Equipment fault analysis and estimation system and method based on frequency domain characteristics

Abstract

The invention relates to a frequency domain characteristic-based equipment fault analysis and estimation system and method, and relates to the field of data processing. The method comprises the following steps of: acquiring a vibration signal in an operation process of target equipment, performing frequency domain processing to obtain a side frequency parameter, and performing side frequency reproduction analysis in historical equipment frequency domain data to obtain a side frequency reproduction coefficient; a workpiece machining image of the workpiece in the machining process of the target equipment is collected, workpiece anomaly analysis is carried out, and workpiece anomaly parameters are obtained; configuring a fault identification strategy according to the side frequency reproduction coefficient and a workpiece abnormal parameter, and performing fault identification on the side frequency parameter to obtain a first fault rate; according to the side frequency parameter, calculating to obtain a second fault rate, and combining with the first fault rate, calculating to obtain an equipment fault rate as an equipment fault analysis and estimation result, thereby solving the technical problems that the fault detection efficiency is low and the fault occurrence is difficult to accurately predict.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a system and method for analyzing and predicting equipment faults based on frequency domain characteristics. Background Art

[0002] In modern industrial production, the stable operation of equipment is crucial to production efficiency and product quality. However, as the equipment runs for a long time, its internal components often fail due to wear, aging or external environmental factors, thus affecting production progress and product quality. Traditional equipment fault detection methods usually rely on manual inspections and empirical judgments, which are not only inefficient but also difficult to accurately predict the occurrence of faults. In order to overcome the shortcomings of traditional equipment fault detection methods, the prior art proposes a fault prediction technology based on data analysis. Among them, frequency domain analysis, as an effective signal processing method, is widely used in the field of equipment fault diagnosis. Frequency domain analysis can extract frequency domain features related to the operating status of the equipment by converting the vibration signal of the equipment from the time domain to the frequency domain. These frequency domain features can reflect the vibration state of the internal components of the equipment, thereby providing a strong basis for fault prediction. However, there are still limitations to fault prediction based on frequency domain analysis alone. The reality is that equipment failures are often related to multiple factors. In addition to vibration signals, abnormalities of the workpiece during processing are also one of the important fault precursors. For example, abnormal phenomena such as deformation and cracks during the processing of the workpiece are often closely related to the operating status of the equipment. Therefore, how to further improve the accuracy of fault analysis and ensure the maintenance and servicing conditions of equipment deserves further attention. Summary of the invention

[0003] The present invention aims to solve the technical problems in the prior art that fault detection efficiency is low and it is difficult to accurately predict the occurrence of faults, and provides a system and method for analyzing and predicting equipment faults based on frequency domain characteristics.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a system for analyzing and predicting equipment faults based on frequency domain characteristics, the system comprising: a signal acquisition module for acquiring vibration signals during the operation of a target equipment, performing frequency domain processing, obtaining sideband parameters, performing sideband recurrence analysis in historical equipment frequency domain data, and obtaining sideband recurrence coefficients; an image acquisition module for acquiring workpiece processing images of workpieces during the processing of the target equipment, performing workpiece abnormality analysis, and obtaining workpiece abnormality parameters; a fault identification module for configuring a fault identification strategy based on the sideband recurrence coefficient and the workpiece abnormality parameters, performing fault identification on the sideband parameters, and obtaining a first fault rate; and a result prediction module for calculating a second fault rate based on the sideband parameters, and calculating the equipment failure rate in combination with the first failure rate as an equipment fault analysis prediction result.

[0005] In a second aspect, the present invention provides a method for analyzing and predicting equipment faults based on frequency domain characteristics, the method comprising: collecting vibration signals during the operation of the target equipment, performing frequency domain processing to obtain sideband parameters, performing sideband recurrence analysis in historical equipment frequency domain data to obtain sideband recurrence coefficients; collecting workpiece processing images of workpieces during the processing of the target equipment, performing workpiece abnormality analysis to obtain workpiece abnormality parameters; configuring a fault identification strategy based on the sideband recurrence coefficient and the workpiece abnormality parameters, performing fault identification on the sideband parameters to obtain a first failure rate; calculating a second failure rate based on the sideband parameters, and combining the first failure rate to calculate the equipment failure rate as an equipment fault analysis prediction result.

[0006] The beneficial effects of the present invention are as follows: by combining the sideband parameters obtained by frequency domain processing with the workpiece abnormality parameters obtained by workpiece abnormality analysis, equipment failures can be predicted more efficiently and accurately, the accuracy of fault identification can be improved, and the equipment failure rate can be obtained by comprehensively calculating the first failure rate and the second failure rate, providing a reliable basis for preventive maintenance and fault warning of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A schematic diagram of the structure of a device fault analysis and prediction system based on frequency domain characteristics provided by the present invention.

[0008] Figure 2 A schematic flow chart of a method for analyzing and predicting equipment faults based on frequency domain characteristics provided by the present invention.

[0009] Explanation of reference numerals: signal acquisition module 11 , image acquisition module 12 , fault identification module 13 , result estimation module 14 . DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0011] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0012] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0013] Embodiment 1:

[0014] like Figure 1 As shown, an embodiment of the present invention provides a device fault analysis and prediction system based on frequency domain characteristics, the system comprising: The signal acquisition module 11 is used to collect vibration signals during the operation of the target equipment, perform frequency domain processing, obtain sideband parameters, perform sideband recurrence analysis in historical equipment frequency domain data, and obtain sideband recurrence coefficients.

