Method and system for predicting service life of mechanical vulnerable part of wind driven generator

Abstract

The invention relates to the technical field of wind driven generators, and discloses a life prediction method and system for a mechanical vulnerable part of a wind driven generator, and the method comprises the steps: obtaining a life influence factor corresponding to the mechanical vulnerable part, and determining a target life influence factor based on a life influence value model; analyzing the target life influence factor, and calculating a single influence factor and a comprehensive influence factor; calculating a target life influence factor of the mechanical vulnerable part based on the unicity influence factor and the comprehensive influence factor; historical maintenance records are collected, and historical maintenance factors of the mechanical quick-wear parts are calculated according to the historical maintenance records; according to the target life influence factor and the historical maintenance factor, life prediction is carried out on the mechanical vulnerable part, accurate life prediction of the mechanical vulnerable part of the wind driven generator is realized by continuously collecting and analyzing operation data of the vulnerable part, the reliability and safety of wind power generation equipment are improved, and the service life of the wind power generation equipment is prolonged. The method is of great significance in improving the technical level and maintenance efficiency of the wind power industry.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbines, and in particular to a method and system for predicting the life of mechanical wearing parts of a wind turbine. Background Art

[0002] In the field of wind power generation, the reliable operation and maintenance of wind turbines is one of the key factors to ensure power generation efficiency and reduce operating costs. Wind turbines are composed of multiple subsystems, including blades, gearboxes, generators and towers, many of which are mechanical wearing parts. Mechanical wearing parts such as bearings, gearboxes, brake systems and blades are particularly prone to wear and aging due to long-term exposure to complex external environments and alternating loads. Effective life prediction methods can help wind power stations arrange maintenance plans in advance and avoid downtime losses caused by sudden equipment failures.

[0003] Existing prediction methods mainly rely on statistical models, physical models or data-driven methods, such as machine learning techniques based on historical operating data. These methods usually require a large amount of real-time monitoring data to train the model in order to accurately estimate the remaining service life of the components. However, due to the complex and changeable working environment of wind turbines, as well as the diversity and uncertainty of the wearing parts themselves, existing prediction methods often find it difficult to provide high-precision and high-reliability prediction results. Summary of the invention

[0004] The embodiment of the present invention provides a life prediction method and system for mechanical wearing parts of a wind turbine. By continuously collecting and analyzing the operating data of the wearing parts, accurate life prediction of the mechanical wearing parts of the wind turbine can be achieved, thereby improving the reliability and safety of wind power generation equipment, which is of great significance for improving the technical level and maintenance efficiency of the wind power industry.

[0005] In order to achieve the above object, the present invention provides a life prediction method for mechanical wearing parts of a wind turbine, comprising:

[0006] Obtain life influencing factors corresponding to mechanical wearing parts, and determine target life influencing factors from all life influencing factors based on a pre-trained life influencing value model;

[0007] Analyze the factors affecting the target life, and calculate the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results;

[0008] Calculating the target life influencing factor of the mechanical wearing parts based on the single influencing factor and the comprehensive influencing factor;

[0009] Collecting historical maintenance records of the mechanical wearing parts, and calculating historical maintenance factors of the mechanical wearing parts according to the historical maintenance records;

[0010] The life of the mechanical wearing parts is predicted according to the target life influencing factor and the historical maintenance factor.

[0011] Furthermore, when obtaining the life influencing factors corresponding to the mechanical wearing parts and determining the target life influencing factors from all the life influencing factors based on the pre-trained life influencing value model, it includes:

[0012] Output the life impact value corresponding to each life impact factor based on the pre-trained life impact value model;

[0013] All life impact values ​​are sorted by numerical size, and all life impact values ​​are combined in pairs based on a position jump combination method to obtain multiple life impact value series, wherein the position jump combination method is to combine the nth life impact value and the n+2th life impact value;

[0014] Calculate the life impact difference between two life impact values ​​in the series of all life impact values;

[0015] All life impact differences that are less than a preset life impact difference are retained, and a target life impact factor tag is generated for the corresponding life impact value series;

[0016] Generate a target life impact factor tag for the larger life impact value in the remaining life impact value series;

[0017] The life influencing factor corresponding to the generated target life influencing factor mark is determined as the target life influencing factor.

[0018] Furthermore, the life impact value model is trained according to the following method:

[0019] Preprocess and standardize the factors affecting life span, where preprocessing includes data cleaning, elimination of invalid data, elimination of abnormal data and format unification;

[0020] Construct a data set based on factors affecting life span after treatment;

[0021] Sampling the data set according to a preset ratio to obtain a training subset and a test subset;

[0022] A pre-selected neural network model is obtained, and the neural network model is iteratively trained according to the training subset, and the iteratively trained neural network model is evaluated according to the test subset to obtain the life impact value model.

[0023] Furthermore, when analyzing the factors affecting the target life and calculating the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results, it includes:

[0024] Determine a target life influencing factor and an adjacent target life influencing factor, and obtain the corresponding historical impact value and historical adjacent impact value;

[0025] Calculate the absolute value of the influence value difference between the historical influence value and the historical adjacent influence value;

[0026] Determine the maximum impact value and the minimum impact value corresponding to all target life influencing factors, and calculate the impact value difference between the maximum impact value and the minimum impact value;

[0027] Calculate the absolute value of the impact value difference and the impact value difference ratio of the impact difference;

[0028] Calculate the absolute value of the target life influencing factor difference between the target life influencing factor and the adjacent target life influencing factor;

[0029] Determine a maximum target life influencing factor and a minimum target life influencing factor from all target life influencing factors, and calculate a target life influencing factor difference between the maximum target life influencing factor and the minimum target life influencing factor;

[0030] Calculate the absolute value of the target life influencing factor difference and the influencing factor difference ratio of the target life influencing factor difference;

[0031] Calculate the product of the impact value difference ratio and the impact factor difference ratio, and perform normalization processing to obtain a single impact factor;

[0032] The remaining influencing factors of the target life are processed to obtain multiple single influencing factors;

[0033] Calculate the average of all single impact factors to get the comprehensive impact factor.

