Bearing fault early warning method and device, medium, electronic equipment and program product

Abstract

The invention relates to a bearing fault early warning method and device, a medium, electronic equipment and a program product, and relates to the technical field of wind power. The method comprises the following steps: determining the working condition of a bearing according to the operating parameters and state of the doubly-fed wind generating set; based on the thermodynamic model corresponding to the working condition, fitting the bearing temperature time sequence corresponding to the working condition to obtain a temperature fitting function corresponding to the working condition; determining a temperature influence factor according to the coefficient of the temperature fitting function; and early warning the fault state of the bearing according to the temperature influence factor and the deviation of the historical value thereof. According to the method, the specific reason of the abnormal bearing temperature can be determined, and the accuracy and timeliness of fault early warning are improved.

Description

Technical Field

[0001] The present application relates to the field of wind power technology, and in particular, to a bearing fault early warning method, device, medium, electronic equipment and program product. Background Art

[0002] With the rapid development of wind power generation industry, the problem of bearing damage in wind turbines has become increasingly prominent. Bearings are subjected to alternating loads caused by impellers for a long time, and the balls and raceways are prone to wear and plastic deformation; and lack of effective lubrication or poor alignment during high-speed operation will also accelerate bearing wear and fatigue.

[0003] In the related art, when the bearing temperature exceeds the predetermined threshold, the shutdown is triggered. This single temperature monitoring has a lag. The cause of the temperature rise cannot be analyzed in time and can only be checked during maintenance. When the temperature rises to the alarm value, the staff is limited and it is difficult to take timely measures to reduce the damage. In extreme cases, the bearing may lock or the internal high temperature may catch fire. If the shutdown is not carried out until the temperature reaches the fault value, the consequences will be very serious. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present application provides a bearing fault early warning method, device, medium, electronic equipment and program product.

[0005] According to a first aspect of the present application, a bearing fault early warning method is provided, comprising: Determine the working condition of the bearing according to the operating parameters and status of the doubly-fed wind turbine generator set; Based on the thermodynamic model corresponding to the working condition, the bearing temperature time series corresponding to the working condition is fitted to obtain a temperature fitting function corresponding to the working condition; Determining a temperature influence factor according to a coefficient of the temperature fitting function; Based on the deviation of the temperature influencing factor and its historical value, the fault status of the bearing is warned.

[0006] Optionally, determining the working condition of the bearing according to the operating parameters and state of the doubly-fed wind turbine generator set includes: When the generator speed is zero, determining that the bearing is in a stationary state; When the generator speed continues to increase and the generator speed is less than a first speed, determining that the bearing is in a speed increasing state; When the generator speed is greater than or equal to the first speed and less than the second speed, and the generator is in a power generation state, it is determined that the bearing is in a grid-connected state and the first speed is less than the second speed; When the heat dissipation device is activated, determining that the bearing is in a thermal equilibrium state; When the active power of the generator is zero and the rotation speed of the generator continues to decrease until it reaches zero, it is determined that the bearing is in the running-to-stop state.

[0007] Optionally, fitting the bearing temperature time series corresponding to the working condition based on the thermodynamic model corresponding to the working condition to obtain the temperature fitting function corresponding to the working condition includes: When the bearing is in a stationary state, fitting a first temperature sequence corresponding to the stationary state based on a first thermodynamic model to obtain a first fitting function; When the bearing is in a speed increasing state, fitting a second temperature sequence corresponding to the speed increasing state based on a second thermodynamic model to obtain a second fitting function; When the bearing is in a grid-connected state, fitting a third temperature sequence corresponding to the grid-connected state based on a third thermodynamic model to obtain a third fitting function; When the bearing is in a thermal equilibrium state, fitting a fourth temperature sequence corresponding to the thermal equilibrium state based on a fourth thermodynamic model to determine a fourth fitting function; When the bearing is in the running-to-stop state, a fifth temperature sequence corresponding to the running-to-stop state is fitted based on a fifth thermodynamic model to determine a fifth fitting function.

[0008] Optionally, determining the temperature influence factor according to the coefficient of the temperature fitting function includes: Determine any one of the first influencing factor, the second influencing factor, the third influencing factor, the fourth influencing factor and the fifth influencing factor based on any multiple of the coefficients of the first fitting function, the coefficients of the second fitting function, the coefficients of the third fitting function, the coefficients of the fourth fitting function and the coefficients of the fifth fitting function.

[0009] The first influencing factor characterizes the influence of the cabin ambient temperature on the bearing temperature, the second influencing factor characterizes the influence of the rolling relative friction inside the bearing on the bearing temperature, the third influencing factor characterizes the influence of the conductive heat dissipation of the bearing on the bearing temperature, the fourth influencing factor characterizes the influence of the generator winding heating on the bearing temperature, and the fifth influencing factor characterizes the influence of the convective heat dissipation of the heat dissipation device on the bearing temperature.

[0010] Optionally, the warning of a bearing fault state according to the deviation of the temperature influence factor and its historical value includes: When the second influencing factor is greater than a second preset multiple of its historical value, an early warning of the relative rolling friction state inside the bearing is provided; When the third impact factor is less than a third preset multiple of its historical value, an early warning of the lubrication state of the bearing is issued; When the fourth impact factor is greater than a fourth preset multiple of its historical value, an early warning is given on the temperature state of the generator winding; When the fifth impact factor is smaller than the fifth preset multiple of its historical value, an early warning is issued on the operating state of the heat dissipation device.

[0011] Optionally, the method further comprises: Determine a sixth fitting function according to the thermodynamic model of each of the working conditions and the influencing factors, wherein the sixth fitting function is used to predict the bearing temperature under any of the working conditions; Determining a target operating condition corresponding to the sixth temperature sequence according to the operating parameters and state of the doubly-fed wind turbine generator set corresponding to the sixth temperature sequence; The temperature influence factor in the sixth fitting function that is not related to the target operating condition is set to zero to obtain a target fitting function; Based on the target fitting function, determining a fitting temperature corresponding to an end temperature of the sixth temperature sequence according to a starting temperature of the sixth temperature sequence and a duration corresponding to the sixth temperature sequence; When the termination temperature is greater than a first preset multiple of the fitting temperature, a bearing fault state is warned based on an estimated time period between the termination temperature rising to a preset fault temperature and the bearing vibration acceleration.

