Fault diagnosis method for paired bearings of fan motor, electronic equipment and medium

Abstract

The embodiment of the invention relates to the field of fan monitoring, and discloses a fault diagnosis method for paired bearings of a fan motor, electronic equipment and a medium. According to the invention, the motor comprises a first bearing and a second bearing which are arranged in a paired manner, the types of the first bearing and the second bearing are different, and the method comprises the following steps: obtaining a first temperature sequence of the first bearing and a second temperature sequence of the second bearing in a preset statistical period; based on a difference value between the first temperature sequence and the second temperature sequence, obtaining a temperature difference sequence in a preset statistical period; acquiring a preset temperature difference reference sequence corresponding to the temperature difference sequence; and determining a fault state of the second bearing according to a temperature difference deviation characteristic of the temperature difference sequence relative to a preset temperature difference reference sequence. The problems that in the prior art, bearing fault recognition sensitivity is low, the early fault recognition capacity is insufficient, and diagnosis accuracy is poor are solved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of wind turbine monitoring, and particularly to a fault diagnosis method, electronic equipment and medium for paired bearings of wind turbine motors. Background Technology

[0002] The motor in a wind turbine generator is the core component for converting mechanical energy into electrical energy, and its operational reliability directly affects the power generation efficiency and service life of the wind turbine. As a critical supporting component of the motor, the motor bearings bear continuous radial and axial loads during wind turbine operation. To meet the load requirements in different directions, the motor typically employs a paired bearing structure, that is, two different types of bearings are arranged along the axial direction. For example, cylindrical roller bearings are used to bear the main radial load, while deep groove ball bearings are used to bear the axial load and achieve shaft positioning.

[0003] When monitoring the condition of motor bearings, related technologies typically employ temperature monitoring of individual bearings, triggering an alarm when the bearing temperature exceeds a preset absolute temperature threshold. However, this single-point temperature monitoring method suffers from low fault identification sensitivity. Specifically, when early wear or lubrication abnormalities occur in the bearing, the temperature rise may not yet have reached the absolute temperature alarm threshold, making it difficult to detect the fault in a timely manner. Furthermore, since bearing temperature is influenced by a combination of factors such as ambient temperature, motor load, and wind speed, relying solely on absolute temperature for judgment can easily lead to false alarms or missed alarms, failing to accurately reflect the true health status of the bearing. Therefore, the bearing fault diagnosis methods in related technologies are insufficient in terms of early fault identification and diagnostic accuracy. Summary of the Invention

[0004] The purpose of this invention is to provide a fault diagnosis method for paired bearings of a wind turbine motor, so as to solve the problems of low bearing fault identification sensitivity, insufficient early fault identification capability, and poor diagnostic accuracy in related technologies.

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a fault diagnosis method for paired bearings of a wind turbine motor. The motor includes a first bearing and a second bearing that are paired together, and the first bearing and the second bearing are of different types. The method includes: acquiring a first temperature sequence of the first bearing and a second temperature sequence of the second bearing within a preset statistical period; acquiring a temperature difference sequence within the preset statistical period based on the difference between the first temperature sequence and the second temperature sequence; acquiring a preset temperature difference reference sequence corresponding to the temperature difference sequence; and determining the fault state of the second bearing based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence.

[0006] Embodiments of the present invention also provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the fault diagnosis method for the mating bearings of a wind turbine motor as described above.

[0007] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the fault diagnosis method for the paired bearings of a wind turbine motor as described above.

[0008] In this embodiment of the invention, by acquiring the temperature sequences of the paired first and second bearings within a preset statistical period and calculating their temperature difference sequence, the inherent temperature difference characteristics of different types of bearings under the same operating conditions are fully utilized. Because the first and second bearings are of different types, their rolling elements and raceways have different contact methods; for example, cylindrical roller bearings use line contact while deep groove ball bearings use point contact. This results in different heating characteristics of the two bearings under normal operating conditions, thus forming a relatively stable temperature difference benchmark. Specifically, this solution defines the first temperature sequence as the data of the first bearing under normal conditions, i.e., using the first bearing confirmed to be in normal operating condition as the temperature reference benchmark. When the second bearing experiences abnormal wear or lubrication failure, its increased heat generation causes the temperature difference sequence between the two bearings to deviate from the preset temperature difference benchmark sequence. By detecting this temperature difference deviation characteristic rather than the absolute temperature change of the second bearing, the interference of common-mode factors such as ambient temperature and load changes can be effectively eliminated, thereby improving the sensitivity and accuracy of second bearing fault identification and achieving early warning of second bearing faults.

