Power equipment health state automatic detection method, equipment, medium and product

Abstract

The invention discloses a power equipment health state automatic detection method, equipment, a medium and a product, and relates to the field of power equipment. The method comprises the following steps: acquiring vibration data of to-be-detected power equipment during working; determining vibration characteristic parameters according to the vibration data; determining a parameter mean value and a parameter standard deviation based on the vibration characteristic parameters; determining a 3 sigma criterion interval according to the parameter mean value and the parameter standard deviation; determining an abnormal characteristic parameter from the vibration characteristic parameters based on the 3 sigma criterion interval; determining an abnormal data set from the vibration data according to the abnormal characteristic parameters; and determining that the power equipment is in a healthy state according to the abnormal data set. According to the method, the accuracy and timeliness of fault detection are improved by analyzing the vibration data in real time and applying the principle of statistics, the reliability of equipment operation is improved, and the problem that the fault is misreported or missed to report due to the fact that the method cannot adapt to the change and fluctuation of the working state of power equipment and the difference between different pieces of equipment is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment, and in particular to a method, equipment, medium and product for automatically detecting the health status of power equipment. Background Art

[0002] As an important equipment in industrial fields such as self-contained power supply, emergency power supply or mobile power supply, power equipment is widely used in various industrial sites such as municipal transportation and industrial projects. Due to its large number of parts and complex structure, it is very difficult to troubleshoot and analyze power equipment failures, and in severe cases it will cause huge economic losses.

[0003] In order to ensure that the power equipment is in a healthy state and can work normally, it is usually necessary to monitor the operating status of the equipment in real time. The normal state of the equipment during operation accounts for the vast majority. When the monitoring time is relatively long, a large amount of normal data that is not very relevant to the analysis of operating status faults will be generated, and the dynamic data collection rate is relatively high, which makes data storage and fault feature extraction extremely difficult.

[0004] To overcome this problem, the common solution in related technologies is to set a fixed threshold to filter the vibration data generated during operation. However, this method cannot adapt to the changes and fluctuations in the working state of power equipment, as well as the differences between different equipment, resulting in false or missed fault reports, thus affecting the accuracy of equipment health status detection. Summary of the invention

[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a method, equipment, medium and product for automatic detection of the health status of power equipment, which improves the accuracy and timeliness of fault detection by real-time analysis of vibration data and application of statistical principles, enhances the reliability of equipment operation, and alleviates the problem that related technologies are unable to adapt to changes and fluctuations in the working state of power equipment, as well as differences between different equipment, leading to false alarms or missed alarms.

[0006] To achieve the above-mentioned objectives, in a first aspect, the present invention provides a method for automatically detecting the health status of a power equipment, comprising: obtaining vibration data of the power equipment to be detected when it is working; determining vibration characteristic parameters based on the vibration data; determining a parameter mean and a parameter standard deviation based on the vibration characteristic parameters; determining a 3σ criterion interval based on the parameter mean and the parameter standard deviation; determining abnormal characteristic parameters from the vibration characteristic parameters based on the 3σ criterion interval; determining an abnormal data set from the vibration data based on the abnormal characteristic parameters; and determining that the power equipment is in a healthy state based on the abnormal data set.

[0007] The present invention firstly acquires the vibration data of the equipment in real time and extracts key characteristic parameters, which can accurately capture the subtle changes in the operating state of the equipment and provide a rich data basis for subsequent analysis. Then, by using the 3σ criterion in statistics, the mean and standard deviation of the parameters can be dynamically determined, and the normal and abnormal vibration characteristic parameters can be automatically divided. Compared with the traditional fixed threshold method, this method is more adaptable to the dynamic changes in the operating state of the equipment and improves the accuracy and response speed of fault detection. In addition, by intelligently screening abnormal data sets, the invalid analysis of a large amount of normal data is effectively reduced, the data storage and processing efficiency is optimized, and the maintenance cost is reduced. The present invention can warn of potential faults in advance, help operators take timely measures, avoid production interruptions and safety accidents caused by equipment failures, thereby significantly reducing economic losses and improving the continuity and reliability of industrial production.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of determining an abnormal data set from the vibration data based on the abnormal characteristic parameters includes: determining an abnormal timestamp of the abnormal characteristic parameters; and determining the abnormal data set from the vibration data based on the abnormal timestamp.