[0012] According to a second aspect of the present application, a bearing fault early warning device is provided, comprising: A working condition determination module, used to determine the working condition of the bearing according to the operating parameters and status of the doubly-fed wind turbine generator set; A temperature fitting module, used to fit the bearing temperature time series corresponding to the working condition based on the thermodynamic model corresponding to the working condition, and obtain a temperature fitting function corresponding to the working condition; An influence factor determination module, used to determine the temperature influence factor according to the coefficient of the temperature fitting function; The first early warning module is used to warn of a bearing failure state based on a deviation of a temperature influence factor from its historical value.

[0013] According to the third aspect of the present application, a non-temporary computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods provided in the first aspect of the present application are implemented.

[0014] According to a fourth aspect of the present application, there is provided an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods provided in the first aspect of the present application.

[0015] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present application.

[0016] The above technical solution can more accurately predict the temperature change trend by determining the working condition of the bearing and establishing the corresponding temperature prediction model. At the same time, by analyzing the deviation of each influencing factor in the temperature fitting function, the specific cause of the increase in bearing temperature can be accurately diagnosed. This timely and accurate fault warning enables the staff to take necessary maintenance measures before the bearing is seriously damaged, effectively reducing the risk of bearing damage and improving the reliability and safety of the wind turbine.

[0017] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present application but do not constitute a limitation to the present application. In the accompanying drawings: Figure 1 is a flow chart of a bearing fault early warning method according to an exemplary embodiment; Figure 2 is a bearing temperature prediction simulation diagram shown according to an exemplary embodiment; Figure 3 is a block diagram of a bearing fault early warning device according to an exemplary embodiment; Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0019] The specific implementation of the present application is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present application, and is not used to limit the present application.

[0020] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0021] Herein, the terms "first", "second", etc. are only used to distinguish one element from another element, and do not require or imply any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa.

[0022] Figure 1 is a flow chart of a bearing fault early warning method according to an exemplary embodiment. Figure 1 ,This method can be applied to the bearing fault warning of wind ,generator sets, especially the bearing fault warning of generator sets.

[0023] The method comprises the following steps: In step 110, the working condition of the bearing is determined according to the operating parameters and state of the doubly-fed wind turbine generator set; In step 120, based on the thermodynamic model corresponding to the working condition, the bearing temperature time series corresponding to the working condition is fitted to obtain a temperature fitting function corresponding to the working condition; In step 130, a temperature influence factor is determined according to the coefficient of the temperature fitting function; In step 140, a fault state of the bearing is warned based on the temperature influence factor and the deviation of its historical value.

[0024] Here, the operating parameters and status of the doubly-fed wind turbine generator set refer to the parameters that can reflect the operating status of the wind turbine generator set, which may include generator speed, active power, cabin temperature, wind speed, etc. The working condition of the bearing refers to the operating state of the bearing, including static state, speed increase state, grid-connected state, thermal balance state, running-to-shutdown state, etc.

[0025] The thermodynamic model corresponding to the working condition refers to the thermodynamic model of the bearing temperature change established for different working conditions, including factors such as cabin temperature, bearing friction, conduction heat dissipation, etc. The bearing temperature time series corresponding to the working condition refers to the data series of the bearing temperature change over time under a certain working condition.

[0026] The temperature fitting function corresponding to the working condition refers to the mathematical function that is fitted based on the bearing temperature time series and describes the temperature change law under the working condition. The coefficients of the temperature fitting function refer to the coefficients of each parameter in the temperature fitting function. The temperature influence factor refers to the influence of various factors that cause the bearing temperature change on the bearing temperature, such as cabin temperature, relative rolling friction inside the bearing, heat dissipation, etc. The historical value of the temperature influence factor refers to the actual calculated value of each temperature influence factor in a period of time before this data processing.

[0027] The above technical solution determines the current working state of the bearing, including stationary, speed increase, grid connection, thermal balance, operation to shutdown, etc., by real-time monitoring of the speed, power, cabin temperature, wind speed, wind turbine main control program status flag and other parameters of the generator. For different working conditions, the corresponding thermodynamic model is established in advance, which includes various influencing factors such as cabin temperature, bearing friction, and heat dissipation. The actual monitored bearing temperature time series is substituted into the temperature prediction model of the corresponding working condition for fitting, and the temperature fitting function under the working condition is obtained. By analyzing the various parameter coefficients in the temperature fitting function, the current main factors affecting the bearing temperature, namely the temperature influence factor, can be determined. Compare the current temperature influence factor with its historical value. If abnormal deviations are found in some temperature influence factors, possible bearing failures can be predicted, such as poor lubrication and poor heat dissipation.

[0028] The above technical solution can more accurately predict the temperature change trend by determining the working condition of the bearing and establishing the corresponding temperature prediction model. At the same time, by analyzing the deviation of each influencing factor in the temperature fitting function, the specific cause of the temperature rise can be accurately diagnosed. This timely and accurate fault warning enables the staff to take necessary maintenance measures before the bearing is seriously damaged, effectively reducing the risk of bearing damage and improving the reliability and safety of the wind turbine.

[0029] In one embodiment, step 110 may include: when the generator speed is zero, determining that the bearing is in a stationary state; when the generator speed continues to increase and the generator speed is less than a first speed, determining that the bearing is in a speed increasing state; when the generator speed is greater than or equal to the first speed and the generator speed is less than a second speed, and the generator is in a power generation state, determining that the bearing is in a grid-connected state and the first speed is less than the second speed; when the heat dissipation device is started, determining that the bearing is in a thermal equilibrium state; when the active power of the generator is zero and the generator speed continues to decrease to zero, determining that the bearing is in a running-to-shutdown state.

[0030] Here, the generator speed refers to the speed of the generator rotor of the wind turbine. In this embodiment, the first speed can be set to about 1000 rad / min (radians per minute), which is the approximate speed of the wind turbine when it is connected to the grid. The second speed can be set to about 1200 rad / min, which is the upper limit speed of the wind turbine when it is connected to the grid. The grid-connected state refers to the state in which the generator speed of the wind turbine reaches the grid-connected requirement (such as 1000-1200 rad / min) and is connected to the grid through the converter. The heat dissipation device refers to a device used by a doubly-fed wind turbine to dissipate heat from the generator winding, usually a heat dissipation fan on the generator. The thermal equilibrium state refers to the state in which the temperature of the generator winding rises to a certain level, and after the heat dissipation device is started, the bearing temperature reaches a relatively stable state. The run-to-shutdown state refers to the state in which the generator changes from the normal operating state to the shutdown state, at which time the power generation power is zero and the speed continues to drop to zero.

