A method, device, and equipment for early warning monitoring of wind turbine bearing temperature.

Abstract

This invention provides a method, apparatus, and device for early warning monitoring of wind turbine bearing temperature, relating to the field of wind turbines. The method includes: acquiring operating temperature data and operating environment parameters of the wind turbine bearing; filtering operating temperature influencing factors in the operating environment parameters based on the operating temperature data to determine target influencing factors; performing feature transformation processing on each target influencing factor to obtain a first lag feature parameter corresponding to the target influencing factor; performing feature transformation processing on the operating temperature data to obtain a second lag feature parameter corresponding to the operating temperature data; fusing the first lag feature parameter and the second lag feature parameter to determine a target temperature; performing early warning monitoring based on the target temperature and outputting early warning parameters. This invention achieves accurate monitoring and early warning of wind turbine bearing temperature.

Description

Technical Field

[0001] This invention relates to the field of wind turbines, and more specifically to a method, device, and equipment for early warning monitoring of wind turbine bearing temperature. Background Technology

[0002] With the rapid development of wind power technology, wind turbines, as key equipment in the renewable energy field, directly affect power generation efficiency and maintenance costs due to their operational stability and reliability. As one of the core components of a wind turbine, the motor bearing endures complex alternating loads and harsh environmental conditions for extended periods. It is prone to abnormal temperature increases due to friction, fatigue, and poor lubrication, leading to bearing failure and even turbine shutdown. Statistics show that bearing failures account for over 30% of wind turbine failures, and abnormal temperature is one of the main early signs of bearing failure. Therefore, real-time monitoring and accurate early warning of motor bearing temperature are crucial for preventing sudden failures and reducing maintenance costs. Currently, wind... Wind turbine bearing temperature monitoring primarily relies on a fixed threshold alarm mechanism, where an alarm is triggered when the bearing temperature exceeds a preset threshold. However, this method has significant limitations: First, wind turbine operating conditions are complex and variable (such as wind speed fluctuations, load changes, and ambient temperature differences), making it difficult for fixed thresholds to adapt to dynamic conditions and prone to false alarms or missed alarms. Second, traditional systems typically alarm individually for each measuring point, lacking comprehensive analysis of the correlation between multiple measuring points, which may increase the burden on maintenance personnel due to frequent alarms. Furthermore, existing technologies lack the ability to analyze temperature data trends and provide early warnings, often triggering alarms only when a fault has already occurred or is nearing failure, making it difficult to provide sufficient response time for preventative maintenance. Summary of the Invention

[0003] This invention provides a method, device, and equipment for early warning monitoring of wind turbine bearing temperature, which solves the problems of low monitoring accuracy and difficulty in adapting to dynamic operating conditions, which can easily lead to false alarms or missed alarms in existing wind turbine bearing temperature monitoring.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0005] Embodiments of the present invention provide a method for early warning monitoring of wind turbine bearing temperature, comprising:

[0006] The operating temperature data and operating environment parameters of the wind turbine bearing are obtained, including multiple operating temperature influencing factors.

[0007] Based on the operating temperature data, the operating temperature influencing factors in the operating environment parameters are screened to determine the target influencing factors;

[0008] Each of the target impact factors is subjected to feature transformation processing to obtain the first lag feature parameter corresponding to the target impact factor;

[0009] The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data;

[0010] The first hysteresis characteristic parameter and the second hysteresis characteristic parameter are fused to determine the target temperature;

[0011] The system performs early warning monitoring based on the target temperature and outputs early warning parameters.

[0012] Optionally, based on the operating temperature data, the operating temperature influencing factors in the operating environment parameters are screened to determine the target influencing factors, including:

[0013] Based on the operating temperature data, through The operating environment parameters are filtered to determine the correlation coefficient ρX,Y(t) corresponding to each operating temperature influencing factor; where X represents the current operating temperature influencing factor; X i This represents the parameter value corresponding to the current operating temperature influence factor at time i. Y represents the average value of the parameter values ​​of the current operating temperature influencing factors over a time period t; t is the operating time period of the wind turbine; Y represents the operating temperature data; Y i This represents the temperature value corresponding to the running temperature data at time i. The average parameter value of the current operating temperature data over a time period t; w is the window width, taken as 24h;

[0014] The target influencing factor is determined based on the correlation coefficient values ​​and preset values.

