If they are consistent, proceed to the next step; if they are inconsistent, record the abnormal situation and adjust the troubleshooting path according to the situation. Through the above steps, the vacuum pump fault troubleshooting work can be carried out in a more systematic and orderly manner, improving the troubleshooting efficiency and accuracy.

[0108] like Figure 2 As shown, an embodiment of the present invention further provides a vacuum pump fault monitoring system 20, comprising:

[0109] The acquisition module 21 is used to acquire vacuum pump fault data and perform feature extraction on the vacuum pump fault data to extract vacuum pump parameters; analyze the failure mode in the vacuum pump fault data according to the vacuum pump parameters to calculate the frequency and severity index of failure of each functional module; determine the failure risk index of each functional module according to the frequency and severity index of failure of each functional module;

[0110] The processing module 22 is used to calculate the weight corresponding to each functional module according to the failure risk index; analyze the failure risk index of each functional module to determine the vacuum pump failure module; analyze the historical failure risk index and operation log of the vacuum pump failure module to determine the cause of the vacuum pump failure; and determine the troubleshooting path that ultimately leads to the vacuum pump failure according to the cause of the vacuum pump failure.

[0111] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0112] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0113] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0114] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0116] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0119] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a medium that can store program code, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0120] In addition, it should be pointed out that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it can be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in hardware, firmware, software or a combination thereof in any computing device (including processors, storage media, etc.) or a network of computing devices, which can be achieved by those of ordinary skill in the art using basic programming skills after reading the description of the present invention.

[0121] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0122] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring a vacuum pump failure. It is characterized in that The method comprises: Acquire vacuum pump fault data, and perform feature extraction on the vacuum pump fault data to extract vacuum pump parameters; According to the vacuum pump parameters, the failure modes in the vacuum pump fault data are analyzed to calculate the frequency and severity index of the failure of each functional module; Determine the failure risk index of each functional module based on the frequency and severity index of failures in each functional module; According to the failure risk index, calculate the weight corresponding to each functional module; Analyze the failure risk index of each functional module to determine the vacuum pump failure module; According to the vacuum pump failure module, analyze its historical failure risk index and operation log to determine the cause of the vacuum pump failure; According to the cause of the vacuum pump failure, determine the troubleshooting path that ultimately leads to the vacuum pump failure; Obtain vacuum pump fault data and perform feature extraction on the vacuum pump fault data to extract vacuum pump parameters, including: Obtain vacuum pump fault data of the vacuum pump; Preprocessing the vacuum pump fault data to obtain preprocessed data; According to the preprocessed data, the number of clusters k is determined, and k data points are randomly determined as the initial cluster centers; Calculate the distance between each data point and each cluster center, and assign the data point to the corresponding cluster center. For each cluster, calculate the average value of all data points within it, and set the average value as the new cluster center. Repeat the steps until the preset number of iterations is reached to obtain the cluster analysis results; According to the cluster analysis results, the data in each cluster is analyzed to extract the vacuum pump parameters related to the vacuum pump failure, and the vacuum pump parameters include temperature, pressure and vibration frequency; The vacuum pump fault data is preprocessed to obtain preprocessed data, including: The number of wavelet transform layers is determined by Fourier transform; according to the number of wavelet transform layers, the vacuum pump fault data is convolved with the wavelet basis function to obtain a series of wavelet coefficients, and the wavelet transform is repeated until the number of wavelet transform layers is reached, and each iteration will generate new approximate coefficients and detail coefficients; Threshold processing is performed on all the obtained new approximate coefficients and detail coefficients to obtain processed wavelet coefficients; Perform wavelet reconstruction on the processed wavelet coefficients to obtain the denoised signal; According to the original value of the denoised signal, the signal is proportionally converted into a value within the target range to obtain preprocessed data; According to the vacuum pump parameters, the failure modes in the vacuum pump fault data are analyzed to calculate the frequency and severity index of failures in each functional module, including: Based on the vacuum pump failure data, the failure modes are classified to divide the equipment into different functional modules; For each functional module, determining the number of times a failure occurs in the vacuum pump failure data, and calculating the failure frequency of each functional module; According to the failure frequency of each functional module, Calculate the corresponding severity index, where is the severity index, is the fault frequency, It’s downtime; is the maintenance cost; is the failure recovery time; is the probability of failure occurring; is the maximum acceptable downtime; is the maximum acceptable repair cost; is the maximum acceptable fault recovery time; is the maximum acceptable probability of failure; According to the frequency and severity index of failures in each functional module, the failure risk index of each functional module is determined, including: According to the frequency and severity index of failure of each functional module, Calculate the failure risk index of each functional module, where: is the failure risk index; is the weight coefficient of the i-th influencing factor; is the value of the i-th influencing factor; n is the number of influencing factors, and the summation symbol It means to sum all items from i=1 to i=n, ​​where i is the index; According to the failure risk index, the weight corresponding to each functional module is calculated, including: According to the failure risk index, Calculate the weights corresponding to each functional module, where: Represents the weight of the jth functional module; represents the failure risk index of the jth functional module; Represents the criticality coefficient of the jth functional module; Represents the usage frequency coefficient of the jth functional module; Indicates the total number of functional modules; represents the sum of the adjusted failure risk indexes of all functional modules, j and are all index variables; summation symbol express Change from 1 to , the adjustment failure risk index of all functional modules is accumulated.

2. The vacuum pump fault monitoring method according to claim 1, It is characterized in that The failure risk index of each functional module is analyzed to determine the vacuum pump failure module, including: Compare and analyze the failure risk index of each functional module, and obtain the change trend of the failure risk index by comparing the failure risk index of different modules; According to the changing trend of the failure risk index, a comprehensive evaluation is conducted on the functional modules to determine the vacuum pump fault module.

3. A vacuum pump fault monitoring system, It is characterized in that The method as claimed in any one of claims 1 to 2 comprises: An acquisition module is used to acquire vacuum pump fault data and perform feature extraction on the vacuum pump fault data to extract vacuum pump parameters; analyze failure modes in the vacuum pump fault data according to the vacuum pump parameters to calculate the frequency and severity index of failure of each functional module; determine the failure risk index of each functional module according to the frequency and severity index of failure of each functional module; The processing module is used to calculate the weight corresponding to each functional module according to the failure risk index; analyze the failure risk index of each functional module to determine the vacuum pump failure module; analyze the historical failure risk index and operation log of the vacuum pump failure module to determine the cause of the vacuum pump failure; and determine the troubleshooting path that ultimately leads to the vacuum pump failure according to the cause of the vacuum pump failure.

4. A computing device, It is characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 2.

5. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a program, which implements the method according to any one of claims 1 to 2 when executed by a processor.

Citation Information

Patent Citations

  • A modeling method for a hybrid fault early warning model and the hybrid fault early warning model.

    CN102262690A

  • Fault detection method and system based on wavelet transform and neural network, and medium

    CN113670610A