Sealing element service life prediction method and device, equipment and storage medium

Abstract

The invention discloses a service life prediction method, device and equipment for a sealing element and a storage medium, the rack service life of a first sealing element is obtained, the rack service life is used for indicating the effective duration of the first sealing element on a test rack, and the test rack is used for simulating the working condition environment of a wind power plant; based on the rack service life of the first sealing element and a service life prediction model, obtaining the predicted field service life of the first sealing element, the predicted field service life being used for indicating the effective duration of the first sealing element in the working condition environment of the wind power plant, and the service life prediction model being used for indicating the corresponding relationship between the rack service life and the predicted field service life; the life prediction model is determined based on the rack life of a sample seal set and the actual on-site life of the sample seal set, and the sample seal set comprises at least one seal that has been applied in the wind farm working condition environment. The service life of the sealing element under the working condition of the wind power plant can be accurately predicted in combination with the service life of the sealing element on the test bench.

Description

Technical Field

[0001] The present application relates to the field of wind power technology, and in particular to a method, device, equipment and storage medium for predicting the life of a seal. Background Art

[0002] Seals are an important component in wind turbines. Currently, it is impossible to know the life of seals in wind farm working conditions. Since wind turbines are mostly located in places with inconvenient transportation, it is impossible to board the machine in time to check the operating status of the seals (such as performance or degree of wear). As a result, if the seal has been used for a long time and has not been discovered in time, it is very likely to cause a seal failure and oil leakage accident. If the seal is replaced in advance before the seal has been used for a long time, it will inevitably cause a waste of various resources.

[0003] In view of this, further discussion and research is needed on how to predict the life of seals. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for predicting the life of a seal, which can more accurately predict the life of a seal.

[0005] In a first aspect, a method for predicting the life of a seal is provided, the method comprising:

[0006] Acquire a test bench life of the first seal, where the test bench life is used to indicate how long the first seal remains effective on a test bench, where the test bench is used to simulate a wind farm operating environment;

[0007] The predicted field life of the first seal is obtained based on the bench life and the life prediction model of the first seal, the predicted field life is used to indicate the length of time the first seal remains effective in the wind farm operating environment, the life prediction model is used to indicate the correspondence between the bench life and the predicted field life, the life prediction model is determined based on the bench life of a sample seal set and the actual field life of the sample seal set, the sample seal set including at least one seal that has been applied in the wind farm operating environment.

[0008] In a possible implementation, obtaining the bench life of the first seal includes: loading environmental stress parameters onto the test bench; performing a durability test on the first seal on the test bench loaded with the environmental stress parameters to obtain the bench life of the first seal.

[0009] In a possible implementation manner, the environmental stress parameter includes at least one of temperature, rotation speed, processing parameter or assembly parameter.

[0010] In one possible implementation, before obtaining the predicted field life of the first seal based on the bench life and the life prediction model of the first seal, the method also includes: obtaining the bench life of the sample seal set and the actual field life of the sample seal set; and generating the life prediction model of the seal based on the bench life of the sample seal set and the actual field life of the sample seal set.

[0011] In one possible implementation, the sample seal set includes a first sample seal and a second sample seal, the first sample seal and the second sample seal have the same specification and the same batch, and obtaining the bench life of the sample seal set and the actual field life of the sample seal set includes: performing a durability test on the first sample seal on a test bench loaded with the environmental stress parameters to obtain the bench life of the first sample seal; and obtaining the actual field life of the second sample seal from the wind farm operating environment.

[0012] In a possible implementation, the first sample seal has been used for a first period of time in the wind farm working environment before being assembled to the test bench, the bench life of the first sample seal includes an actual remaining bench life, the life prediction model includes an initial life prediction model and a target life prediction model, and determining the life prediction model of the seal based on the bench life of the sample seal set and the actual field life of the sample seal set includes:

[0013] The parameters in the initial life prediction model are adjusted based on the actual remaining bench life of the first sample seal and the first duration to obtain the target life prediction model. The actual remaining bench life refers to the duration for which the first sample seal remains effective during the durability test after being reassembled from the wind farm operating environment to the test bench.

[0014] In a possible implementation, adjusting the parameters in the initial life prediction model based on the actual remaining bench life of the first sample seal and the first time length includes:

[0015] Based on the first time period and the initial life prediction model, obtaining a predicted remaining bench life of the first sample seal;

[0016] Obtaining a first deviation based on an actual remaining bench life of the first sample seal and a predicted remaining bench life of the first sample seal, wherein the first deviation refers to a deviation between the predicted remaining bench life and the actual remaining bench life;

[0017] Parameters in the initial life prediction model are adjusted based on the first deviation.

[0018] In a possible implementation, the second sample seal has been used for a second period of time on the test bench before being assembled in the wind farm working environment, the field life of the second sample seal includes an actual remaining field life, the life prediction model includes an initial life prediction model and a target life prediction model, and determining the life prediction model of the seal based on the field life of the sample seal set and the actual field life of the sample seal set includes:

[0019] Based on the actual remaining field life of the second sample seal and the second duration, the parameters in the initial life prediction model are adjusted to obtain the target life prediction model. The actual remaining field life refers to the effective duration after the second sample seal is reassembled from the test bench to the wind farm operating environment.

[0020] In a possible implementation, adjusting the parameters in the initial life prediction model based on the actual remaining field life of the second sample seal and the second duration includes:

[0021] Based on the second time period and the initial life prediction model, obtaining a predicted remaining field life of the second sample seal;

[0022] Obtaining a second deviation based on the actual remaining field life of the second sample seal and the predicted remaining field life of the second sample seal, wherein the second deviation refers to a deviation between the predicted remaining field life and the actual remaining field life;

[0023] Parameters in the initial life prediction model are adjusted based on the second deviation.

[0024] In a possible implementation, the obtaining of the bench life of the sample seal set and the actual field life of the sample seal set includes:

[0025] Based on the failure cause information of the plurality of seals, the actual field life of the sample seal set is determined from the actual field life of the plurality of seals.

[0026] In a possible implementation, the determining the actual field life of the sample seal set from the actual field life of the multiple seals based on the failure cause information of the multiple seals includes:

[0027] In response to the failure cause information of the first sample seal indicating that the first sample seal failed due to material aging or wear, adding the actual field life of the first sample seal to the actual field life of the sample seal set; or,

[0028] In response to the failure reason information of the third sample seal indicating that the third sample seal fails due to installation or product quality, the actual field life of the third sample seal is deleted from the actual field life of the sample seal set.

[0029] In a possible implementation, obtaining the actual field life of the second sample seal from the wind farm working environment includes:

[0030] From the actual field life of each sample seal in the set of sample seals, the shortest actual field life is selected as the actual field life of the second sample seal.

[0031] In a possible implementation, after obtaining the predicted field life of the first seal based on the bench life and the life prediction model of the first seal, the method further includes:

[0032] Based on the predicted field life and life index of the first sealing component, testing the reliability of the first sealing component;

[0033] In response to the predicted field life of the first seal being greater than or equal to the life index, outputting a first test result, the first test result indicating that the first seal meets the life index; or,

[0034] In response to the predicted field life of the first seal being less than the life indicator, a second detection result is output, wherein the first detection result is used to indicate that the first seal does not meet the life indicator.

[0035] In a possible implementation, the method further includes:

[0036] Obtaining a predicted field life of the reference seal based on the bench life of the reference seal and a life prediction model;

[0037] comparing the predicted field life of the first seal with the predicted field life of the reference seal to obtain a comparison result;

[0038] A life improveability report is output based on the comparison result, the life improveability report indicating the extent to which the predicted field life of the first seal is improved compared to the predicted field life of the baseline seal.