[0009] Furthermore, obtaining the preset temperature difference reference sequence corresponding to the temperature difference sequence includes: obtaining the operating condition data of the motor within the preset statistical period; and obtaining the temperature difference reference sequence based on the operating condition data and the pre-built reference model. Thus, the temperature difference reference can be dynamically determined according to the actual operating conditions of the motor, enabling the temperature difference reference to adapt to the changing patterns of the temperature difference characteristics of the two bearings under different load conditions, further improving the accuracy of fault diagnosis.

[0010] In addition, the operating condition data includes at least one of the motor's active power, speed, and wind speed; the benchmark model is used to characterize the mapping relationship between the temperature difference between the first bearing and the second bearing under normal conditions and the changes in the operating condition data. Therefore, by establishing a mapping model between temperature difference and operating parameters such as active power, speed, or wind speed, the expected temperature difference performance of a normal bearing under different operating conditions can be accurately predicted, providing a precise benchmark for fault diagnosis.

[0011] Furthermore, the preset temperature difference reference sequence is a preset temperature difference threshold or a preset temperature difference range. Therefore, a single threshold or a range can be flexibly selected as the judgment benchmark according to the actual application scenario, simplifying system implementation while ensuring diagnostic accuracy.

[0012] Furthermore, the temperature difference deviation characteristics include the proportion of time during which data points in the temperature difference sequence have values ​​lower than the preset temperature difference benchmark sequence within the preset statistical period, and the amplitude distribution characteristics of the temperature difference sequence having values ​​lower than the preset temperature difference benchmark sequence. Therefore, by comprehensively considering both the proportion of time during which deviations occur and the magnitude of the deviation, the severity of temperature difference deviations can be more comprehensively characterized, distinguishing between occasional abnormal data and persistent fault characteristics, thus improving the reliability of fault diagnosis.

[0013] Furthermore, determining the fault state of the second bearing based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence includes: if the amplitude distribution characteristic is in the data points of the first amplitude interval and the time proportion exceeds the first time threshold, then the second bearing is determined to have a first type of fault; if the amplitude distribution characteristic is in the data points of the second amplitude interval and the time proportion exceeds the second time threshold, then the second bearing is determined to have a second type of fault; wherein, the deviation degree corresponding to the first amplitude interval is less than the deviation degree corresponding to the second amplitude interval, and the first time threshold is greater than the second time threshold. Therefore, for cases with small deviations, a longer duration is required to determine a fault, while for cases with large deviations, a shorter duration is sufficient. This differentiated determination strategy effectively balances the fault detection rate and false alarm rate, while distinguishing fault types of different severity levels, providing a tiered reference for subsequent maintenance decisions.

[0014] Furthermore, the step of obtaining the first temperature sequence of the first bearing and the second temperature sequence of the second bearing within a preset statistical period includes: obtaining the first real-time temperature of the first bearing and the second real-time temperature of the second bearing within the preset statistical period; if the first real-time temperature is abnormal, then the corresponding data is removed from the first temperature sequence; if the second real-time temperature is abnormal, then the corresponding data is removed from the second temperature sequence; if the difference between the first real-time temperature and the second real-time temperature is abnormal, then the corresponding data is removed from both the first and second temperature sequences. Thus, by pre-removing data with real-time anomalies, the influence of abnormal data points caused by factors such as sensor malfunctions, signal interference, or sudden changes in operating conditions on the temperature difference sequence can be eliminated. Simultaneously, it ensures that the data retained in the first temperature sequence is indeed data from the first bearing under normal conditions, guaranteeing the data quality used for fault diagnosis and avoiding misjudgments due to data anomalies.

[0015] Furthermore, after obtaining the preset temperature difference reference sequence corresponding to the temperature difference sequence, the method further includes: obtaining operating condition data of motors of the same type located in the same wind farm as the motor; calculating a group temperature difference characteristic value based on the operating condition data of the same type of motor; and correcting the preset temperature difference reference sequence based on the group temperature difference characteristic value to obtain a preset temperature difference reference sequence after eliminating common deviations. Thus, by introducing group data of motors of the same type within the same wind farm for horizontal comparison, systematic deviations caused by batch differences, installation deviations, or common environmental factors can be identified and eliminated, making the fault diagnosis of the second bearing more accurate and reducing false alarms caused by overall offset. Attached Figure Description

