Oil collecting device and oil leakage monitoring system for fan gear box

Abstract

The present application relates to the technical field of wind turbine group monitoring, in particular to an oil collecting device for a wind turbine gearbox and an oil leakage monitoring system, comprising: acquiring temperature data of the gearbox part at the current time and in the previous preset time range, liquid level data of the oil in the oil collecting tank, and pressure data in the gearbox; determining a first oil leakage risk index of temperature characteristic influence based on the temperature data change; determining a second oil leakage risk index of liquid level characteristic influence based on the correlation between the liquid level drop rate and the temperature change; combining the first oil leakage risk index, the second oil leakage risk index, and the pressure data distribution in the gearbox to determine the oil leakage possibility; and monitoring the oil leakage according to the oil leakage possibility. The present application can comprehensively judge multiple dimensional parameters, each parameter verifies each other, accurately and reliably realizes the oil leakage judgment, effectively eliminates the false judgment caused by single parameter interference, and greatly improves the accuracy of oil leakage monitoring.

Description

Technical Field

[0001] This invention relates to the field of wind turbine generator monitoring technology, specifically to an oil collection device and oil leakage monitoring system for wind turbine gearboxes. Background Technology

[0002] The wind turbine gearbox is a key transmission component in a wind turbine generator set. It is mainly used to transmit the power of the low-speed rotation of the wind turbine to the gearbox speed-increasing device, thereby achieving the high-speed rotation required for power generation. The oil collection tank, as an auxiliary device of the wind turbine gearbox lubrication system, is mainly used to collect and store lubricating oil that may be lost due to seal failure, splashing, or gravity dripping during gearbox operation. This prevents oil from dripping directly into the nacelle or external environment, avoids oil loss or contamination, ensures effective recycling of lubricating oil, and can be used in conjunction with an oil leak detection device to help determine the sealing status of the gearbox.

[0003] Oil leakage monitoring of the wind turbine gearbox oil collection tank is a crucial aspect of ensuring the safe operation of the equipment. By monitoring the oil leakage status in real time, early warnings of faults can be provided, reducing maintenance costs. Existing level monitoring devices can only detect changes in the oil level in the collection tank, but cannot accurately determine whether a drop in the oil level is due to normal consumption or leakage. When the oil level in the collection tank drops, it could be due to normal oil circulation within the gearbox carrying away some oil, or it could be due to a leak in the collection tank. Relying solely on level monitoring cannot distinguish between these two situations, making it impossible to promptly and accurately determine whether an oil leak has occurred, let alone monitor the leakage status in real time. In other words, relying on a single-dimensional oil level parameter is susceptible to interference and misjudgments, making accurate oil leakage detection impossible. Summary of the Invention

[0004] To address the technical problem in related technologies where relying solely on a single-dimensional oil level parameter is susceptible to interference and prone to misjudgment, thus failing to accurately determine oil leaks, this invention provides an oil collection device and oil leak monitoring system for a wind turbine gearbox. The specific technical solution adopted is as follows:

[0005] This invention proposes an oil leakage monitoring system for wind turbine gearboxes, comprising:

[0006] The acquisition module is used to acquire temperature data of the gearbox, oil level data of the oil collection tank, and pressure data of the gearbox within the current time and the preset time range before that time.

[0007] The temperature change analysis module is used to determine the heating time period based on the heating rate of temperature data at different sampling times; and to determine the first oil leakage risk indicator affected by temperature characteristics based on the distribution of the heating rate during the heating time period and the temperature changes within a preset time range.

[0008] The liquid level change analysis module is used to determine the liquid level drop period based on the drop rate of the liquid level data; to determine the temperature-liquid level change correlation coefficient based on the temperature data change during the heating period and the liquid level data change during the drop period; and to determine the second oil leakage risk indicator affected by the liquid level characteristics based on the time interval between the heating period and the drop period at the initial moment, as well as the temperature-liquid level change correlation coefficient.

[0009] The monitoring module is used to combine the first oil leakage risk indicator, the second oil leakage risk indicator, and the pressure data distribution inside the gearbox to determine the possibility of oil leakage, and to monitor oil leakage based on the possibility of oil leakage.

[0010] Furthermore, determining the heating time period based on the heating rate at different sampling times of the temperature data includes:

[0011] Calculate the temperature difference between the next sampling time and the previous sampling time in two adjacent sampling times, and use it as the temperature rise value;

[0012] The sampling time after the first time the temperature rise value within the preset time range exceeds the preset temperature rise threshold is taken as the initial time of the temperature rise period, and the current time is taken as the termination time, thus obtaining the temperature rise period.