[0039] In a second aspect, a life prediction device for a seal is provided, the device comprising:

[0040] A test bench life acquisition module, used to acquire the test bench life of the first seal, where the test bench life is used to indicate the length of time the first seal remains effective on a test bench, where the test bench is used to simulate a wind farm operating environment;

[0041] A field life prediction module is used to obtain the predicted field life of the first seal based on the bench life of the first seal and a life prediction model, the predicted field life is used to indicate the length of time the first seal remains effective in the wind farm operating environment, the life prediction model is used to indicate the correspondence between the bench life and the predicted field life, the life prediction model is determined based on the bench life of a sample seal set and the actual field life of the sample seal set, the sample seal set includes at least one seal that has been applied in the wind farm operating environment.

[0042] In a possible implementation, the test bench life acquisition module is used to load environmental stress parameters to the test bench; on the test bench loaded with the environmental stress parameters, a durability test is performed on the first seal to obtain the test bench life of the first seal.

[0043] In a possible implementation manner, the environmental stress parameter includes at least one of temperature, rotation speed, processing parameter or assembly parameter.

[0044] In a possible implementation, the device further includes: a sample acquisition module, configured to acquire the bench life of the sample seal set and the actual field life of the sample seal set;

[0045] A model generation module is used to generate a life prediction model for the seal based on the bench life of the sample seal set and the actual field life of the sample seal set.

[0046] In one possible implementation, the sample seal set includes a first sample seal and a second sample seal, the first sample seal and the second sample seal have the same specifications and the same batch, and the sample acquisition module is used to perform a durability test on the first sample seal on a test bench loaded with the environmental stress parameters to obtain the bench life of the first sample seal; and obtain the actual field life of the second sample seal from the wind farm operating environment.

[0047] In one possible implementation, the first sample seal has been used for a first period of time in the wind farm operating environment before being assembled to the test bench, the bench life of the first sample seal includes an actual remaining bench life, the life prediction model includes an initial life prediction model and a target life prediction model, and the model generation module is used to adjust the parameters in the initial life prediction model based on the actual remaining bench life of the first sample seal and the first period of time to obtain the target life prediction model, and the actual remaining bench life refers to the length of time that the first sample seal remains effective during the durability test after being reassembled from the wind farm operating environment to the test bench.

[0048] In one possible implementation, the model generation module is used to obtain a predicted remaining scaffold life of the first sample seal based on the first time length and the initial life prediction model; obtain a first deviation based on the actual remaining scaffold life of the first sample seal and the predicted remaining scaffold life of the first sample seal, wherein the first deviation refers to the deviation between the predicted remaining scaffold life and the actual remaining scaffold life; and adjust the parameters in the initial life prediction model based on the first deviation.

[0049] In one possible implementation, the second sample seal has been used on the test bench for a second period of time before being assembled to the wind farm operating environment, the field life of the second sample seal includes an actual remaining field life, the life prediction model includes an initial life prediction model and a target life prediction model, and the model generation module is used to adjust the parameters in the initial life prediction model based on the actual remaining field life of the second sample seal and the second period of time to obtain the target life prediction model, and the actual remaining field life refers to the effective period of time after the second sample seal is reassembled from the test bench to the wind farm operating environment.

[0050] In a possible implementation, the model generation module is used to obtain the predicted remaining field life of the second sample seal based on the second time length and the initial life prediction model; obtain a second deviation based on the actual remaining field life of the second sample seal and the predicted remaining field life of the second sample seal, wherein the second deviation refers to the deviation of the predicted remaining field life compared to the actual remaining field life;

[0051] Parameters in the initial life prediction model are adjusted based on the second deviation.

[0052] In a possible implementation, the sample acquisition module is used to determine the actual field life of the sample seal set from the actual field life of the multiple seals based on failure cause information of the multiple seals.

[0053] In one possible implementation, the sample acquisition module is used to, in response to the failure cause information of the first sample seal indicating that the first sample seal failed due to material aging or wear, add the actual field life of the first sample seal to the actual field life of the sample seal set; or, in response to the failure cause information of the third sample seal indicating that the third sample seal failed due to installation or product quality, delete the actual field life of the third sample seal from the actual field life of the sample seal set.

[0054] In a possible implementation, the sample acquisition module is used to select the shortest actual field life from the actual field life of each sample seal in the sample seal set as the actual field life of the second sample seal.

[0055] In a possible implementation manner, the device further includes:

[0056] A reliability detection module, configured to detect the reliability of the first sealing component based on the predicted field life and life index of the first sealing component;

[0057] an output module, configured to output a first test result in response to the predicted field life of the first seal being greater than or equal to the life index, wherein the first test result indicates that the first seal meets the life index; or

[0058] In response to the predicted field life of the first seal being less than the life indicator, a second detection result is output, wherein the first detection result is used to indicate that the first seal does not meet the life indicator.

[0059] In a possible implementation, the on-site life prediction module is further used to obtain the predicted on-site life of the reference seal based on the bench life of the reference seal and the life prediction model;

[0060] The device further comprises: a comparison module, configured to compare the predicted field life of the first seal with the predicted field life of the reference seal to obtain a comparison result;

[0061] An output module is configured to output a life improvement report based on the comparison result, wherein the life improvement report indicates the degree to which the predicted field life of the first seal is improved compared to the predicted field life of the reference seal.

[0062] In a third aspect, a computing device is provided, comprising: a processor, the processor being coupled to a memory, the memory storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the processor so that the computing device implements the above-mentioned first aspect or any optional method of the first aspect.

[0063] In a fourth aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and when the instruction is executed on a computer, the computer executes the above-mentioned first aspect or any optional method of the first aspect.

[0064] In a fifth aspect, a computer program product is provided, which includes one or more computer program instructions. When the computer program instructions are loaded and executed by a computer, the computer executes the method provided by the first aspect or any optional manner of the first aspect.

[0065] In a sixth aspect, a chip is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call and run the computer instructions from the memory to execute the method in the above-mentioned first aspect and any possible implementation of the first aspect.

[0066] It can be seen that the embodiments of the present application have the following beneficial effects:

[0067] Since the model is determined based on the life of the sample seal set on the test bench and the actual life of the sample seal set in the wind farm operating environment, the model can learn the correspondence between the life of the seal on the test bench and the life in the wind farm operating environment through samples. Therefore, for a seal (first seal) with unknown life under wind farm conditions, the model can accurately predict the life of the seal under wind farm conditions based on the life of the seal on the test bench. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a flow chart of a method for generating a life prediction model of a seal provided in an embodiment of the present application;

[0069] Figure 2 It is a flow chart of a method for predicting the life of a seal provided in an embodiment of the present application;

[0070] Figure 3 is a schematic structural diagram of a life prediction device for a sealing component provided in this embodiment;

[0071] Figure 4 It is a structural diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0073] The following is an explanation of some terminology concepts involved in the embodiments of the present application.

[0074] (1) Seals

[0075] A seal is a component used to restrict the flow of fluid (such as liquid or gas) out of or into an area of ​​a machine, equipment or system. Seals are usually made of elastic materials and have good sealing performance and durability. For example, a seal is assembled in a cavity formed by a mating shaft and a structural part, and forms an interference contact with the mating shaft to achieve the sealing and restriction function of the fluid (oil or oil and gas) in dynamic and static conditions.

[0076] (2) Environmental stress

[0077] Environmental stress refers to the various forces, temperatures, pressures and other external factors applied to seals in their actual use environment. Environmental stress can have an impact on the life of seals.