[0015] Exemplarily, this scheme is to perform fault diagnosis of rotating equipment based on sidebands in the frequency domain. As the frequency components on both sides of the carrier signal, the existence and characteristics of sidebands are crucial for analyzing equipment faults. Specifically, in the fault diagnosis process of rotating equipment, it is first necessary to collect vibration signals during the operation of the target equipment. These vibration signals contain the operating status information of each component inside the equipment and are an important basis for diagnosing faults. After the vibration signal is collected, it is processed in the frequency domain. Frequency domain processing is the process of converting time domain signals into frequency domain signals. Through this process, the frequency components of the vibration signal can be obtained, including fundamental frequency and sidebands. Sidebands refer to the frequency components that appear near the main frequency in addition to the main frequency (i.e., fundamental frequency, main vibration frequency) after the vibration signal is transformed in the frequency domain. The changes in parameters such as the spacing and amplitude of these sidebands are often associated with the specific fault mode of the equipment. Therefore, the fault condition of the equipment can be identified by analyzing the sideband parameters. After obtaining the sideband parameters, the sideband recurrence analysis is further performed in the historical equipment frequency domain data. The purpose of this step is to compare the sideband parameters of the current equipment with the sideband parameters of the historically known faulty equipment to identify whether the current equipment has sideband characteristics similar to the historically known faults. Specifically, we focus on the key parameter of sideband spacing, because when a fault occurs, the sideband spacing often changes in a similar way. If a certain spacing appears in a large proportion of the sideband spacing in the historical time, then it is considered that this spacing may be related to a certain fault. The sideband recurrence coefficient can be obtained through sideband recurrence analysis. The sideband recurrence coefficient is a quantitative indicator used to measure the similarity between the sideband parameters of the current device and the sideband parameters of the historically known faulty device. The larger the sideband recurrence coefficient, the more similar the sideband characteristics of the current device are to the sideband characteristics of the historically known faulty device, so the probability of a fault is greater. Conversely, if the sideband recurrence coefficient is small, it means that the sideband characteristics of the current device are greatly different from the sideband characteristics of the historically known faulty device, so the probability of a fault is smaller, and it is more likely that the workpiece is deformed abnormally or the device itself is not faulty. In summary, the sideband recurrence coefficient provides a method for quantitatively evaluating the possibility of equipment failure, which helps to detect potential faults in a timely manner and ensure the normal operation of the equipment.

[0016] The image acquisition module 12 is used to acquire the workpiece processing image of the workpiece during the processing of the target device, perform workpiece abnormality analysis, and obtain workpiece abnormality parameters.

[0017] Optionally, in the industrial production process, in order to ensure product quality and production efficiency, it is crucial to monitor the workpiece in the process of target equipment in real time. This monitoring process is achieved by collecting workpiece processing images and identifying whether the workpiece is abnormal through image analysis. Using advanced image acquisition equipment, such as high-definition cameras or industrial cameras, the workpiece in the process of target equipment is photographed in real time. These images capture the real-time status of the workpiece during the processing process and provide basic data for subsequent abnormal analysis. Next, the collected workpiece images are analyzed for abnormalities. This process usually involves steps such as image preprocessing, feature extraction, and abnormality recognition. In the image preprocessing stage, the image is denoised, contrast enhanced, and other operations are performed to improve the image quality and facilitate subsequent feature extraction. In the feature extraction stage, image processing algorithms, such as edge detection and contour extraction, are used to extract key features related to workpiece deformation from the image. These features may include the size, shape, surface texture, etc. of the workpiece. Finally, based on the extracted features, machine learning or deep learning algorithms are used to identify abnormalities of the workpiece. The purpose of this step is to determine whether the workpiece has abnormal conditions such as deformation. Specifically, the extracted features are compared with the preset normal workpiece feature library, and the degree of abnormality of the workpiece is evaluated by calculating the difference or similarity between the features. If the difference exceeds the preset threshold, or the similarity is lower than a certain standard, the workpiece is considered to be abnormal, and the corresponding workpiece abnormality parameters are output. These parameters include the amplitude, position, direction and other information of the workpiece deformation, which are of great reference value for subsequent equipment failure analysis and product quality control. In summary, by collecting workpiece processing images and performing abnormality analysis, abnormal conditions such as deformation of the workpiece during processing can be effectively identified, providing strong support for the monitoring and control of the production process.

[0018] The fault identification module 13 is used to configure a fault identification strategy according to the sideband recurrence coefficient and the workpiece abnormality parameter, perform fault identification on the sideband parameter, and obtain a first fault rate.

