Coupling failure detection method, device and readable storage medium

Abstract

Embodiments of the present application provide a kind of coupling fault detection method, equipment and readable storage medium, electronic equipment obtains the first vibration signal of gear box, the second vibration signal of generator, the speed signal of generator and the power signal of generator in current period, determine multiple order rotation frequency according to speed signal, and then determine the vibration amplitude of coupling in each order rotation frequency in multiple order rotation frequency, to obtain multiple vibration amplitudes.In addition, electronic equipment also determines the target working condition interval of coupling, and then carries out fault detection according to target working condition interval and multiple vibration amplitudes.By using this kind of scheme, the vibration signal of the two ends of coupling is collected, and the vibration amplitude of coupling in each order rotation frequency is extracted, whether the coupling is faulty is detected based on vibration amplitude in real time, precise detection and reliable early warning of coupling fault are realized, the damage of wind turbine generator unit caused by the expansion of fault and the risk of ESH are avoided, and the purpose of guaranteeing the safe operation of wind turbine generator unit is realized.

Description

Technical Field

[0001] This application relates to the field of wind power technology, and in particular to a method, device and readable storage medium for detecting faults in couplings. Background Technology

[0002] Wind energy, as a clean and renewable energy source, is receiving increasing attention from countries around the world. A wind turbine, or simply a wind turbine, is a device that uses wind energy to generate electricity. The core components of a wind turbine include a gearbox, generator, and coupling.

[0003] The gearbox high-speed output shaft is the power output shaft of the gearbox, and the generator input shaft is the power input shaft of the generator. A coupling is used to connect the gearbox high-speed output shaft and the generator input shaft. The coupling is mainly used to transmit torque, compensate for relative displacement between the two shafts, and buffer vibration and shock. Due to changes in the operating conditions of the wind turbine generator set and temperature variations, couplings are prone to failure during long-term operation. Therefore, it is necessary to monitor the coupling for malfunctions in real time. A common fault detection method is to check the alignment of the high-speed output shaft and the generator input shaft. If the high-speed output shaft and the generator input shaft are not aligned, the coupling is considered faulty.

[0004] However, early failures of couplings often do not manifest as shaft misalignment, making it difficult for conventional alignment detection methods to identify early failures, thus preventing wind turbine generators from meeting safe operation requirements. Summary of the Invention

[0005] This application provides a method, device, and readable storage medium for detecting coupling faults. By collecting vibration signals from both ends of the coupling and extracting the vibration amplitude at each rotational frequency, the method determines whether the coupling is faulty based on the vibration amplitude, thereby achieving early and accurate identification and reliable early warning of coupling faults and ensuring the safe operation of wind turbine generator sets.

[0006] In a first aspect, embodiments of this application provide a method for detecting faults in a coupling, including: In the current cycle, the first vibration signal of the gearbox, the second vibration signal of the generator, the speed signal of the generator, and the power signal of the generator are acquired. The high-speed output shaft of the gearbox and the generator input shaft of the generator are connected by a coupling. Determine the multi-stage rotational frequency based on the rotational speed signal; Based on the multi-order rotational frequencies, the first vibration signal, and the second vibration signal, the vibration amplitude of the coupling at each order of rotational frequencies is determined to obtain multiple vibration amplitudes. The target operating range of the coupling is determined based on the speed signal and the power signal; Fault detection is performed based on the target operating condition range and the multiple vibration amplitudes.

[0007] Secondly, embodiments of this application provide a fault detection device for a coupling, comprising: The acquisition module is used to acquire the first vibration signal of the gearbox, the second vibration signal of the generator, the speed signal of the generator, and the power signal of the generator in the current cycle. The high-speed output shaft of the gearbox and the generator input shaft of the generator are connected by a coupling. The first determining module is used to determine the multi-order rotational frequency based on the rotational speed signal; The second determining module is used to determine the vibration amplitude of the coupling at each of the multiple rotational frequencies based on the multi-order rotational frequencies, the first vibration signal, and the second vibration signal, so as to obtain multiple vibration amplitudes. The third determining module is used to determine the target operating range of the coupling based on the speed signal and the power signal; The processing module is used to perform fault detection based on the target operating condition range and the multiple vibration amplitudes.

[0008] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the electronic device to implement the method described in the first aspect or various possible implementations of the first aspect.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which, when executed by a processor, are used to implement the method described in the first aspect or various possible implementations of the first aspect.

[0010] Fifthly, embodiments of this application provide a computer program product comprising a computing program, wherein when the computer program is executed by a processor, it implements the method described in the first aspect or various possible implementations of the first aspect.

[0011] This application provides a method, device, and readable storage medium for detecting coupling faults. The coupling is used to connect the high-speed output shaft of a gearbox and the generator input shaft of a generator. During real-time detection of coupling faults, the electronic device acquires a first vibration signal from the gearbox, a second vibration signal from the generator, a speed signal from the generator, and a power signal from the generator in the current cycle. Based on the speed signal, it determines multiple rotational frequencies, and then determines the vibration amplitude of the coupling at each rotational frequency based on the multiple rotational frequencies, the first vibration signal, and the second vibration signal, thus obtaining multiple vibration amplitudes. Furthermore, the electronic device determines the target operating range of the coupling based on the speed signal and the power signal, and then performs fault detection based on the target operating range and multiple vibration amplitudes. This scheme, by collecting vibration signals from both ends of the coupling and extracting the vibration amplitude at each rotational frequency, allows for real-time detection of coupling faults, achieving accurate detection and reliable early warning of coupling faults. This prevents the fault from escalating and causing damage to the wind turbine generator set and ESH risks, thereby ensuring the safe operation of the wind turbine generator set. Moreover, the target operating condition range is determined adaptively based on speed and power to avoid unstable fluctuations in vibration amplitude caused by differences in operating conditions, thus avoiding misjudgment and improving the accuracy of fault detection. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the connection relationship of each component in the coupling fault detection method provided in the embodiments of this application; Figure 2 This is a flowchart of the coupling fault detection method provided in the embodiments of this application; Figure 3 This is another flowchart of the coupling fault detection method provided in the embodiments of this application; Figure 4 A schematic diagram of a coupling fault detection device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0014] A wind turbine generator set, also known as a wind turbine or wind turbine unit, consists of blades, a hub, a nacelle, and a tower. The nacelle is the "heart" of the wind turbine generator set, integrating core equipment and control systems that convert wind energy into electrical energy, such as the gearbox, generator, hydraulic system, transmission system, and yaw system. The wind turbine generator set converts wind energy into electrical energy through the coordinated work of its components: when wind blows over the aerodynamically designed blades, it drives the blades to rotate. Multiple blades are connected by the hub to form the rotor, which transmits rotational kinetic energy to the main shaft inside the nacelle. The main shaft in the nacelle is connected to the low-speed input shaft of the gearbox, and the high-speed output shaft of the gearbox is connected to the generator input shaft via a coupling. The low-speed rotation of the main shaft is accelerated by the gearbox and then transmitted from the high-speed output shaft to the generator input shaft through the coupling, driving the generator to operate and converting mechanical energy into electrical energy through electromagnetic induction.