[0078] (3) Environmental stress parameters

[0079] The environmental stress parameter includes at least one of temperature, rotation speed, processing parameter or assembly parameter. For example, the environmental stress parameter includes at least one of the minimum working environment temperature, the maximum working environment temperature, rotation speed, pressure in the sealing cavity, shaft material, shaft diameter, shaft surface hardness, shaft roughness, shaft eccentricity, cavity material, cavity diameter, cavity eccentricity, cavity roughness or the coaxiality of the shaft and cavity.

[0080] (4) Durability test

[0081] Durability testing is a test method to evaluate the performance stability and life of a product or material during long-term use. Products or materials are tested continuously or intermittently under specific conditions to simulate the stress and working conditions in the actual use environment.

[0082] (5) Dynamic bench test of seals

[0083] The dynamic bench test of seals refers to determining the key environmental stress parameters of seals under wind farm operating conditions, and loading the environmental stress parameters on the test bench, so as to perform durability tests on seals when the failure mechanism of the skeleton seal remains basically unchanged. The skeleton seal failure mechanism of seals refers to the failure mode caused by key components or structures in the seals under specific working environments and stresses. By loading environmental stress parameters on the test bench, the failure mechanism of the seals in the bench test is consistent with the failure mechanism of the seals under wind farm operating conditions, that is, the skeleton seal failure mechanism remains unchanged, so that the test bench accurately simulates the key environmental stresses in the wind farm operating environment.

[0084] (6) Seal failure mechanism

[0085] The failure mechanism of seals refers to the reasons that cause seals to fail and not work properly. The failure mechanism of seals mainly includes material aging and wear.

[0086] Material aging: During the use of seals, due to the long-term influence of environmental, temperature, pressure and other factors, the material may undergo physical, chemical and structural changes, resulting in performance degradation or failure. Material aging can lead to problems such as weakened elastic recovery ability, hardness changes, cracks or fractures.

[0087] Wear: When seals come into contact with other parts or media under the influence of friction, vibration and pressure, surface wear and particle peeling will occur. Wear can cause the size of the seal to change, the sealing performance to decline, and even cause leakage or failure.

[0088] These two mechanisms can be dominant alone or in combination. Which mechanism is dominant or the combination of them depends on the actual use conditions and the characteristics of the seal.

[0089] The following is an example of an application scenario of the embodiment of the present application.

[0090] In some embodiments of the present application, for a seal whose field life is to be determined, the life of the seal in a wind farm operating environment can be determined based on the life of the seal on the test bench combined with the correspondence between the life of a sample seal on the bench and the field life of the sample seal (expressed by a model). This allows the life of the seal in a wind farm operating environment to be predicted in advance, thereby reducing the probability of failure accidents or waste of resources due to unknown life.

[0091] Furthermore, under actual working conditions of wind farms, environmental stress parameters (such as rotation speed) are often unstable. For example, the speed of the wind turbine will increase when there is wind and stop when there is no wind. The wind speed will also affect the speed. This unstable environmental stress causes on-site testing to usually take a long time to detect the failure of the seal, which is too time-consuming. In addition, relying solely on on-site life test results cannot accurately predict and evaluate the life and performance of the seal in actual use.

[0092] By testing the life of seals on a test bench loaded with environmental stress parameters, the actual working environmental stress can be simulated, providing stable and continuous conditions to more accurately evaluate the life of seals. For example, the bench provides stable environmental stress parameters, such as constant speed, constant temperature, and constant medium pressure. These stable environmental stress parameters allow seals to be exposed to relatively constant working conditions during long-term testing, which is conducive to evaluating the performance and life of seals under specific environmental stresses. In addition, the test bench can simulate the working conditions on site in a relatively short time, accelerate the aging and failure process of seals, and thus evaluate the life of seals more quickly. In addition, the design and working conditions of the bench can be consistent with the boundary conditions on site (such as the minimum operating temperature and the maximum operating temperature). By simulating the on-site working conditions on the bench, the test results can be closer to the actual use and the accuracy of the prediction can be improved.

[0093] The embodiments of the present application relate to a generation process of a life prediction model for a seal and an application process of the life prediction model. Figure 1 The embodiment illustrates the generation process of the life prediction model by example. Figure 2 The embodiment illustrates the application process of the life prediction model. In order to distinguish the seals targeted by the model generation process and the seals targeted by the model application process, the seals targeted by the model generation process are described as "sample seals". Figure 1 Embodiments and appendices Figure 2 The execution subject of the embodiment may be one or more computing devices.

[0094] Attached Figure 1 Attached is a flow chart of a method for generating a life prediction model for a seal provided in an embodiment of the present application. Figure 1 The method shown includes the following steps S120 to S140.

[0095] S120, obtaining the bench life of the sample seal set and the actual field life of the sample seal set;

[0096] The sample seal set includes at least one seal that has been used in a wind farm working environment. Since the model is determined based on sample data in an actual working environment, the accuracy of model establishment and prediction results is improved.

[0097] The bench life of a sample seal is used to indicate how long the sample seal remains effective on the test bench. For example, the bench life of a sample seal is the time difference between the time the seal begins to be used on the test bench and the time the seal fails on the test bench. The bench life indicates the reliable operating time of the sample seal in a test bench environment that simulates actual working conditions, reflecting the durability and reliability of the sample seal in the test bench environment.

[0098] The test bench is used to simulate the working environment of a wind farm. For example, the test bench is deployed indoors, such as the test bench is deployed in a laboratory.

[0099] The actual field life is used to indicate how long a seal remains effective in a wind farm operating environment. For example, the actual field life of a sample seal is the time difference between the time the seal begins to be used in a wind farm operating environment and the time the seal fails in a wind farm operating environment. The actual field life indicates the reliable operating time of the sample seal in a wind farm operating environment, reflecting the durability and reliability of the sample seal in a wind farm operating environment.

[0100] In order to distinguish different sample seals in a sample seal set, “first sample seal” and “second sample seal” are used to distinguish and describe a plurality of different sample seals.

[0101] Exemplarily, the sample seal set includes a first sample seal and a second sample seal, the first sample seal and the second sample seal have the same specifications and the same batch, and the process of acquiring the life data of the sample seal set includes the following steps (1) to (2).

[0102] Step (1) performs a durability test on a first sample seal on a test bench loaded with environmental stress parameters to obtain a bench life of the first sample seal.

[0103] The environmental stress parameter includes at least one of temperature, rotation speed, processing parameter or assembly parameter. For example, the temperature includes at least one of the lowest working environment temperature of the seal or the highest working environment temperature of the seal. By obtaining the lowest working environment temperature of the seal or the highest working environment temperature of the seal, the lowest working environment temperature or the highest working environment temperature of the seal is loaded to the test bench, so that the temperature boundary value provided by the test bench is the same as the temperature boundary value provided under the wind farm working condition, so that the test bench can simulate the real working condition more accurately.

[0104] Processing parameters refer to the parameters set when processing the seal during the manufacturing process, such as size, surface hardness and roughness. For example, the processing parameters of the seal include at least one of the seal size, shaft diameter, shaft surface hardness, shaft roughness, or the coaxiality of the shaft and cavity. Assembly parameters refer to the parameters involved in assembling parts during the assembly process. For example, the assembly parameters of the seal include at least one of the pressure in the sealing cavity, shaft material, shaft eccentricity, cavity material, cavity material, cavity diameter, cavity eccentricity, or cavity roughness.

[0105] In some embodiments, through the analysis of typical failure mechanisms of seals, it is determined that the factors affecting the life of seals mainly include: temperature boundary value, especially the impact on the sealing function of seals at low temperature boundaries; rotation speed value; pressure value in the sealing cavity; shaft material and mating surface parameters (shaft diameter, surface hardness, roughness, shaft eccentricity); cavity material and mating surface parameters (cavity diameter, eccentricity, roughness); shaft cavity coaxiality, etc. Combined with the above analysis, the following table shows the actual operating condition range of the seal, and the environmental stress parameters are determined based on the following Table 1.