[0016] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0017] Figure 1 This is a schematic diagram of a fault diagnosis method for paired bearings of a fan motor according to the present application; Figure 2 This is the runtime sequence data of the abnormal bearing position as an example in the fault diagnosis method for the paired bearings of a wind turbine motor provided in this application; Figure 3 This is the running sequence data of the bearing in normal position as an example in the fault diagnosis method for the paired bearings of a wind turbine motor provided in this application; Figure 4 This is an example of a fault diagnosis method for paired bearings of a wind turbine motor provided in this application, showing the relationship between bearing temperature and active power at a normal bearing position. Figure 5 This is a diagram illustrating the relationship between bearing temperature and active power at an abnormal bearing location, as exemplified in a fault diagnosis method for paired bearings of a wind turbine motor provided in this application. Figure 6 This is a flowchart of a method for diagnosing faults in the mating bearings of a wind turbine motor, according to the present application. Figure 7 This is a structural diagram of an electronic device provided in this application. Detailed Implementation

[0018] As described in the background section, related technologies typically employ temperature monitoring of individual bearings, triggering an alarm when the bearing temperature exceeds a preset absolute temperature threshold. However, this approach suffers from low fault identification sensitivity. The applicant's research reveals that the root cause of this problem lies in the fact that the operating temperature of a bearing is not solely determined by its own health condition, but is influenced by a combination of external factors such as ambient temperature, motor load, rotational speed, and wind speed. When the ambient temperature is low, even if the bearing has experienced early wear leading to increased friction, its absolute temperature may still remain within the normal threshold range. Conversely, in high-temperature environments or under high-load conditions, the temperature of a healthy bearing may approach or even reach the alarm threshold. This monitoring method, which uses absolute temperature as the sole criterion, essentially drowns out the changes in the bearing's own health condition amidst fluctuations in environmental conditions, failing to effectively separate the temperature rise caused by faults from the temperature rise caused by operating conditions, resulting in insufficient sensitivity for early fault identification. Furthermore, due to differences in the structural types, installation locations, and load-bearing characteristics of different bearings, using a uniform absolute temperature threshold for judgment is difficult to adapt to individualized bearing condition assessment needs, further reducing diagnostic accuracy.

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the various embodiments of the present invention to facilitate a better understanding of this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments. The division of the various embodiments below is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0020] This invention relates to a fault diagnosis method for paired bearings of a wind turbine motor, applicable to the health status monitoring of motor bearings in wind turbine generator sets. Specifically, the method can be executed by a programmable logic controller deployed at the wind farm site, an edge computing device installed in the wind turbine nacelle, a local server located in the wind farm's control center, or a cloud processing platform deployed in a remote data center. Optionally, the method can also be executed by, but is not limited to, embedded control systems, industrial computers, distributed computing clusters, and other electronic devices with data processing capabilities.

[0021] In this embodiment of the invention, the motor includes a first bearing and a second bearing arranged in pairs. The first bearing and the second bearing are of different types. The method includes: acquiring a first temperature sequence of the first bearing and a second temperature sequence of the second bearing within a preset statistical period; acquiring a temperature difference sequence within the preset statistical period based on the difference between the first temperature sequence and the second temperature sequence; acquiring a preset temperature difference reference sequence corresponding to the temperature difference sequence; and determining the fault state of the second bearing based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence. In this embodiment of the invention, by acquiring the temperature sequences of the paired first bearing and the second bearing within a preset statistical period and calculating their temperature difference sequence, the physical law that different types of bearings have inherent temperature difference characteristics under the same operating conditions is fully utilized. Because the first bearing and the second bearing are of different types, their rolling elements and raceways have different contact methods. For example, cylindrical roller bearings have line contact while deep groove ball bearings have point contact, resulting in different heating characteristics of the two types of bearings under normal operating conditions, thereby forming a relatively stable temperature difference reference. In particular, this solution limits the first temperature sequence to the data of the first bearing under normal conditions, that is, the first bearing confirmed to be in normal operating condition is used as the temperature reference. When the second bearing experiences abnormal wear or lubrication failure, the increased heat generation causes the temperature difference sequence between the two bearings to deviate from the preset temperature difference reference sequence. By detecting this temperature difference deviation characteristic rather than the absolute temperature change of the second bearing, interference from common-mode factors such as ambient temperature and load changes can be effectively eliminated, thereby improving the sensitivity and accuracy of second bearing fault identification and enabling early warning of second bearing failures.

[0022] The following is a detailed description of the implementation details of the fault diagnosis method for the paired bearings of the wind turbine motor according to an embodiment of the present invention. The following content is only for the convenience of understanding and is not necessary for implementing this solution.

[0023] In this embodiment, the motor in the wind turbine generator set includes a paired first bearing and a second bearing, which are of different types. In a specific example, the first bearing is a cylindrical roller bearing, and the second bearing is a deep groove ball bearing. Thus, the cylindrical roller bearing bears radial loads through line contact, while the deep groove ball bearing bears axial loads and positions the shaft through point contact. Due to the fundamental difference in the contact methods between the rolling elements and raceways of the two types of bearings, under the same operating conditions, the cylindrical roller bearing has a larger contact area, and the frictional heat generated is generally higher than that of the deep groove ball bearing, forming a relatively stable positive temperature difference between the two. This inherent temperature difference characteristic lays the physical basis for this solution's use of temperature difference deviation for fault diagnosis.