[0019] Furthermore, the fault identification strategy is configured by combining the sideband recurrence coefficient and the workpiece abnormality parameter. This process aims to more accurately evaluate the fault status of the equipment. Specifically, the sideband recurrence coefficient is calculated based on historical data and the currently collected sideband parameters. This coefficient reflects the similarity between the sideband characteristics of the current equipment and the sideband characteristics of the historically known faulty equipment. The larger the sideband recurrence coefficient, the more similar the sideband parameters of the current equipment are to the sideband parameters of the historically faulty equipment. Therefore, it is inclined to believe that the possibility of equipment failure is higher. In this case, in order to more comprehensively evaluate the fault, the number of paths for identification W is increased, that is, more analysis methods and detection means are used to confirm the fault. At the same time, the influence of the workpiece abnormality parameter on fault identification is also considered. The workpiece abnormality parameter is obtained by collecting and analyzing the workpiece processing image, which reflects the abnormal conditions such as deformation and cracks that may occur in the workpiece during the processing. When the workpiece abnormality parameter is larger, it is more inclined to believe that the abnormality of the sideband parameter is caused by the workpiece abnormality rather than the equipment failure. Therefore, in this case, the number of paths for identification W is reduced, because the workpiece abnormality has provided a reasonable explanation, and there is no need to further explore the possibility of equipment failure. After the fault identification strategy is configured, the sideband parameters are used for fault identification. This process comprehensively considers the influence of the sideband recurrence coefficient and the workpiece abnormality parameters, and obtains the first failure rate through comparative analysis, pattern recognition and other methods. The first failure rate is a quantitative indicator used to evaluate the probability of the current equipment failure. It comprehensively considers the abnormal degree of the sideband parameters and the possibility of workpiece abnormality, providing a more accurate basis for fault judgment. In summary, configuring the fault identification strategy according to the sideband recurrence coefficient and the workpiece abnormality parameters and performing fault identification on the sideband parameters can more accurately evaluate the fault status of the equipment and provide strong support for subsequent maintenance and repair work. The larger the sideband recurrence coefficient, the more likely it is that the equipment has a fault, so the number of identification paths W will increase; while the larger the workpiece abnormality parameter, the more likely it is that the fault is caused by the workpiece abnormality, so the number of identification paths W will be reduced. This flexible strategy adjustment improves the efficiency of fault analysis.

[0020] The result estimation module 14 is used to calculate a second failure rate according to the sideband parameter, and calculate the equipment failure rate in combination with the first failure rate as an equipment failure analysis estimation result.

[0021] Specifically, by comprehensively considering the influence of the sideband parameters and the workpiece abnormality parameters, two failure rates, namely the first failure rate and the second failure rate, are obtained through calculation, and finally the equipment failure rate is obtained by combining the two as the estimated result. Specifically, the second failure rate is calculated based on the sideband parameters. The sideband parameters refer to the occurrence of certain specific frequency components during the operation of the equipment, and these frequency components are often closely related to the operating status of the equipment. By monitoring and analyzing the sideband parameters, the recurrence ratio of the sideband can be obtained, that is, the frequency of occurrence of a specific frequency component in the monitoring time period accounts for the proportion of the total monitoring time. This recurrence ratio can reflect the stability and reliability of the equipment under certain specific conditions. The second failure rate is calculated by analyzing the recurrence ratio of the sideband parameters. The larger the recurrence ratio, the smaller the second failure rate, that is, the larger the recurrence ratio, the more stable the operating status of the equipment at this frequency, and therefore the smaller the second failure rate. This is because if the equipment can operate stably at a certain frequency, then the possibility of failure is relatively low, so the failure risk of the equipment at this frequency can be indirectly evaluated by the sideband recurrence ratio. Next, the equipment failure rate is calculated by combining the first failure rate previously calculated based on the workpiece abnormality parameters and the sideband recurrence coefficient. The first failure rate is a basic failure rate based on a variety of factors such as the equipment's historical failure data, operating environment, and maintenance records. This failure rate reflects the possibility of failure of the equipment under normal operating conditions. The first failure rate and the second failure rate are weighted to calculate the equipment failure rate as the final estimated result. Among them, the weight of the first failure rate is greater than the second failure rate. This is because the first failure rate comprehensively considers the influence of the sideband recurrence coefficient and the workpiece abnormality parameters during the analysis, and more comprehensively reflects the failure state of the equipment. Although the second failure rate is also calculated based on the sideband parameters, it is affected by the nonlinear relationship between the recurrence ratio and the failure probability in a specific situation. The final estimated result provides a quantitative assessment of the current failure state of the equipment, taking into account both the overall operating state of the equipment and the stability at a specific frequency, so that the failure risk of the equipment can be more comprehensively assessed.

[0022] In a preferred embodiment, the vibration signal of the target device during operation is collected, frequency domain processing is performed to obtain sideband parameters, and sideband recurrence analysis is performed in historical device frequency domain data to obtain sideband recurrence coefficients. The execution steps also include: collecting the vibration signal of the target device during operation; performing frequency domain transformation on the vibration signal to obtain a frequency domain signal; extracting sidebands in the frequency domain signal to obtain sideband parameters, wherein the sideband parameters include sideband spacing; and performing sideband recurrence analysis in the historical device frequency domain data based on the sideband spacing to obtain sideband recurrence coefficients.

[0023] Specifically, vibration signals are an important reflection of the operating status of the equipment. By collecting these signals, a lot of information about the equipment's operation can be obtained. After the vibration signals are collected, they need to be processed for further analysis. The frequency domain processing method is used here, that is, the vibration signal is converted from the time domain to the frequency domain. Frequency domain analysis can reveal the components and strength of the signal at different frequencies, which is crucial for understanding the operating status and failure mode of the equipment. Focus on specific frequency components in the frequency domain signal, namely sidebands. Sidebands are specific frequency components generated during the operation of the equipment, and they are often related to certain operating states or failure modes of the equipment. In order to extract these sidebands, sideband extraction needs to be performed in the frequency domain signal. In this process, the specific parameters of the sidebands are identified and recorded, and one of the most important parameters is the sideband spacing. The sideband spacing refers to the frequency difference between adjacent sidebands, which reflects the vibration characteristics of certain structures or components inside the equipment. After obtaining the sideband parameters, it is necessary to further analyze the recurrence of these parameters in the historical data of the equipment. Sideband recurrence analysis refers to comparing the sideband parameters of the current equipment with the historical equipment frequency domain data to evaluate the stability and reliability of the sidebands in the current equipment's operating status. In this process, a sideband recurrence coefficient is calculated, which reflects the frequency and stability of the sideband in historical data. The higher the sideband recurrence coefficient, the more stable the sideband is in the equipment operation state, and the lower the possibility of failure.