[0015] In the wind power sector, couplings are crucial components connecting the high-speed output shaft of the gearbox to the input shaft of the generator. They primarily transmit torque, compensate for relative displacement between the two shafts, and buffer shocks and vibrations during operation. Due to factors such as changes in operating conditions, temperature variations, and nacelle vibration, couplings are prone to failure during long-term operation. Taking diaphragm couplings as an example, long-term operation can lead to problems such as loose bolts, breakage, detachment, diaphragm fatigue, deformation, damage, and even ejection. Early coupling failures typically do not manifest as shaft misalignment, making them difficult to identify using conventional alignment detection methods. Furthermore, diaphragm couplings are also prone to diaphragm installation backwards, which also does not present as misalignment.

[0016] If the fault is not detected and addressed in time, it may cause minor issues such as abnormal vibration of the drivetrain and damage to the high-speed output shaft and generator input shaft; in severe cases, it may lead to coupling detachment, meaning the connection between the coupling and the two shafts fails, making it no longer reliably transmit torque, or even the entire coupling may come off. Once the coupling detaches, it may penetrate the engine compartment housing, causing equipment damage, and even posing serious environmental, health, and safety (ESH) risks.

[0017] Based on this, embodiments of this application provide a method, device, and readable storage medium for detecting coupling faults. By collecting vibration signals from both ends of the coupling and extracting the vibration amplitude at various rotational frequencies of the coupling, the method determines whether the coupling is faulty based on the vibration amplitude, thereby achieving early and accurate identification and reliable early warning of coupling faults, avoiding the expansion of faults that could lead to damage to wind turbine generators and ESH risks, and ultimately ensuring the safe operation of wind turbine generators.

[0018] Figure 1 This is a schematic diagram showing the connection relationships of various components in the coupling fault detection method provided in this application embodiment. Please refer to... Figure 1The gearbox 11 has a high-speed output shaft 111, and the generator 12 has a generator input shaft 121. The high-speed output shaft 111 is the power output shaft of the gearbox 11, and the generator input shaft 121 is the power input shaft of the generator 12. The high-speed output shaft 111 is connected to one end of the coupling 13, and the generator input shaft 121 is connected to the other end of the coupling 13. A first vibration acceleration sensor 112 is installed on the gearbox 11, and a second vibration acceleration sensor 122 and a speed sensor 123 are installed on the generator 12. The first vibration acceleration sensor 112, the second vibration acceleration sensor 122, and the speed sensor 123 are respectively connected to the electronic equipment 14 in the engine room. The electronic device 14 includes a data acquisition module 141 and a main control module 142. The data acquisition module 141 acquires the first vibration signal of the gearbox 11 through the first vibration acceleration sensor 112, the second vibration signal of the generator 12 through the second vibration acceleration sensor 122, the speed signal of the generator 12 through the speed sensor 123, and the power signal of the generator 12.

[0019] During the real-time fault detection process, after the acquisition module 141 acquires the first vibration signal, the second vibration signal, the speed signal and the power signal in each detection cycle, it sends these signals to the main control module 142. The main control module 142 detects whether the coupling 13 is faulty based on these signals.

[0020] In the embodiments of this application, the coupling 13 can be a diaphragm coupling, a flexible coupling, a flexible pin coupling, etc. Unless otherwise specified, the following description will use a diaphragm coupling as an example for coupling 13.

[0021] Typically, the first vibration acceleration sensor 112 and the second vibration acceleration sensor 122 are simple to install and require no calibration or adjustment, making them standard equipment for wind turbine generator sets. The coupling fault detection method described in this application embodiment does not require the additional installation of displacement sensors and corresponding signal processing and transmission modules, thus reducing the cost of coupling fault detection to a certain extent.

[0022] The coupling fault detection method provided in this application is applicable to both early-stage and mid-to-late-stage coupling fault detection. Early-stage faults manifest as slight wear, micro-cracks, and loosening of the coupling, without significant alignment deviation. Mid-to-late-stage faults manifest as severe wear, breakage, significant misalignment, coupling failure, or even detachment of the coupling. Alignment refers to the absence of significant change in the relative position between the two shafts, with normal alignment measurement data, and no abnormality detected by conventional alignment instruments. Misalignment refers to the two shafts being out of sync, not aligned, or tilted at an angle, resulting in abnormal alignment measurement data. When the coupling experiences early-stage faults or is installed backwards, the alignment indicator may appear normal, making it impossible to detect the fault through alignment testing.

[0023] The execution subject of this application embodiment is an electronic device, which may be located in locations including, but not limited to, inside the nacelle, in the frequency converter cabinet at the bottom of the tower, or in the electrical cabinet on the top or side of the nacelle. When the electronic device is located inside the nacelle, it is also referred to as the machine terminal.

[0024] Figure 2 This is a flowchart of a coupling fault detection method provided in this application embodiment. This embodiment is applied to the above-mentioned electronic equipment and includes: 201. In the current cycle, acquire the first vibration signal of the gearbox, the second vibration signal of the generator, the speed signal of the generator, and the power signal of the generator. The high-speed output shaft of the gearbox and the generator input shaft of the generator are connected by a coupling.

[0025] In this embodiment, the electronic device periodically acquires a first vibration signal, a second vibration signal, a rotational speed signal, and a generator power signal to detect whether the coupling is faulty in real time. The length of the detection period is, for example, 1 second, 3 seconds, 2 seconds, etc., and is not limited in this embodiment.

[0026] 202. Determine the multi-stage rotational frequency based on the rotational speed signal.