[0024] In an optional embodiment, the paired bearings applicable to the embodiments of the present invention are not limited to the combination of cylindrical roller bearings and deep groove ball bearings described above, but can also be applied to other combinations of different types of paired bearings. The core mechanism of the fault diagnosis method of the embodiments of the present invention lies in the fact that different types of bearings, due to differences in their rolling element shapes, contact methods, and load-bearing characteristics, exhibit different frictional heating characteristics under the same operating conditions, thus forming a relatively stable temperature difference benchmark under normal operating conditions. When one of the paired bearings experiences abnormal wear, lubrication failure, or other faults, its heating characteristics change, causing the temperature difference between the two bearings to deviate from the normal benchmark. Fault identification can then be achieved by detecting this temperature difference deviation characteristic.

[0025] Specifically, in addition to the pairing combination of cylindrical roller bearings and deep groove ball bearings, the embodiments of the present invention can also be applied to the following paired bearing types: pairing combination of cylindrical roller bearings and angular contact ball bearings, pairing combination of tapered roller bearings and deep groove ball bearings, pairing combination of tapered roller bearings and angular contact ball bearings, pairing combination of self-aligning roller bearings and deep groove ball bearings, or any other pairing combination of two different types of bearings. From the perspective of bearing contact form, roller bearings adopt line contact or surface contact, with a relatively large contact area, and the frictional torque changes more significantly with the load; ball bearings adopt point contact, with a relatively small contact area, and the frictional characteristics are different. Regardless of the specific pairing combination used, as long as the two bearings are of different types and are paired and installed on the same motor shaft system, their heating characteristics will inevitably differ, and the temperature difference deviation detection method of the embodiments of the present invention can be applied.

[0026] Furthermore, the number of paired bearings in this embodiment of the invention is not limited to two. In application scenarios where three or more different types of bearings are paired and installed on the motor shaft system, the two bearings with the most significant differences in heating characteristics can be selected as monitoring objects, or temperature difference monitoring can be performed on multiple pairs of bearings separately, thereby achieving comprehensive fault diagnosis coverage of the multi-bearing system.

[0027] like Figure 1 As shown, the execution steps of this embodiment of the invention include steps 101 to 104.

[0028] In step 101, the first temperature sequence of the first bearing and the second temperature sequence of the second bearing within a preset statistical period are obtained, wherein the first temperature sequence contains data of the first bearing under normal conditions.

[0029] In this embodiment, the preset statistical period can be set according to actual monitoring needs, including but not limited to long periods such as 30 days, 60 days, or 90 days. Temperature data can be acquired by temperature sensors installed on the outer ring of each bearing. The temperature sensors can be placed in the non-load-bearing area of ​​the bearing to ensure the accuracy of temperature measurement. Temperature data is acquired by the data acquisition module at a preset sampling frequency, which can be on the order of seconds, minutes, or longer time intervals. The acquired temperature data is transmitted to the data processing unit via a wired or wireless link.

[0030] In a specific example, obtaining the first temperature sequence of the first bearing and the second temperature sequence of the second bearing within a preset statistical period includes: obtaining the first real-time temperature of the first bearing and the second real-time temperature of the second bearing within the preset statistical period; if the first real-time temperature is abnormal, the corresponding data is removed from the first temperature sequence; if the second real-time temperature is abnormal, the corresponding data is removed from the second temperature sequence; if the difference between the first and second real-time temperatures is abnormal, the corresponding data is removed from both the first and second temperature sequences. Specifically, determining whether the real-time temperature is abnormal can be done using a fixed threshold method, such as setting an effective temperature range, where data exceeding this range is considered abnormal data caused by sensor malfunction or signal interference. This abnormal data removal process can be implemented based on a sliding window statistical method or a spike filtering algorithm, thereby effectively eliminating the influence of abnormal data points caused by factors such as sensor malfunction, communication interruption, or sudden changes in operating conditions on subsequent temperature difference analysis, ensuring that the data retained in the first temperature sequence is indeed valid data of the first bearing under normal operating conditions, and guaranteeing the data quality used for fault diagnosis.