[0106] Table 1

[0107] Seal size (380~520)x(420~590)x(15~25) Minimum working environment temperature (℃) -10～-30 Maximum operating temperature (°C) 50～75 Given speed (rpm) 419～680 Pressure in sealing chamber (Pa) 0～250 Shaft material 42CrMo4 Shaft diameter(mm) 380～520h7 Shaft surface hardness ≥HRC45 Shaft roughness Ra0.4~0.8 Shaft eccentricity (mm) 0.05～0.1 Cavity material QT400 / 45# Cavity diameter (mm) 420～590h7 Cavity eccentricity (mm) 0.05～0.1 Cavity roughness Ra3.2 Coaxiality between shaft and cavity (mm) 0.1～0.2

[0108] Regarding the process of loading the temperature to the test bench, in one possible implementation, a device or system with a temperature control function, such as a thermostatic bath, a temperature controller, etc., is used to set the temperature to, for example, the minimum working environment temperature shown in Table 1, and the test bench is placed in the system for testing, so that the test bench provides the same minimum working environment temperature as the actual working condition of the wind farm; or, the temperature is set to, for example, the maximum working environment temperature shown in Table 1, and the test bench is placed in the system for testing, so that the test bench provides the same maximum working environment temperature as the actual working condition of the wind farm; or, the temperature is set to switch between the maximum working environment temperature shown in Table 1 and the minimum working environment temperature shown in Table 1, so that the test bench provides a cycle between the minimum working environment temperature and the maximum working environment temperature. In another possible implementation, as needed, a heating or cooling device is used to directly heat or cool the seal to achieve the minimum working environment temperature and the maximum working environment temperature. This can be achieved by means of a heating element, a cooling liquid or gas, etc. In another possible implementation, the entire test bench is placed in a closed space with a temperature control function, such as a temperature control room or box, so that the bench maintains a required minimum working environment temperature or a maximum working environment temperature.

[0109] Regarding the process of applying the rotation speed to the test bench, in a possible implementation, a motor or a driving device may be electrically connected to the test bench, and the motor or the driving device may provide a rotation speed such as shown in Table 1. By applying the rotation speed to the test bench, the test bench is continuously rotated at the rotation speed, thereby determining the life of the seal at a constant rotation speed.

[0110] Regarding the process of loading the assembly parameters to the test bench, for example, using a pressure control device or apparatus, the pressure in the sealed cavity, for example, as shown in Table 1, is loaded into the sealed cavity in the test bench, so that

[0111] The test bench can simulate the pressure in the sealing cavity under actual working conditions. For another example, the shaft material shown in Table 1 is installed in the appropriate position in the test bench. For another example, the eccentricity of the shaft is measured using appropriate measuring equipment, and corresponding adjustments and calibrations are performed to achieve the eccentricity requirements shown in Table 1.

[0112] In summary, by analyzing the influencing factors (such as temperature, rotation speed, processing parameters or assembly parameters) that seals are subjected to during service in wind farms, designing a test method for evaluating the indoor service performance of seals and establishing a test bench, loading environmental stress parameters on the test bench, so that the test bench can simulate the working conditions of the wind farm environment and reproduce the actual field conditions. Specifically, the test bench can simulate the various stresses and conditions that seals are subjected to in the actual working environment, which helps to more accurately evaluate the life of seals in actual use.

[0113] Step (2) obtains the actual field life of the second sample seal from the wind farm working environment.

[0114] In one possible implementation, based on the failure cause information of the plurality of seals, the actual field life of the sample seal set is determined from the actual field life of the plurality of seals. The failure cause information is used to indicate the failure cause of the seal. The failure cause includes material aging, wear, installation problems or product quality, etc.

[0115] In one possible implementation, in response to determining that the failure cause information of the first sample seal indicates that the first sample seal fails due to material aging or wear, the actual field life of the first sample seal is added to the actual field life of the sample seal set. Since the model is established based on the life data of the sample seal only when it is determined that the failure of the sample seal is caused by material aging or wear, it is equivalent to screening out the life data of failure caused by normal reasons (material aging or wear) from all sample life data, so that the life data more accurately reflects the influence of factors such as material aging or wear on the life of the seal, thereby improving the accuracy of the life prediction model, so that it can more truly predict the life of the seal in actual use.

[0116] In a possible implementation, in response to determining that the failure cause information of the third sample seal indicates that the failure of the third sample seal is caused by installation or product quality, the actual field life of the third sample seal is deleted from the actual field life of the sample seal set. Since the model is established based on the life data of the sample seal only when it is determined that the failure of the sample seal is caused by installation problems or wear, it is equivalent to eliminating failures caused by abnormal reasons such as installation problems or product quality problems, so that the sample data of failures caused by abnormal reasons do not need to be considered during the model establishment process, thereby improving the credibility and representativeness of the sample data, so that the sample data can more accurately reflect the actual field life of the seal under normal working conditions, and increase the reliability of the data. In addition, failures caused by abnormal factors are often unpredictable and uncontrollable, which may have an adverse effect on data analysis and model establishment. By eliminating these abnormal factors, the interference of abnormal conditions on life prediction can be reduced, making the model more accurate and reliable. In addition, eliminating failures caused by abnormal reasons can make the model more suitable for other seals under similar working conditions. By establishing a model based on normal operating conditions, the service life of other seals in actual use can be predicted more accurately, the applicability of the model can be improved, and more valuable reference results can be provided.

[0117] In one possible implementation, the shortest actual field life is selected from the actual field life of each sample seal in the sample seal set, and the shortest actual field life is used as the actual field life of the second sample seal. Considering that selecting the shortest actual field life is equivalent to adopting a relatively conservative estimation method, because a shorter life is considered to be the most unfavorable situation because it represents the possibility of failure in a shorter time. This conservative consideration helps to ensure that the reliability of the seal is more fully evaluated in actual use. In addition, by setting the actual field life to a shorter value, the risk of failure can be reduced. Specifically, a shorter life means a lower probability of failure within the time period, so selecting the shortest life as a reference can reduce potential problems and losses caused by failure. This helps to improve the reliability of the seal in the actual working environment. In addition, by selecting the shortest actual field life, a more accurate prediction result can be provided. A shorter life reflects an earlier failure that may occur in actual use, which is more important for predicting the life performance of the seal under similar working conditions, so that the reliability of the seal can be more accurately evaluated and a more reliable basis can be provided for subsequent decision-making and optimization. In addition, by setting the actual field life to a shorter value, it helps the system have sufficient margin and safety during design and operation. A shorter life can help identify potential problems and risks, so that corresponding measures can be taken to improve the reliability and safety of the system.

[0118] In another possible implementation, an average value of the actual field life of each sample seal in the sample seal set is taken, and the average value of the sample seals is used as the actual field life of the second sample seal.

[0119] S140 , generating a seal life prediction model based on the bench life of the sample seal set and the actual field life of the sample seal set.

[0120] The life prediction model can also be called a life equivalence model. The life prediction model is used to indicate the correspondence between the bench life and the predicted field life. Specifically, by analyzing the data from the wind farm operating environment and the data from the test bench in the laboratory, a model is established to associate the bench test results with the field service life. This model can be used to describe the life differences of seals in different environments, help understand the life characteristics of seals, and can quickly predict the life of seals in actual use scenarios based on the bench test results. For example, the input parameters (independent variables) of the life prediction model include the bench life of the seal, and the output parameters (dependent variables) of the life prediction model include the predicted field life of the seal.