[0031] The above technical solution can accurately identify the working condition of the bearing, laying the foundation for subsequent temperature prediction and fault diagnosis. It can also improve the accuracy of temperature prediction and avoid the problem that a single model cannot adapt to different working conditions.

[0032] In one embodiment, step 120 may include: when the bearing is in a stationary state, fitting a first temperature sequence corresponding to the stationary state based on a first thermodynamic model to obtain a first fitting function; when the bearing is in a speed increasing state, fitting a second temperature sequence corresponding to the speed increasing state based on a second thermodynamic model to obtain a second fitting function; when the bearing is in a grid-connected state, fitting a third temperature sequence corresponding to the grid-connected state based on a third thermodynamic model to obtain a third fitting function; when the bearing is in a thermal equilibrium state, fitting a fourth temperature sequence corresponding to the thermal equilibrium state based on a fourth thermodynamic model to determine a fourth fitting function; when the bearing is in a run-to-shutdown state, fitting a fifth temperature sequence corresponding to the run-to-shutdown state based on a fifth thermodynamic model to determine a fifth fitting function.

[0033] It should be understood that under the same working condition, the temperature variation law of the bearing is determined by the thermodynamic model corresponding to the working condition. The thermodynamic model corresponding to the working condition can be obtained based on the thermal analysis of the temperature variation under a working condition.

[0034] Here, the first thermodynamic model is a heat conduction model between the bearing temperature and the cabin ambient temperature. The first temperature sequence refers to the data sequence in the bearing temperature time series corresponding to the bearing being in a stationary state. The first fitting function is to substitute the first temperature sequence into the first thermodynamic model for fitting, and obtain a mathematical function that describes the bearing temperature change in a stationary state.

[0035] It should be understood that, in a stationary state, the bearing temperature is mainly affected by the cabin ambient temperature. Therefore, the first thermodynamic model can be as shown in equation (1). Where t is the time relative to the start time of the first temperature sequence, is the theoretical temperature of the bearing affected by ambient heat conduction at time t in the first temperature sequence, and H is the cabin ambient temperature. Since the temperature change is continuous, the cabin ambient temperature can be assumed to be constant in a short period of time. Therefore, the first temperature sequence can be fitted as a constant function. The coefficient of the constant function is the approximate value of the cabin ambient temperature.

[0036] (1) Based on the first thermodynamic model, the first temperature sequence is fitted to obtain the first fitting function as shown in formula (2). Where t is the time relative to the start time of the first temperature sequence, is the fitting temperature of the bearing at time t in the first temperature sequence, It can be the arithmetic mean of all temperatures in the first temperature series.

[0037] (2) The second temperature sequence refers to the data sequence in the bearing temperature time series corresponding to the bearing in the state of increasing speed. The second fitting function is to substitute the second temperature sequence into the second thermodynamic model for fitting to obtain a mathematical function describing the bearing temperature change in the state of increasing speed.

[0038] It should be understood that, in the state of increasing speed, the factors affecting the bearing temperature are mainly the cabin ambient temperature, the relative rolling friction inside the bearing, and the conductive heat dissipation of the bearing. Therefore, the second thermodynamic model can include a friction heat conduction model and a conductive heat dissipation model. The friction heat conduction model is a heat conduction model for heat generation by relative rolling friction inside the bearing. The conductive heat dissipation model is a heat conduction model that describes the heat dissipation process of the bearing itself being conducted to the environment.

[0039] The friction heat conduction model can be derived as follows.

[0040] According to the frictional heat generation of rolling bearings as shown in equation (3) and the relationship between heat and temperature as shown in equation (4), the friction heat conduction model is obtained as shown in equation (5). Among them, Q is the heat generated by the relative rolling friction inside the bearing itself, t is the time relative to the starting moment of the second temperature sequence, F is the friction between the bearing raceway and the ball, V is the bearing speed, C is the bearing specific heat capacity, M is the bearing mass, is the theoretical temperature of the bearing at time t in the second temperature sequence affected by the rolling relative friction heat conduction inside the bearing, is the starting temperature of the second temperature sequence.

[0041] (3) (4) (5) It should be understood that since the bearing structure and operating environment remain basically unchanged, the friction between the bearing raceway and the ball can be assumed to be constant, unless there is a problem with the bearing lubrication or the friction changes when the contact environment between the bearing ball and the raceway is damaged. Since the generator speed increases very quickly, the duration of this state is short, and the generator speed can be assumed to be constant. After the generator speed reaches the first speed, the speed fluctuates between the first speed and the second speed, and the effect of the speed change on the bearing temperature can be ignored. The bearing specific heat capacity and the bearing mass are also constants. Based on the observation of the actual historical data scatter plot, the second temperature series can be fitted as a linear function.

[0042] Based on the friction heat conduction model, the function fitted according to the second temperature sequence can be as shown in equation (6). Where t is the time relative to the start time of the second temperature sequence, is the fitting temperature of the bearing at time t in the second temperature sequence affected by the rolling relative friction heat conduction inside the bearing, is the starting temperature of the second temperature sequence, It is an approximate value of (F×V) / (C×M).

[0043] (6) The conduction heat dissipation model can be derived as follows.

[0044] According to the derivative of lnx being 1 / x, Newton's cooling law is transformed and integrated as in equation (7) to obtain equation (8), and then equation (8) is transformed into equation (9). Substituting the starting time of the second temperature sequence into equation (9), the expression obtained is as in equation (10). Arranging the above equations, the conduction heat dissipation model can be obtained as in equation (11). Where t is the time relative to the starting time of the second temperature sequence, is the theoretical temperature of the bearing affected by conduction cooling at time t in the second temperature sequence, is the temperature cooling coefficient for conduction heat dissipation, is a positive number (temperature can only diffuse from high to low in natural conditions), H is the cabin ambient temperature, and is a constant coefficient, is the theoretical temperature of the bearing affected by conduction cooling at the initial time (t=0).

[0045] (7) (8) (9) (10) (11) It should be understood that when the speed increases, as time goes by, the bearing temperature increases due to friction. At the same time, as the bearing temperature differs from the cabin ambient temperature, the bearing temperature decreases due to Newton's cooling law. The influence of the two is mutual and continuous. Since the generator speed rises in a short time, it can be considered that the bearing temperature first generates heat due to friction in a very short time, causing the bearing temperature to increase and produce a difference, and then the temperature decreases according to Newton's cooling law. Therefore, the formula (11) can be The final temperature after heat conduction from bearing friction Replacing equation (5) with equation (12) yields the second thermodynamic model.