[0027] In this embodiment, the multi-order frequency includes first-order, second-order, and third-order frequencies, and may also include other higher-order frequencies. Any first-order frequency is usually represented by an N-order frequency, where N is an integer. First-order frequency = generator speed ÷ 60, in Hertz (Hz), N-order frequency = N × first-order frequency. Taking a generator speed of 1500 revolutions per minute (rpm) as an example, 1500 rpm means the generator rotates 1500 times per minute. First-order frequency = 1500 / 60 = 25 Hz, second-order frequency = 2 × 25 Hz = 50 Hz, third-order frequency = 3 × 25 Hz = 75 Hz.

[0028] 203. Based on the multi-stage rotational frequencies, the first vibration signal, and the second vibration signal, determine the vibration amplitude of the coupling at each of the multi-stage rotational frequencies to obtain multiple vibration amplitudes.

[0029] When a coupling malfunctions, the abnormal energy, as observed in the vibration spectrum, is primarily concentrated at various rotational frequencies. Therefore, after determining the multiple rotational frequencies, the electronic equipment determines the vibration amplitude of the coupling at each of these frequencies, based on the multiple rotational frequencies, the first vibration signal, and the second vibration signal. For example, if the multiple rotational frequencies include first, second, and third frequencies of 25Hz, 50Hz, and 75Hz respectively, the electronic equipment can determine the vibration amplitude of the coupling at 25Hz, 50Hz, and 75Hz.

[0030] For each rotational frequency, the vibration amplitude represents the vibration intensity of the coupling at that frequency. For example, if the first-order rotational frequency is 25Hz, a vibration amplitude of 0.2g means that the coupling vibrates at the frequency of 25Hz with an amplitude of 0.2g, where 1g = 9.8m / s². 2 .

[0031] In this embodiment, a coupling failure can cause shaft vibration, and produce significant vibration at first-order, second-order, or other higher-order frequencies, with the corresponding vibration acceleration increasing, i.e., the vibration amplitude increasing.

[0032] For each rotational frequency, the electronic equipment combines the first vibration signal from the gearbox and the second vibration signal from the generator to determine the corresponding vibration amplitude. For example, the electronic equipment performs time-frequency analysis on the first vibration signal to obtain the amplitude corresponding to the rotational frequency, and performs time-frequency analysis on the second vibration signal to obtain the amplitude corresponding to the rotational frequency. Then, the electronic equipment integrates the amplitude obtained based on the first vibration signal and the amplitude obtained based on the second vibration signal to obtain the vibration amplitude corresponding to that rotational frequency of the coupling.

[0033] 204. Determine the target operating range of the coupling based on the speed signal and the power signal.

[0034] In this embodiment, the electronic device pre-divides the generator's possible operating range into multiple operating condition ranges based on the rotational speed and power. For example: Operating condition range 1: 1000rpm≤speed <1200rpm, 0kW≤power <200kW. Operating condition range 2: 1200rpm≤speed<1400rpm, 200kW≤power<400kW; Operating condition range 3: 1400rpm≤speed<1600rpm, 400kW≤power<600kW; ...... After acquiring the speed and power signals of the current cycle, the electronic equipment determines the target operating condition interval from multiple pre-defined operating condition intervals. For example, if the electronic equipment determines that the speed is 1600 rpm based on the speed signal of the current cycle and that the generator power is 500 kW based on the power signal of the current cycle, then the target operating condition interval is determined to be operating condition interval 3.

[0035] It should be noted that there is no strict order between steps 202 and 204 above.

[0036] 205. Perform fault detection based on the target operating condition range and the multiple vibration amplitudes.

[0037] In this embodiment, different operating condition intervals are independent of each other, and the threshold corresponding to each operating condition interval is independent. After the electronic device determines the target operating condition interval, it performs fault detection based on multiple vibration amplitude values ​​obtained from the target operating condition interval and the current cycle.

[0038] The coupling fault detection method provided in this application embodiment connects the high-speed output shaft of a gearbox and the generator input shaft of a generator. During real-time detection of coupling faults, the electronic device acquires a first vibration signal from the gearbox, a second vibration signal from the generator, a speed signal from the generator, and a power signal from the generator in the current cycle. Based on the speed signal, it determines multiple rotational frequencies, and then determines the vibration amplitude of the coupling at each rotational frequency based on these frequencies, the first vibration signal, and the second vibration signal, thus obtaining multiple vibration amplitudes. Furthermore, the electronic device determines the target operating range of the coupling based on the speed signal and the power signal, and then performs fault detection based on the target operating range and the multiple vibration amplitudes. This approach, by collecting vibration signals from both ends of the coupling and extracting the vibration amplitude at each rotational frequency, allows for real-time detection of coupling faults, achieving accurate detection and reliable early warning of coupling faults. This prevents the fault from escalating and causing damage to the wind turbine generator set and ESH (Electrical Safety Hazard) risks, thereby ensuring the safe operation of the wind turbine generator set. Moreover, the target operating condition range is determined adaptively based on speed and power to avoid unstable fluctuations in vibration amplitude caused by differences in operating conditions, thus avoiding misjudgment and improving the accuracy of fault detection.

[0039] Optionally, in the above embodiments, during the process of the electronic device determining the vibration amplitude of the coupling at each of the multiple rotational frequencies based on the multi-order rotational frequencies, the first vibration signal, and the second vibration signal to obtain multiple vibration amplitudes, for any target rotational frequency among the multiple orders of rotational frequencies, the electronic device determines the first vibration amplitude of the coupling at the target rotational frequency based on the first vibration signal, and determines the second vibration amplitude of the coupling at the target rotational frequency based on the second vibration signal. Then, the electronic device fuses the first vibration amplitude and the second vibration amplitude to obtain the vibration amplitude of the coupling at the target rotational frequency.

[0040] For example, for any target rotational frequency in a multi-order rotational frequency series, the electronic equipment collects a first vibration signal and a second vibration signal from the gearbox side and the generator side, respectively. The first and second vibration signals are collected by vibration acceleration sensors deployed at different locations, reflecting the vibration of the coupling at the target rotational frequency from different dimensions. The electronic equipment fuses the first and second vibration amplitudes to avoid deviations and interference from single vibration signals, ultimately obtaining a vibration amplitude that truly reflects the actual vibration of the coupling at the target rotational frequency.

[0041] By adopting this scheme, the electronic equipment integrates the first vibration amplitude corresponding to the first vibration signal and the second vibration amplitude corresponding to the second vibration signal, effectively reducing the measurement error and interference caused by single-point acquisition, and significantly improving the accuracy of vibration amplitude at various rotational frequencies, thereby achieving the goal of improving the accuracy of coupling fault detection.