[0024] In a preferred embodiment, a sideband recurrence analysis is performed in the historical equipment frequency domain data according to the sideband spacing to obtain a sideband recurrence coefficient, and the execution steps also include: extracting a set of historical sideband spacings when equipment failure occurs in the historical equipment frequency domain data; obtaining the number of occurrences of the sideband spacing in the historical sideband spacing set to obtain a recurrence ratio; obtaining the maximum ratio of occurrences of different historical sideband spacings in the historical sideband spacing set as the maximum recurrence ratio; and calculating the ratio of the recurrence ratio to the maximum recurrence ratio as the sideband recurrence coefficient.

[0025] Furthermore, in order to perform sideband recurrence analysis, it is necessary to extract information from the historical device frequency domain data. Specifically, extract the historical sideband spacing set of the device when a fault occurs. This set contains the sideband spacing data recorded by the device in the fault state in the past, which is the basis for recurrence analysis. Subsequently, calculate the recurrence of the sideband spacing of the current device in this set. Count the number of times the sideband spacing of the current device appears in the historical sideband spacing set, and calculate the proportion of this number to the total number of the set, that is, the recurrence ratio. The recurrence ratio reflects the similarity between the sideband spacing of the current device and the historical fault data. However, since different historical sideband spacings may have different recurrence ratios, in order to evaluate whether the recurrence of the current sideband spacing is significant, it is also necessary to obtain the maximum proportion of different historical sideband spacings in the historical sideband spacing set as the maximum recurrence ratio. The maximum recurrence ratio represents the highest level of sideband spacing recurrence in historical data and is an important reference for evaluating the recurrence of the current sideband spacing. Calculate the ratio of the recurrence ratio to the maximum recurrence ratio as the sideband recurrence coefficient. The sideband recurrence coefficient is a dimensionless value that reflects the relative recurrence degree of the sideband spacing of the current device in the historical fault data. The larger the sideband recurrence coefficient, the more similar the sideband spacing of the current device is to the historical fault data, and therefore the higher the possibility of a fault. Conversely, the smaller the sideband recurrence coefficient, the greater the difference between the sideband spacing of the current device and the historical fault data, and the lower the possibility of a fault.

[0026] In a preferred embodiment, a workpiece processing image of a workpiece during processing of a target device is collected, and workpiece abnormality analysis is performed to obtain workpiece abnormality parameters. The execution steps also include: collecting a set of sample workpiece processing images based on processing data of similar workpieces, and collecting the deformation amplitudes of the workpieces in different sample workpiece processing images, and marking them as a set of sample workpiece abnormality parameters; constructing a workpiece image recognizer based on a convolutional neural network; using the sample workpiece processing image set and the sample workpiece abnormality parameter set, supervised training is performed on the workpiece image recognizer until the accuracy of the workpiece image recognizer meets the requirements; and inputting the workpiece processing image into the workpiece image recognizer to identify and output workpiece abnormality parameters.

[0027] Preferably, the processing data of similar workpieces are collected, and representative sample workpiece processing image sets are selected from them. These image sets cover the performance of the workpieces at different processing stages and under different conditions. Subsequently, for each sample workpiece processing image, the deformation amplitude of the workpiece is observed and recorded, and these data are marked as a sample workpiece abnormal parameter set. This step provides supervision information for the subsequent training process. Subsequently, a workpiece image recognizer is constructed based on the powerful image processing capability of the convolutional neural network (CNN), which can automatically extract feature information from the image and identify the abnormal state of the workpiece through these features. The structural design of CNN enables it to have high accuracy and robustness when processing image data. Next, the workpiece image recognizer is supervised and trained using a sample workpiece processing image set and a sample workpiece abnormal parameter set. During the training process, the recognizer will continuously try to extract features from the image and match these features with the annotated abnormal parameters. Through multiple iterations and optimizations, the accuracy of the recognizer is gradually improved until it meets the requirements. This step is the key to ensure that the recognizer can accurately identify the abnormal state of the workpiece. Finally, the workpiece processing image of the target equipment during the processing is input into the trained workpiece image recognizer, which automatically processes the image data and outputs the workpiece abnormality parameters. These parameters can quickly determine whether there is any abnormality in the processing state of the workpiece, so as to take corresponding measures to correct it. In summary, this process not only improves the accuracy of recognition and monitoring efficiency, but also reduces the failure rate in the production process.

[0028] In a preferred embodiment, a fault identification strategy is configured according to the sideband recurrence coefficient and the workpiece abnormality parameter, fault identification is performed on the sideband parameter to obtain a first fault rate, and the execution step also includes: constructing a sideband fault identifier, wherein the sideband fault identifier includes U sideband fault identification paths, and U is a positive integer; obtaining the maximum workpiece abnormality parameter in workpiece processing; calculating the ratio of the workpiece abnormality parameter to the maximum workpiece abnormality parameter as the workpiece abnormality coefficient, and calculating the workpiece equipment fault coefficient; calculating the fault identification coefficient according to the sideband recurrence coefficient and the workpiece equipment fault coefficient; multiplying the fault identification coefficient by U and rounding it to obtain W, and randomly selecting and configuring W sideband fault identification paths as the fault identification strategy; inputting the sideband parameters into the W sideband fault identification paths, identifying and obtaining W sideband fault rates, and calculating the mean to obtain the first fault rate.