[0031] Furthermore, if the first real-time temperature is abnormal, the corresponding data is removed from the first temperature sequence, and a real-time fault is identified in the first bearing; if the second real-time temperature is abnormal, the corresponding data is removed from the second temperature sequence, and a real-time fault is identified in the second bearing; if the difference between the first and second real-time temperatures is abnormal, the corresponding data is removed from both the first and second temperature sequences, and a real-time fault is identified in both the first and second bearings. Specifically, when the real-time temperature of a single bearing exceeds a preset absolute temperature threshold, or the real-time temperature difference between two bearings exceeds a preset temperature difference threshold, the system can trigger real-time shutdown protection to prevent further damage to the bearings. This real-time diagnostic mechanism, together with the subsequent long-cycle temperature difference analysis, forms a dual-layer protection system. The real-time diagnostic mechanism is responsible for capturing rapidly developing severe faults, while the long-cycle temperature difference analysis is responsible for identifying slowly evolving early fault characteristics.

[0032] In step 102, a temperature difference sequence within a preset statistical period is obtained based on the difference between the first temperature sequence and the second temperature sequence.

[0033] In this embodiment, the temperature difference sequence is calculated as follows: for the first bearing temperature T1 and the second bearing temperature T2 collected at the same time, the difference between them is calculated as ΔT = T1 - T2. Taking a cylindrical roller bearing as the first bearing and a deep groove ball bearing as the second bearing as an example, the frictional heat generated by the first bearing is usually higher than that of the second bearing under normal operating conditions. Therefore, the temperature difference ΔT is usually positive under normal conditions. When the second bearing experiences abnormal wear or lubrication failure, its heat generation increases, which may cause the temperature difference ΔT to decrease or even become negative. Figure 2 and Figure 3 For example, Figure 2 The running sequence data of the bearing abnormal position is shown. It can be observed that the temperature difference of the bearing at the drive end is negative, indicating that the temperature of the deep groove ball bearing has risen abnormally and exceeded the temperature of the cylindrical roller bearing. Figure 3 The data shows the operating sequence of the bearing in its normal position. The temperature difference remains positive throughout, which is consistent with the difference in the heating characteristics of the two types of bearings under normal operating conditions.

[0034] In step 103, a preset temperature difference reference sequence corresponding to the temperature difference sequence is obtained.

[0035] In this embodiment, the preset temperature difference reference sequence is used to characterize the expected temperature difference between the two bearings under normal operating conditions, serving as a reference for determining whether the current temperature difference sequence has deviated abnormally. The preset temperature difference reference sequence can be in the form of a fixed threshold or a dynamic reference.

[0036] Optionally, in the first example using a fixed threshold, the preset temperature difference reference sequence is either a preset temperature difference threshold or a preset temperature difference range. Specifically, the preset temperature difference threshold can be set to 0, meaning that whether the temperature difference is below 0 is used as the judgment criterion; the preset temperature difference range can be determined based on the statistical distribution of historical normal operation data, for example, it can be set as the range formed by adding or subtracting a certain number of standard deviations from the mean temperature difference. Using a single threshold simplifies the judgment logic, while using a range can accommodate temperature fluctuations under normal operating conditions, and can be flexibly selected according to the actual application scenario.

[0037] Optionally, in the second example using a dynamic reference, obtaining a preset temperature difference reference sequence corresponding to the temperature difference sequence includes: acquiring the motor's operating condition data within a preset statistical period; and obtaining a temperature difference reference sequence based on the operating condition data and a pre-built reference model. This allows for the dynamic determination of the temperature difference reference based on the motor's actual operating conditions, enabling the temperature difference reference to adapt to the changing characteristics of the temperature difference between the two bearings under different load conditions, further improving the accuracy of fault diagnosis.

[0038] Furthermore, the aforementioned operating condition data includes at least one of the following: the motor's active power, speed, and wind speed; the benchmark model is used to characterize the mapping relationship between the temperature difference between the first and second bearings and the changes in operating condition data under normal conditions.

[0039] like Figure 4 and Figure 5 As shown, Figure 4 The scatter plot distribution and fitting curves of bearing temperature and active power (under normal bearing conditions) are shown. It can be observed that there is a stable gap between the fitting curve of cylindrical roller bearing temperature and the fitting curve of deep groove ball bearing temperature, and this gap increases slightly with the increase of active power. Figure 5 The data shows the scatter plot distribution of temperature and power under abnormal bearing conditions. The temperature of the deep groove ball bearing is significantly higher than that under normal conditions, causing the two fitted curves to intersect or even reverse. This characteristic indicates that there is a definite mapping relationship between temperature difference and operating conditions, which can be characterized by establishing a benchmark model.