[0009] By adopting the technical solution of the above embodiment, the accuracy of fault detection is improved by determining the abnormal timestamps of the abnormal characteristic parameters and determining the abnormal data set from the vibration data based on these timestamps. This method can ensure that only those data points that actually show abnormalities are focused on, thereby reducing the possibility of false positives and false negatives. The determination of abnormal timestamps provides a specific time reference point for fault diagnosis, allowing maintenance personnel to quickly locate the specific moment when the problem occurs, and then conduct effective fault analysis and timely maintenance response. This precise time positioning function is crucial to the implementation of preventive maintenance strategies, helping to reduce unexpected downtime and improve the operating efficiency of equipment.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the abnormal data set from the vibration data according to the abnormal timestamp includes: determining multiple abnormal data groups from the vibration data according to the abnormal timestamp, the abnormal data groups including acceleration, velocity and displacement; sorting the multiple abnormal data groups according to the abnormal timestamp to obtain the abnormal data set.

[0011] By adopting the technical solution of the above embodiment, an ordered abnormal data set is formed by sorting the abnormal data group according to the abnormal timestamp, which makes the analysis process more systematic and orderly. This sorting not only helps to identify the frequency and pattern of abnormal occurrence, but also reveals the potential development trend of faults. By sorting the abnormal data group, it is easier to identify those abnormal data that are most likely to indicate serious problems, so as to give priority to them. This method improves the efficiency of data analysis, enables maintenance teams to respond to potential faults more quickly, reduce equipment downtime, and optimize the allocation of maintenance resources.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of determining that the power equipment is in a healthy state based on the abnormal data set includes: substituting the abnormal data group in the abnormal data set into the equipment health score formula to calculate the health score of the power equipment; and determining that the power equipment is healthy based on the health score.

[0013] By adopting the technical solution of the above embodiment, a method for quantifying the health status of the equipment is provided by substituting the abnormal data group into the equipment health score formula to calculate the health score. This method allows the health status of the equipment to be represented by a specific numerical value, which is convenient for comparing and tracking changes in the equipment status. The introduction of the health score makes the maintenance decision of the equipment more data-driven, reduces the influence of subjective judgment, and improves the efficiency and effectiveness of maintenance activities. By monitoring the changes in the health score, the decline in equipment performance can be discovered in time, so that preventive measures can be taken before a failure occurs, reducing maintenance costs and extending the life of the equipment.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the device health score formula includes: Among them, S is the health score, M is the constant term, w is the influence coefficient, An is the value after acceleration standardization, Vn is the value after velocity standardization, and Dn is the value after displacement standardization.

[0015] By adopting the technical solution of the above embodiment, a specific equipment health score formula is introduced, which includes standardized processing values ​​of acceleration, velocity and displacement, so that the calculation of the health score is more scientific and accurate. This formula comprehensively considers multiple vibration parameters through sine functions and influence coefficients, providing a comprehensive perspective on the health status of the equipment. This method not only improves the sensitivity and adaptability of the score, but also allows different weights to be given to different parameters to adapt to the characteristics of different equipment. This comprehensive scoring method helps to more accurately evaluate the health status of the equipment and provide a more reliable basis for equipment maintenance and repair.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of obtaining the vibration data of the power equipment to be detected during operation, it includes: segmenting the vibration data according to a preset time period to obtain current time segment data and previous time segment data; merging the current time segment data and the previous time segment data into the vibration data to be processed.

[0017] The technical solution of the above embodiment is adopted, by performing segmented processing after acquiring the vibration data and merging the data of the current and previous time periods, providing data support for the dynamic update of the characteristic parameters. This method enables the system to adapt to changes in the operating status of the equipment and improves the timeliness and accuracy of fault detection. Segmented processing and data merging not only help capture short-term changes in the equipment status, but also reduce data processing delays, making health status assessment more timely. This processing method provides an effective data management strategy for continuous monitoring and maintenance of equipment, which helps to achieve real-time health monitoring and predictive maintenance of equipment.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the step of determining that the power equipment is in a healthy state based on the abnormal data set includes: determining the aging condition of the power equipment; and determining that the power equipment is in a healthy state based on the aging condition and the abnormal data set.

[0019] By adopting the technical solution of the above embodiment, the health assessment is made more comprehensive and accurate by considering the aging condition of the equipment and combining it with the abnormal data set to determine the health status of the equipment. This method recognizes the impact of equipment aging on vibration characteristics and makes adaptive adjustments to ensure that the health status of the equipment can be accurately judged even in the case of natural aging of the equipment. Considering the aging condition helps the maintenance team better understand the changes in equipment performance, thereby formulating more appropriate maintenance plans, reducing unnecessary maintenance activities, extending the service life of the equipment, and optimizing maintenance costs.

[0020] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation method of the first aspect or the second aspect.