[0015] Optionally, feature transformation processing is performed on each of the target impact factors to obtain the first lag feature parameter corresponding to the target impact factor, including:

[0016] pass For each of the target impact factors, feature transformation is performed to obtain the first lag feature parameter X corresponding to the target impact factor. eff (t1); where τ is the lag step size; t represents the operating time of the wind turbine; X1(t-τ) represents the original observation value of the current target influence factor at time point t1-τ; ωX1(τ) represents the weight coefficient of the target influence factor at lag time τ.

[0017] Optionally, feature transformation processing is performed on the operating temperature data to obtain a second hysteresis feature parameter corresponding to the operating temperature data, including:

[0018] pass The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data. Among them, T bearing This represents the operating temperature data; λ represents the inertia of the control baseline update, which is set to 0.95.

[0019] Optionally, the first hysteresis characteristic parameter and the second hysteresis characteristic parameter are fused to determine the target temperature, including:

[0020] The operating status of the wind turbine is segmented to obtain multiple operating conditions, and the corresponding preset operating condition parameters for each operating condition are determined.

[0021] The target temperature is determined by fusing the preset operating condition parameters corresponding to the current operating condition of the wind turbine with the first hysteresis characteristic parameter and the second hysteresis characteristic parameter.

[0022] Optionally, the preset operating condition parameters corresponding to the current operating condition of the wind turbine are fused with the first hysteresis characteristic parameter and the second hysteresis characteristic parameter to determine the target temperature, including:

[0023] Through formula The preset operating condition parameters corresponding to the current operating condition of the wind turbine are fused with the first and second hysteresis characteristic parameters to determine the target temperature T. threshold Wherein, λ1 represents the first preset parameter, and λ2 represents the second preset parameter. X represents the second hysteresis characteristic parameter; eff (1) represents the first hysteresis characteristic parameter.

[0024] Optionally, early warning monitoring is performed based on the target temperature, and early warning parameters are output, including:

[0025] The alarm difference is determined based on the target temperature and operating temperature data.

[0026] Based on the alarm difference, the corresponding early warning parameters are output.

[0027] Embodiments of the present invention also provide an early warning monitoring device for wind turbine bearing temperature, comprising:

[0028] The acquisition module is used to acquire the operating temperature data and operating environment parameters of the wind turbine bearing, including multiple operating temperature influencing factors.

[0029] The processing module is used to: filter the operating temperature influencing factors in the operating environment parameters based on the operating temperature data to determine the target influencing factors; perform feature transformation processing on each target influencing factor to obtain the first lag feature parameter corresponding to the target influencing factor; perform feature transformation processing on the operating temperature data to obtain the second lag feature parameter corresponding to the operating temperature data; perform fusion processing on the first lag feature parameter and the second lag feature parameter to determine the target temperature; perform early warning monitoring based on the target temperature and output early warning parameters.

[0030] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program is executed by the processor to perform the above-described method.

[0031] Embodiments of the present invention also provide a computer-readable storage medium, comprising: storage instructions that, when executed on a computer, cause the computer to perform the above-described method.

[0032] The above-described solution of the present invention has at least the following beneficial effects:

[0033] The wind turbine bearing temperature early warning monitoring method of the present invention includes: acquiring operating temperature data and operating environment parameters of the wind turbine bearing, wherein the operating environment parameters include multiple operating temperature influencing factors; filtering the operating temperature influencing factors in the operating environment parameters based on the operating temperature data to determine target influencing factors; performing feature transformation processing on each target influencing factor to obtain a first lag feature parameter corresponding to the target influencing factor; performing feature transformation processing on the operating temperature data to obtain a second lag feature parameter corresponding to the operating temperature data; fusing the first lag feature parameter and the second lag feature parameter to determine a target temperature; performing early warning monitoring based on the target temperature and outputting early warning parameters. This method achieves accurate monitoring and early warning of wind turbine bearing temperature, ensuring the long-term normal operation of the wind turbine and reducing the maintenance costs associated with wind turbine overheating. Attached Figure Description

[0034] Figure 1 This is a flowchart illustrating the early warning monitoring method for wind turbine bearing temperature according to the present invention.