[0029] Further, the subsequent fault identification strategy configuration is prepared based on the previous sideband recurrence coefficient and workpiece abnormality parameter. The workpiece abnormality parameter is obtained by collecting the workpiece processing image during the processing of the target equipment and performing abnormality analysis. At the same time, the maximum workpiece abnormality parameter in the workpiece processing is also obtained. Next, the workpiece abnormality coefficient is calculated, which is the ratio of the current workpiece abnormality parameter to the maximum workpiece abnormality parameter. This ratio reflects the severity of the current workpiece abnormal state relative to the maximum abnormal state. Then the workpiece equipment failure coefficient is calculated based on the workpiece abnormality coefficient, which is obtained by subtracting the workpiece abnormality coefficient from 1. The larger the workpiece equipment failure coefficient, the higher the possibility of equipment failure. Construct a sideband fault identifier and design U sideband fault identification paths, where U is a positive integer. These paths represent different fault identification modes and can cover possible fault conditions more comprehensively. In order to determine which paths to use for fault identification, the fault identification coefficient is calculated based on the sideband recurrence coefficient and the workpiece equipment failure coefficient. Here, the sideband recurrence coefficient and the workpiece equipment failure coefficient can be combined by weighted calculation or mean calculation to obtain a comprehensive fault identification coefficient. After obtaining the fault identification coefficient, the coefficient is multiplied by U and rounded to get W. W represents the number of randomly selected sideband fault identification paths. This method can ensure that the influence of the sideband recurrence coefficient and the workpiece abnormality parameter is considered in the fault identification process, and has a certain degree of randomness and flexibility. Then, the sideband parameters are input into the W sideband fault identification paths, and each path will output a sideband failure rate. Finally, the average of these sideband failure rates is calculated to get the first failure rate. This first failure rate reflects the comprehensive probability of failure of the current equipment. For example, suppose there is a target equipment, and the sideband recurrence coefficient and workpiece abnormality parameters are collected during the processing. At this time, a sideband fault identifier containing 5 sideband fault identification paths (U=5) is constructed. Through calculation, the workpiece abnormality coefficient is 0.6 (that is, the current workpiece abnormality parameter is 60% of the maximum abnormality parameter), and then the workpiece equipment failure coefficient is 0.4 (1-0.6=0.4). Then, the sideband recurrence coefficient (assuming it is 0.8) and the workpiece equipment failure coefficient (0.4) are combined by weighted calculation to obtain a fault identification coefficient of 0.6. According to the fault identification coefficient, W=3 (0.6×5=3, rounded). Therefore, three sideband fault identification paths are randomly selected for fault identification. Finally, the mean of the sideband failure rates output by these three paths is calculated, and the first failure rate is 0.25 (assuming that the failure rates output by the three paths are 0.2, 0.3 and 0.25 respectively, the mean is (0.2+0.3+0.25) / 3=0.25).

[0030] In a preferred embodiment, a sideband fault identifier is constructed, and the execution steps also include: collecting a set of sample sideband parameters based on the fault diagnosis data of the device in the historical time, and collecting the probability of the device failure when different sample sideband parameters appear, and marking them as a set of sample sideband fault rates; randomly extracting U training samples with replacement in the sample sideband parameter set and the sample sideband fault rate set; using a feedforward neural network to construct U sideband fault identification paths, and using the U training samples respectively to supervise the training and testing of the U sideband fault identification paths until the accuracy meets the requirements; combining the U sideband fault identification paths to obtain a sideband fault identifier.

[0031] Optionally, a set of sample sideband parameters is collected from the fault diagnosis data of the device in the historical time. These parameters are obtained by sensors or other monitoring means during the operation of the device, and they can reflect the operating status and possible fault conditions of the device. At the same time, it is also necessary to collect the fault probabilities corresponding to these sample sideband parameters, that is, the set of sample sideband fault rates. These fault probabilities are calculated by actual fault records in historical data, and they provide label information for subsequent model training. Subsequently, U training samples are randomly selected from them. Here, the extraction is carried out with replacement, which means that the same sample may be selected multiple times, which helps to increase the generalization ability of the model. U represents the number of constructed sideband fault identification paths, which can be adjusted according to actual needs. Next, a feedforward neural network is used to construct U sideband fault identification paths. Feedforward neural network is a commonly used machine learning model that can handle complex nonlinear relationships and has strong generalization ability. For each sideband fault identification path, a training sample is used for supervised training and testing. During the training process, the model will continuously adjust its parameters to minimize the difference between the predicted failure rate and the actual failure rate. The testing process is used to verify the performance of the model to ensure that it can maintain a high accuracy rate on new data. When all the sideband fault identification paths have been fully trained and tested, they are combined to form a complete sideband fault identifier. This identifier can process multiple sideband parameters at the same time and output a comprehensive failure rate prediction result. Since multiple paths are used for combination, even if the prediction result of a certain path deviates, other paths can compensate, thereby improving the overall prediction accuracy. By constructing a sideband fault identifier, the historical fault diagnosis data of the equipment can be fully utilized to train a model that can accurately predict the probability of equipment failure. This model can not only improve the accuracy and reliability of fault identification, but also because multiple sideband fault identification paths are used for combination, the robustness and generalization ability of the model are also significantly improved.

[0032] In a preferred embodiment, a second failure rate is calculated based on the sideband parameters, and the execution steps also include: obtaining the average proportion of different historical sideband spacings in the historical sideband spacing set as the average recurrence proportion; when the recurrence proportion is less than the average recurrence proportion, calculating the ratio of the difference between the recurrence proportion and the average recurrence proportion to the average recurrence proportion as the second failure probability; when the recurrence proportion is greater than or equal to the average recurrence proportion, outputting the second failure probability as 0.