[0021] In a third aspect, the present invention provides a computer-readable storage medium comprising instructions, which, when executed on the electronic device, causes the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0022] In a fourth aspect, the present invention provides a computer program product comprising instructions, which, when the computer program product is run on the electronic device, enables the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0023] It is understandable that the electronic device provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. The present invention significantly improves the accuracy of fault detection by real-time monitoring of vibration data of power equipment and combining the 3σ criterion and equipment health scoring formula. The present invention can quickly identify abnormal characteristic parameters that exceed the normal operating range and determine abnormal data sets based on these parameters, thereby quickly locating potential fault points. This real-time response mechanism reduces false positives and false negatives, allowing maintenance personnel to take timely measures to avoid production interruptions and economic losses caused by equipment failures.

[0025] 2. The present invention introduces a formula for equipment health scoring, which quantifies the combined effects of key vibration parameters such as acceleration, velocity and displacement into a specific health score. This score not only provides an intuitive representation of the health of the equipment, but also allows the performance degradation of the equipment to be predicted based on the trend of the score, so that preventive maintenance measures can be taken before a failure occurs. This quantitative evaluation method makes equipment maintenance decisions more scientific and data-driven, and improves the efficiency and effectiveness of maintenance activities.

[0026] 3. The present invention takes into account the impact of equipment aging on vibration characteristics and allows adaptive adjustment of abnormality determination criteria. By analyzing the aging condition of the equipment and combining it with the abnormal data set, the actual health status of the equipment can be more accurately assessed. This adaptive adjustment ensures that the accuracy of health assessment is maintained even in the case of natural aging of the equipment, allowing maintenance strategies to be dynamically adjusted as the equipment status changes. This helps to extend the service life of the equipment, reduce unnecessary maintenance activities, and optimize the allocation of maintenance resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 It is a flow chart of a method for automatically detecting the health status of a power device according to an embodiment of the present invention; Figure 2 It is a flow chart of another method for automatically detecting the health status of power equipment according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the architecture of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0030] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0031] The embodiment of the present invention provides a method for automatically detecting the health status of a power device. Figure 1 As shown, the following steps are included: Step 201, obtaining vibration data of the power equipment to be tested when it is working.

[0032] Among them, vibration data mainly includes time domain signals (such as acceleration, velocity, displacement), or frequency domain signals (such as frequency components, power spectrum density). Vibration data reflects the dynamic characteristics of power equipment during operation.

[0033] This embodiment installs high-precision vibration sensors at key parts of the power equipment, such as bearings, gear boxes, motors, etc. These sensors can capture the vibration signals generated by the equipment in real time during operation and convert these analog signals into digital signals.

[0034] Subsequently, these digital signals can be collected and recorded at high sampling rate and high resolution through a data acquisition system, such as an intelligent acquisition terminal. The collected data can include time domain signals, frequency domain signals, or time-frequency domain signals, which will be used for subsequent feature extraction and health status analysis.

[0035] Step 202: Determine vibration characteristic parameters according to the vibration data.

[0036] Among them, vibration characteristic parameters include statistics and signal characteristics extracted from these raw data, such as frequency, amplitude, phase difference, peak value, valley value, kurtosis, waveform factor, energy spectrum density, etc., or spectrum characteristics obtained through time-frequency analysis. These parameters can reveal the operating status and potential failure modes of the equipment, and are the key to realizing equipment health status monitoring and fault diagnosis.

[0037] In this embodiment, the original vibration data needs to be preprocessed, including filtering and denoising to eliminate irrelevant signal interference and ensure the accuracy of feature extraction. Then, by applying signal processing techniques such as Fourier transform and wavelet transform, the time domain signal is converted into a frequency domain signal to facilitate the analysis of the frequency components of the vibration signal. Then, key vibration characteristic parameters are extracted from the processed data, and the vibration parameters can characterize the operating status and potential failure modes of the equipment.

[0038] In addition, machine learning algorithms can be used to learn historical data to automatically identify and extract the most representative characteristic parameters. These characteristic parameter sets will be used for subsequent statistical analysis and health status assessment, providing a scientific basis for predictive maintenance and predictive repair of power equipment.

[0039] The purpose of this step is that these parameters can directly reflect the operating status and potential failure modes of the equipment. Vibration data usually contains a large amount of time domain and frequency domain information. If this information is directly analyzed, not only the data volume is large, but it is also difficult to intuitively identify the actual problems of the equipment. By extracting vibration characteristic parameters such as frequency, amplitude, peak value, energy spectrum density, etc., complex vibration signals can be converted into several key and quantifiable indicators, which are easier to compare with the normal operating status of the equipment, so as to quickly identify abnormalities.

[0040] In addition, the determination of characteristic parameters helps to simplify the data analysis process, reduce computational complexity, and provide accurate basic data for subsequent statistical analysis, fault diagnosis, and predictive maintenance, making equipment health monitoring and fault prediction more efficient and accurate.