[0013] Furthermore, the step of determining the first oil leakage risk indicator influenced by temperature characteristics based on the distribution of the heating rate during the heating period and the temperature changes within a preset time range includes:

[0014] The duration of consecutive temperature increases greater than 0 within the heating period is taken as the target period, and the ratio of the duration of the target period to that of the heating period is taken as the heating ratio.

[0015] Calculate the temperature range within a preset time range and normalize it to obtain the temperature difference coefficient;

[0016] The product of the heating ratio and the temperature difference coefficient is calculated and normalized to obtain the first oil leakage risk index affected by temperature characteristics.

[0017] Furthermore, determining the time period of liquid level descent based on the rate of descent of the liquid level data includes:

[0018] Calculate the difference between the liquid level data of the next sampling time and the previous sampling time in two adjacent sampling times, and use it as the decrease value;

[0019] The sampling time after the first time the decrease value within the preset time range exceeds the preset decrease threshold is taken as the initial time of the decrease period, and the current time is taken as the termination time, thus obtaining the decrease period.

[0020] Furthermore, determining the temperature-liquid level change correlation coefficient based on temperature data changes during the heating period and liquid level data changes during the cooling period includes:

[0021] Temperature data from different sampling times during the heating period are arranged into a temperature rise sequence according to time sequence; liquid level data from different sampling times during the cooling period are arranged into a liquid level fall sequence according to time sequence.

[0022] Calculate the Pearson correlation coefficient between the temperature rise sequence and the liquid level fall sequence, and normalize the negative of the Pearson correlation coefficient to obtain the temperature-liquid level change correlation coefficient.

[0023] Furthermore, the determination of the second oil leakage risk indicator influenced by the liquid level characteristics based on the time interval between the heating and cooling periods at the initial moment, and the temperature-liquid level change correlation coefficient, includes:

[0024] The negative of the time interval between the heating and cooling periods at the initial moment is normalized and used as a consistency coefficient.

[0025] The product of the consistency coefficient and the temperature-level change correlation coefficient is calculated to obtain the second oil leakage risk index.

[0026] Furthermore, the determination of the likelihood of an oil leak by combining the first oil leak risk indicator, the second oil leak risk indicator, and the pressure data distribution within the gearbox includes:

[0027] The pressure fluctuation index is determined based on the numerical distribution of the pressure data within the gearbox;

[0028] The product of the first oil leak risk indicator, the second oil leak risk indicator, and the pressure fluctuation indicator is normalized and used as the probability of oil leak.

[0029] Furthermore, based on the numerical distribution of pressure data within the gearbox, a pressure fluctuation index is determined, including:

[0030] Calculate the range and variance of the pressure data at all sampling times;

[0031] The product of the range and variance of the pressure data is used as the pressure fluctuation index.

[0032] Furthermore, the oil leak monitoring based on the probability of oil leakage includes:

[0033] When the probability of oil leakage exceeds a preset probability threshold, it indicates a potential risk of oil leakage, and an early warning is triggered.

[0034] On the other hand, an oil collection device for a wind turbine gearbox is also provided, the oil collection device including a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the oil leakage monitoring system as described in any of the foregoing.

[0035] The present invention has the following beneficial effects:

[0036] This invention achieves comprehensive analysis for oil leak monitoring by combining three dimensions: temperature data from the gearbox, oil level data from the oil collection tank, and pressure data from the gearbox. First, it analyzes a first oil leak risk index based on temperature rise characteristics. Then, by combining the correlation between liquid level changes and temperature changes, it further verifies the probability of oil leaks caused by temperature changes, determining a second oil leak risk index influenced by liquid level characteristics. Next, by combining pressure data distribution, the first oil leak risk index, and the second oil leak risk index, a more sensitive and reliable oil leak probability is obtained through multi-dimensional data analysis. Oil leak monitoring is then performed based on this probability. In summary, this invention can comprehensively judge based on multiple parameters, with each parameter mutually verifying the others, achieving accurate and reliable oil leak determination. It effectively eliminates misjudgments caused by interference from a single parameter, greatly improving the accuracy of oil leak monitoring. Attached Figure Description

[0037] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a structural diagram of an oil leakage monitoring system for a wind turbine gearbox provided in one embodiment of the present invention. Detailed Implementation

[0039] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an oil collection device and oil leakage monitoring system for a wind turbine gearbox according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0041] The following description, in conjunction with the accompanying drawings, details a specific solution for an oil leakage monitoring system for a wind turbine gearbox provided by the present invention.