[0040] Specifically, the baseline model can be represented as T ref =f(P,n,v), where P is the active power, n is the rotational speed, v is the wind speed, and T is the wind speed. ref This represents the baseline temperature difference value under the current conditions. The construction process of the baseline model includes: screening historical normal operation data and removing data from periods of failure and downtime; performing regression analysis or machine learning training with operating condition parameters as independent variables and the temperature difference under normal conditions as the dependent variable; and setting allowable fluctuation ranges to obtain dynamic upper and lower thresholds. The baseline model can be periodically updated based on recent health data to offset the overall temperature rise drift caused by material aging and ensure the timeliness of the baseline model.

[0041] In an optional embodiment, after obtaining the preset temperature difference benchmark sequence corresponding to the temperature difference sequence, the method further includes: obtaining operating condition data of motors of the same type located in the same wind farm as the motor; calculating a group temperature difference characteristic value based on the operating condition data of the same type of motor; and correcting the preset temperature difference benchmark sequence based on the group temperature difference characteristic value to obtain a preset temperature difference benchmark sequence after eliminating common deviations. Specifically, by introducing group data of the same type of motor in the same wind farm for horizontal comparison, systematic deviations caused by batch differences, installation deviations, or common environmental factors can be identified and eliminated. For example, when the temperature differences of multiple units of the same type in a wind farm all show the same direction of shift, the shift is likely due to changes in common environmental factors rather than bearing failure of a single unit. In this case, the preset temperature difference benchmark sequence can be corrected accordingly based on group statistical characteristics to avoid batch false alarms caused by overall shift.

[0042] In step 104, the fault state of the second bearing is determined based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence.

[0043] In this embodiment, the temperature difference deviation feature is used to comprehensively characterize the degree of abnormality of the temperature difference sequence relative to the preset temperature difference reference sequence, and serves as the basis for determining whether the second bearing has a fault.

[0044] In a specific example, the temperature difference deviation characteristics include the proportion of time during which data points in the temperature difference sequence have values ​​lower than the preset temperature difference benchmark sequence within a preset statistical period, and the amplitude distribution characteristics of data points in the temperature difference sequence with values ​​lower than the preset temperature difference benchmark sequence relative to the preset temperature difference benchmark sequence. Therefore, by comprehensively considering both the proportion of time during which deviations occur and the magnitude of the deviations, the severity of temperature difference deviations can be more comprehensively characterized, distinguishing between occasional abnormal data and persistent fault characteristics, thus improving the reliability of fault diagnosis.

[0045] Furthermore, based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence, the fault state of the second bearing is determined, including: if the time proportion of data points with amplitude distribution characteristics in the first amplitude interval exceeds the first time threshold, then the second bearing is determined to have a first type of fault; if the time proportion of data points with amplitude distribution characteristics in the second amplitude interval exceeds the second time threshold, then the second bearing is determined to have a second type of fault; wherein, the deviation degree corresponding to the first amplitude interval is less than the deviation degree corresponding to the second amplitude interval, and the first time threshold is greater than the second time threshold. Specifically, this differentiated judgment strategy reflects a balance between fault detection sensitivity and false alarm rate. For cases with small deviation degrees, it may be due to slight early wear, requiring a longer period of continuous observation to confirm it as a real fault, avoiding misjudgment due to short-term operating condition fluctuations; while for cases with large deviation degrees, it indicates that the bearing has already experienced obvious abnormal heating, which should be taken seriously even if the duration is short, therefore a shorter time threshold is sufficient to determine it as a fault.

[0046] In an optional embodiment, multiple amplitude ranges can be set for graded judgment: the first amplitude range can be set as a temperature difference below a benchmark value but above -1℃, corresponding to a first time threshold of 80%; the second amplitude range can be set as a temperature difference below -1℃ but above -2℃, corresponding to a second time threshold of 50%; the third amplitude range can be set as a temperature difference below -2℃ but above -4℃, corresponding to a third time threshold of 30%; and the fourth amplitude range can be set as a temperature difference below -4℃, corresponding to a fourth time threshold of 20%. This parameter setting can be calibrated based on statistical analysis of failure case data and normal operation data, ensuring a high fault detection rate while controlling the false alarm rate.

[0047] In an optional embodiment, after determining that the second bearing is faulty, the system can automatically generate corresponding handling instructions based on the fault type and severity. For type I faults, a planned maintenance work order can be generated and scheduled for inspection during the next routine maintenance; for type II faults or more severe fault types, an alarm can be triggered and an emergency maintenance work order can be generated, prompting maintenance personnel to handle the issue first. The maintenance work order can be integrated with the equipment management system to automate fault prediction, spare parts scheduling, and maintenance priority ranking.

[0048] like Figure 6 As shown, in this embodiment, the fault diagnosis method for paired bearings includes two parallel processing channels: a local processing side and a cloud server side.