[0041] Step 203: Determine a parameter mean and a parameter standard deviation based on the vibration characteristic parameter.

[0042] Specifically, the calculation of the parameter mean is to sum all the collected data points of the same vibration characteristic parameter and then divide it by the total number of data points. For example, assuming there are n frequency data points a1, a2, a3, ..., a, then the mean μ of the vibration characteristic parameter of frequency is equal to (a1+a2+a3+...+a) / n. The parameter mean is μ.

[0043] As for the calculation of parameter standard deviation, first calculate the square of the difference between each data point and the mean, that is, for the above frequency data points, calculate (a1-μ) 2 、(a2-μ) 2 、(a3-μ) 2 Then sum the squares of these differences and divide them by the total number of data points n. The result is called variance. Finally, the parameter standard deviation σ is the square root of the variance. This standard deviation can well reflect the degree of dispersion of the vibration characteristic parameter data.

[0044] Step 204: Determine a 3σ criterion interval according to the parameter mean and the parameter standard deviation.

[0045] Among them, the method of determining the 3σ criterion interval based on the mean (μ) and standard deviation (σ) of the vibration characteristic parameters is to use the normal distribution principle in statistics. The 3σ criterion, also known as the empirical rule, states that in a normal distribution, about 99.74% of the data values ​​fall within three standard deviations of the mean.

[0046] Therefore, the 3σ criterion interval is defined as the range from the mean minus three standard deviations to the mean plus three standard deviations, that is, (μ-3σ, μ+3σ). This interval represents the normal fluctuation range of the data, and data points falling outside this interval can be regarded as abnormal, which may indicate that the equipment is faulty or performance is degraded. By calculating the 3σ criterion interval of each characteristic parameter, vibration data that does not conform to the normal operating mode can be effectively identified and filtered out, thereby providing an accurate basis for fault diagnosis and health monitoring of power equipment.

[0047] Step 205: determining abnormal characteristic parameters from the vibration characteristic parameters based on the 3σ criterion interval.

[0048] The process of determining abnormal characteristic parameters from vibration characteristic parameters based on the 3σ criterion interval involves comparing the actual value of each characteristic parameter with its corresponding 3σ criterion interval. Specifically, the characteristic parameter value monitored in real time is compared with this interval: if the characteristic parameter value falls within the interval, it is considered to be within the normal range; if the characteristic parameter value exceeds this interval, higher than μ+3σ or lower than μ-3σ, it is marked as an abnormal characteristic parameter.

[0049] This approach can effectively identify vibration data that may indicate equipment failure or performance issues, providing key information for further fault diagnosis and health status assessment.

[0050] Step 206: determining an abnormal data set from the vibration data according to the abnormal characteristic parameter.

[0051] Specifically, once the abnormal characteristic parameters are determined by comparing the actual value of each characteristic parameter with the 3σ criterion interval, the next step is to filter out the original vibration data corresponding to these abnormal characteristic parameters. Specifically, the entire vibration data set can be checked, and those data points corresponding to the timestamps of the abnormal characteristic parameters can be identified, and these data points can be grouped into an abnormal data set. This abnormal data set contains all the vibration data marked as abnormal, which may be related to equipment failure or performance degradation.

[0052] Through this method, key abnormal data can be extracted from a large amount of vibration data, providing accurate data support for further analysis and diagnosis.

[0053] Step 207: Determine, based on the abnormal data set, that the power equipment is in a healthy state.

[0054] Specifically, the health status of the power equipment can be evaluated by analyzing the distribution, frequency and severity of these data. If the abnormal data set is relatively small and the deviation of the abnormal characteristic parameters is not large, it may indicate that the equipment is still in a healthy or nearly healthy state, but there are some minor abnormalities that are within an acceptable range.

[0055] On the contrary, if the abnormal data set is large, or the deviation of the abnormal feature parameters exceeds the preset safety threshold, this may indicate that the equipment health status is abnormal, there is a serious fault or performance problem, and immediate maintenance or repair is required.

[0056] In addition, historical data and maintenance records can be combined to use machine learning algorithms to conduct in-depth analysis of abnormal data sets to more accurately predict the health status and remaining service life of equipment.

[0057] Through this comprehensive analysis, an accurate judgment can be made on the health status of the power equipment, and corresponding maintenance measures can be taken to ensure the stable operation of the equipment and extend its service life.

[0058] In some embodiments, as the power equipment ages normally, the vibration characteristics of the equipment will also change to a certain extent, which is also a normal phenomenon. Therefore, when determining that the power equipment is in a healthy state based on the abnormal data set, it is also necessary to consider the impact of equipment aging and make some adaptive adjustments to the abnormal judgment criteria.