[0042] Please see Figure 1 The diagram illustrates a structural diagram of an oil leakage monitoring system for a fan gearbox provided by an embodiment of the present invention, including: an acquisition module 101, a temperature change analysis module 102, a liquid level change analysis module 103, and a monitoring module 104.

[0043] The acquisition module 101 is used to acquire the temperature data of the gearbox, the oil level data in the oil collection tank, and the pressure data in the gearbox within the current time and the preset time range.

[0044] The wind turbine gearbox is a key transmission component in a wind turbine generator set. It is mainly used to transmit the power of the low-speed rotation of the wind turbine to the gearbox speed-increasing device, thereby achieving the high-speed rotation required for power generation. The oil collection tank, as an auxiliary device of the wind turbine gearbox lubrication system, is mainly used to collect and store lubricating oil that may be lost due to seal failure, splashing, or gravity dripping during gearbox operation. This prevents oil from dripping directly into the nacelle or external environment, avoids oil loss or contamination, ensures effective recycling of lubricating oil, and can be used in conjunction with an oil leak detection device to help determine the sealing status of the gearbox.

[0045] Oil leakage monitoring of the wind turbine gearbox oil collection tank is a crucial aspect of ensuring the safe operation of the equipment. By monitoring the oil leakage status in real time, early warnings of faults can be provided, reducing maintenance costs. Existing level monitoring devices can only detect changes in the oil level in the collection tank, but cannot accurately determine whether a drop in the oil level is due to normal consumption or leakage. When the oil level in the collection tank drops, it could be due to normal oil circulation within the gearbox carrying away some oil, or it could be due to a leak in the collection tank. Relying solely on level monitoring cannot distinguish between these two situations, making it impossible to promptly and accurately determine whether an oil leak has occurred, let alone monitor the leakage status in real time.

[0046] Therefore, this application achieves accurate oil leakage monitoring by combining multi-dimensional data analysis. This analysis mainly includes three dimensions: temperature data, oil level data in the oil collection tank, and pressure data within the gearbox.

[0047] Temperature data acquisition in the gearbox: High-precision temperature sensors are installed at key friction points in the wind turbine gearbox, such as near the meshing point of the gears and the surface of the bearing housing. These locations are most prone to temperature rise due to increased friction when there is insufficient oil lubrication. Thermocouples can be used as temperature sensors with a measurement accuracy of ±0.5℃.

[0048] Pressure data acquisition inside the gearbox: Pressure changes inside the gearbox can also reflect the circulation and flow of oil in the system, so the pressure changes inside the gearbox are selected to represent its operating conditions. According to the type of gearbox and the possible pressure range, select a high-precision pressure sensor with an appropriate measurement range and install it at a location that can reflect the main pressure of the oil during circulation, such as the oil pump outlet or main oil passage. The installation location should avoid high-speed rotating parts inside the gearbox, areas prone to air bubbles, and locations that may be subject to mechanical impact, so as not to affect the normal operation and measurement accuracy of the sensor.

[0049] Oil level data acquisition in the oil collection tank: Install a high-resolution level sensor at a suitable location in the oil collection tank to ensure accurate detection of minute changes in the oil level. The resolution can be set to 1mm. To avoid interference from oil fluctuations in the oil collection tank on the level measurement, a level sensor with a damping device, such as a hydrostatic level sensor, can be used. This sensor calculates the liquid height by measuring the liquid pressure, which can effectively reduce the error in level measurement caused by oil fluctuations.

[0050] In this embodiment of the invention, data can be collected every 30 seconds as a sampling moment, with a preset time range of 1 hour. That is, the temperature data, liquid level data and pressure data of all sampling moments in the hour before the current moment are used as the data information for oil leakage risk analysis at the current moment.

[0051] The temperature change analysis module 102 is used to determine the heating time period based on the heating rate of temperature data at different sampling times; and to determine the first oil leakage risk indicator affected by temperature characteristics based on the distribution of the heating rate during the heating time period and the temperature changes within a preset time range.