[0035] Figure 2 This is a schematic diagram of the module block of the wind turbine bearing temperature early warning monitoring device of the present invention. Detailed Implementation

[0036] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0037] like Figure 1 As shown, an embodiment of the present invention proposes an early warning monitoring method for wind turbine bearing temperature, comprising:

[0038] Step 11: Obtain the operating temperature data and operating environment parameters of the wind turbine bearing, wherein the operating environment parameters include multiple operating temperature influencing factors;

[0039] Step 12: Based on the operating temperature data, filter the operating temperature influencing factors in the operating environment parameters to determine the target influencing factors;

[0040] Step 13: Perform feature transformation processing on each of the target impact factors to obtain the first lag feature parameter corresponding to the target impact factor;

[0041] Step 14: Perform feature transformation processing on the operating temperature data to obtain the second hysteresis feature parameter corresponding to the operating temperature data;

[0042] Step 15: Perform fusion processing on the first hysteresis characteristic parameter and the second hysteresis characteristic parameter to determine the target temperature;

[0043] Step 16: Perform early warning monitoring based on the target temperature and output early warning parameters.

[0044] In this embodiment, the operating temperature data can be collected in real time by temperature sensors installed on the wind turbine bearings. The operating environment parameters include environmental parameters, operating parameters, and control parameters. Each parameter includes multiple operating temperature influencing factors. The environmental parameters only include natural conditions or uncontrollable physical quantities, including operating temperature influencing factors such as ambient temperature, wind speed, wind direction, nacelle temperature, and nacelle humidity. The operating parameters cover all monitoring data reflecting the health status of the equipment, including operating temperature influencing factors such as bearing temperature (multiple measuring points), motor current, speed, main shaft load, winding temperature, grid-side voltage, and active power. The control parameters are variables that are explicitly adjusted or fed back by the control system, including operating temperature influencing factors such as pitch angle, windward angle, yaw position, and yaw rate.

[0045] In this embodiment, the wind turbine bearing temperature early warning monitoring method combines the operating temperature data of the wind turbine bearing itself with externally influenced temperature data to construct a dynamic threshold model for bearing temperature. This model is then used to provide early warnings, solving the problems of low monitoring accuracy and difficulty in adapting to dynamic operating conditions, which can easily lead to false alarms or missed alarms in existing wind turbine bearing temperature monitoring systems. This method achieves accurate monitoring and early warning of wind turbine bearing temperature, and accurately and promptly diagnoses main shaft faults. This is crucial for ensuring the reliable operation of wind turbine generators, improving power generation efficiency, and reducing operation and maintenance costs. Effective diagnosis of main shaft faults allows for the early detection of potential problems, enabling appropriate maintenance measures to prevent further deterioration, extend the service life of the main shaft, and improve the overall performance and economic benefits of the wind power generation system.

[0046] In an optional embodiment of the present invention, step 12 may include:

[0047] Based on the operating temperature data, the operating temperature influencing factors in the operating environment parameters are screened to determine the target influencing factors, including:

[0048] Step 121, based on the operating temperature data, through... The operating environment parameters are filtered to determine the correlation coefficient ρX,Y(t) corresponding to each operating temperature influencing factor; where X represents the current operating temperature influencing factor; X i This represents the parameter value corresponding to the current operating temperature influence factor at time i. Y represents the average value of the parameter values ​​of the current operating temperature influencing factors over a time period t; t is the operating time period of the wind turbine; Y represents the operating temperature data; Y i This represents the temperature value corresponding to the running temperature data at time i. The average value of the parameter over the current operating temperature data within the time period t; w is the window width, set to 24h (matching the day-night temperature cycle);

[0049] Step 122: Determine the target influencing factor based on the correlation coefficient value and the preset value.