[0033] In detail, a set of sideband spacings is obtained from the historical data of the equipment. These sideband spacings are important parameters that reflect the vibration characteristics of the equipment obtained by monitoring means under different operating conditions. Next, the average proportion of different historical sideband spacings in these historical sideband spacing sets is calculated. This proportion is the average recurrence ratio, which reflects the universality and stability of each sideband spacing under normal conditions. Now, suppose there is a new recurrence ratio of the sideband spacing (that is, the proportion of the sideband spacing in the new data). Compare this recurrence ratio with the average recurrence ratio calculated previously. If the recurrence ratio is less than the average recurrence ratio, it means that the number of times this sideband spacing appears in the new data is less than normal. Then the smaller the recurrence ratio, the fewer the number of sideband spacings, the higher the randomness, and the more likely it is that the sideband spacing changes caused by workpiece deformation or other abnormal conditions. Therefore, the ratio of (average recurrence ratio-recurrence ratio) / average recurrence ratio is calculated, and this ratio is used as the second fault probability. The larger this ratio is, the greater the difference between the recurrence ratio of the sideband spacing and the average recurrence ratio, and the higher the probability of fault. If the recurrence ratio is greater than or equal to the average recurrence ratio, it is considered that the number of occurrences of this side frequency interval in the new data is normal and does not show abnormal fault characteristics, so the second fault probability is directly output as 0.

[0034] In a preferred embodiment, the equipment failure rate is calculated in combination with the first failure rate as the equipment failure analysis prediction result, and the execution step also includes: performing weighted calculation on the first failure rate and the second failure rate to obtain the equipment failure rate; and using the equipment failure rate as the equipment failure analysis prediction result.

[0035] Specifically, the first failure rate is calculated by the sideband fault identifier based on the sideband parameters and the fault identification strategy; while the second failure rate is calculated based on the difference between the recurrence ratio of the sideband spacing and the average recurrence ratio. These two failure rates reflect the fault possibility of the device from different perspectives. In order to obtain a comprehensive device failure rate, it is necessary to perform weighted calculation on the first failure rate and the second failure rate. The purpose of weighting is to allocate different weights according to the importance and reliability of the two failure rates. The allocation of weights can be determined according to the actual situation and expert experience, or can be automatically optimized by methods such as machine learning. The formula for weighted calculation can be expressed as: device failure rate = α × first failure rate + β × second failure rate, where α and β are the weights of the first failure rate and the second failure rate respectively, and α + β = 1, for example, 0.7 and 0.3 respectively. After weighted calculation, a comprehensive device failure rate is obtained. This failure rate is a quantitative indicator that reflects the fault possibility of the device in the current operating state. This failure rate can be used as the result of device fault analysis and prediction for device maintenance, management and decision-making. By combining the first failure rate and the second failure rate to calculate the device failure rate, the fault possibility of the device can be evaluated more comprehensively. The first failure rate reflects the vibration characteristics and fault characteristics of the device from the perspective of sideband parameters, while the second failure rate provides additional fault information from the perspective of the recurrence ratio of sideband spacing. The combined use of these two failure rates can complement and verify each other, thereby improving the accuracy and reliability of device fault analysis. At the same time, the weighted calculation method also allows adjusting the weights of the two failure rates according to the actual situation and requirements, so as to more flexibly respond to different application scenarios and device types. This makes the result of device fault analysis and prediction more in line with the actual needs and can provide more powerful support for device maintenance and management.

[0036] The device fault analysis and prediction system based on frequency domain characteristics provided by the embodiments of the present invention has at least the following technical effects: 1. It combines the frequency domain vibration signal analysis during the operation of the target device and the anomaly analysis of the workpiece processing image. By collecting vibration signals and performing frequency domain processing, sideband parameters and sideband recurrence coefficients are obtained. At the same time, the workpiece processing image is collected and anomaly analysis is performed using a convolutional neural network to obtain workpiece anomaly parameters. The fusion of such multi-dimensional data enables the system to more comprehensively capture the early signs of device faults and improve the accuracy and reliability of fault analysis.

[0037] 2. The sideband recurrence coefficient and workpiece anomaly coefficient are introduced as key indicators for fault identification. The sideband recurrence coefficient evaluates the possibility of fault by comparing the recurrence of the current sideband spacing in historical data. The workpiece anomaly coefficient quantifies the degree of workpiece deformation based on the recognition results of the workpiece image. The fault identification strategy is intelligently configured according to these two coefficients, and the appropriate sideband fault identification path is selected for fault identification, thereby realizing the personalization and intelligence of fault identification.

[0038] 3. Not only is the first failure rate obtained through the sideband fault identifier, but the second failure rate is also calculated based on the recurrence ratio of the sideband spacing. These two failure rates reflect the failure status of the equipment from different angles. By weighted calculation of these two failure rates, a comprehensive equipment failure rate is obtained as the equipment failure analysis prediction result. This method comprehensively considers multiple failure factors, improves the accuracy and practicality of equipment failure prediction, and provides strong support for equipment maintenance and management.

[0039] Embodiment 2:

[0040] like Figure 2 As shown, based on the same inventive concept of a device fault analysis and prediction system based on frequency domain characteristics provided in Embodiment 1, an embodiment of the present invention further provides a device fault analysis and prediction method based on frequency domain characteristics, the method comprising: The vibration signals of the target equipment during operation are collected and processed in the frequency domain to obtain the sideband parameters. The sideband recurrence analysis is performed in the historical equipment frequency domain data to obtain the sideband recurrence coefficients.