[0052] During the operation of the wind turbine gearbox, the temperature changes of key parts can effectively reflect the operating status of the equipment. Under normal circumstances, the temperature will be stable within a certain range. However, when oil leakage leads to insufficient lubrication, the friction of these key parts will increase, thereby generating more heat and causing their temperature to rise. Therefore, it is necessary to analyze the temperature changes during the operation of the wind turbine gearbox.

[0053] Furthermore, in some embodiments of the present invention, determining the heating time period based on the heating rate of temperature data at different sampling times includes: calculating the temperature data difference between the next sampling time and the previous sampling time under two adjacent sampling times as the heating value; taking the next sampling time when the heating value first exceeds the preset heating threshold within the preset time range as the initial time of the heating time period, and taking the current time as the termination time to obtain the heating time period.

[0054] Here, the temperature rise value is the first-order difference of the temperature data. A temperature rise value greater than 0 indicates a temperature increase, while a temperature rise value less than 0 indicates a temperature decrease. Since the temperature changes during machine operation, this change is normally in a dynamic thermal equilibrium. Therefore, in this embodiment of the invention, to avoid the influence of heat, a preset temperature rise threshold of 10 degrees Celsius can be set. That is, the sampling moment after the temperature rise value first exceeds 10 degrees Celsius within a preset time range is taken as the initial moment of the temperature rise period, and the current moment is taken as the termination moment, thus obtaining the temperature rise period.

[0055] When the difference between adjacent temperatures is greater than 10℃, it is considered that the temperature has changed significantly at that sampling moment, and the temperature stability has been broken. This moment is recorded as the initial moment. The time period of temperature rise is likely due to insufficient lubrication caused by oil leakage, which will continuously increase the friction between key parts, leading to the time period of temperature rise.

[0056] Based on the distribution of the heating rate during the heating period and the temperature changes within a preset time range, a first oil leakage risk index influenced by temperature characteristics is determined, including: taking the duration of consecutive heating values ​​greater than 0 during the heating period as the target time period; taking the ratio of the duration of the target time period to that of the heating period as the heating ratio; calculating the temperature range within the preset time range and normalizing it to obtain the temperature difference coefficient; and calculating the product of the heating ratio and the temperature difference coefficient and normalizing it to obtain the first oil leakage risk index influenced by temperature characteristics.

[0057] In this embodiment of the invention, if the temperature rise value is continuously greater than 0, it indicates that the corresponding temperature is continuously rising and will remain at a high temperature without decreasing after rising, which is more likely caused by insufficient lubrication due to friction. Therefore, the duration of the continuous temperature rise value greater than 0 within the heating period is taken as the target time period. There can be multiple target time periods. The duration of all target time periods is compared with the duration of the heating period to obtain the temperature rise ratio. The higher the temperature rise ratio, the more obvious the temperature rise, and the greater the probability that oil leakage causes friction and temperature rise of the component; while the lower the temperature rise ratio, the more cooling time there is, and the closer to the dynamic temperature equilibrium stage.

[0058] Here, the temperature range represents the difference between the maximum and minimum temperature values ​​within a preset time range. The larger this value, the greater the temperature difference, and the more likely it is to be a high-temperature effect caused by oil leakage and heating. Therefore, in this embodiment of the invention, the product of the heating ratio and the temperature difference coefficient is directly calculated and normalized to obtain the first oil leakage risk index affected by temperature characteristics.

[0059] In one embodiment of the present invention, the normalization process can be specifically, for example, maximum and minimum value normalization. Furthermore, the normalization in subsequent steps can all adopt maximum and minimum value normalization. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of the numerical values, which will not be elaborated further.

[0060] The liquid level change analysis module 103 is used to determine the liquid level drop period based on the drop rate of the liquid level data; to determine the temperature-liquid level change correlation coefficient based on the temperature data change during the heating period and the liquid level data change during the drop period; and to determine the second oil leakage risk indicator affected by the liquid level characteristics based on the time interval between the heating period and the drop period at the initial moment, as well as the temperature-liquid level change correlation coefficient.

[0061] The above steps yielded the first oil leakage risk indicator based on the temperature change characteristics of the current moment and the period before it. However, during the operation of the wind turbine gearbox, the abnormal temperature rise is not necessarily caused entirely by oil leakage. Other factors, such as sudden changes in wind turbine load or cooling system failure, may also cause similar temperature changes. Therefore, it is necessary to further determine whether the abnormal temperature is caused by insufficient lubrication due to leakage based on the oil level drop during this period.