[0046] (12) Based on the second thermodynamic model, the second temperature sequence is fitted to obtain the second fitting function as shown in formula (13). Where t is the time relative to the start time of the second temperature sequence, is the fitting temperature of the bearing at time t in the second temperature sequence, is the starting temperature of the second temperature sequence, is the approximate value of the cabin ambient temperature H, is the approximate value of (F×V) / (C×M) (where F is the friction between the bearing raceway and the ball, V is the bearing speed, C is the bearing specific heat capacity, and M is the bearing mass). The temperature cooling coefficient for conduction heat dissipation Approximate value of .

[0047] (13) The third temperature sequence refers to the data sequence in the bearing temperature time series corresponding to the bearing being in the grid-connected state. The third fitting function is to substitute the third temperature sequence into the third thermodynamic model for fitting to obtain a mathematical function describing the bearing temperature change in the grid-connected state.

[0048] It should be understood that the factors affecting the bearing temperature in the grid-connected state are mainly the cabin ambient temperature, relative rolling friction inside the bearing, bearing conduction heat dissipation, and generator winding heating. Therefore, the third thermodynamic model includes the Joule heat conduction model, the friction heat conduction model, and the conduction heat dissipation model. The Joule heat conduction model is a heat conduction model for electromagnetic induction heat generation in the generator winding.

[0049] When the wind turbine is running, the main control system adjusts the excitation current of the generator rotor through the converter to generate electricity according to the wind power and grid demand. When the generator power remains unchanged, the bearing temperature rises approximately linearly. During the power generation process, current passes through the generator winding. Due to various physical and chemical processes inside, losses are inevitable. These losses will eventually cause the winding, core or other components to heat up. The increase in the active power of the generator will increase the rate of temperature rise. Part of the energy of the active power of the generator is transferred to the bearing in the form of heat through the generator winding, that is, a certain proportion of the heat that causes the bearing temperature to rise is lost during the conduction process.

[0050] Therefore, the Joule heat conduction model can be derived as follows.

[0051] According to Joule's law (Equation (14), the relationship between heat and temperature (Equation (15) and the relationship between heat loss (Equation (16), the Joule heat conduction model can be obtained (Equation (17). Among them, is the heat generated by the generator winding, I is the excitation current value, R is the generator winding resistance value, t is the time relative to the starting moment of the third temperature sequence, and P is the generator power, which can be obtained according to the wind power. is the heat generated by the generator winding and transferred to the bearing, C is the specific heat capacity, M is the mass, is the theoretical temperature of the bearing affected by the heating of the generator winding at time t of the third temperature sequence, is the starting temperature of the third temperature sequence, and β is the heat loss coefficient.

[0052] (14) (15) (16) (17) It should be understood that in the grid-connected state, the frictional heat generated by the bearings and the heat generated by the generator windings cause the bearing temperature to rise. At the same time, the bearings diffuse their own heat to the cabin environment by conduction heat dissipation. The above three influencing factors affect the change of bearing temperature at the same time. Because the bearing generates heat by friction and absorbs the heat from the generator windings during operation, the temperature difference between the bearing temperature and the environment can be generated first. After the temperature difference exists, the heat dissipation by the bearing conduction can be carried out, and then they continue to affect each other. Therefore, it can be assumed that in a short period of time, the bearing generates heat first, then absorbs heat, and finally dissipates heat. According to the above order, the equation (13) can be The final temperature after the bearing generates and absorbs heat As shown in equation (17), equation (13) is adaptively transformed to obtain the third thermodynamic model as shown in equation (18).

[0053] (18) Based on the third thermodynamic model, the third temperature sequence is fitted to obtain the third fitting function as shown in formula (19). Wherein, t is the time relative to the start time of the third temperature sequence, The fitting temperature of the bearing at time t in the third temperature sequence, is the starting temperature of the third temperature sequence, is the approximate value of the cabin ambient temperature H, is the approximate value of (F×V) / (C×M) (F is the friction between the bearing raceway and the ball, V is the bearing speed, C is the bearing specific heat capacity, and M is the bearing mass). The temperature cooling coefficient for conduction heat dissipation The approximate value of It is an approximate value of β / (C×M) (β is the heat loss coefficient).

[0054] (19) The fourth temperature sequence refers to a data sequence in the bearing temperature time series corresponding to the bearing being in a state of increasing speed. The fourth fitting function is to substitute the fourth temperature sequence into the fourth thermodynamic model for fitting to obtain a mathematical function describing the bearing temperature change under a thermal equilibrium state.

[0055] It should be understood that the generator speed is maintained at about the first to second speeds of the grid-connected speed. After the generator is in the grid-connected state, the temperature of the generator winding increases with time. When the temperature of the generator winding exceeds a certain temperature (generally 55 degrees Celsius), the main control system controls the heat dissipation device to start. At this time, the bearing temperature begins to drop due to the start of the heat dissipation device. Therefore, the factors affecting the bearing temperature in the thermal equilibrium state are mainly the cabin ambient temperature, the relative rolling friction inside the bearing, the conduction heat dissipation of the bearing, the heating of the generator winding, and the heat dissipation of the heat dissipation device. The fourth thermodynamic model includes the convection heat dissipation model, the conduction heat dissipation model, the friction heat conduction model, and the Joule heat conduction model. The convection heat dissipation model is a Newtonian cooling model for forced convection heat dissipation of the heat dissipation device.

[0056] The temperature cooling coefficient of conduction heat dissipation in equation (11) can be replaced by the temperature cooling coefficient of convection heat dissipation to obtain the convection heat dissipation model as shown in equation (20). Where t is the time relative to the start time of the fourth temperature sequence, is the theoretical temperature of the bearing affected by convection heat dissipation at time t in the fourth temperature sequence, is the temperature cooling coefficient for convective heat dissipation, is a positive number (the temperature can only diffuse from high to low under the influence of the cooling fan), H is the cabin ambient temperature, is the theoretical temperature of the bearing affected by convection heat dissipation at the starting time (t=0) of the fourth temperature series.