[0050] In this embodiment, the motor bearing temperature is affected by various factors (such as load, speed, ambient temperature, lubrication status, etc.), but not all factors play a decisive role in temperature change. The purpose of screening key indicators is to: reduce data dimensionality: remove redundant or irrelevant variables and reduce noise interference; improve model efficiency: in the prediction or diagnostic model, only variables that have a significant impact on temperature are retained to improve calculation speed and accuracy; the target influencing factors include: wind speed influencing factor and ambient temperature influencing factor; wherein, step 122 specifically involves setting the preset value of the ambient temperature influencing factor to 0.62 and the preset value of the wind speed influencing factor to 0.41. Based on the preset value corresponding to each indicator, the current operating temperature influencing factor is judged, and the indicators that are greater than the preset value are output as the target influencing factors; in a preferred embodiment, step 122 further includes: performing a dynamic update mechanism: when the ambient temperature changes abruptly ΔTamb>5℃ / h, an immediate recalculation of correlation is triggered.

[0051] In an optional embodiment of the present invention, step 13 may include:

[0052] pass For each of the target impact factors, feature transformation is performed to obtain the first lag feature parameter X corresponding to the target impact factor. eff (t1); where τ is the lag step size; t represents the operating time of the wind turbine; X1(t-τ) represents the original observation value of the current target influence factor at time point t-τ; ωX1(τ) represents the weight coefficient of the target influence factor at lag time τ.

[0053] In this embodiment, wind speed and ambient temperature are used as target influencing factors for illustration. When the target influencing factor is ambient temperature, the lag step τ is first determined, which is the time difference τ required for the ambient temperature change to be transmitted to the bearing = 2-6 hours; then, the weighting coefficient ω(τ) = e is determined based on the lag step. -0.5∣τ-4∣ Finally, the first lag characteristic parameter corresponding to the environmental temperature influence factor is determined according to the formula. T amb This represents the original observed value of the current environmental temperature influence factor at time point t-τ; similarly, for the wind speed influence factor, the lag step τ = 0-1h; the weighting coefficient is taken as 1-0.8τ; and the first lag characteristic parameter corresponding to the wind speed influence factor.

[0054] In an optional embodiment of the present invention, step 14 may include:

[0055] pass The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data. Among them, T bearing This represents the operating temperature data; λ represents the inertia of the control baseline update, which is set to 0.95. This indicates the temperature baseline.

[0056] In this embodiment, the The temperature baseline indicates the filter's healthy operating condition and refers to temperature fluctuations caused by non-malfunctions (such as sudden changes in wind speed, transient frictional heat, etc.). This value can be set as needed; T bearing This refers to the raw signal (including noise and short-term fluctuations) collected by the temperature sensor; in addition, λ = 0.95 represents the inertia of the control baseline update: 95% weight is given to the historical baseline (to maintain stability) and 5% to the new data (to adapt to slow changes).

[0057] In an optional embodiment of the present invention, step 15 may include:

[0058] Step 151: The operating status of the wind turbine is segmented to obtain multiple operating conditions, and the corresponding preset operating condition parameters for each operating condition are determined.

[0059] Step 152: The preset operating condition parameters corresponding to the current operating condition of the wind turbine are fused with the first hysteresis characteristic parameter and the second hysteresis characteristic parameter to determine the target temperature.

[0060] In this embodiment, the operating status of the wind power equipment is dynamically adjusted according to wind speed changes and control objectives (such as power maximization, equipment protection, etc.). By setting reasonable thresholds or rules, the continuous operation process can be divided into discrete typical operating conditions. For example, the operating status of the wind turbine can be divided into four conditions: shutdown, power curtailment, full power generation, and ramping. For the shutdown condition, the triggering condition is: blade angle > 30° (feather protection). This means that the wind turbine stops generating electricity, and the blades are adjusted to the feather position to reduce wind load. It is usually triggered due to excessively high wind speed, fault, or maintenance needs. Typical characteristics: active power is close to 0, and the wind speed may be high (such as exceeding the cut-off wind speed). Power curtailment condition: triggering condition... Item: Blade angle is moderate (3°~30°) but power is below the threshold (e.g., <6000kW); Meaning: Power generation is artificially limited (e.g., grid dispatch requires load reduction, equipment noise reduction, or maintenance needs); Typical characteristics: Power is actively limited, wind speed is sufficient but power generation does not reach the theoretical maximum value; Full-power operation: Triggering condition: Power is close to the rated value (e.g., >9900kW); Meaning: The wind turbine operates at rated power, wind speed reaches or exceeds the rated wind speed, and blade angle and rotation speed are in optimal condition; Typical characteristics: Power is stable near the rated value, wind speed is relatively high (e.g., 12~25m / s); Climbing operation: Triggering condition: None of the above conditions are reached (initial default state).