[0042] Optionally, in the above embodiments, the coupling is in an aligned state.

[0043] The coupling fault detection method provided in this application is applicable to both early-stage and mid-to-late-stage coupling fault detection. Early-stage faults manifest as slight wear, micro-cracks, loose bolts, reversed diaphragm installation, and diaphragm deformation, without significant alignment deviations. When an early-stage coupling fault occurs, alignment is normal, making fault detection impossible. Early-stage coupling faults induce shaft vibration, producing significant vibrations at higher frequencies such as first and second order, with increased vibration acceleration and amplitude. Therefore, this application collects vibration signals from both ends of the coupling and extracts the vibration amplitude at various frequencies. Based on the vibration amplitude, it determines whether an early-stage coupling fault has occurred. This facilitates timely detection of faults such as loose bolts, broken or even detached diaphragms, and reversed installation when the shaft alignment is good. In other words, it enables accurate detection and reliable early warning of coupling faults even when the high-speed output shaft and generator input shaft are aligned.

[0044] The following is a detailed explanation of how electronic equipment performs fault detection based on the target operating condition range and the multiple vibration amplitudes.

[0045] In one method, the electronic device determines the rate of change of vibration amplitude corresponding to each rotational frequency. If the rate of change of vibration amplitude corresponding to a certain rotational frequency is greater than a preset rate of change, the coupling is determined to be faulty. Here, the rotational frequency is at least one of a first-order, second-order, or third-order frequency.

[0046] In another approach, the electronic equipment determines the ratio of the vibration amplitude of the coupling at second-order and other higher-order frequencies to the vibration amplitude at the first-order frequency. If at least one ratio exceeds a threshold value for the corresponding frequency, the coupling is deemed to be faulty.

[0047] In another approach, during the fault detection process performed by the electronic device based on the target operating condition range and the plurality of vibration amplitudes, the electronic device first determines multiple thresholds based on the target operating condition range, with each threshold corresponding to a vibration amplitude in turn. Then, the electronic device determines whether any of the multiple vibration amplitudes contains a target vibration amplitude greater than the corresponding threshold. If the target vibration amplitude is present among the multiple vibration amplitudes, the electronic device determines that the coupling is faulty; if the target vibration amplitude is not present, the electronic device determines that the coupling is not faulty and continues with the next detection cycle.

[0048] In this method, the electronic device determines a threshold for each rotational frequency. Clearly, since there is a one-to-one correspondence between rotational frequency and vibration amplitude, there is also a one-to-one correspondence between the threshold and vibration amplitude. The electronic device then determines whether there exists a target vibration amplitude among the multiple vibration amplitudes that is greater than the corresponding threshold. If at least one vibration amplitude is greater than the corresponding threshold, the coupling is determined to be faulty. For example, if the vibration amplitude of the coupling at the first rotational frequency is greater than the threshold, meaning the target vibration amplitude is the vibration amplitude corresponding to the first rotational frequency, the electronic device determines the coupling to be faulty. Similarly, if the vibration amplitude of the coupling at the second rotational frequency is greater than the corresponding threshold, and the vibration amplitude of the coupling at the third rotational frequency is also greater than the corresponding threshold, meaning the target vibration amplitude is the vibration amplitude corresponding to both the second and third rotational frequencies, then the coupling is determined to be faulty.

[0049] The embodiments of this application do not limit the size of the threshold corresponding to each frequency order. For example, the threshold corresponding to the first frequency order is the largest, the threshold corresponding to the second frequency order is the second largest, and the threshold corresponding to the third frequency order is smaller than the threshold corresponding to the second frequency order.

[0050] By adopting this approach and combining the threshold values ​​for operating condition intervals, the interference of power and speed on vibration amplitude can be eliminated, thus avoiding missed or false detections and improving the reliability of coupling fault detection.

[0051] Optionally, in the above embodiments, when the target vibration amplitude exists among the plurality of vibration amplitudes, during the process of the electronic device determining that the coupling is faulty, the electronic device first determines whether the number of target cycles within a series of consecutive detection cycles is greater than a first number, where the target cycle is the detection cycle in which the target vibration amplitude is greater than a corresponding threshold. When the number of target cycles within a series of consecutive detection cycles is greater than the first number, the electronic device determines that the coupling is faulty; when the number of target cycles within a series of consecutive detection cycles is less than or equal to the first number, the electronic device determines that the coupling is not faulty and continues to execute the detection of the next detection cycle.

[0052] In this embodiment, to prevent occasional increases in vibration amplitude caused by external factors such as electrical interference, load fluctuations, and sudden wind changes, rather than a fault in the coupling itself, the electronic device determines whether the number of target cycles within a series of consecutive detection cycles is greater than a first number. The last detection cycle in the series of consecutive detection cycles is the current cycle, and the number of consecutive detection cycles is, for example, 8, 10, 20, 100, etc.; correspondingly, the first number is, for example, 5, 7, 15, 90, etc. The target cycle is the detection cycle in which the target vibration amplitude is greater than the corresponding threshold. For example, among the multiple vibration amplitudes in the current cycle, the vibration amplitude corresponding to the second-order frequency is greater than the corresponding threshold, that is, the target vibration amplitude is the vibration amplitude corresponding to the second-order frequency. If, within a series of consecutive detection cycles, the vibration amplitude corresponding to the second-order frequency is greater than the corresponding threshold for a detection cycle greater than the first number, that is, the number of target detection cycles is greater than the first number, the electronic device determines that the coupling is faulty. After a coupling fault is detected, the electronic system triggers the wind turbine generator to shut down in order to check whether the coupling diaphragm is damaged, whether the bolts are loose, whether the diaphragm is installed backwards, or whether the two shafts are misaligned. If the number of target cycles is less than or equal to the first number in multiple consecutive testing cycles, the electronic system determines that the coupling is not faulty.

[0053] In the above embodiments, when the number of target cycles is greater than the first number, the target cycle can be a continuous detection cycle or a non-continuous detection cycle, and the embodiments of this application are not limited thereto.

[0054] Since multiple consecutive detection cycles correspond to a certain duration, taking one detection cycle as 1 second as an example, 10 consecutive detection cycles correspond to a duration of 10 seconds. Therefore, the electronic device can also detect whether the number of target cycles within the target duration is greater than a first number. The target duration is, for example, 5 times, 8 times, 10 times, 20 times, 100 times, etc., of the detection cycle, and this application embodiment is not limited thereto.