[0121] In one possible implementation, a life prediction model is established by regression analysis. For example, the life prediction model is a regression model such as linear regression, polynomial regression or logistic regression. Model fitting is performed based on the bench life of the sample seal set and the actual field life of the sample seal set to obtain the parameters of the life prediction model. The fitting process is determined, for example, by minimizing the difference between the actual field life of the sample seal set and the predicted field life output by the model. In another possible implementation, a machine learning algorithm is used to establish a life prediction model, such as a decision tree, a support vector machine, a random forest, a neural network, etc. These machine learning algorithms can automatically discover the relationship between the bench life and the field life by training and learning the bench life of the sample seal set and the actual field life of the sample seal set, and establish a prediction model.

[0122] In a possible implementation, a comparative analysis method is used to correct the life prediction model based on the remaining life of the seal.

[0123] The remaining life of a seal refers to the length of time that the seal can continue to remain effective after a certain period of use. For example, the remaining life of a seal includes at least one of the remaining bench life of the seal or the remaining field life of the seal. The remaining field life of a seal refers to the length of time that a seal that has been used on a test bench for a certain period of time continues to remain effective after being reassembled to a wind farm operating environment. The remaining bench life of a seal refers to the length of time that a seal that has been used in a wind farm operating environment for a certain period of time continues to remain effective after being reassembled to a test bench.

[0124] In order to distinguish the models before and after correction, the model before correction is described as "initial life prediction model" and the model after correction is described as "target life prediction model". The correction process includes forward correction and reverse correction.

[0125] (1) Reverse correction process

[0126] Reverse correction refers to correcting the model based on the remaining life obtained by removing seals that have been used for a certain period of time from the wind farm and installing them on a test bench for testing.

[0127] For example, the first sample seal has been used in a wind farm operating environment for a first period of time before being assembled to the test bench. Based on the actual remaining bench life of the first sample seal and the first period of time, the parameters in the initial life prediction model are adjusted to obtain a target life prediction model. The actual remaining bench life refers to the length of time that the first sample seal remains effective during the durability test after being reassembled from the wind farm operating environment to the test bench. By using the actual remaining bench life to adjust the parameters in the initial life prediction model, the accuracy of the model is improved, allowing the model to more accurately predict the life. In addition, since the data of seals that have been used in wind farm operating environments are re-placed on the bench for testing is used, the impact of actual operating environments on seals can be better simulated, and the impact of environmental factors on seal life can be taken into account, thereby improving the authenticity and reliability of life prediction.

[0128] For example, the first time period is 10%, 30%, 50%, 70% or 90% of the predicted total field life.

[0129] In a possible implementation, the process of adjusting the model parameters based on inverse correction includes the following steps 1 to 3.

[0130] Step 1: Based on the first time length and the initial life prediction model, obtain the predicted remaining bench life of the first sample seal.

[0131] Step 2: obtaining a first deviation based on the actual remaining bench life of the first sample seal and the predicted remaining bench life of the first sample seal.

[0132] The first deviation refers to the deviation between the predicted remaining rig life and the actual remaining rig life. If the first deviation is small, it means that the model's prediction is relatively accurate. On the contrary, if the first deviation is large, it means that there is a certain error in the model's prediction. For example, the first deviation is the difference between the predicted remaining rig life and the actual remaining rig life, or the average error or the root mean square error, etc.

[0133] Step three, adjusting the parameters in the initial life prediction model based on the first deviation.

[0134] Since the parameters in the initial life prediction model are adjusted according to the first deviation, the prediction accuracy of the model can be improved, and the model parameters can be continuously optimized so that the model can better fit the corresponding relationship between the actual bench life and the field life, thereby improving the prediction ability of the seal life. This helps to more accurately evaluate the reliability and life of the seal and provide a more reliable basis for maintenance and decision-making.

[0135] Through the above steps one to three, taking into account the differences in adaptability of different seals, by analyzing the remaining life of the seals after a period of field use and returning to indoor test conditions, the life prediction model of this type of seal is corrected to make the life prediction model more accurate.

[0136] (2) Positive Correction Process

[0137] Positive correction refers to correcting the model based on the remaining life obtained after removing the seals that have been used for a certain period of time from the test bench and installing the seals on the wind farm for testing.

[0138] For example, the second sample seal has been used on the test bench for a second period of time before being assembled in the wind farm working environment. Based on the actual remaining field life of the second sample seal and the second period of time, the parameters in the initial life prediction model are adjusted to obtain a target life prediction model. The actual remaining field life refers to the effective period after the second sample seal is reassembled from the test bench to the wind farm working environment. By using the actual remaining field life to adjust the parameters in the initial life prediction model, the accuracy of the model is improved, allowing the model to more accurately predict the life. In addition, since the data of the seal that has been used under the bench is re-placed in the wind farm working environment for testing is used, the impact of the actual working environment on the seal can be better simulated, and the impact of environmental factors on the life of the seal can be taken into account, thereby improving the authenticity and reliability of the life prediction.

[0139] For example, the second time period is 10%, 30%, 50%, 70% or 90% of the predicted total field life.

[0140] In a possible implementation, the process of adjusting the model parameters based on forward correction includes the following steps 1 to 3.

[0141] Step 1: based on the second time period and the initial life prediction model, obtain the predicted remaining field life of the second sample seal;

[0142] Step 2, obtaining a second deviation based on the actual remaining field life of the second sample seal and the predicted remaining field life of the second sample seal, wherein the second deviation refers to the deviation between the predicted remaining field life and the actual remaining field life;

[0143] Step three, adjusting the parameters in the initial life prediction model based on the second deviation.

[0144] Through the above method, the remaining fatigue life of the seals that have reached the end of their service life under the test method is realized and the model is corrected.

[0145] Through the above steps one to three, taking into account the differences in adaptability of different seals, by analyzing the remaining life of the seals after returning to the field after being used for a period of time under indoor test conditions, the life prediction model of this type of seal is corrected to make the life prediction model more accurate.

[0146] The method provided in this embodiment establishes a model based on the bench life of a set of sample seals and the actual field life of the set of sample seals, so that the model can learn the correspondence between the life of the seal on the test bench and the life in the wind farm operating environment through samples. Therefore, the model can accurately predict the life of a seal under wind farm conditions for a seal with unknown life under wind farm conditions, combined with the life of the seal on the test bench.

[0147] Attached Figure 2 This is a flow chart of a method for predicting the life of a seal provided in an embodiment of the present application.

[0148] This embodiment can be optionally used for a scenario where the life of multiple seals is predicted. Figure 2 The method shown is described by taking the life prediction of the first sealing component as an example. The life prediction method of other sealing components other than the first sealing component can refer to the life prediction method of the first sealing component.

[0149] Attached Figure 2 The method shown includes the following steps S220 to S240.

[0150] S220, obtaining the bench life of the first sealing component.

[0151] The first seal is, for example, a new seal or a seal to be designed and improved. The bench life of the first seal is used to indicate the length of time the first seal remains effective on a test bench, where the test bench is used to simulate a wind farm operating environment.

[0152] In a possible implementation, environmental stress parameters are loaded onto a test bench; on the test bench loaded with the environmental stress parameters, a durability test is performed on the first sealing component to obtain the bench life of the first sealing component.

[0153] S240, obtaining a predicted field life of the first seal based on the bench life of the first seal and a life prediction model, where the predicted field life is used to indicate how long the first seal remains effective in a wind farm operating environment.

[0154] The method provided in this embodiment can accurately predict the field life of the seal based on the bench life of the seal on the test bench and the model.