[0062] Under normal circumstances, the rate of oil level drop due to normal consumption is relatively stable and slow. However, when an oil leak occurs, the rate of drop accelerates significantly, exceeding the normal consumption rate. Therefore, it is necessary to first analyze the rate of drop.

[0063] Furthermore, in some embodiments of the present invention, determining the time period of liquid level decline based on the rate of decline of liquid level data includes: calculating the difference between the liquid level data of the next sampling time and the previous sampling time in two adjacent sampling times as the decline value; taking the next sampling time in which the decline value first exceeds a preset decline threshold within a preset time range as the initial time of the time period of decline, and taking the current time as the termination time to obtain the time period of decline.

[0064] The drop value represents the amount of liquid level decrease between two adjacent sampling times. Since the liquid level is also in a dynamic state, such as the normal oil circulation inside the gearbox causing some oil to be carried away, in this embodiment of the invention, the preset drop threshold is set to 5mm to avoid the sensitive effect caused by slight oil changes. The sampling time after the drop value first exceeds 5mm within the preset time range is taken as the initial time of the drop period, and the current time is taken as the termination time to obtain the drop period.

[0065] Based on the temperature data changes during the heating period and the liquid level data changes during the falling period, the temperature-liquid level change correlation coefficient is determined, including: forming a temperature rise sequence from the temperature data at different sampling times during the heating period; forming a liquid level fall sequence from the liquid level data at different sampling times during the falling period; calculating the Pearson correlation coefficient between the temperature rise sequence and the liquid level fall sequence; and normalizing the negative of the Pearson correlation coefficient as the temperature-liquid level change correlation coefficient.

[0066] It is understandable that when there is a corresponding correlation between temperature rise and oil level drop, it indicates that an oil leak has occurred, leading to a temperature rise. The higher the temperature rise and the lower the oil level, the more obvious the friction effect and the greater the possibility of an oil leak. Therefore, in this embodiment of the invention, the oil leak phenomenon is determined by analyzing the correlation between the temperature rise sequence and the oil level drop sequence.

[0067] The correlation can be specifically calculated using the Pearson correlation coefficient, which ranges from -1 to 1. The closer the Pearson correlation coefficient is to -1, the more negatively correlated the corresponding temperature and liquid level values ​​are, and the more consistent it is with the systematic characteristics caused by oil leakage. Therefore, the negative value of the Pearson correlation coefficient is normalized as the temperature-liquid level change correlation coefficient. That is, the larger the temperature-liquid level change correlation coefficient is, the more correlated the liquid level drop and temperature rise are, and the more likely this correlation is to be caused by oil leakage.

[0068] Furthermore, in some embodiments of the present invention, a second oil leakage risk index influenced by liquid level characteristics is determined based on the time interval between the heating period and the falling period at the initial moment, and the temperature-liquid level change correlation coefficient. This includes: normalizing the negative of the time interval between the heating period and the falling period at the initial moment as a consistency coefficient; and calculating the product of the consistency coefficient and the temperature-liquid level change correlation coefficient to obtain the second oil leakage risk index.

[0069] The time interval characterizes the time characteristics between the temperature rise and the liquid level drop. Since the speed of operation inside the fan gearbox is relatively fast, a large amount of friction will be generated when the liquid level drops, which will lead to the temperature rise. Therefore, the smaller the time interval, the faster the process from the drop in oil level to the rise in temperature. It is more likely that the oil level drop rate is accelerated due to oil leakage. This is because if other factors cause the temperature to rise, such as cooling system failure or sudden change in fan load, there is usually no such close time proximity between them and the accelerated oil consumption.

[0070] For example, a sudden change in fan load can cause a temperature rise. This is often because the load change is instantaneous and causes a rapid temperature increase, while the oil consumption rate may not have changed at this time. Similarly, a cooling system malfunction will first affect heat dissipation, leading to a temperature rise, and it is generally not directly related to an increase in the oil consumption rate.

[0071] In this embodiment of the invention, the smaller the time interval, the more obvious the correlation between temperature rise and liquid level drop. Therefore, the negative of the time interval is normalized by a minimum-maximum value to obtain a consistency coefficient. The larger the consistency coefficient, the stronger the correlation between temperature rise and liquid level drop, indicating that insufficient lubrication may occur due to a large reduction in oil in a short period of time, leading to rapid temperature rise, which is more likely to be caused by oil leakage.