[0057] (20) It should be understood that in the thermal equilibrium state, the heat generated by bearing friction and the heat generated by the generator winding both cause the bearing temperature to rise. And the bearing diffuses its own heat to the cabin environment by conduction heat dissipation and convection heat dissipation. The above four influencing factors affect the change of bearing temperature at the same time. Since the heat generated by bearing friction and the heat absorbed by the generator winding first cause the temperature difference between the bearing and the environment, the temperature difference then causes the bearing to dissipate heat, and then they continue to affect each other. Therefore, it can be assumed that in a short period of time, the bearing first generates heat, then absorbs heat, and finally conducts heat dissipation and convection heat dissipation at the same time. According to the above order, the exponent of e in formula (20) can be replaced by . And replace the formula (20) The final temperature after the bearing generates and absorbs heat The adaptively deformed equation (17) is used to replace it, and the fourth thermodynamic model is obtained as equation (21).

[0058] (twenty one) Based on the fourth thermodynamic model, the fourth temperature sequence is fitted to obtain the fourth fitting function as shown in formula (22). Wherein, t is the time relative to the start time of the fourth temperature sequence, The fitting temperature of the bearing at time t in the fourth temperature series, is the starting temperature of the fourth temperature sequence, is the approximate value of the cabin ambient temperature H, is the approximate value of (F×V) / (C×M) (F is the friction between the bearing raceway and the ball, V is the bearing speed, C is the bearing specific heat capacity, and M is the bearing mass). The temperature cooling coefficient for conduction heat dissipation The approximate value of is the approximate value of β / (C×M), β is the heat loss coefficient, The temperature cooling coefficient for convection heat dissipation Approximate value of .

[0059] (twenty two) The fifth temperature sequence refers to the data sequence in the bearing temperature time series corresponding to the bearing being in the running-to-stop state. The fifth fitting function is to substitute the fifth temperature sequence into the second thermodynamic model for fitting to obtain a mathematical function describing the bearing temperature change in the running-to-stop state.

[0060] It should be understood that in the running-to-shutdown state, the generator is disconnected from the grid, its active power is zero, the generator speed drops to zero, and the heat dissipation device stops operating. However, because the bearing temperature is still higher than the cabin ambient temperature, the bearing temperature is mainly affected by its own conduction heat dissipation. Therefore, similar to equation (11), the fifth thermodynamic model is adaptively deformed as shown in equation (23). Where t is the time relative to the starting moment of the fifth temperature sequence, is the theoretical temperature of the bearing affected by conduction heat dissipation at time t of the fifth temperature sequence, is the temperature cooling coefficient for conduction heat dissipation, is a positive number (temperature can only diffuse from high to low in natural conditions), H is the cabin ambient temperature, is the starting temperature of the fifth temperature sequence.

[0061] (twenty three) Based on the fifth thermodynamic model, the fifth temperature series is fitted to obtain the fifth fitting function as shown in formula (24). is the fitting temperature of the bearing at time t in the fifth temperature sequence, is the approximate value of the cabin ambient temperature, is the starting temperature of the fifth temperature sequence, is an approximate value for the temperature cooling coefficient for conduction heat dissipation.

[0062] (twenty four) The above scheme combines the characteristics of each working condition and the corresponding thermodynamic theory to describe the temperature variation law of the bearing. According to different working conditions, the corresponding thermodynamic model is adopted to fit the corresponding bearing temperature time series to obtain the temperature fitting function under each working condition, which can provide a basis for subsequent fault diagnosis.

[0063] In one embodiment, step 130 may include: determining any one of a first influencing factor, a second influencing factor, a third influencing factor, a fourth influencing factor and a fifth influencing factor based on any multiple of the coefficients of the first fitting function, the coefficients of the second fitting function, the coefficients of the third fitting function, the coefficients of the fourth fitting function and the coefficients of the fifth fitting function, wherein the first influencing factor characterizes the degree of influence of the cabin ambient temperature on the bearing temperature, the second influencing factor characterizes the degree of influence of the rolling relative friction inside the bearing on the bearing temperature, the third influencing factor characterizes the degree of influence of the conductive heat dissipation of the bearing on the bearing temperature, the fourth influencing factor characterizes the degree of influence of the heating of the generator winding on the bearing temperature, and the fifth influencing factor characterizes the degree of influence of the convective heat dissipation of the heat dissipation device on the bearing temperature.

[0064] Here, the first fitting function can be as shown in formula (2), the second fitting function can be as shown in formula (13), the third fitting function can be as shown in formula (19), the fourth fitting function can be as shown in formula (22), and the fifth fitting function can be as shown in formula (24). The first influencing factor can be The second influencing factor can be The third influencing factor can be: The fourth impact factor can be The fifth impact factor can be For example, the first influencing factor, the second influencing factor, the third influencing factor, the fourth influencing factor and the fifth influencing factor can be determined by the following method. The constant coefficient of the first fitting function is the first influencing factor Based on the fifth fitting function, at the starting temperature of the fifth temperature sequence , time t, can be determined as the third influencing factor Based on the second fitting function, at the starting temperature of the second temperature sequence , time t, third impact factor And the first impact factor If both are known, the second impact factor can be determined Based on the third fitting function, at the starting temperature of the third temperature sequence , time t, first impact factor , the second impact factor 、Third Impact Factor And generator power If all are known, the fourth impact factor can be determined Based on the fourth fitting function, at the starting temperature of the fourth temperature sequence , time t, first impact factor , the second impact factor 、Third Impact Factor 、The fourth impact factor And generator power If all are known, the fifth impact factor can be determined .

[0065] The above method can more accurately determine the value of each temperature influencing factor, laying the foundation for the subsequent early warning of the fault status of the bearing based on each temperature influencing factor, thereby improving the accuracy of the early warning.

[0066] In one embodiment, step 140 may include: when the second impact factor is greater than the second preset multiple of its historical value, warning of the relative friction state between the rolling bearing and the raceway of the bearing; when the third impact factor is less than the third preset multiple of its historical value, warning of the lubrication state of the bearing; when the fourth impact factor is greater than the fourth preset multiple of its historical value, warning of the temperature state of the generator winding; when the fifth impact factor is less than the fifth preset multiple of its historical value, warning of the operating state of the heat dissipation device.

[0067] Here, the second preset multiple, the third preset multiple, the fourth preset multiple, and the fifth preset multiple may be set to 1.05.