[0059] Therefore, step 207 may also include: determining the aging condition of the power equipment; and determining that the power equipment is in a healthy state according to the aging condition and the abnormal data set.

[0060] Specifically, determining the aging status of power equipment usually requires analyzing the equipment's historical operating data and current performance indicators to identify the trend and degree of performance degradation. This can be achieved by comparing the equipment's current vibration characteristic parameters with data from a new machine or baseline state, and monitoring the wear of key components. Based on this information, the degree of aging can be quantified, such as by calculating an aging coefficient or a performance degradation percentage.

[0061] When determining the health status of the equipment based on the abnormal data set, considering the impact of equipment aging on vibration characteristics, it is necessary to adaptively adjust the abnormality judgment criteria, such as relaxing the thresholds of some parameters or introducing aging correction factors. If the aging degree is within an acceptable range and the abnormal data set shows no significant abnormalities, the equipment can be considered to be in a healthy state; conversely, if the aging degree is severe or there are frequent abnormal indicators in the abnormal data set, this may indicate that the equipment has potential performance problems or failures, requiring further maintenance or repair.

[0062] Furthermore, the degree of aging of power equipment can be quantified from multiple aspects. The first is the operating time. The cumulative operating time of the equipment is a basic indicator, because over time, the internal parts of the equipment will gradually wear and age due to continuous physical and chemical effects. For example, for an engine, the number of operating hours can intuitively reflect its working fatigue. Generally speaking, the longer the operating time, the higher the degree of aging.

[0063] The second is the change in performance parameters. The key performance indicators of the equipment, such as the power and efficiency of the power equipment, can be monitored regularly. Taking the motor as an example, as it ages, the output power of the motor may gradually decrease, and the efficiency will also become lower. By comparing the initial performance parameters of the equipment with the current performance parameters, the percentage of performance decline is calculated to quantify the degree of aging. For example, the initial efficiency of the motor is 90%, and now it has dropped to 80%. The degree of aging can be measured based on this change ratio.

[0064] The next is the degree of wear of parts. This needs to be determined by inspecting or measuring the physical dimensions, surface quality, etc. of key parts. For example, for gears in mechanical transmission equipment, the wear of tooth thickness is measured. If the initial tooth thickness is 10mm, and after a period of use, the tooth thickness becomes 9mm, the wear amount is 1mm. The degree of aging can be quantified based on the ratio of the wear amount to the initial size or the comparison with the allowable wear limit.

[0065] There are also changes in material properties. By testing the materials of key equipment components, such as the hardness and toughness of metal parts, when the hardness of the material decreases or the toughness deteriorates, it means that the material properties have changed and the equipment is aging. For example, through hardness testing, it is found that the hardness of a certain part of the equipment has decreased to a certain extent compared with the initial value, and this can be used as a basis to quantify the degree of aging of the equipment in this part.

[0066] In addition, you can also consider the frequency of equipment maintenance. If the equipment frequently fails and needs maintenance, it means that the aging of the equipment has caused its reliability to decrease. The more maintenance times, the higher the degree of aging may be. You can count the number of times the equipment is repaired within a certain period of time, or quantify the degree of aging based on the proportion of maintenance costs to the initial value of the equipment.

[0067] This embodiment uses the method of combining aging conditions and real-time abnormal data analysis to more accurately evaluate the health status of power equipment and formulate corresponding maintenance strategies.

[0068] The embodiment of the present invention firstly acquires the vibration data of the equipment in real time and extracts the key characteristic parameters, which can accurately capture the subtle changes in the operating state of the equipment and provide a rich data basis for subsequent analysis. Then, by using the 3σ criterion in statistics, the mean and standard deviation of the parameters can be dynamically determined, and the normal and abnormal vibration characteristic parameters can be automatically divided. Compared with the traditional fixed threshold method, this method is more adaptable to the dynamic changes of the operating state of the equipment and improves the accuracy and response speed of fault detection. In addition, by intelligently screening abnormal data sets, the invalid analysis of a large amount of normal data is effectively reduced, the data storage and processing efficiency is optimized, and the maintenance cost is reduced. The present invention can warn of potential faults in advance, help operators take timely measures, avoid production interruptions and safety accidents caused by equipment failures, thereby significantly reducing economic losses and improving the continuity and reliability of industrial production.

[0069] Combine the following Figure 2 To further illustrate the method of the embodiment of the present invention, the method includes the following steps.

[0070] Step 301, obtaining vibration data of the power equipment to be tested when it is working.

[0071] This step may refer to step 201 of the above embodiment and will not be described in detail here.