[0061] In an optional embodiment of the present invention, step 152 may include:

[0062] Through formula The preset operating condition parameters corresponding to the current operating condition of the wind turbine are fused with the first and second hysteresis characteristic parameters to determine the target temperature T. threshold Wherein, λ1 represents the first preset parameter, and λ2 represents the second preset parameter. X represents the second hysteresis characteristic parameter; eff (t) represents the first lag characteristic parameter.

[0063] In this embodiment, a prediction model is established for each wind turbine's operating condition based on preset operating condition parameters for each operating condition. This enables precise fusion of the first and second hysteresis characteristic parameters under different operating conditions, resulting in a more accurate target temperature. Specifically, for example, when the target influencing factors are wind speed and ambient temperature, assuming the preset operating condition parameters for the shutdown condition are 0.7, 0.2, and 0.1, the target temperature under the shutdown condition is... in, This is the first lag characteristic parameter corresponding to the environmental temperature influencing factor; This is the first lag characteristic parameter corresponding to the wind speed influence factor; This refers to the second hysteresis characteristic parameter corresponding to the operating temperature data; assuming the preset operating parameters corresponding to full-load operation are 0.6, 0.3, and 0.1, then the target temperature under full-load operation is... This involves determining multiple prediction models based on different operating conditions. The process first involves judging the operating conditions, and then using the corresponding operating condition model to determine the temperature, thereby further ensuring the accuracy of the temperature results.

[0064] In an optional embodiment of the present invention, step 16 may include:

[0065] Step 161: Determine the alarm difference based on the target temperature and operating temperature data;

[0066] Step 162: Output the corresponding early warning parameters based on the alarm difference.

[0067] In this embodiment, step 161 can specifically be achieved by using ΔT = |T bearing -T threshold | Determine the alarm difference ΔT; where T bearing For operating temperature data, T thresholdThe target temperature is set; step 162 specifically involves presetting early warning conditions, such as a three-level alarm logic: a wind power monitoring system defines: Level 1 warning: ΔT>5℃ for 10 minutes → log recording; Level 2 alarm: for 30 minutes → triggering a maintenance work order; Level 3 emergency shutdown: for 60 minutes and ΔT>8℃ → forced shutdown protection; dynamic threshold adjustment: in extreme environments (such as typhoons, extreme cold), the threshold can be temporarily relaxed by 2℃ to avoid false alarms caused by sudden environmental changes. Based on the alarm difference and preset conditions, the corresponding early warning parameters are output.

[0068] The wind turbine bearing temperature early warning monitoring method of the present invention establishes a typical operating condition feature library by segmenting the wind turbine's operating status, constructs a dynamic threshold model for bearing temperature by combining environmental parameters and equipment operating parameters, and finally achieves alarm merging optimization through multi-point anomaly correlation analysis. This realizes accurate monitoring and early warning of wind turbine bearing temperature, ensures the long-term normal operation of wind turbines, and reduces the maintenance cost of wind turbine overheating.

[0069] like Figure 2 As shown, an embodiment of the present invention also provides an early warning monitoring device 20 for wind turbine bearing temperature, comprising:

[0070] The acquisition module 21 is used to acquire the operating temperature data and operating environment parameters of the wind turbine bearing, wherein the operating environment parameters include multiple operating temperature influencing factors;

[0071] The processing module 22 is used to: filter the operating temperature influencing factors in the operating environment parameters based on the operating temperature data to determine the target influencing factors; perform feature transformation processing on each target influencing factor to obtain the first lag feature parameter corresponding to the target influencing factor; perform feature transformation processing on the operating temperature data to obtain the second lag feature parameter corresponding to the operating temperature data; perform fusion processing on the first lag feature parameter and the second lag feature parameter to determine the target temperature; perform early warning monitoring based on the target temperature and output early warning parameters.