[0068] Since the second influencing factor represents the influence of the relative rolling friction inside the bearing on the bearing temperature, when the second influencing factor is greater than the second preset multiple of its historical value, early warning information can be output to focus on whether the bearing balls and raceways are well lubricated, whether there is a deviation in the alignment of the bearing, whether the bearing balls and raceways have large clearance, whether pitting occurs on the surfaces of the balls and raceways, and whether the bearing has already experienced obvious vibration.

[0069] Since the third influencing factor represents the influence of the bearing conduction heat dissipation on the bearing temperature, when the third influencing factor is less than the third preset multiple of its historical value, a warning message focusing on whether the bearing grease is sufficient can be output.

[0070] Since the fourth influencing factor represents the influence degree of the generator winding heating on the bearing temperature, when the fourth influencing factor is greater than the fourth preset multiple of its historical value, a warning message focusing on whether the generator winding temperature is abnormal can be output.

[0071] Since the fifth influencing factor represents the influence of the convective heat dissipation of the heat sink on the bearing temperature, when the fifth influencing factor is less than the fifth preset multiple of its historical value, early warning information can be output focusing on whether the filter of the heat sink is blocked and whether the heat sink is damaged.

[0072] After the staff determines whether the above warning information is true, if it is not true, the above temperature impact factor will be updated as the historical value of each temperature factor for the next warning.

[0073] Through the above method, different possible fault types can be warned more accurately, and based on the fluctuation values ​​of different influencing factors, the cause of abnormal bearing temperature can be known, thereby improving the accuracy and timeliness of bearing temperature warning.

[0074] In one embodiment, the method may further include: determining a sixth fitting function based on the thermodynamic model of each of the operating conditions and the influencing factors, wherein the sixth fitting function is used to predict the bearing temperature under any of the operating conditions; determining the target operating condition corresponding to the sixth temperature sequence based on the operating parameters and state of the doubly-fed wind turbine generator set corresponding to the sixth temperature sequence; setting the temperature influencing factors in the sixth fitting function that are not related to the target operating condition to zero to obtain a target fitting function; based on the target fitting function, determining the fitting temperature corresponding to the termination temperature of the sixth temperature sequence according to the starting temperature of the sixth temperature sequence and the time corresponding to the sixth temperature sequence; when the termination temperature is greater than a first preset multiple of the fitting temperature, warning of a bearing fault state is issued based on the estimated time between the termination temperature rising to the preset fault temperature and the bearing vibration acceleration.

[0075] Here, the sixth temperature sequence can be any temperature sequence of any working condition. The duration corresponding to the sixth temperature sequence is the duration between the moment corresponding to the starting temperature and the moment corresponding to the ending temperature. The first preset multiple can be set to 1.1.

[0076] It should be understood that the factors affecting the bearing temperature under thermal equilibrium are mainly the cabin ambient temperature, relative rolling friction inside the bearing, heat dissipation by bearing conduction, heating of the generator winding, and heat dissipation by the heat dissipation device. That is, the fourth fitting function corresponding to the thermal equilibrium state includes the first influencing factor, the second influencing factor, the third influencing factor, the fourth influencing factor, and the fifth influencing factor. Therefore, the formula (22) of the fourth thermodynamic model can be adaptively deformed to obtain the sixth fitting function such as formula (25).

[0077] (25) Wherein, t is the time relative to the start time of the sixth temperature sequence, The fitting temperature of the bearing at time t in the sixth temperature sequence, is the starting temperature of the sixth temperature sequence, is the first influencing factor, i.e. the approximate value of the cabin ambient temperature H, is the second influencing factor, which is the approximate value of (F×V) / (C×M), where F is the friction between the bearing raceway and the ball, V is the bearing speed, C is the bearing specific heat capacity, and M is the bearing mass. The third influencing factor is the temperature cooling coefficient of conduction heat dissipation. The approximate value of is the fourth influencing factor, i.e. the approximate value of β / (C×M), where β is the heat loss coefficient, The fifth influencing factor is the temperature cooling coefficient of convection heat dissipation. Approximate value of .

[0078] For example, based on formula (25), each temperature influencing factor is simulated and assigned a value, and the simulation scatter plot of the bearing temperature prediction function corresponding to the above five working conditions is obtained, as shown in Figure 2 And the change trend of the simulation scatter plot of the bearing temperature prediction function is basically consistent with the change trend of the scatter plot of the actual bearing temperature historical data.

[0079] The target operating condition of the sixth temperature sequence may be determined according to the operating parameters and state of the doubly-fed wind turbine generator set corresponding to the sixth temperature sequence, so that the sixth fitting function may be adjusted to determine the target fitting function.

[0080] For example, if the target operating condition is a stationary state, the first influencing factor may be retained and set as its historical value, and the remaining temperature influencing factors may be set to 0, thereby obtaining a target fitting function for the stationary state.

[0081] If the target operating condition is a speed increase state, the first influencing factor, the second influencing factor and the third influencing factor can be retained and set to corresponding historical values ​​respectively, and the remaining temperature influencing factors are set to 0 to obtain the target fitting function of the speed increase state.

[0082] If the target operating condition is a grid-connected state, the first influencing factor, the second influencing factor, the third influencing factor and the fourth influencing factor can be retained and set to corresponding historical values ​​respectively, and the fifth influencing factor is set to 0 to obtain the target fitting function of the grid-connected state.

[0083] If the target operating condition is a thermal equilibrium state, all temperature influencing factors can be retained and set to corresponding historical values ​​respectively to obtain the target fitting function of the thermal equilibrium state.

[0084] If the target operating condition is the run-to-shutdown state, the first influencing factor and the third influencing factor can be retained and set to corresponding historical values ​​respectively, and the remaining temperature influencing factors are set to 0 to obtain the target fitting function of the run-to-shutdown state.

[0085] After determining the target fitting function, the starting temperature and duration are substituted to determine the fitting temperature. When the end temperature is greater than the first preset multiple of the fitting temperature, the estimated time and the bearing vibration acceleration can be calculated based on the target fitting function according to the rise of the end temperature to the preset fault temperature, and the bearing fault state can be warned.