[0055] This approach combines multiple consecutive testing cycles to determine whether the coupling is faulty. It can effectively eliminate transient interference caused by external factors such as electrical interference, load fluctuations, and sudden changes in wind force, avoid false alarms, and improve the reliability of fault detection.

[0056] The following section provides a detailed explanation of how electronic devices determine multiple thresholds based on target operating condition ranges.

[0057] In one approach, a set of default thresholds is pre-set for each operating condition interval. This set of default thresholds includes the vibration amplitude threshold for each frequency order in the multi-frequency range. In this approach, the threshold values ​​for each operating condition interval are fixed. Taking a multi-frequency range including first-order, second-order, and third-order frequencies as an example, for each operating condition interval, the electronic equipment pre-acquires three thresholds, corresponding to the vibration amplitude at the first-order, second-order, and third-order frequencies, respectively. The vibration amplitude at the Nth-order frequency is used to characterize the vibration intensity of the coupling at the Nth-order frequency.

[0058] Based on the current cycle's multi-stage rotational frequencies, the first vibration signal, and the second vibration signal, the electronic device determines the vibration amplitude of the coupling at each of the multi-stage rotational frequencies. For each rotational frequency, the electronic device compares the vibration amplitude with the default threshold corresponding to that rotational frequency to determine whether the vibration amplitude is greater than the default threshold.

[0059] In another approach, the electronic device adaptively learns thresholds for each operating condition interval. That is, the set of thresholds corresponding to each operating condition interval may be constantly changing, and the thresholds used in adjacent detection cycles may not be the same. In this approach, during the process of determining multiple thresholds based on the target operating condition interval, the electronic device determines whether multiple historical thresholds exist based on a first sample set of the target operating condition interval. The first sample set is the sum of samples obtained from the start of sample collection for the target operating condition interval to the end of a historical period, where the historical period is the previous detection cycle of the current cycle, and one sample in the first sample set represents multiple vibration amplitude values ​​for one detection cycle. When multiple historical thresholds exist based on the first sample set, the electronic device determines these multiple historical thresholds as multiple thresholds for the target operating condition interval; when multiple historical thresholds do not exist based on the first sample set, the electronic device determines that the multiple thresholds for the target operating condition interval are preset thresholds.

[0060] For example, after determining the target operating condition range and performing fault detection on the coupling, the electronic device determines whether multiple historical thresholds already exist based on a first sample set of the target operating condition range. In other words, before performing fault detection on the coupling in the current cycle, the electronic device first determines whether multiple historical thresholds adaptively learned for the target operating condition range already exist. If multiple historical thresholds adaptively learned for the target operating condition range already exist, then these multiple historical thresholds are directly used as the thresholds for the target operating condition range. For example, if the current cycle is the 15th detection cycle, the target operating condition range is operating condition range a, and the target operating condition range of the 14th detection cycle is also operating condition range a, and the electronic device adaptively learns multiple historical thresholds after performing detection in the 14th detection cycle, then when performing detection in the 15th detection cycle, the electronic device directly uses these multiple historical thresholds as the thresholds for the 15th detection cycle.

[0061] For example, the current cycle is the 15th detection cycle, and the target operating condition interval is operating condition interval a. The target operating condition interval for detection cycles 12-14 is operating condition interval b, but the target operating condition interval for the 11th detection cycle is operating condition interval a. After the electronic device completes the detection of the 11th detection cycle, it adaptively learns multiple historical thresholds. Therefore, in the 15th detection cycle, the electronic device directly uses these multiple historical thresholds as the thresholds for the 15th detection cycle.

[0062] For example, the target operating condition intervals for the 11th, 15th, 16th, and 17th detection cycles are all operating condition interval 'a', while the target operating condition intervals for the 12th to 14th detection cycles are operating condition interval 'b'. When the current cycle is the 15th detection cycle, the electronic device directly uses the multiple historical thresholds obtained in the 11th detection cycle as the threshold for the 15th detection cycle. Assuming that the target operating condition intervals for the 1st to 10th detection cycles are all operating condition interval 'a', then the first sample set includes the samples collected in the 1st to 11th detection cycles.

[0063] When the current period is the 16th detection period, the electronic device adaptively learns multiple thresholds after completing the detection of the 15th detection period, which are called historical thresholds. The electronic device directly uses the multiple historical thresholds obtained in the 15th detection period as the thresholds for the 16th detection period. Assuming that the target operating condition interval for the 1st to 10th detection periods is operating condition interval 'a', then the first sample set includes the samples collected in the 1st to 11th and 15th detection periods.

[0064] Similarly, when the current period is the 17th detection period, the electronic device adaptively learns multiple thresholds after completing the detection of the 16th detection period, which are called historical thresholds. The electronic device directly uses the multiple historical thresholds obtained in the 16th detection period as the thresholds for the 17th detection period. Assuming that the target operating condition intervals for the 1st to 10th detection periods are all operating condition intervals a, then the first sample set includes the samples collected in the 1st to 11th, 15th, and 16th detection periods.

[0065] When multiple historical thresholds determined based on the first sample set are not available, the electronic device determines that the multiple thresholds for the target operating condition are preset thresholds. For example, if the current cycle is the 8th detection cycle, the target operating condition interval is operating condition interval a, the target operating condition interval for the 1st to 7th detection cycles is operating condition interval b, the first sample set is empty, and the electronic device has not adaptively learned multiple historical thresholds, therefore, when performing detection in the 8th detection cycle, the electronic device determines that the multiple thresholds for the target operating condition a are preset thresholds.

[0066] For example, in the current 8th detection cycle, the target operating condition interval is operating condition interval a. The target operating condition interval for the 1st detection cycle was operating condition interval b, and the target operating condition intervals for the 2nd to 7th detection cycles are operating condition interval a. Although the first sample set is not empty, the number of samples is too small for the electronic device to perform adaptive learning. Therefore, when the electronic device performs detection in the 8th detection cycle, it determines multiple thresholds for the target operating condition a, each of which is a preset threshold.

[0067] As described above, a sample in the first sample set is actually a group of vibration amplitude values. The samples in the first sample set may only include samples obtained from a portion of the detection cycles, rather than samples obtained from each detection cycle from the start of sample collection for the target operating condition interval to the end of the historical cycle. This is because the target operating condition intervals are not the same for some detection cycles, and each operating condition interval has its own first sample set. After each fault detection cycle is completed, the electronic device adds multiple vibration amplitude values ​​obtained in the current cycle as a single sample to the first sample set corresponding to the target operating condition interval to update the first sample set.