[0072] Step 302: segment the vibration data according to preset time periods to obtain current time segment data and previous time segment data.

[0073] With the continuous collection of new vibration data, it is necessary to dynamically update the statistics of characteristic parameters (parameter mean and parameter standard deviation) to ensure the accuracy and timeliness of the power equipment health status monitoring system.

[0074] First, set a fixed time interval, such as every 5 minutes or every 10 minutes. This time period can be customized according to the characteristics of the equipment and monitoring requirements. At the end of each time period, mark the vibration data collected during that period as "previous time segment data", and mark the data collected after the next time period starts as "current time segment data". In this way, two continuous and non-overlapping data sets can be obtained, representing the operating status of the equipment in two adjacent time periods.

[0075] This segmentation method helps to capture the real-time dynamic changes of equipment status and provides an accurate data basis for subsequent feature parameter updates and health status assessment.

[0076] Step 303: merge the current time segment data and the previous time segment data into vibration data to be processed.

[0077] Specifically, the current time segment data and the previous time segment data are arranged in sequence to form a complete data set containing information from two consecutive time periods. The merged data set not only contains the operating status of the equipment in adjacent time periods, but also connects the data of the two time periods to more comprehensively analyze the continuous changes and development trends of the power equipment status.

[0078] This merging process provides more comprehensive data support for subsequent data analysis and dynamic updating of characteristic parameters, making health status assessment more accurate and timely.

[0079] Step 304: Determine vibration characteristic parameters according to the vibration data.

[0080] This step may refer to step 202 provided in the aforementioned embodiment, and will not be described in detail here.

[0081] Step 305: Determine a parameter mean and a parameter standard deviation based on the vibration characteristic parameter.

[0082] This step may refer to step 203 provided in the aforementioned embodiment, and will not be described in detail here.

[0083] Step 306: Determine a 3σ criterion interval according to the parameter mean and the parameter standard deviation.

[0084] This step may refer to step 204 provided in the aforementioned embodiment, and will not be described in detail here.

[0085] Step 307: determining abnormal characteristic parameters from the vibration characteristic parameters based on the 3σ criterion interval.

[0086] This step may refer to step 205 provided in the aforementioned embodiment, and will not be described in detail here.

[0087] Step 308: Determine the abnormal timestamp of the abnormal characteristic parameter.

[0088] Specifically, first identify those abnormal characteristic parameters that exceed the 3σ criterion interval. For each abnormal characteristic parameter, record its corresponding time point, which is called the abnormal timestamp. The abnormal timestamp accurately marks the exact moment when the abnormal characteristic parameter appears, which is crucial for subsequent fault diagnosis and analysis.

[0089] By determining the abnormal timestamp, the specific location where the abnormality occurs in the original vibration data can be quickly located, preparing for the extraction of the abnormal data set.

[0090] Step 309 : determining the abnormal data set from the vibration data according to the abnormal timestamp.

[0091] Specifically, the corresponding abnormal data points are extracted from the original Russian vibration data according to these timestamps. The data segments or data points corresponding to the abnormal timestamps are collected to form an abnormal data set. This abnormal data set contains all the vibration data identified as abnormal, which may be related to equipment failure or performance degradation.

[0092] In this way, key abnormal data can be extracted from a large amount of vibration data, providing accurate data support for further analysis and diagnosis. This abnormal data set will be used for subsequent fault diagnosis and health status assessment to determine the health status of the equipment and take corresponding maintenance measures.

[0093] In some embodiments, this step may specifically include: determining a plurality of abnormal data groups from the vibration data according to the abnormal timestamp; and sorting the plurality of abnormal data groups according to the abnormal timestamp to obtain the abnormal data set.

[0094] Among them, the abnormal data group includes acceleration, velocity and displacement. According to the previously determined abnormal timestamp, the corresponding data points are extracted from the overall vibration data. Since the abnormal timestamp marks the exact moment when the abnormal characteristic parameters appear, the acceleration, velocity and displacement data at these moments can be accurately found. For each abnormal timestamp, the corresponding acceleration, velocity and displacement measurements are collected to form an abnormal data group. This data group contains multi-dimensional vibration information at the same timestamp, which can provide a comprehensive data view for analyzing and identifying potential equipment failures.

[0095] After collecting all the abnormal data sets, these data sets need to be sorted according to their corresponding abnormal timestamps to ensure the time sequence of the data. This sorting process ensures that the abnormal data set can reflect the abnormal state of the power equipment at different time points, so that the abnormal data set becomes a continuous time series. The sorted abnormal data set can be used for further analysis, such as trend analysis, pattern recognition, or machine learning modeling, to more accurately diagnose the health status of the equipment and predict potential failures.