[0072] In summary, the product of the consistency coefficient and the temperature-level change correlation coefficient is used to obtain the second oil leakage risk index.

[0073] The monitoring module 104 is used to combine the first oil leakage risk indicator, the second oil leakage risk indicator, and the pressure data distribution inside the gearbox to determine the possibility of oil leakage, and to monitor oil leakage based on the possibility of oil leakage.

[0074] Among them, the first oil leakage risk index represents the oil leakage risk characteristics of temperature changes, and the second oil leakage risk index represents the correlation between oil level drop and temperature changes, thus demonstrating the oil leakage risk characteristics. The pressure inside the gearbox also has a significant impact on the oil level drop. Under higher pressure, oil can leak through tiny gaps or weak seals, and oil evaporation can also be promoted. Under the dual effect, oil consumption is accelerated, which in turn affects the rate at which the oil level drops in the oil tank. Therefore, it is necessary to combine the first and second oil leakage risk indices with pressure data for specific analysis.

[0075] Combining the first oil leakage risk indicator, the second oil leakage risk indicator, and the pressure data distribution within the gearbox, the probability of oil leakage is determined, including: determining the pressure fluctuation indicator based on the numerical distribution of the pressure data within the gearbox; and normalizing the product of the first oil leakage risk indicator, the second oil leakage risk indicator, and the pressure fluctuation indicator to obtain the probability of oil leakage.

[0076] The pressure fluctuation index is determined based on the numerical distribution of pressure data within the gearbox, including: calculating the range and variance of pressure data at all sampling times; and using the product of the range and variance of the pressure data as the pressure fluctuation index.

[0077] The larger the range of the pressure data, the more significant the pressure change. The larger the variance of the pressure data, the greater the volatility of the pressure change. Therefore, in this embodiment of the invention, the product of the range and variance of the pressure data is calculated as a pressure fluctuation index. The larger the pressure fluctuation index, the more unstable the pressure in the gearbox, and the more likely it is that oil leakage is causing liquid level changes, thus generating pressure fluctuation characteristics. Therefore, in this embodiment of the invention, the product of the first oil leakage risk index, the second oil leakage risk index, and the pressure fluctuation index is calculated and normalized to obtain the probability of oil leakage.

[0078] The numerical acquisition of the probability of oil leakage combines changes in temperature rise, changes in liquid level drop, the correlation characteristics between temperature and liquid level, and pressure fluctuation characteristics. This makes the numerical value of the probability of oil leakage more sensitive and reliable, enabling timely and accurate oil leakage analysis.

[0079] In this embodiment of the invention, when the probability of oil leakage is greater than a preset probability threshold, it indicates a potential risk of oil leakage, and an early warning is activated. The preset probability threshold is a threshold value for the probability of oil leakage. In this embodiment, the preset probability threshold can be, for example, 0.7, meaning that when the probability of oil leakage is greater than 0.7, it indicates a potential risk of oil leakage, and an early warning is activated.

[0080] In other embodiments of the present invention, the probability of oil leakage can be classified into different levels to achieve different handling methods: if the probability of oil leakage is in the range of [0, 0.3), it indicates that the probability of oil leakage is extremely low and continuous monitoring is required. At this time, prevention and monitoring are the main focus to avoid downtime losses due to misjudgment; if the probability of oil leakage is in the range of [0.3, 0.7), it indicates that there is a potential risk of oil leakage and early warning is required. Cross-validation with other operating data is needed to identify potential hazards in advance; if the probability of oil leakage is in the range of [0.7, 1], it indicates that oil leakage is highly suspected and emergency handling is required to quickly locate the oil leakage point and intervene.

[0081] This invention achieves comprehensive analysis of oil leak monitoring by combining three dimensions: temperature data from the gearbox, oil level data from the oil collection tank, and pressure data from the gearbox. First, a first oil leak risk index analysis is performed based on temperature rise characteristics. Then, by combining the correlation between liquid level changes and temperature changes, the probability of oil leaks due to temperature changes is further verified, determining a second oil leak risk index influenced by liquid level characteristics. Subsequently, by combining pressure data distribution, the first oil leak risk index, and the second oil leak risk index, a more sensitive and reliable oil leak probability is obtained through multi-dimensional data analysis. Oil leak monitoring is then performed based on this probability. In summary, this invention comprehensively judges oil leaks using multiple parameters, with each parameter mutually verifying the others, achieving accurate and reliable oil leak detection. This effectively eliminates misjudgments caused by interference from a single parameter, significantly improving the accuracy of oil leak monitoring.