[0041] Collect workpiece processing images of the workpiece during the processing of the target equipment, perform workpiece abnormality analysis, and obtain workpiece abnormality parameters.

[0042] A fault identification strategy is configured according to the sideband recurrence coefficient and the workpiece abnormality parameter, and fault identification is performed on the sideband parameter to obtain a first fault rate.

[0043] A second failure rate is calculated based on the sideband parameters, and combined with the first failure rate, an equipment failure rate is calculated as an equipment failure analysis prediction result.

[0044] Furthermore, the vibration signal of the target device during operation is collected, frequency domain processing is performed to obtain sideband parameters, and sideband recurrence analysis is performed in historical device frequency domain data to obtain sideband recurrence coefficients, including: collecting the vibration signal of the target device during operation; performing frequency domain transformation on the vibration signal to obtain a frequency domain signal; extracting sidebands in the frequency domain signal to obtain sideband parameters, wherein the sideband parameters include sideband spacing; and performing sideband recurrence analysis in historical device frequency domain data based on the sideband spacing to obtain sideband recurrence coefficients.

[0045] Furthermore, based on the sideband spacing, a sideband recurrence analysis is performed in the historical equipment frequency domain data to obtain a sideband recurrence coefficient, including: extracting a set of historical sideband spacings when equipment failures occur in the historical equipment frequency domain data; obtaining the number of occurrences of the sideband spacing in the historical sideband spacing set to obtain a recurrence ratio; obtaining the maximum ratio of occurrences of different historical sideband spacings in the historical sideband spacing set as the maximum recurrence ratio; and calculating the ratio of the recurrence ratio to the maximum recurrence ratio as the sideband recurrence coefficient.

[0046] Furthermore, workpiece processing images of the workpiece during the processing of the target equipment are collected, and workpiece abnormality analysis is performed to obtain workpiece abnormality parameters, including: collecting a set of sample workpiece processing images based on processing data of similar workpieces, and collecting the deformation amplitudes of the workpieces in different sample workpiece processing images, and marking them as a set of sample workpiece abnormality parameters; constructing a workpiece image recognizer based on a convolutional neural network; using the sample workpiece processing image set and the sample workpiece abnormality parameter set, supervised training is performed on the workpiece image recognizer until the accuracy of the workpiece image recognizer meets the requirements; and inputting the workpiece processing image into the workpiece image recognizer to identify and output workpiece abnormality parameters.

[0047] Furthermore, according to the sideband recurrence coefficient and the workpiece abnormality parameter, a fault identification strategy is configured, and fault identification is performed on the sideband parameters to obtain a first failure rate, including: constructing a sideband fault identifier, wherein the sideband fault identifier includes U sideband fault identification paths, and U is a positive integer; obtaining the maximum workpiece abnormality parameter in workpiece processing; calculating the ratio of the workpiece abnormality parameter to the maximum workpiece abnormality parameter as the workpiece abnormality coefficient, and calculating the workpiece equipment failure coefficient; calculating the fault identification coefficient according to the sideband recurrence coefficient and the workpiece equipment failure coefficient; multiplying the fault identification coefficient by U and rounding it to obtain W, and randomly selecting and configuring W sideband fault identification paths as the fault identification strategy; inputting the sideband parameters into the W sideband fault identification paths, identifying and obtaining W sideband failure rates, and calculating the average to obtain the first failure rate.

[0048] Furthermore, a sideband fault identifier is constructed, including: collecting a set of sample sideband parameters based on the fault diagnosis data of the equipment in historical time, and collecting the probability of equipment failure when different sample sideband parameters appear, and marking them as a set of sample sideband fault rates; randomly extracting U training samples with replacement from the sample sideband parameter set and the sample sideband fault rate set; using a feedforward neural network to construct U sideband fault identification paths, and using the U training samples respectively to perform supervised training and testing on the U sideband fault identification paths until the accuracy meets the requirements; combining the U sideband fault identification paths to obtain a sideband fault identifier.

[0049] Furthermore, according to the sideband parameters, a second failure rate is calculated, including: obtaining the average proportion of different historical sideband spacings in the historical sideband spacing set as the average recurrence proportion; when the recurrence proportion is less than the average recurrence proportion, calculating the ratio of the difference between the recurrence proportion and the average recurrence proportion to the average recurrence proportion as the second failure probability; when the recurrence proportion is greater than or equal to the average recurrence proportion, outputting the second failure probability as 0.

[0050] Furthermore, in combination with the first failure rate, the equipment failure rate is calculated as the equipment failure analysis prediction result, including: performing weighted calculation on the first failure rate and the second failure rate to obtain the equipment failure rate; and using the equipment failure rate as the equipment failure analysis prediction result.

[0051] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0052] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0053] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A device fault analysis and prediction system based on frequency domain characteristics, characterized in that: The system comprises: The signal acquisition module is used to collect the vibration signal of the target equipment during operation, perform frequency domain processing, obtain the sideband parameters, perform sideband recurrence analysis in the historical equipment frequency domain data, and obtain the sideband recurrence coefficient; An image acquisition module is used to acquire a workpiece processing image of a workpiece during the processing of a target device, perform workpiece abnormality analysis, and obtain workpiece abnormality parameters; A fault identification module, configured to configure a fault identification strategy according to the sideband recurrence coefficient and the workpiece abnormality parameter, perform fault identification on the sideband parameter, and obtain a first fault rate; The result prediction module is used to calculate the second failure rate according to the sideband parameter, and calculate the equipment failure rate in combination with the first failure rate as the equipment failure analysis prediction result.

2. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 1 is characterized in that: Collect vibration signals during the operation of the target equipment, perform frequency domain processing, obtain sideband parameters, perform sideband recurrence analysis in historical equipment frequency domain data, and obtain sideband recurrence coefficients, including: Collect vibration signals during the operation of the target equipment; Performing frequency domain transformation on the vibration signal to obtain a frequency domain signal; Extracting sidebands in the frequency domain signal to obtain sideband parameters, wherein the sideband parameters include sideband spacing; According to the sideband spacing, a sideband recurrence analysis is performed in the historical device frequency domain data to obtain a sideband recurrence coefficient.

3. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 2 is characterized in that: According to the sideband spacing, a sideband recurrence analysis is performed in the historical device frequency domain data to obtain a sideband recurrence coefficient, including: Extract the historical edge frequency spacing set when the equipment fails from the historical equipment frequency domain data; Obtaining the number of occurrences of the edge frequency spacing in the historical edge frequency spacing set, and obtaining a recurrence ratio; Obtaining the maximum ratio of occurrence of different historical side frequency intervals in the historical side frequency interval set as the maximum recurrence ratio; The ratio of the recurrence ratio to the maximum recurrence ratio is calculated as the sideband recurrence coefficient.

4. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 1 is characterized in that: Collect workpiece processing images of the workpiece during the processing of the target equipment, perform workpiece abnormality analysis, and obtain workpiece abnormality parameters, including: According to the processing data of the same type of workpieces, a set of sample workpiece processing images is collected, and the deformation amplitudes of the workpieces in different sample workpiece processing images are collected and marked as a set of sample workpiece abnormal parameters; Based on convolutional neural network, build workpiece image recognizer; Using the sample workpiece processing image set and the sample workpiece abnormal parameter set, supervised training is performed on the workpiece image recognizer until the accuracy of the workpiece image recognizer meets the requirement; The workpiece processing image is input into the workpiece image recognizer to recognize and output workpiece abnormality parameters.

5. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 1 is characterized in that: According to the sideband recurrence coefficient and the workpiece abnormality parameter, a fault identification strategy is configured, fault identification is performed on the sideband parameter, and a first fault rate is obtained, including: Constructing a sideband fault identifier, wherein the sideband fault identifier includes U sideband fault identification paths, where U is a positive integer; Obtain the maximum workpiece abnormality parameter during workpiece processing; Calculating the ratio of the workpiece abnormality parameter to the maximum workpiece abnormality parameter as the workpiece abnormality coefficient, and calculating the workpiece equipment failure coefficient; Calculating a fault identification coefficient based on the sideband recurrence coefficient and the workpiece equipment fault coefficient; The fault identification coefficient is multiplied by U and rounded to an integer to obtain W, and W sideband fault identification paths are randomly selected and configured as a fault identification strategy; The sideband parameters are input into the W sideband fault identification paths, W sideband fault rates are identified and obtained, and the average is calculated to obtain the first fault rate.

6. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 5 is characterized in that: Build a sideband fault identifier, including: According to the fault diagnosis data of the equipment in the historical time, a set of sample sideband parameters is collected, and the probability of equipment failure when different sample sideband parameters appear is collected, and marked as a set of sample sideband failure rates; Randomly extracting U training samples with replacement from the sample sideband parameter set and the sample sideband failure rate set; Using a feedforward neural network to construct U sideband fault identification paths, and using the U training samples respectively to perform supervised training and testing on the U sideband fault identification paths until the accuracy meets the requirements; The U sideband fault identification paths are combined to obtain a sideband fault identifier.

7. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 3 is characterized in that: Calculating and obtaining a second failure rate according to the sideband parameter includes: Obtain the average proportion of occurrence of different historical edge frequency intervals in the historical edge frequency interval set as the average recurrence proportion; When the recurrence ratio is less than the average recurrence ratio, calculating a ratio of a difference between the recurrence ratio and the average recurrence ratio to the average recurrence ratio as a second fault probability; When the recurrence ratio is greater than or equal to the average recurrence ratio, the second fault probability is output as 0.

8. The equipment fault analysis and prediction system based on frequency domain characteristics according to claim 1 is characterized in that: In combination with the first failure rate, the equipment failure rate is calculated as the equipment failure analysis prediction result, including: Performing weighted calculation on the first failure rate and the second failure rate to obtain a device failure rate; The equipment failure rate is used as an estimated result of equipment failure analysis.

9. A method for analyzing and predicting equipment failure based on frequency domain characteristics, characterized in that: The method is applied to a device fault analysis and prediction system based on frequency domain characteristics as described in any one of claims 1 to 8, and the method comprises: Collect vibration signals during the operation of the target equipment, perform frequency domain processing, obtain sideband parameters, perform sideband recurrence analysis in historical equipment frequency domain data, and obtain sideband recurrence coefficients; Collect workpiece processing images of the workpiece during the processing of the target equipment, perform workpiece abnormality analysis, and obtain workpiece abnormality parameters; According to the sideband recurrence coefficient and the workpiece abnormality parameter, a fault identification strategy is configured to perform fault identification on the sideband parameter to obtain a first fault rate; A second failure rate is calculated based on the sideband parameters, and combined with the first failure rate, an equipment failure rate is calculated as an equipment failure analysis prediction result.

Images