[0068] With this approach, after the electronic device determines the target operating condition range, if a historical threshold obtained through adaptive learning exists, the historical threshold is used; otherwise, the default threshold is used. This approach balances detection flexibility and versatility, adapts to different operating condition ranges, improves fault detection sensitivity, and reduces false alarms.

[0069] The following section details how electronic devices adaptively learn thresholds.

[0070] Optionally, after determining the target operating range of the coupling based on the speed signal and power signal, the electronic device, in addition to performing fault detection based on the target operating range and the plurality of vibration amplitudes, also determines the cumulative learning time of the second sample set. When the cumulative learning time is greater than a preset time and the number of samples in the second sample set is greater than a second quantity, the electronic device determines the thresholds corresponding to the plurality of vibration amplitudes respectively based on the second sample set.

[0071] For example, after the electronic device determines the target operating range of the coupling based on the speed signal and power signal in the current cycle, on the one hand, the electronic device performs fault detection based on the target operating range and multiple vibration amplitude values; on the other hand, the electronic device adds the multiple vibration amplitude values ​​obtained in the current cycle as a sample to the first sample set corresponding to the target operating range to obtain a second sample set. Then, the electronic device determines the cumulative learning time of the second sample set. This cumulative learning time is the duration from the start of sample collection for the target operating range to the end of the current cycle. For example, if the current cycle is the 10th detection cycle, the target operating range for the 1st to 5th detection cycles is operating range a, and the target operating range for the 6th detection cycle is operating range b, then the cumulative learning time for operating range b is the duration from the 6th detection cycle to the end of the 10th detection cycle. Assuming that the target operating range for the 6th to 10th detection cycles is all operating range b, then the second sample set contains 5 samples, that is, it contains multiple vibration amplitude values ​​obtained in each of the 6th to 10th detection cycles, with each vibration amplitude value in each detection cycle being a sample. Assuming that in the 6th, 9th and 10th detection cycles, the target operating condition interval is operating condition interval b, and the target operating condition interval is operating condition interval c in the 7th and 8th detection cycles, then the second sample set contains 3 samples, namely multiple vibration amplitude values ​​obtained in the 6th detection cycle, multiple vibration amplitude values ​​obtained in the 9th detection cycle, and multiple vibration amplitude values ​​obtained in the 10th detection cycle.

[0072] For the target operating range, after determining the cumulative learning time of the second sample, the electronic device checks whether the cumulative learning time is greater than a preset time. If the cumulative learning time is greater than the preset time, the electronic device determines the thresholds corresponding to multiple vibration amplitudes based on the second sample set.

[0073] Optionally, to avoid low threshold accuracy due to insufficient sample size in the second sample set despite sufficient cumulative learning time, the electronic device, after determining the cumulative learning time for the second sample, checks whether the cumulative learning time exceeds a preset time and whether the number of samples in the second sample set exceeds a second quantity. Only when the cumulative learning time exceeds the preset time and the number of samples in the second sample set exceeds the second quantity, does the electronic device adaptively learn based on the second sample set to determine the thresholds corresponding to the multiple vibration amplitudes.

[0074] With this approach, the electronic device can only perform adaptive learning when the cumulative learning time of the second sample set is greater than the preset time and the number of samples in the second sample set is greater than the second quantity. This avoids threshold deviation caused by biased samples or insufficient cumulative learning time, thereby improving the accuracy of the threshold and reducing misjudgments of coupling failures.

[0075] Optionally, in the above embodiments, when the cumulative learning time is not greater than the preset time, and / or when the number of samples in the second sample set is not greater than the second number, the multiple thresholds of the target working condition interval are determined to be preset thresholds.

[0076] In this embodiment, if wind speed and direction change frequently, the generator power and speed will fluctuate frequently, and the generator's target operating condition range will switch frequently. This results in insufficient sample size and short cumulative learning time in the second sample set for the same operating condition range, leading to poor sample representativeness. Conversely, if wind speed and direction change gradually, the generator power and speed will change steadily, and the target operating condition range will switch less frequently. This can lead to a situation where the cumulative learning time is sufficient, but the sample size is too small and the sample diversity is insufficient. Therefore, when the cumulative learning time is not greater than a preset time, and / or when the number of samples in the second sample set is not greater than a second number, multiple thresholds for the target operating condition range are determined as preset thresholds.

[0077] This approach uses dual conditions to determine whether to use a preset threshold, avoiding distortion of the learning threshold due to insufficient samples, ensuring the reliability of the fault judgment benchmark, improving detection stability, and reducing the risk of false alarms and missed detections.

[0078] The following section provides a detailed explanation of how the electronic device determines the thresholds corresponding to the plurality of vibration amplitudes based on the second sample set.

[0079] In one approach, for each rotational frequency, the electronic device performs time-series fitting on samples in the second sample set to obtain the variation curve of the vibration amplitude of the coupling at that rotational frequency. The threshold is then determined based on the variation curve to adapt to long-term operating condition drift.

[0080] In another approach, when the cumulative learning duration exceeds a preset duration and the number of samples in the second sample set is greater than a second quantity, the electronic device determines the statistical distribution of vibration amplitudes at each order based on the second sample set. Then, for each frequency order, the electronic device determines a threshold based on the statistical distribution of the vibration amplitudes to obtain thresholds corresponding to the plurality of vibration amplitudes respectively.

[0081] In this embodiment, a sample contains vibration amplitude values ​​corresponding to each of multiple rotational frequencies. For each rotational frequency, the electronic device determines a statistical distribution based on the vibration amplitude values ​​at that frequency in the second sample set, thereby obtaining a statistical distribution of the vibration amplitude values ​​of the coupling at each rotational frequency. The statistical distribution includes, but is not limited to, the mean and standard deviation of the vibration amplitude values. Then, for each rotational frequency, the electronic device determines a threshold value based on the statistical distribution of the vibration amplitude values ​​corresponding to that frequency, thereby obtaining threshold values ​​corresponding to multiple vibration amplitude values ​​respectively. For example, the threshold value T1 for the vibration amplitude of the coupling at a first-order rotational frequency is T1 = μ1 + K × σ1, where μ1 is the mean, σ1 is the standard deviation, and K is a preset coefficient.