[0096] In this way, a structured abnormal data set can be constructed, which not only contains detailed vibration information at the time of the equipment abnormality, but also maintains the time order of the data, which is crucial for subsequent in-depth analysis and fault diagnosis. Such a data set enables the maintenance team to respond quickly and take necessary maintenance measures to avoid production interruptions and cost losses caused by equipment failures.

[0097] Step 310: Substitute the abnormal data group in the abnormal data set into the equipment health score formula to calculate the health score of the power equipment.

[0098] Among them, the process of substituting the abnormal data groups in the abnormal data set into the equipment health score formula involves quantitatively scoring the parameters such as acceleration, velocity and displacement in each abnormal data group according to their deviation from the normal operating threshold. Specifically, first set a threshold based on historical data and equipment characteristics for each parameter, and then calculate the deviation between the actual value of the parameter in each abnormal data group and these thresholds. Next, assign a health score to each parameter based on the size of the deviation, which reflects the impact of the current state of the parameter on the overall health of the equipment. Finally, the health scores of all parameters are summarized to obtain a comprehensive health score, which can quantitatively represent the current health status of the power equipment. This comprehensive score can be used to monitor the health status of the equipment in real time and provide data support for maintenance decisions.

[0099] In some embodiments, the device health score formula includes: Among them, S is the health score, M is the constant term, w is the influence coefficient, An is the value after acceleration standardization, Vn is the value after velocity standardization, and Dn is the value after displacement standardization.

[0100] In this embodiment, the normalization process can be achieved by subtracting each parameter from a set parameter threshold, and then dividing the obtained difference by the threshold. The specific steps of this method are as follows: Set parameter thresholds: First, set a normal operating threshold for each vibration data (such as acceleration, velocity, and displacement). Usually these thresholds are based on historical data or recommended values ​​from equipment manufacturers.

[0101] Calculate the difference: For each parameter, calculate the difference between its current value and the set threshold: Difference = X T, where X is the current vibration parameter value (such as acceleration, velocity or displacement), and T is the corresponding set threshold.

[0102] Perform standardization: Divide the calculated difference by the set threshold to achieve standardization: Zn=Difference / T=(XT) / T, where Zn is the value after standardization, indicating the degree of deviation of the current parameter value from the threshold.

[0103] Through this standardization process, the Zn value obtained can reflect the difference between the current vibration parameters and the normal operating state, which is convenient for subsequent use in the health score formula. The standardized value allows different parameters to be compared on the same scale, thereby improving the accuracy and effectiveness of the health score.

[0104] The equipment health scoring formula of this embodiment comprehensively considers the three key vibration parameters of acceleration, velocity and displacement, and ensures the comparability of parameters of different dimensions through standardization. In this equipment health scoring formula, by comparing the actual value of each parameter with the set threshold, the degree to which each parameter deviates from the normal operating state can be quantified.

[0105] The value range of the trigonometric function (sine function) is between [-1,1], which makes the final health score have a reasonable upper and lower limit range. When the sum of the normalized values ​​of acceleration, velocity, and displacement is low, that is, when the abnormality of the equipment is low, the denominator in the formula approaches 1, and the value of the trigonometric function approaches 1, which means that the health score of the equipment is high. As the degree of abnormality increases, the denominator increases, the value of the trigonometric function gradually decreases, and the health score also decreases, which is consistent with people's intuitive understanding that the health status of the equipment deteriorates as the abnormality worsens.

[0106] The introduction of the influence coefficient w allows adjusting the contribution of different parameters to the overall health score to adapt to the characteristics and operating environment of different devices.

[0107] The constant term M provides a scaling adjustment for the scores, ensuring that the scores are both sensitive and meaningful.

[0108] Overall, this formula achieves a quantitative assessment of the health status of power equipment through ingenious mathematical construction, providing a reasonable and practical tool for predictive maintenance and predictive repair of equipment.

[0109] Step 311: Determine whether the power equipment is healthy according to the health score.

[0110] Specifically, according to the power equipment health score S calculated by the health score formula, a score threshold T can be set h To determine the health status of the device. If the calculated health score S is greater than or equal to the threshold T h , the power equipment is considered to be in a healthy state; if S is less than T h , it indicates that the device may be abnormal or faulty. This scoring threshold T h It can be set based on historical data and expert experience to ensure that the scoring system is both sensitive and capable of distinguishing the health status of the equipment.

[0111] In this way, the health score provides a quantitative, actionable indicator to help maintenance teams monitor and evaluate the health status of power equipment in real time and take necessary maintenance measures in a timely manner.