[0155] Furthermore, since the predicted field life of the first seal is provided, the reliability and durability of the seal can be quantitatively evaluated. In addition, since the test bench can provide stable and continuous environmental stress and the bench life can be quickly obtained, the life of the seal in the wind farm operating environment can be predicted more quickly, providing a basis for equipment maintenance and replacement plans.

[0156] The following is an illustration of the application scenario of predicting the field life of the first seal by combining two scenarios.

[0157] Scenario 1: Reliability testing of seals

[0158] For example, based on the predicted on-site life and life index of the first seal, the reliability of the first seal is tested; for example, the predicted on-site life of the first seal is compared with the life index, and in response to the predicted on-site life of the first seal being greater than or equal to the life index, a first test result is output, and the first test result indicates that the first seal meets the life index; or, in response to the predicted on-site life of the first seal being less than the life index, a second test result is output, and the first test result is used to indicate that the first seal does not meet the life index. In the above manner, it is possible to verify whether the seal meets the life index and effectively evaluate the reliability of the seal.

[0159] Scenario 2: Evaluation of seal life test results

[0160] For example, based on the bench life of the benchmark seal and the life prediction model, the predicted field life of the benchmark seal is obtained; the predicted field life of the first seal is compared with the predicted field life of the benchmark seal to obtain a comparison result; and a life improvement report is output based on the comparison result.

[0161] The Life Improvement Report indicates the degree to which the predicted field life of the first seal has improved compared to the predicted field life of the baseline seal. Life Improvement indicates that the improvement has improved the life of the first seal relative to the baseline. The Life Improvement Report measures the life improvement by comparing the difference between the predicted life after improvement and the predicted life under the baseline.

[0162] In an exemplary embodiment, the bench life (x1) of the reference seal is input into the life prediction model to obtain the predicted field life (y1) of the reference seal; the bench life (x2) of the first seal is input into the life prediction model to obtain the predicted field life (y2) of the first seal;

[0163] By calculating the difference between the predicted field life (y2) of the first seal and the predicted field life (y1) of the reference seal (Δy=y2-y1), the value of the life improvement effect of the first seal compared to the reference seal can be obtained. A positive value indicates that the life of the first seal is improved compared to the reference seal, and a negative value indicates that the life of the first seal is reduced compared to the reference seal.

[0164] The following is an example of a specific application scenario to illustrate the above method.

[0165] In the medium-speed permanent magnet technology route, the gearbox and generator are integrated into one design, and there is no space for replacing the output shaft seal. Therefore, the reliability of the seal needs to be improved. The technical standard for the gearbox also requires that the life of the seal be no less than 10 years. In order to determine whether the life of the seal is no less than 10 years, a seal life prediction method needs to be provided.

[0166] Based on this, in some embodiments of the present application, a model is established by comparing and analyzing the life data obtained from a test bench in a laboratory with the life data obtained from a wind farm, so that the model can predict the field service life of the seal based on the indoor test data of the seal.

[0167] Specifically, when the current gearbox and power generation price are integrated designs, it is difficult to replace the rotating seal of the gearbox output shaft, and the oil seal needs to be durable and reliable. Therefore, it is necessary to establish an oil seal life prediction method to evaluate the actual service life of the seal on site. The equivalent relationship between the bench durability life and the field durability life is established through research to intuitively evaluate the service life of the seal.

[0168] In view of this, the present embodiment provides a durability evaluation method for a rotary seal whose sealing lip is an elastomer. Specifically, the environmental stress parameters of the seal under the actual working conditions of the wind farm are collected, including temperature, rotation speed, processing parameters and assembly parameters consistent with the actual working conditions of the wind farm, etc.; then the environmental stress parameters are loaded on the test bench to carry out the bench durability test of the seal; the durability life of the seal under the actual working conditions of the wind farm is collected; seals with different service times (such as 10%, 30%, 50%, 70%, 90%) are selected to perform durability tests on the seals on the test bench to obtain the remaining durability life of the seals. Or the durability test is performed on seals with different bench test times (such as 10%, 30%, 50%, 70%, 90%) to obtain the research on the remaining life on site; the correlation between the on-site durability life and the bench durability life is analyzed to establish a life prediction model; the actual service life of the seal is predicted according to the established life prediction model and the bench life of the seal.

[0169] Exemplarily, the steps of the life durability determination method are as follows:

[0170] Step (1) carries out a durability test of the seal on a test bench loaded with environmental stress parameters until the seal fails, so that the failure mechanism of the seal is consistent with the failure mechanism in the actual working conditions of the wind farm.

[0171] Step (2) collects the durability life of the seal under actual working conditions of the wind farm.

[0172] Step (3) collects seals that have been used for different lengths of time under actual working conditions in a wind farm and reinstalls them on a test bench to conduct a test bench durability test of the seals, or selects seals that have been used for different test bench times and reinstalls them in actual working conditions in a wind farm to conduct a test on the remaining life of the seals.

[0173] Step (4) is based on the equivalent relationship between the field life and the bench test life of the seal, and establishes a model between the bench durability life and the field durability life according to the results of step (3) and the results of step (1).

[0174] Step (5) quickly predicts the field durability life of the seal through the seal bench durability life test results.

[0175] For example, the process of establishing a model by applying indoor data and field data of seal life in batches at a wind farm includes the following steps.

[0176] Step a, obtain the life of each seal used in the wind farm from the actual working conditions of the wind farm, calculate the shortest life of each seal used in the wind farm, and after eliminating the data of failure due to abnormal factors, select the data with the shortest field life as the field life of the seal. Among them, abnormal failures mainly include failures caused by abnormal reasons such as seal installation problems or product quality problems. Considering that the shortest service time is more conservative in a statistical sense, the data for benchmarking analysis is more reliable, and the specification of seal failure risk is more effective.

[0177] Step b: Select seals of the same specification and batch for indoor testing. The indoor standard test needs to consider the impact of key service environment stress on the life of the seal, and obtain the indoor life of the seal through indoor test research.

[0178] Step c, based on the principle that seals of the same specification and batch have the same life under the same conditions, a data correspondence model or correspondence relationship between the field data and indoor data of the seals in this wind farm is established. The same conditions refer to the same operating conditions, including service temperature, service speed, and processing and assembly parameters consistent with the actual situation.

[0179] The method provided in this embodiment can guide the establishment of a standard bench test for oil seals, realize the prediction of the life of seals under wind farm working conditions, and fully utilize the value of seals while preventing seal failure accidents.

[0180] Figure 3 is a schematic diagram of the structure of a sealing component life prediction device 300 provided in this embodiment, the device 300 comprises:

[0181] A test bench life acquisition module 301 is used to acquire the test bench life of the first seal, where the test bench life indicates the length of time the first seal remains effective on a test bench, where the test bench is used to simulate a wind farm operating environment;

[0182] The field life prediction module 302 is used to obtain the predicted field life of the first seal based on the bench life of the first seal and a life prediction model, the predicted field life is used to indicate the length of time the first seal remains effective in the wind farm operating environment, the life prediction model is used to indicate the correspondence between the bench life and the predicted field life, the life prediction model is determined based on the bench life of a sample seal set and the actual field life of the sample seal set, the sample seal set includes at least one seal that has been applied in the wind farm operating environment.

[0183] In a possible implementation, the test bench life acquisition module 301 is used to load environmental stress parameters to the test bench; on the test bench loaded with the environmental stress parameters, perform a durability test on the first seal to obtain the test bench life of the first seal.

[0184] In a possible implementation manner, the environmental stress parameter includes at least one of temperature, rotation speed, processing parameter or assembly parameter.