[0072] Optionally, based on the operating temperature data, the operating temperature influencing factors in the operating environment parameters are screened to determine the target influencing factors, including:

[0073] Based on the operating temperature data, through The operating environment parameters are filtered to determine the correlation coefficient ρX,Y(t) corresponding to each operating temperature influencing factor; where X represents the current operating temperature influencing factor; X i This represents the parameter value corresponding to the current operating temperature influence factor at time i. Y represents the average value of the parameter values ​​of the current operating temperature influencing factors over a time period t; t is the operating time period of the wind turbine; Y represents the operating temperature data; Y i This represents the temperature value corresponding to the running temperature data at time i. The average parameter value of the current operating temperature data over a time period t; w is the window width, taken as 24h;

[0074] The target influencing factor is determined based on the correlation coefficient values ​​and preset values.

[0075] Optionally, feature transformation processing is performed on each of the target impact factors to obtain the first lag feature parameter corresponding to the target impact factor, including:

[0076] pass For each of the target impact factors, feature transformation is performed to obtain the first lag feature parameter X corresponding to the target impact factor. eff (t1); where τ is the lag step size; t represents the operating time of the wind turbine; X1(t-τ) represents the original observation value of the current target influence factor at time point t1-τ; ωX1(τ) represents the weight coefficient of the target influence factor at lag time τ.

[0077] Optionally, feature transformation processing is performed on the operating temperature data to obtain a second hysteresis feature parameter corresponding to the operating temperature data, including:

[0078] pass The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data. Among them, T bearing This represents the operating temperature data; λ represents the inertia of the control baseline update, which is set to 0.95.

[0079] Optionally, the first hysteresis characteristic parameter and the second hysteresis characteristic parameter are fused to determine the target temperature, including:

[0080] The operating status of the wind turbine is segmented to obtain multiple operating conditions, and the corresponding preset operating condition parameters for each operating condition are determined.

[0081] The target temperature is determined by fusing the preset operating condition parameters corresponding to the current operating condition of the wind turbine with the first hysteresis characteristic parameter and the second hysteresis characteristic parameter.

[0082] Optionally, the preset operating condition parameters corresponding to the current operating condition of the wind turbine are fused with the first hysteresis characteristic parameter and the second hysteresis characteristic parameter to determine the target temperature, including:

[0083] Through formula The preset operating condition parameters corresponding to the current operating condition of the wind turbine are fused with the first and second hysteresis characteristic parameters to determine the target temperature T. threshold Wherein, λ1 represents the first preset parameter, and λ2 represents the second preset parameter. X represents the second hysteresis characteristic parameter; eff (1) represents the first hysteresis characteristic parameter.

[0084] Optionally, early warning monitoring is performed based on the target temperature, and early warning parameters are output, including:

[0085] The alarm difference is determined based on the target temperature and operating temperature data.

[0086] Based on the alarm difference, the corresponding early warning parameters are output.

[0087] It should be noted that this device is the same as the method described above. All implementations of the method described above are applicable to the embodiments of this device and can achieve the same technical effect.

[0088] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the above-described method. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0089] Embodiments of the present invention also provide a computer-readable storage medium, comprising: stored instructions, which, when executed on a computer, cause the computer to perform the above-described method. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0090] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0091] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0092] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0095] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0096] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above-described series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0097] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code for implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps for performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0098] The above are preferred embodiments of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for early warning monitoring of wind turbine bearing temperature, characterized in that, include: The operating temperature data and operating environment parameters of the wind turbine bearing are obtained, including multiple operating temperature influencing factors. Based on the operating temperature data, the operating temperature influencing factors in the operating environment parameters are screened to determine the target influencing factors; Each of the target impact factors is subjected to feature transformation processing to obtain the first lag feature parameter corresponding to the target impact factor; The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data; The first hysteresis characteristic parameter and the second hysteresis characteristic parameter are fused to determine the target temperature; Based on the target temperature, early warning monitoring is performed, and early warning parameters are output; Specifically, feature transformation processing is performed on each of the target impact factors to obtain the first lag feature parameter corresponding to the target impact factor, including: pass For each of the target impact factors, feature transformation processing is performed to obtain the first lag feature parameter corresponding to the target impact factor. ;in, X1(t) represents the lag step size; t represents the operating time of the wind turbine; τ) represents the current target influencing factor at time point t. The original observed value of τ; ωX1(τ) represents the weighting coefficient of the target influence factor at the lag time τ; The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data, including: pass The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data. ;in, This represents the operating temperature data; λ represents the inertia of the control baseline update, which is set to 0.