[0112] An embodiment of the present invention provides a method for automatically detecting the health status of a power device, which aims to evaluate the health status of the device by real-time monitoring and intelligent analysis of the vibration data of the device. The method first obtains the vibration data of the device in a working state through a high-precision vibration sensor, and then extracts key vibration characteristic parameters such as acceleration, velocity and displacement from these data. Next, the mean and standard deviation of these characteristic parameters are calculated, and the parameter range for normal operation is determined using the 3σ criterion, that is, the range of the mean ±3 times the standard deviation. The characteristic parameters that exceed this range are marked as abnormal, and then the abnormal data sets are determined based on the timestamps of the abnormal characteristic parameters. These data sets contain the acceleration, velocity and displacement data at the time of the abnormality, and are sorted by timestamp.

[0113] In order to quantify the health status of the equipment, this embodiment introduces a equipment health score formula, which comprehensively considers the standardized acceleration, velocity and displacement values, and calculates a health score between 0 and 1 through the sine function and the influence coefficient. In addition, this embodiment also considers the impact of equipment aging on vibration characteristics, and comprehensively evaluates the health status of the equipment by analyzing the aging status of the equipment and combining it with the abnormal data set. This adaptive adjustment ensures that even in the case of natural aging of the equipment, its health status can be accurately judged.

[0114] Furthermore, this embodiment also includes a step of preprocessing the vibration data, that is, segmenting the vibration data according to a preset time period and merging the data of the current and previous time periods to form a vibration data set to be processed. This helps to capture short-term changes in the state of the equipment and provides data support for the dynamic update of characteristic parameters.

[0115] In summary, this embodiment provides a comprehensive automatic detection method for the health status of power equipment by combining real-time data monitoring, statistical analysis, health score calculation and aging status assessment. This method can not only timely identify and respond to abnormal conditions of equipment, but also adapt to the aging changes of equipment, and provide a scientific basis for predictive maintenance and predictive repair of equipment, thereby improving equipment reliability and maintenance efficiency, reducing unexpected downtime, and reducing maintenance costs.

[0116] The method provided in the above embodiment can be executed by a computer device, which is an electronic device. The following describes the electronic device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0117] It should be noted that Figure 3 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0118] like Figure 3 As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In RAM 403, various programs and data required for system operation are also stored. CPU 401, ROM 402 and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0119] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0120] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0121] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0123] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0124] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.

[0125] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0126] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0127] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for automatically detecting the health status of a power device, characterized in that: include: Obtain vibration data of the power equipment to be tested during operation; determining vibration characteristic parameters according to the vibration data; Determine a parameter mean and a parameter standard deviation based on the vibration characteristic parameters; Determine a 3σ criterion interval according to the parameter mean and the parameter standard deviation; Determining abnormal characteristic parameters from the vibration characteristic parameters based on the 3σ criterion interval; determining an abnormal data set from the vibration data according to the abnormal characteristic parameters; It is determined that the power equipment is in a healthy state according to the abnormal data set.

2. The method according to claim 1, characterized in that The step of determining an abnormal data set from the vibration data according to the abnormal characteristic parameters comprises: Determining an abnormal timestamp of the abnormal characteristic parameter; The abnormal data set is determined from the vibration data according to the abnormal timestamp.

3. The method according to claim 2, characterized in that The step of determining the abnormal data set from the vibration data according to the abnormal timestamp comprises: determining a plurality of abnormal data groups from the vibration data according to the abnormal timestamps, the abnormal data groups including acceleration, velocity, and displacement; The plurality of abnormal data groups are sorted according to the abnormal timestamps to obtain the abnormal data set.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining that the power equipment is in a healthy state according to the abnormal data set comprises: Substituting the abnormal data group in the abnormal data set into the equipment health score formula to calculate the health score of the power equipment; The power equipment is determined to be healthy according to the health score.

5. The method according to claim 4, characterized in that The device health score formula includes: Among them, S is the health score, M is a constant term, w is an influence coefficient, An is a value after acceleration standardization, Vn is a value after velocity standardization, and Dn is a value after displacement standardization.

6. The method according to claim 1, characterized in that After the step of obtaining the vibration data of the power equipment to be detected when it is working, the method further comprises: The vibration data is processed in segments according to a preset time period to obtain current time segment data and previous time segment data; The current time segment data and the previous time segment data are combined into vibration data to be processed.

7. The method according to claim 1, characterized in that The step of determining that the power equipment is in a healthy state according to the abnormal data set comprises: determining an aging condition of the power equipment; It is determined that the power equipment is in a healthy state according to the aging condition and the abnormal data set.

8. An electronic device, characterized in that: including one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on an electronic device, the electronic device is caused to execute the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images