[0086] In one embodiment, the warning of the bearing fault state according to the estimated time between the termination temperature rising to the preset fault temperature and the bearing vibration acceleration may include: When the estimated duration is less than the first preset duration and the vibration acceleration is less than the preset acceleration, a first-level warning is issued, and the warning object is the lubrication state and heat dissipation state of the bearing; When the estimated duration is less than the first preset duration and the vibration acceleration is greater than or equal to the preset acceleration, a first-level warning is issued, and the warning object is the structural damage state of the bearing; When the estimated duration is less than or equal to the second preset duration, and the vibration acceleration is less than the preset acceleration, a second-level warning is issued, and the warning objects are the lubrication state and heat dissipation state of the bearing; When the estimated duration is less than or equal to the second preset duration, and the vibration acceleration is greater than or equal to the preset acceleration, a second-level warning is issued, and the warning object is the structural damage state of the bearing; When the estimated duration is less than or equal to the third preset duration, and the vibration acceleration is less than the preset acceleration, a third-level warning is issued, and the warning objects are the lubrication state and heat dissipation state of the bearing; When the estimated duration is less than or equal to the third preset duration, and the vibration acceleration is greater than or equal to the preset acceleration, a third-level warning is issued, and the warning object is the structural damage state of the bearing. The first preset duration is greater than the second preset duration, and the second preset duration is greater than the third preset duration.

[0087] Here, the first preset time length can be 240 hours, the second preset time length can be 24 hours, and the third preset time length can be 1 hour. The preset acceleration can be the acceleration reference value corresponding to the slight vibration of the bearing, which can be obtained according to relevant standards. The first-level warning indicates that the bearing has a minor fault, and a warning suggestion to check the bearing status on a selected day can be output. The second-level warning indicates that the bearing has a moderate fault, and a warning suggestion to check the bearing status immediately can be output. The third-level warning indicates that the bearing has a serious fault, and a warning suggestion to stop the machine immediately to check the bearing status can be output.

[0088] Through the above technical solution, it is possible to comprehensively monitor the various stages in which the bearing evolves from a normal state to a minor fault, a moderate fault, and a major fault, and give recommendations on which parts of the bearing should be checked at each stage, thereby improving the comprehensiveness, accuracy, and timeliness of bearing warnings.

[0089] Figure 3 1 is a block diagram of a bearing fault early warning device according to an exemplary embodiment. The device includes the following modules: The working condition determination module 310 is used to determine the working condition of the bearing according to the operating parameters and state of the doubly-fed wind turbine generator set; A temperature fitting module 320 is used to fit the bearing temperature time series corresponding to the working condition based on the thermodynamic model corresponding to the working condition to obtain a temperature fitting function corresponding to the working condition; An influence factor determination module 330, used to determine a temperature influence factor according to the coefficient of the temperature fitting function; The first warning module 340 is used to warn of a bearing failure state according to a deviation between the temperature influence factor and its historical value.

[0090] Optionally, the operating condition determination module 310 is specifically configured to: When the generator speed is zero, determining that the bearing is in a stationary state; When the generator speed continues to increase and the generator speed is less than a first speed, determining that the bearing is in a speed increasing state; When the generator speed is greater than or equal to the first speed and less than the second speed, and the generator is in a power generation state, it is determined that the bearing is in a grid-connected state and the first speed is less than the second speed; When the heat dissipation device is activated, determining that the bearing is in a thermal equilibrium state; When the active power of the generator is zero and the rotation speed of the generator continues to decrease until it reaches zero, it is determined that the bearing is in the running-to-stop state.

[0091] Optionally, the temperature fitting module 320 is specifically used for: When the bearing is in a stationary state, fitting a first temperature sequence corresponding to the stationary state based on a first thermodynamic model to obtain a first fitting function; When the bearing is in a speed increasing state, fitting a second temperature sequence corresponding to the speed increasing state based on a second thermodynamic model to obtain a second fitting function; When the bearing is in a grid-connected state, fitting a third temperature sequence corresponding to the grid-connected state based on a third thermodynamic model to obtain a third fitting function; When the bearing is in a thermal equilibrium state, fitting a fourth temperature sequence corresponding to the thermal equilibrium state based on a fourth thermodynamic model to determine a fourth fitting function; When the bearing is in the running-to-stop state, a fifth temperature sequence corresponding to the running-to-stop state is fitted based on a fifth thermodynamic model to determine a fifth fitting function.

[0092] Optionally, the impact factor determination module 330 is specifically used for: Determine any one of a first influencing factor, a second influencing factor, a third influencing factor, a fourth influencing factor, and a fifth influencing factor according to any multiple of the coefficients of the first fitting function, the coefficients of the second fitting function, the coefficients of the third fitting function, the coefficients of the fourth fitting function, and the coefficients of the fifth fitting function, The first influencing factor characterizes the influence of the cabin ambient temperature on the bearing temperature, the second influencing factor characterizes the influence of the rolling relative friction inside the bearing on the bearing temperature, the third influencing factor characterizes the influence of the conductive heat dissipation of the bearing on the bearing temperature, the fourth influencing factor characterizes the influence of the generator winding heating on the bearing temperature, and the fifth influencing factor characterizes the influence of the convective heat dissipation of the heat dissipation device on the bearing temperature.

[0093] Optionally, the first early warning module 340 is specifically used for: When the second influencing factor is greater than a second preset multiple of its historical value, a warning is given of the relative friction state between the rolling bearing and the raceway of the bearing; When the third impact factor is less than a third preset multiple of its historical value, an early warning of the lubrication state of the bearing is issued; When the fourth impact factor is greater than a fourth preset multiple of its historical value, an early warning is given on the temperature state of the generator winding; When the fifth impact factor is smaller than the fifth preset multiple of its historical value, an early warning is issued on the operating state of the heat dissipation device.

[0094] Optionally, the device may further include a second early warning module, configured to: Determine a sixth fitting function according to the thermodynamic model of each of the working conditions and the influencing factors, wherein the sixth fitting function is used to predict the bearing temperature under any of the working conditions; Determining a target operating condition corresponding to the sixth temperature sequence according to the operating parameters and state of the doubly-fed wind turbine generator set corresponding to the sixth temperature sequence; The temperature influence factor in the sixth fitting function that is not related to the target operating condition is set to zero to obtain a target fitting function; Based on the target fitting function, determining a fitting temperature corresponding to an end temperature of the sixth temperature sequence according to a starting temperature of the sixth temperature sequence and a duration corresponding to the sixth temperature sequence; When the termination temperature is greater than a first preset multiple of the fitting temperature, a bearing fault state is warned based on an estimated time period between the termination temperature rising to a preset fault temperature and the bearing vibration acceleration.

[0095] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0096] Figure 4 FIG. 4 is a block diagram of an electronic device 400 according to an exemplary embodiment. Figure 4As shown, the electronic device 400 may include: a processor 401 and a memory 402. The electronic device 400 may also include one or more of a multimedia component 403, an input / output (I / O) interface 404, and a communication component 405.