[0049] On the local processing side, the system executes a real-time diagnostic process: First, temperature data of the first and second bearings is acquired and preprocessed, and the preprocessed temperature data is stored in the local storage unit; then, real-time temperature diagnosis is performed on the first real-time temperature of the first bearing and the second real-time temperature of the second bearing to determine whether there are any abnormalities in the real-time temperature of each bearing; if the real-time temperature diagnosis result is normal, real-time temperature difference diagnosis is further performed to determine whether there are any abnormalities in the difference between the first and second real-time temperatures; if the real-time temperature diagnosis result is abnormal, or the real-time temperature difference diagnosis result is abnormal, real-time shutdown protection is triggered, and a motor bearing repair or replacement instruction is generated; if both the real-time temperature diagnosis and the real-time temperature difference diagnosis results are normal, the real-time diagnostic process on the local processing side ends.

[0050] On the cloud server side, the system executes a long-cycle diagnostic process: First, the received temperature data undergoes cloud data preprocessing; then, sensor anomaly diagnosis is performed to determine if the temperature sensor is faulty; if the sensor anomaly diagnosis result is abnormal, a sensor repair or replacement instruction is generated; if the sensor anomaly diagnosis result is normal, the system enters the operational data filtering stage, removing abnormal data from the temperature data within a preset statistical period, and obtaining the first temperature sequence of the first bearing under normal conditions and the second temperature sequence of the second bearing; subsequently, temperature difference sequence calculation is performed, obtaining the temperature difference sequence based on the difference between the first and second temperature sequences; simultaneously, a preset temperature difference reference sequence corresponding to the temperature difference sequence is obtained for calibration; finally, a long-cycle temperature difference deviation judgment is performed, determining the fault state of the second bearing based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence; if the long-cycle temperature difference deviation judgment result is abnormal, a motor bearing repair or replacement instruction is generated; if the judgment result is normal, the long-cycle diagnostic process on the cloud server side ends.

[0051] Therefore, this embodiment forms a dual-layer protection system through real-time diagnosis on the local processing side and long-term diagnosis on the cloud server side. The local processing side is responsible for capturing rapidly developing serious faults. When the real-time temperature of a single bearing exceeds a preset threshold or the real-time temperature difference between two bearings exceeds a preset threshold, it promptly triggers shutdown protection to prevent further damage to the bearings. The cloud server side is responsible for identifying slowly evolving early fault characteristics and achieving early warning of second bearing faults through deviation analysis of the temperature difference sequence within a preset statistical period. The two processing channels work together to achieve comprehensive monitoring and graded response to paired bearing faults.

[0052] In this embodiment of the invention, by acquiring the temperature sequences of the paired first and second bearings within a preset statistical period and calculating their temperature difference sequence, the inherent temperature difference characteristics of different types of bearings under the same operating conditions are fully utilized. Because the first and second bearings are of different types, their rolling elements and raceways have different contact methods; for example, cylindrical roller bearings use line contact while deep groove ball bearings use point contact. This results in different heating characteristics of the two bearings under normal operating conditions, thus forming a relatively stable temperature difference benchmark. Specifically, this solution defines the first temperature sequence as the data of the first bearing under normal conditions, i.e., using the first bearing confirmed to be in normal operating condition as the temperature reference benchmark. When the second bearing experiences abnormal wear or lubrication failure, its increased heat generation causes the temperature difference sequence between the two bearings to deviate from the preset temperature difference benchmark sequence. By detecting this temperature difference deviation characteristic rather than the absolute temperature change of the second bearing, the interference of common-mode factors such as ambient temperature and load changes can be effectively eliminated, thereby improving the sensitivity and accuracy of second bearing fault identification and achieving early warning of second bearing faults.

[0053] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0054] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0055] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0056] The steps described above are for clarity only. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this invention. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, without changing the core design of the algorithm and process, are also within the protection scope of this invention.

[0057] Furthermore, the examples mentioned in the above embodiments can be freely combined, and any combination can be understood as an embodiment. The terms "embodiment" or "example" appearing in various locations in the specification do not necessarily refer to the same embodiment, nor are they independent or alternative embodiments mutually exclusive with other embodiments. Those skilled in the art will understand that the embodiments described herein can be combined with other embodiments.

[0058] Another embodiment of the present invention relates to an electronic device, such as Figure 7 As shown, it includes at least one processor 201; and a memory 202 communicatively connected to at least one processor 201; wherein the memory 202 stores instructions executable by at least one processor 201, the instructions being executed by at least one processor 201 to enable at least one processor 201 to perform the fault diagnosis method, electronic equipment and medium for the mating bearings of the wind turbine motor as described above.

[0059] The memory 202 and processor 201 are connected via a bus, which may include any number of interconnecting buses and bridges, connecting various circuits of one or more processors 201 and memory 202 together. The bus may also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 201 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 201.