95. Indicates the temperature baseline.

2. The method for early warning monitoring of wind turbine bearing temperature according to claim 1, characterized in that, Based on the operating temperature data, the operating temperature influencing factors in the operating environment parameters are screened to determine the target influencing factors, including: Based on the operating temperature data, through The operating environment parameters are filtered to determine the correlation coefficient value corresponding to each operating temperature influencing factor. Where X represents the current operating temperature influence factor; This represents the parameter value corresponding to the current operating temperature influence factor at time i. Y represents the average value of the parameter values ​​of the current operating temperature influencing factors over a time period t; t is the operating time period of the wind turbine; Y represents the operating temperature data. This represents the temperature value corresponding to the running temperature data at time i. The average parameter value of the current operating temperature data over a time period t; w is the window width, taken as 24h; The target influencing factor is determined based on the correlation coefficient values ​​and preset values.

3. The method for early warning monitoring of wind turbine bearing temperature according to claim 1, characterized in that, The target temperature is determined by fusing the first hysteresis characteristic parameter and the second hysteresis characteristic parameter, including: The operating status of the wind turbine is segmented to obtain multiple operating conditions, and the corresponding preset operating condition parameters for each operating condition are determined. The target temperature is determined by fusing the preset operating condition parameters corresponding to the current operating condition of the wind turbine with the first hysteresis characteristic parameter and the second hysteresis characteristic parameter.

4. The method for early warning monitoring of wind turbine bearing temperature according to claim 1, characterized in that, The target temperature is determined by fusing the preset operating condition parameters corresponding to the current operating condition of the wind turbine with the first and second hysteresis characteristic parameters, including: Through formula The target temperature is determined by fusing the preset operating parameters corresponding to the current operating condition of the wind turbine with the first and second hysteresis characteristic parameters. Wherein, λ1 represents the first preset parameter, and λ2 represents the second preset parameter. This represents the second hysteresis characteristic parameter; This represents the first hysteresis characteristic parameter.

5. The method for early warning monitoring of wind turbine bearing temperature according to claim 1, characterized in that, Based on the target temperature, early warning monitoring is performed, and early warning parameters are output, including: The alarm difference is determined based on the target temperature and operating temperature data. Based on the alarm difference, the corresponding early warning parameters are output.

6. A wind turbine bearing temperature early warning monitoring device, characterized in that, include: The acquisition module is used to acquire the operating temperature data and operating environment parameters of the wind turbine bearing, including multiple operating temperature influencing factors. The processing module is used to: filter the operating temperature influencing factors in the operating environment parameters based on the operating temperature data to determine target influencing factors; perform feature transformation processing on each target influencing factor to obtain a first lag feature parameter corresponding to the target influencing factor; perform feature transformation processing on the operating temperature data to obtain a second lag feature parameter corresponding to the operating temperature data; perform fusion processing on the first lag feature parameter and the second lag feature parameter to determine the target temperature; and perform early warning monitoring based on the target temperature and output early warning parameters. Specifically, feature transformation processing is performed on each of the target impact factors to obtain the first lag feature parameter corresponding to the target impact factor, including: pass For each of the target impact factors, feature transformation processing is performed to obtain the first lag feature parameter corresponding to the target impact factor. ;in, X1(t) represents the lag step size; t represents the operating time of the wind turbine; τ) represents the current target influencing factor at time point t. The original observed value of τ; ωX1(τ) represents the weighting coefficient of the target influence factor at the lag time τ; The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data, including: pass The operating temperature data is subjected to feature transformation processing to obtain the second hysteresis feature parameter corresponding to the operating temperature data. ;in, This represents the operating temperature data; λ represents the inertia of the control baseline update, which is set to 0.

95. Indicates the temperature baseline.

7. A computing device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A storage instruction that, when executed on a computer, causes the computer to perform the method as described in any one of claims 1 to 5.

Images