[0097] The processor 401 is used to control the overall operation of the electronic device 400 to complete each or part of the steps in the above-mentioned bearing fault warning device method. The memory 402 is used to store various types of data to support the operation of the electronic device 400, and these data may include instructions for any application or method used to operate on the electronic device 400, and application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 402 or sent through the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 404 provides an interface between the processor 401 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 4G, 4G, NB-IOT, eMTC or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 405 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0098] In an exemplary embodiment, the electronic device 400 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned bearing fault warning device method.

[0099] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned bearing fault early warning device method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 402 including program instructions, and the above-mentioned program instructions can be executed by the processor 401 of the electronic device 400 to complete the above-mentioned bearing fault early warning device method.

[0100] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned bearing fault early warning device method when executed by the programmable device.

[0101] The preferred embodiments of the present application are described in detail above in conjunction with the accompanying drawings; however, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, a variety of simple modifications can be made to the technical solution of the present application, and these simple modifications all fall within the protection scope of the present application.

[0102] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this application will not further describe various possible combinations.

[0103] In addition, the various implementation modes of the present application may be arbitrarily combined, and as long as they do not violate the concept of the present application, they should also be regarded as the contents disclosed in the present application.

Claims

1. A bearing fault early warning method, characterized in that: include: Determine the working condition of the bearing according to the operating parameters and status of the doubly-fed wind turbine generator set; Based on the thermodynamic model corresponding to the working condition, the bearing temperature time series corresponding to the working condition is fitted to obtain a temperature fitting function corresponding to the working condition; Determining a temperature influence factor according to a coefficient of the temperature fitting function; Based on the deviation of the temperature influencing factor and its historical value, the fault status of the bearing is warned.

2. The method according to claim 1, characterized in that Determining the working condition of the bearing according to the operating parameters and state of the doubly-fed wind turbine generator set includes: When the generator speed is zero, determining that the bearing is in a stationary state; When the generator speed continues to increase and the generator speed is less than a first speed, determining that the bearing is in a speed increasing state; When the generator speed is greater than or equal to the first speed and less than the second speed, and the generator is in a power generation state, it is determined that the bearing is in a grid-connected state and the first speed is less than the second speed; When the heat dissipation device is activated, determining that the bearing is in a thermal equilibrium state; When the active power of the generator is zero and the rotation speed of the generator continues to decrease until it reaches zero, it is determined that the bearing is in the running-to-stop state.

3. The method according to claim 2, characterized in that The step of fitting the bearing temperature time series corresponding to the working condition based on the thermodynamic model corresponding to the working condition to obtain the temperature fitting function corresponding to the working condition includes: When the bearing is in a stationary state, fitting a first temperature sequence corresponding to the stationary state based on a first thermodynamic model to obtain a first fitting function; When the bearing is in a speed increasing state, fitting a second temperature sequence corresponding to the speed increasing state based on a second thermodynamic model to obtain a second fitting function; When the bearing is in a grid-connected state, fitting a third temperature sequence corresponding to the grid-connected state based on a third thermodynamic model to obtain a third fitting function; When the bearing is in a thermal equilibrium state, fitting a fourth temperature sequence corresponding to the thermal equilibrium state based on a fourth thermodynamic model to determine a fourth fitting function; When the bearing is in the running-to-stop state, a fifth temperature sequence corresponding to the running-to-stop state is fitted based on a fifth thermodynamic model to determine a fifth fitting function.

4. The method according to claim 3, characterized in that Determining the temperature influence factor according to the coefficient of the temperature fitting function includes: Determine any one of a first influencing factor, a second influencing factor, a third influencing factor, a fourth influencing factor, and a fifth influencing factor according to any multiple of the coefficients of the first fitting function, the coefficients of the second fitting function, the coefficients of the third fitting function, the coefficients of the fourth fitting function, and the coefficients of the fifth fitting function, The first influencing factor characterizes the influence of the cabin ambient temperature on the bearing temperature, the second influencing factor characterizes the influence of the rolling relative friction inside the bearing on the bearing temperature, the third influencing factor characterizes the influence of the conductive heat dissipation of the bearing on the bearing temperature, the fourth influencing factor characterizes the influence of the generator winding heating on the bearing temperature, and the fifth influencing factor characterizes the influence of the convective heat dissipation of the heat dissipation device on the bearing temperature.

5. The method according to claim 4, characterized in that The method of warning the bearing fault state based on the deviation of the temperature influence factor and its historical value includes: When the second influencing factor is greater than a second preset multiple of its historical value, a warning is given of the relative friction state between the rolling bearing and the raceway of the bearing; When the third impact factor is less than a third preset multiple of its historical value, an early warning of the lubrication state of the bearing is issued; When the fourth impact factor is greater than a fourth preset multiple of its historical value, an early warning is given on the temperature state of the generator winding; When the fifth impact factor is smaller than the fifth preset multiple of its historical value, an early warning is issued on the operating state of the heat dissipation device.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Determine a sixth fitting function according to the thermodynamic model of each of the working conditions and the influencing factors, wherein the sixth fitting function is used to predict the bearing temperature under any of the working conditions; Determining a target operating condition corresponding to the sixth temperature sequence according to the operating parameters and state of the doubly-fed wind turbine generator set corresponding to the sixth temperature sequence; The temperature influence factor in the sixth fitting function that is not related to the target operating condition is set to zero to obtain a target fitting function; Based on the target fitting function, determining a fitting temperature corresponding to an end temperature of the sixth temperature sequence according to a starting temperature of the sixth temperature sequence and a duration corresponding to the sixth temperature sequence; When the termination temperature is greater than a first preset multiple of the fitting temperature, a bearing fault state is warned based on an estimated time period between the termination temperature rising to a preset fault temperature and the bearing vibration acceleration.

7. A bearing fault warning device, characterized in that: include: A working condition determination module, used to determine the working condition of the bearing according to the operating parameters and status of the doubly-fed wind turbine generator set; A temperature fitting module, used to fit the bearing temperature time series corresponding to the working condition based on the thermodynamic model corresponding to the working condition, and obtain a temperature fitting function corresponding to the working condition; An influence factor determination module, used to determine the temperature influence factor according to the coefficient of the temperature fitting function; The first early warning module is used to warn of a bearing failure state based on a deviation of a temperature influence factor from its historical value.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images