[0185] In a possible implementation, the device further includes: a sample acquisition module 303, configured to acquire the bench life of the sample seal set and the actual field life of the sample seal set;

[0186] The model generation module 304 is used to generate a life prediction model for the seals based on the bench life of the sample seal set and the actual field life of the sample seal set.

[0187] In one possible implementation, the sample seal set includes a first sample seal and a second sample seal, the first sample seal and the second sample seal have the same specifications and the same batch, and the sample acquisition module 303 is used to perform a durability test on the first sample seal on a test bench loaded with the environmental stress parameters to obtain the bench life of the first sample seal; and obtain the actual field life of the second sample seal from the wind farm operating environment.

[0188] In one possible implementation, the first sample seal has been used for a first period of time in the wind farm operating environment before being assembled to the test bench, the bench life of the first sample seal includes an actual remaining bench life, the life prediction model includes an initial life prediction model and a target life prediction model, and the model generation module 304 is used to adjust the parameters in the initial life prediction model based on the actual remaining bench life of the first sample seal and the first period of time to obtain the target life prediction model, and the actual remaining bench life refers to the length of time that the first sample seal remains effective during the durability test after being reassembled from the wind farm operating environment to the test bench.

[0189] In one possible implementation, the model generation module 304 is used to obtain a predicted remaining scaffold life of the first sample seal based on the first time length and the initial life prediction model; obtain a first deviation based on the actual remaining scaffold life of the first sample seal and the predicted remaining scaffold life of the first sample seal, wherein the first deviation refers to the deviation between the predicted remaining scaffold life and the actual remaining scaffold life; and adjust the parameters in the initial life prediction model based on the first deviation.

[0190] In one possible implementation, the second sample seal has been used on the test bench for a second period of time before being assembled to the wind farm operating environment, the field life of the second sample seal includes an actual remaining field life, the life prediction model includes an initial life prediction model and a target life prediction model, and the model generation module 304 is used to adjust the parameters in the initial life prediction model based on the actual remaining field life of the second sample seal and the second period of time to obtain the target life prediction model, and the actual remaining field life refers to the effective period after the second sample seal is reassembled from the test bench to the wind farm operating environment.

[0191] In a possible implementation, the model generation module 304 is used to obtain the predicted remaining field life of the second sample seal based on the second time length and the initial life prediction model; obtain a second deviation based on the actual remaining field life of the second sample seal and the predicted remaining field life of the second sample seal, wherein the second deviation refers to the deviation of the predicted remaining field life compared to the actual remaining field life;

[0192] Parameters in the initial life prediction model are adjusted based on the second deviation.

[0193] In a possible implementation, the sample acquisition module 303 is used to determine the actual field life of the sample seal set from the actual field life of the multiple seals based on the failure cause information of the multiple seals.

[0194] In one possible implementation, the sample acquisition module 303 is used to add the actual field life of the first sample seal to the actual field life of the sample seal set in response to the failure cause information of the first sample seal indicating that the first sample seal failed due to material aging or wear; or, in response to the failure cause information of the third sample seal indicating that the third sample seal failed due to installation or product quality, delete the actual field life of the third sample seal from the actual field life of the sample seal set.

[0195] In a possible implementation, the sample acquisition module 303 is used to select the shortest actual field life from the actual field life of each sample seal in the sample seal set as the actual field life of the second sample seal.

[0196] In a possible implementation manner, the device further includes:

[0197] A reliability detection module, configured to detect the reliability of the first sealing component based on the predicted field life and life index of the first sealing component;

[0198] an output module, configured to output a first test result in response to the predicted field life of the first seal being greater than or equal to the life index, wherein the first test result indicates that the first seal meets the life index; or

[0199] In response to the predicted field life of the first seal being less than the life indicator, a second detection result is output, wherein the first detection result is used to indicate that the first seal does not meet the life indicator.

[0200] In a possible implementation, the field life prediction module 302 is further used to obtain the predicted field life of the reference seal based on the bench life of the reference seal and the life prediction model;

[0201] The device further comprises: a comparison module, configured to compare the predicted field life of the first seal with the predicted field life of the reference seal to obtain a comparison result;

[0202] An output module is configured to output a life improvement report based on the comparison result, wherein the life improvement report indicates the degree to which the predicted field life of the first seal is improved compared to the predicted field life of the reference seal.

[0203] Figure 3 The described device embodiments are merely illustrative. For example, the division of the above modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. The functional modules in the various embodiments of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The various modules in the device 300 are implemented in whole or in part by software, hardware, firmware, or any combination thereof.

[0204] Attached Figure 44 is a schematic diagram of a computing device 400 provided in an embodiment of the present application. The computing device 400 includes at least one processor 401 , a memory 402 , and at least one network interface 403 .

[0205] The processor 401 is, for example, a general-purpose central processing unit (CPU), a network processor (NP), a graphics processing unit (GPU), a neural-network processing unit (NPU), a data processing unit (DPU), a microprocessor, or one or more integrated circuits for implementing the solution of the present application. For example, the processor 401 includes an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD is, for example, a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0206] The memory 402 is, for example, a read-only memory (ROM) or other static storage device that can store static information and instructions, a random access memory (RAM) or other dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. Optionally, the memory 402 exists independently and is connected to the processor 401 through the internal connection 404. Alternatively, the memory 402 and the processor 401 are optionally integrated together.

[0207] The network interface 403 uses any transceiver-like device for communicating with other devices or communication networks. The network interface 403 includes, for example, at least one of a wired network interface or a wireless network interface. The wired network interface is, for example, an Ethernet interface. The Ethernet interface is, for example, an optical interface, an electrical interface, or a combination thereof. The wireless network interface is, for example, a wireless local area network (WLAN) interface, a cellular network interface, or a combination thereof.

[0208] In some embodiments, processor 401 includes one or more CPUs, such as Figure 4 CPU0 and CPU1 are shown in the figure.

[0209] In some embodiments, computing device 400 optionally includes multiple processors, such as Figure 4 401 and processor 405 are shown in FIG. Each of these processors is, for example, a single-CPU, or a multi-CPU. The processor herein optionally refers to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0210] In some embodiments, computing device 400 further includes internal connection 404. Processor 401, memory 402, and at least one network interface 403 are connected via internal connection 404. Internal connection 404 includes a path to transmit information between the above components. Optionally, internal connection 404 is a single board or a bus. Optionally, internal connection 404 is divided into an address bus, a data bus, a control bus, etc.

[0211] In some embodiments, computing device 400 further includes an input-output interface 406. Input-output interface 406 is connected to internal connection 404.

[0212] Optionally, the processor 401 implements the method in the above embodiment by reading the program code stored in the memory 402, or the processor 401 implements the method in the above embodiment by the program code stored internally. In the case where the processor 401 implements the method in the above embodiment by reading the program code stored in the memory 402, the memory 402 stores the program code 410 that implements the method provided in the embodiment of the present application.

[0213] For more details on how the processor 401 implements the above functions, please refer to the descriptions in the previous method embodiments, which will not be repeated here.

[0214] In some embodiments, a computer-readable storage medium is further provided, wherein the storage medium stores at least one instruction, which, when executed on a computer, causes the computer to execute Figure 1 The embodiment shown or Figure 2 At least one of the embodiments shown.

[0215] In some embodiments, a computer program product is further provided, the computer program product comprising one or more computer program instructions, which, when loaded and executed by a computer, causes the computer to execute Figure 1 The embodiment shown or Figure 2 At least one of the embodiments shown.

[0216] In some embodiments, a chip is also provided, including a memory and a processor, the memory is used to store computer instructions, and the processor is used to call and run the computer instructions from the memory to execute Figure 1 The embodiment shown or Figure 2 At least one of the embodiments shown.