[0082] Using this approach, the electronic equipment determines the threshold based on the statistical distribution of the vibration amplitude of the coupling at various rotational frequencies, making the threshold fit the target operating range, effectively reducing false alarms and missed alarms, and achieving the goal of improving the accuracy of coupling fault detection.

[0083] Figure 3 This is another flowchart of the coupling fault detection method provided in this application embodiment. This embodiment includes: 301. Real-time acquisition of the first vibration signal of the gearbox, the second vibration signal of the generator, the speed signal of the generator, and the power signal of the generator.

[0084] 302. Determine the multi-stage rotational frequency based on the rotational speed signal.

[0085] 303. Based on the multi-stage rotational frequencies, the first vibration signal, and the second vibration signal, determine the vibration amplitude of the coupling at each stage of the multi-stage rotational frequencies to obtain multiple vibration amplitudes. Then, execute steps 305 and 312.

[0086] 304. Determine the target operating range of the coupling based on the speed and power signals. Then proceed with steps 305 and 312.

[0087] 305. Determine whether there are multiple historical thresholds determined based on the first sample set of the target working condition range. If there are multiple historical thresholds determined based on the first sample set, proceed to step 306; if there are no multiple historical thresholds determined based on the first sample set, proceed to step 307.

[0088] 306. Determine multiple historical thresholds as multiple thresholds for the target operating condition range. Then, proceed to step 308.

[0089] 307. Determine multiple thresholds for the target operating condition, each being a preset threshold. Then, proceed to step 308.

[0090] 308. Determine whether there is a target vibration amplitude greater than the corresponding threshold among the multiple vibration amplitudes. If the target vibration amplitude exists among the multiple vibration amplitudes, proceed to step 309; if the target vibration amplitude does not exist among the multiple vibration amplitudes, return to step 301.

[0091] 309. Determine whether the number of target cycles within a series of consecutive detection cycles is greater than the first number. If the number of target cycles within a series of consecutive detection cycles is greater than the first number, proceed to step 310; if the number of target cycles within a series of consecutive detection cycles is less than or equal to the first number, return to step 301.

[0092] 310. Triggers wind turbine generator shutdown.

[0093] 311. Perform fault detection on the coupling.

[0094] 312. Update the second sample set and the cumulative learning time of the second sample set.

[0095] 313. Determine whether the cumulative learning time of the second sample set is greater than the preset time and whether the number of samples in the second sample set is greater than the second quantity. If the cumulative learning time is greater than the preset time and the number of samples in the second sample set is greater than the second quantity, execute step 313; if the cumulative learning time is not greater than the preset time and / or the number of samples in the second sample set is not greater than the second quantity, execute step 314.

[0096] 314. For each frequency in a multi-frequency series, determine the statistical distribution based on the vibration amplitude corresponding to the second sample set, and determine the threshold based on the statistical distribution of the vibration amplitude corresponding to the frequency, so as to obtain the threshold corresponding to each of the multiple vibration amplitudes.

[0097] 315. The multiple thresholds for the target operating condition range are preset thresholds.

[0098] The multiple thresholds determined in steps 314 and 315 are used as multiple thresholds for the first subsequent working condition interval as the target working condition interval.

[0099] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0100] Figure 4 This is a schematic diagram of a coupling fault detection device provided in an embodiment of this application. The coupling fault detection device 400 includes: an acquisition module 41, a first determination module 42, a second determination module 43, a third determination module 44, and a processing module 45.

[0101] The acquisition module 41 is used to acquire the first vibration signal of the gearbox, the second vibration signal of the generator, the speed signal of the generator, and the power signal of the generator in the current cycle. The high-speed output shaft of the gearbox and the generator input shaft of the generator are connected by a coupling. The first determining module 42 is used to determine the multi-order rotation frequency based on the rotation speed signal; The second determining module 43 is used to determine the vibration amplitude of the coupling at each frequency in the multi-frequency range based on the multi-frequency range, the first vibration signal and the second vibration signal, so as to obtain multiple vibration amplitudes. The third determining module 44 is used to determine the target operating condition range of the coupling based on the speed signal and the power signal; The processing module 45 is used to perform fault detection based on the target operating condition range and the multiple vibration amplitudes.

[0102] In one feasible implementation, the processing module 45 is used to determine multiple thresholds based on the target operating condition range, wherein the thresholds among the multiple thresholds correspond one-to-one with the vibration amplitudes among the multiple vibration amplitudes; determine whether there is a target vibration amplitude among the multiple vibration amplitudes that is greater than the corresponding threshold; and determine that the coupling is faulty when the target vibration amplitude exists among the multiple vibration amplitudes.

[0103] In one feasible implementation, the processing module 45 is used to determine whether the number of target cycles within a series of consecutive detection cycles is greater than a first number when the target vibration amplitude exists among the plurality of vibration amplitudes, wherein the target cycle is the detection cycle in which the target vibration amplitude is greater than a corresponding threshold; and to determine that the coupling is faulty when the number of target cycles within the series of consecutive detection cycles is greater than the first number.

[0104] In one feasible implementation, when the processing module 45 determines multiple thresholds based on the target operating condition interval, it is used to determine whether there are multiple historical thresholds determined based on a first sample set of the target operating condition interval. The first sample set is the sum of samples obtained from the start of sample collection for the target operating condition interval to the end of the historical period. The historical period is the previous detection period of the current period. One sample in the first sample set represents multiple vibration amplitudes of one detection period. When there are multiple historical thresholds determined based on the first sample set, the multiple historical thresholds are determined to be multiple thresholds of the target operating condition interval. When there are no multiple historical thresholds determined based on the first sample set, the multiple thresholds of the target operating condition are determined to be preset thresholds.

[0105] In one feasible implementation, after the third determining module 44 determines the target operating range of the coupling based on the speed signal and the power signal, the processing module 45 is further configured to determine the cumulative learning time of the second sample set. The cumulative learning time is the duration from the start of sample collection for the target operating range to the end of the current cycle. The second sample set is the sum of samples obtained from the start of sample collection for the target operating range to the end of the current cycle. When the cumulative learning time is greater than a preset time and the number of samples in the second sample set is greater than a second number, thresholds corresponding to the plurality of vibration amplitudes are determined based on the second sample set.

[0106] In one feasible implementation, the processing module 45 is further configured to determine multiple thresholds of the target working condition interval as preset thresholds when the cumulative learning time is not greater than the preset time, and / or when the number of samples in the second sample set is not greater than the second number.