[0060] Processor 201 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory 202 can be used for data accessed by processor 201 during operation.

[0061] Another embodiment of the present invention relates to a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the method embodiments described above.

[0062] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0063] Those skilled in the art will understand that the above embodiments are specific embodiments for implementing the present invention, and in practical applications, various changes in form and detail may be made without departing from the spirit and scope of the present invention.

Claims

1. A method for diagnosing faults in paired bearings of a fan motor, characterized in that, The motor includes a first bearing and a second bearing that are paired together, the first bearing and the second bearing being of different types, and the method includes: Obtain the first temperature sequence of the first bearing and the second temperature sequence of the second bearing within a preset statistical period; wherein, the first temperature sequence contains data of the first bearing under normal conditions; Based on the difference between the first temperature sequence and the second temperature sequence, the temperature difference sequence within the preset statistical period is obtained; Obtain a preset temperature difference reference sequence corresponding to the temperature difference sequence; The fault state of the second bearing is determined based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence.

2. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 1, characterized in that, The step of obtaining the preset temperature difference reference sequence corresponding to the temperature difference sequence includes: Obtain the operating condition data of the motor within the preset statistical period; Based on the operating condition data and the pre-built benchmark model, a temperature difference benchmark sequence is obtained.

3. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 2, characterized in that, The operating condition data includes at least one of the following: the active power of the motor, its speed, and the wind speed. The benchmark model is used to characterize the mapping relationship between the temperature difference between the first bearing and the second bearing and the changes in the operating condition data under normal conditions.

4. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 1, characterized in that, The preset temperature difference reference sequence is a preset temperature difference threshold or a preset temperature difference range.

5. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 1, characterized in that, The temperature difference deviation features include the proportion of time during which data points in the temperature difference sequence have values ​​lower than the preset temperature difference benchmark sequence, and the amplitude distribution features of data points in the temperature difference sequence with values ​​lower than the preset temperature difference benchmark sequence relative to the preset temperature difference benchmark sequence.

6. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 5, characterized in that, The step of determining the fault state of the second bearing based on the temperature difference deviation characteristics of the temperature difference sequence relative to the preset temperature difference reference sequence includes: If the amplitude distribution feature is in the data points of the first amplitude interval and the time proportion exceeds the first time threshold, then it is determined that the second bearing has a first type of fault. If the amplitude distribution feature is in the data point of the second amplitude interval and the time proportion exceeds the second time threshold, then it is determined that the second bearing has a second type of fault. Wherein, the deviation degree corresponding to the first amplitude interval is less than the deviation degree corresponding to the second amplitude interval, and the first time threshold is greater than the second time threshold.

7. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 1, characterized in that, The acquisition of the first temperature sequence of the first bearing and the second temperature sequence of the second bearing within a preset statistical period includes: Within a preset statistical period, obtain the first real-time temperature of the first bearing and the second real-time temperature of the second bearing; If the first real-time temperature is abnormal, the corresponding data is removed from the first temperature sequence; If the second real-time temperature is abnormal, the corresponding data is removed from the second temperature sequence; If the difference between the first real-time temperature and the second real-time temperature is abnormal, the corresponding data is removed from the first temperature sequence and the second temperature sequence.

8. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 7, characterized in that, The method includes: If the first real-time temperature is abnormal, the corresponding data is removed from the first temperature sequence, and it is determined that the first bearing has a real-time fault. If the second real-time temperature is abnormal, the corresponding data is removed from the second temperature sequence, and it is determined that the second bearing has a real-time fault. If the difference between the first real-time temperature and the second real-time temperature is abnormal, the corresponding data is removed from the first temperature sequence and the second temperature sequence, and it is determined that the first bearing and the second bearing have real-time faults.

9. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 1, characterized in that, After obtaining the preset temperature difference reference sequence corresponding to the temperature difference sequence, the method further includes: Obtain operating condition data of motors of the same type located in the same wind farm as the motor; Based on the operating condition data of the same type of motors, the characteristic value of the group temperature difference is calculated; The preset temperature difference benchmark sequence is corrected based on the group temperature difference characteristic value to obtain the preset temperature difference benchmark sequence after eliminating common deviations.

10. The fault diagnosis method for the paired bearings of the wind turbine motor according to claim 1, characterized in that, The first bearing is a cylindrical roller bearing, and the second bearing is a deep groove ball bearing.

11. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform a fault diagnosis method for the mating bearings of a wind turbine motor as described in any one of claims 1 to 10.

12. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a fault diagnosis method for the paired bearings of the wind turbine motor as described in any one of claims 1 to 10.

Images