[0217] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0218] A refers to B, which means that A is the same as B or A is a simple variant of B.

[0219] The terms "first" and "second" in the description and claims of the embodiments of the present application are used to distinguish different objects, rather than to describe a specific order of objects, and cannot be understood as indicating or implying relative importance. For example, the first seal and the second seal are used to distinguish different seals, rather than to describe a specific order of seals, and cannot be understood as the first seal being more important than the second seal.

[0220] In the embodiments of the present application, unless otherwise specified, "at least one" means one or more, and "a plurality" means two or more. For example, a plurality of seals means two or more seals.

[0221] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in accordance with the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.

[0222] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting the life of a seal, characterized in that: The method comprises: Acquire a test bench life of the first seal, where the test bench life is used to indicate the length of time the first seal remains effective on a test bench, where the test bench is used to simulate a wind farm operating environment; The predicted field life of the first seal is obtained based on the bench life and the life prediction model of the first seal, the predicted field life is used to indicate the length of time the first seal remains effective in the wind farm operating environment, the life prediction model is used to indicate the correspondence between the bench life and the predicted field life, the life prediction model is determined based on the bench life of a sample seal set and the actual field life of the sample seal set, the sample seal set including at least one seal that has been applied in the wind farm operating environment.

2. The method according to claim 1, characterized in that The step of obtaining the bench life of the first sealing component comprises: loading environmental stress parameters to the test bench; On a test bench loaded with the environmental stress parameters, a durability test is performed on the first sealing component to obtain a test bench life of the first sealing component.

3. The method according to claim 2, characterized in that The environmental stress parameter includes at least one of temperature, rotation speed, processing parameter or assembly parameter.

4. The method according to any one of claims 1 to 3, characterized in that Before obtaining the predicted field life of the first seal based on the bench life and the life prediction model of the first seal, the method further includes: Obtaining a bench life of the sample seal set and an actual field life of the sample seal set; A life prediction model for the seals is generated based on the bench life of the sample seal set and the actual field life of the sample seal set.

5. The method according to claim 4, characterized in that The sample seal set includes a first sample seal and a second sample seal, the first sample seal and the second sample seal have the same specification and the same batch, and obtaining the bench life of the sample seal set and the actual field life of the sample seal set includes: Performing a durability test on the first sample seal on a test bench loaded with the environmental stress parameter to obtain a bench life of the first sample seal; The actual field life of the second sample seal is obtained from the wind farm working environment.

6. The method according to claim 5, characterized in that The first sample seal has been used for a first time in the wind farm working environment before being assembled to the test bench, the bench life of the first sample seal includes an actual remaining bench life, the life prediction model includes an initial life prediction model and a target life prediction model, and the life prediction model of the seal is determined based on the bench life of the sample seal set and the actual field life of the sample seal set, including: The parameters in the initial life prediction model are adjusted based on the actual remaining bench life of the first sample seal and the first duration to obtain the target life prediction model. The actual remaining bench life refers to the duration for which the first sample seal remains effective during the durability test after being reassembled from the wind farm operating environment to the test bench.

7. The method according to claim 6, characterized in that The adjusting the parameters in the initial life prediction model based on the actual remaining bench life of the first sample seal and the first time period comprises: Based on the first time period and the initial life prediction model, obtaining a predicted remaining bench life of the first sample seal; Obtaining a first deviation based on an actual remaining bench life of the first sample seal and a predicted remaining bench life of the first sample seal, wherein the first deviation refers to a deviation between the predicted remaining bench life and the actual remaining bench life; Parameters in the initial life prediction model are adjusted based on the first deviation.

8. The method according to claim 5, characterized in that The second sample seal has been used for a second time period on the test bench before being assembled in the wind farm working environment, the field life of the second sample seal includes an actual remaining field life, the life prediction model includes an initial life prediction model and a target life prediction model, and the life prediction model of the seal is determined based on the field life of the sample seal set and the actual field life of the sample seal set, including: Based on the actual remaining field life of the second sample seal and the second duration, the parameters in the initial life prediction model are adjusted to obtain the target life prediction model. The actual remaining field life refers to the effective duration after the second sample seal is reassembled from the test bench to the wind farm operating environment.

9. The method according to claim 6, characterized in that The adjusting the parameters in the initial life prediction model based on the actual remaining field life of the second sample seal and the second time period includes: Based on the second time period and the initial life prediction model, obtaining a predicted remaining field life of the second sample seal; Obtaining a second deviation based on the actual remaining field life of the second sample seal and the predicted remaining field life of the second sample seal, wherein the second deviation refers to a deviation between the predicted remaining field life and the actual remaining field life; Parameters in the initial life prediction model are adjusted based on the second deviation.

10. The method according to claim 4, characterized in that The obtaining of the bench life of the sample seal set and the actual field life of the sample seal set comprises: Based on the failure cause information of the plurality of seals, the actual field life of the sample seal set is determined from the actual field life of the plurality of seals.

11. The method according to claim 10, characterized in that The determining the actual field life of the sample seal set from the actual field life of the plurality of seals based on the failure cause information of the plurality of seals comprises: In response to the failure cause information of the first sample seal indicating that the first sample seal failed due to material aging or wear, adding the actual field life of the first sample seal to the actual field life of the sample seal set; or, In response to the failure reason information of the third sample seal indicating that the third sample seal fails due to installation or product quality, the actual field life of the third sample seal is deleted from the actual field life of the sample seal set.

12. The method according to claim 5, characterized in that The obtaining the actual field life of the second sample seal from the wind farm working environment comprises: From the actual field life of each sample seal in the set of sample seals, the shortest actual field life is selected as the actual field life of the second sample seal.

13. The method according to any one of claims 1 to 12, characterized in that After obtaining the predicted field life of the first seal based on the bench life and the life prediction model of the first seal, the method further includes: Based on the predicted field life and life index of the first sealing component, testing the reliability of the first sealing component; In response to the predicted field life of the first seal being greater than or equal to the life index, outputting a first test result, the first test result indicating that the first seal meets the life index; or, In response to the predicted field life of the first seal being less than the life indicator, a second detection result is output, wherein the first detection result is used to indicate that the first seal does not meet the life indicator.

14. The method according to any one of claims 1 to 13, characterized in that The method further comprises: Obtaining a predicted field life of the reference seal based on the bench life of the reference seal and a life prediction model; comparing the predicted field life of the first seal with the predicted field life of the reference seal to obtain a comparison result; A life improveability report is output based on the comparison result, the life improveability report indicating the extent to which the predicted field life of the first seal is improved compared to the predicted field life of the baseline seal.

15. A sealing component life prediction device, characterized in that: The device comprises: A test bench life acquisition module, used to acquire the test bench life of the first seal, where the test bench life is used to indicate the length of time the first seal remains effective on a test bench, where the test bench is used to simulate a wind farm operating environment; A field life prediction module is used to obtain the predicted field life of the first seal based on the bench life of the first seal and a life prediction model, the predicted field life is used to indicate the length of time the first seal remains effective in the wind farm operating environment, the life prediction model is used to indicate the correspondence between the bench life and the predicted field life, the life prediction model is determined based on the bench life of a sample seal set and the actual field life of the sample seal set, the sample seal set includes at least one seal that has been applied in the wind farm operating environment.

16. A computing device, characterized in that The computing device comprises: a processor, the processor is coupled to a memory, the memory stores at least one computer program instruction, and the at least one computer program instruction is loaded and executed by the processor so that the computing device implements the method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, and when the instruction is executed on a computer, the computer executes the method according to any one of claims 1 to 14.

Images