[0107] In one feasible implementation, when the cumulative learning time exceeds a preset time and the number of samples in the second sample set is greater than a second quantity, when the processing module 45 determines the thresholds corresponding to the plurality of vibration amplitudes based on the second sample set, it is used to determine a statistical distribution for each of the multi-order rotation frequencies based on the vibration amplitudes corresponding to the second sample set, so as to obtain the statistical distribution of the vibration amplitudes of the coupling at each order of rotation frequencies; for each order of rotation frequency, a threshold is determined based on the statistical distribution of the vibration amplitudes corresponding to the rotation frequency, so as to obtain the thresholds corresponding to the plurality of vibration amplitudes.

[0108] In one feasible implementation, the coupling is in an aligned state.

[0109] In one feasible implementation, the second determining module 43 is used to determine, for any target rotation frequency in the multi-order rotation frequency, a first vibration amplitude of the coupling at the target rotation frequency based on the first vibration signal, and a second vibration amplitude of the coupling at the target rotation frequency based on the second vibration signal; and to fuse the first vibration amplitude and the second vibration amplitude to obtain the vibration amplitude of the coupling at the target rotation frequency.

[0110] The coupling fault detection device provided in this application embodiment can perform the actions of the electronic equipment in the above embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0111] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 500 includes: Processor 51 and memory 52; The memory 52 stores computer instructions and test data; The processor 51 executes the computer instructions stored in the memory 52, causing the processor 51 to perform the coupling fault detection method as described above.

[0112] The specific implementation process of processor 51 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0113] Optionally, the electronic device 500 also includes a communication component 53. The processor 51, memory 52, and communication component 53 can be connected via a bus 54.

[0114] This application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, are used to implement the coupling fault detection method described above.

[0115] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the coupling fault detection method described above.

[0116] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0117] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for detecting faults in a coupling, characterized in that, Applied to electronic devices, the method includes: In the current cycle, the first vibration signal of the gearbox, the second vibration signal of the generator, the speed signal of the generator, and the power signal of the generator are acquired. The high-speed output shaft of the gearbox and the generator input shaft of the generator are connected by a coupling. Determine the multi-stage rotational frequency based on the rotational speed signal; Based on the multi-order rotational frequencies, the first vibration signal, and the second vibration signal, the vibration amplitude of the coupling at each order of rotational frequencies is determined to obtain multiple vibration amplitudes. The target operating range of the coupling is determined based on the speed signal and the power signal; Fault detection is performed based on the target operating condition range and the multiple vibration amplitudes.

2. The method according to claim 1, characterized in that, The fault detection based on the target operating condition range and the multiple vibration amplitudes includes: Multiple thresholds are determined based on the target operating condition range, and the thresholds among the multiple thresholds correspond one-to-one with the vibration amplitudes among the multiple vibration amplitudes; Determine whether there is a target vibration amplitude among the plurality of vibration amplitudes that is greater than the corresponding threshold; When the target vibration amplitude is present among the plurality of vibration amplitudes, the coupling is determined to be faulty.

3. The method according to claim 2, characterized in that, The step of determining a coupling fault when the target vibration amplitude exists among the plurality of vibration amplitudes includes: When the target vibration amplitude exists among the multiple vibration amplitudes, it is determined whether the number of target cycles within multiple consecutive detection cycles is greater than a first number, wherein the target cycle is the detection cycle in which the target vibration amplitude is greater than a corresponding threshold; When the number of target cycles within the consecutive multiple detection cycles exceeds a first number, the coupling is determined to be faulty.

4. The method according to claim 2, characterized in that, The determination of multiple thresholds based on the target operating condition range includes: Determine whether there are multiple historical thresholds determined based on the first sample set of the target working condition interval. The first sample set is the sum of samples obtained from the start of sample collection for the target working condition interval to the end of the historical period. The historical period is the previous detection period of the current period. One sample in the first sample set is multiple vibration amplitude values ​​of one detection period. When there are multiple historical thresholds determined based on the first sample set, the multiple historical thresholds are determined to be multiple thresholds of the target working condition range; When there are no multiple historical thresholds determined based on the first sample set, the multiple thresholds for the target working condition are determined to be preset thresholds.

5. The method according to any one of claims 1 to 4, characterized in that, After determining the target operating range of the coupling based on the speed signal and power signal, the process also includes: The cumulative learning time of the second sample set is determined. The cumulative learning time is the duration from the start of sample collection for the target working condition interval to the end of the current cycle. The second sample set is the sum of the samples obtained from the start of sample collection for the target working condition interval to the end of the current cycle. When the cumulative learning duration is greater than the preset duration and the number of samples in the second sample set is greater than the second quantity, the threshold corresponding to the multiple vibration amplitudes is determined according to the second sample set.

6. The method according to claim 5, characterized in that, Also includes: When the cumulative learning time is not greater than the preset time, and / or when the number of samples in the second sample set is not greater than the second number, the multiple thresholds of the target working condition interval are determined to be preset thresholds.

7. The method according to claim 5, characterized in that, When the cumulative learning duration exceeds a preset duration and the number of samples in the second sample set is greater than a second quantity, the threshold corresponding to each of the multiple vibration amplitudes is determined based on the second sample set, including: When the cumulative learning time is greater than the preset time and the number of samples in the second sample set is greater than the second number, for each frequency in the multi-frequency series, the statistical distribution is determined according to the vibration amplitude corresponding to the second sample set, so as to obtain the statistical distribution of the vibration amplitude of the coupling at each frequency. For each rotational frequency, a threshold is determined based on the statistical distribution of the vibration amplitude corresponding to the rotational frequency, so as to obtain the threshold corresponding to the multiple vibration amplitudes respectively.

8. The method according to any one of claims 1 to 4, characterized in that, The coupling is in the centering state.

9. The method according to any one of claims 1 to 4, characterized in that, The step of determining the vibration amplitude of the coupling at each of the multiple rotational frequencies, the first vibration signal, and the second vibration signal, to obtain multiple vibration amplitudes, includes: For any target rotation frequency among the multi-order rotation frequencies, the first vibration amplitude of the coupling at the target rotation frequency is determined based on the first vibration signal, and the second vibration amplitude of the coupling at the target rotation frequency is determined based on the second vibration signal; By combining the first vibration amplitude and the second vibration amplitude, the vibration amplitude of the coupling at the target rotational frequency is obtained.

10. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to implement the method as described in any one of claims 1 to 8.

Images