[0082] On the other hand, the present invention also provides an oil collection device for a wind turbine gearbox, the oil collection device including a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, it implements the described steps of any of the foregoing descriptions of an oil leakage monitoring system for a wind turbine gearbox.

[0083] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An oil leakage monitoring system for a wind turbine gearbox, characterized in that, include: The acquisition module is used to acquire temperature data of the gearbox, oil level data of the oil collection tank, and pressure data of the gearbox within the current time and the preset time range before that time. The temperature change analysis module is used to determine the heating time period based on the heating rate of temperature data at different sampling times; and to determine the first oil leakage risk indicator affected by temperature characteristics based on the distribution of the heating rate during the heating time period and the temperature changes within a preset time range. The liquid level change analysis module is used to determine the liquid level drop period based on the drop rate of the liquid level data; to determine the temperature-liquid level change correlation coefficient based on the temperature data change during the heating period and the liquid level data change during the drop period; and to determine the second oil leakage risk indicator affected by the liquid level characteristics based on the time interval between the heating period and the drop period at the initial moment, as well as the temperature-liquid level change correlation coefficient. The monitoring module is used to combine the first oil leakage risk indicator, the second oil leakage risk indicator, and the pressure data distribution inside the gearbox to determine the possibility of oil leakage, and to monitor oil leakage based on the possibility of oil leakage. Methods for determining the temperature rise period include: Calculate the temperature difference between the next sampling time and the previous sampling time in two adjacent sampling times, and use it as the temperature rise value; The sampling time after the first time the temperature rise value within the preset time range exceeds the preset temperature rise threshold is taken as the initial time of the temperature rise period, and the current time is taken as the termination time, thus obtaining the temperature rise period. Methods for determining the primary oil leak risk indicator influenced by temperature characteristics include: The duration of consecutive temperature increases greater than 0 within the heating period is taken as the target period, and the ratio of the duration of the target period to that of the heating period is taken as the heating ratio. Calculate the temperature range within a preset time range and normalize it to obtain the temperature difference coefficient; Calculate the product of the heating ratio and the temperature difference coefficient, and normalize it to obtain the first oil leakage risk index affected by temperature characteristics; Methods for determining the time period of liquid level decline include: Calculate the difference between the liquid level data of the next sampling time and the previous sampling time in two adjacent sampling times, and use it as the decrease value; The sampling time after the first time the decrease value within the preset time range exceeds the preset decrease threshold is taken as the initial time of the decrease period, and the current time is taken as the termination time, thus obtaining the decrease period. Methods for determining the correlation coefficient between temperature and liquid level changes include: Temperature data from different sampling times during the heating period are arranged into a temperature rise sequence according to time sequence; liquid level data from different sampling times during the cooling period are arranged into a liquid level fall sequence according to time sequence. Calculate the Pearson correlation coefficient between the temperature rise sequence and the liquid level fall sequence, and normalize the negative of the Pearson correlation coefficient to obtain the temperature-liquid level change correlation coefficient. Methods for determining the second oil leakage risk indicator influenced by liquid level characteristics include: The negative of the time interval between the heating and cooling periods at the initial moment is normalized and used as a consistency coefficient. The product of the consistency coefficient and the temperature-level change correlation coefficient is calculated to obtain the second oil leakage risk index. Methods for determining the likelihood of an oil leak include: The pressure fluctuation index is determined based on the numerical distribution of the pressure data within the gearbox; The product of the first oil leak risk indicator, the second oil leak risk indicator, and the pressure fluctuation indicator is normalized and used as the probability of oil leak.

2. The oil leakage monitoring system for a wind turbine gearbox as described in claim 1, characterized in that, Based on the numerical distribution of pressure data within the gearbox, pressure fluctuation indicators are determined, including: Calculate the range and variance of the pressure data at all sampling times; The product of the range and variance of the pressure data is used as the pressure fluctuation index.

3. The oil leakage monitoring system for a wind turbine gearbox as described in claim 1, characterized in that, The oil leak monitoring based on the probability of oil leakage includes: When the probability of oil leakage exceeds a preset probability threshold, it indicates a potential risk of oil leakage, and an early warning is triggered.

4. An oil collection device for a wind turbine gearbox, the oil collection device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the oil leak monitoring system as described in any one of claims 1 to 3.

Images