[0034] Furthermore, when calculating the target life influencing factor of the mechanical wearing parts according to the single influencing factor and the comprehensive influencing factor, it includes:

[0035] Determine the maximum single impact factor and the minimum single impact factor from all single impact factors;

[0036] The target life influencing factor of the mechanical wearing parts is calculated according to the following formula:

[0037]

[0038] Among them, w is the factor affecting the target life, m is the number of single influencing factors, e i is the i-th single impact factor, tmin is the minimum single impact factor, tmax is the maximum single impact factor, For all The maximum value among them, r is the adjustment coefficient of the factor affecting the target life.

[0039] Furthermore, the adjustment coefficient r of the factor affecting the target life span is determined according to the following method:

[0040] Presetting a first preset target lifespan influencing factor factor and a second preset target lifespan influencing factor factor;

[0041] Presetting a first adjustment coefficient, a second adjustment coefficient, and a third adjustment coefficient;

[0042] When the first preset condition is identified, the adjustment coefficient r of the target life influencing factor is set to the first adjustment coefficient;

[0043] When the second preset condition is identified, the adjustment coefficient r of the target life influencing factor is set to the second adjustment coefficient;

[0044] When the third preset condition is identified, the adjustment coefficient r of the target life influence factor is set to the third adjustment coefficient, wherein the first preset condition is that the target life influence factor is less than the first preset target life influence factor, the second preset condition is that the target life influence factor is greater than or equal to the first preset target life influence factor and less than the second preset target life influence factor, and the third preset condition is that the target life influence factor is greater than or equal to the second preset target life influence factor.

[0045] Furthermore, when collecting the historical maintenance records of the mechanical wearing parts and calculating the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records, it includes:

[0046] Analyze the historical maintenance records to determine the historical maintenance duration corresponding to each historical maintenance record;

[0047] Obtain a preset standard maintenance duration, and classify all historical maintenance durations that are less than or equal to the standard maintenance duration into a standard maintenance set;

[0048] Classify all historical maintenance durations that are greater than the standard maintenance duration into an overtime maintenance set;

[0049] A historical maintenance factor of the mechanical wearing part is calculated according to the standard maintenance set and the overdue maintenance set.

[0050] Further, when calculating the historical maintenance factor of the mechanical wearing part according to the standard maintenance set and the overdue maintenance set, it includes:

[0051] Calculating an average value of the standard maintenance set and calculating an average value of the overdue maintenance set;

[0052] The historical maintenance factor of the mechanical wearing parts is calculated according to the following formula:

[0053]

[0054] Among them, q is the historical maintenance factor of mechanical wearing parts, g1 is the first calculation coefficient, b is the average value of the standard maintenance set, y1 is the number of historical maintenance hours in the standard maintenance set, k1 is the number of historical maintenance hours in the overtime maintenance set, g2 is the second calculation coefficient, and p is the average value of the overtime maintenance set.

[0055] Furthermore, when predicting the life of the mechanical wearing parts according to the target life influencing factor and the historical maintenance factor, it includes:

[0056] The predicted life of the mechanical wearing parts is calculated according to the following formula:

[0057] s=17.56-5.12×((1+w) q +(1+q) w );

[0058] Where s is the predicted life of mechanical wearing parts.

[0059] In order to achieve the above object, the present invention also provides a life prediction system for mechanical wearing parts of a wind turbine, comprising:

[0060] The first module is used to obtain life influencing factors corresponding to mechanical wearing parts, and determine target life influencing factors from all life influencing factors based on a pre-trained life influencing value model;

[0061] The second module is used to analyze the factors affecting the target life, and calculate the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results;

[0062] The third module is used to calculate the target life influencing factor of the mechanical wearing parts based on the single influencing factor and the comprehensive influencing factor;

[0063] The fourth module is used to collect the historical maintenance records of the mechanical wearing parts and calculate the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records;

[0064] The fifth module is used to predict the life of the mechanical wearing parts according to the target life influencing factors and the historical maintenance factors.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] The present invention discloses a life prediction method and system for mechanical wearing parts of a wind turbine, which obtain life influencing factors corresponding to the mechanical wearing parts, determine target life influencing factors based on a life influencing value model; analyze the target life influencing factors, calculate single influencing factors and comprehensive influencing factors; calculate the target life influencing factors of the mechanical wearing parts based on the single influencing factors and the comprehensive influencing factors; collect historical maintenance records, and calculate the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records; predict the life of the mechanical wearing parts according to the target life influencing factors and the historical maintenance factors, and realize accurate life prediction of the mechanical wearing parts of the wind turbine by continuously collecting and analyzing the operating data of the wearing parts, thereby improving the reliability and safety of wind power generation equipment, which is of great significance to improving the technical level and maintenance efficiency of the wind power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0068] Figure 1 A schematic flow chart of a method for predicting the life of mechanical wearing parts of a wind turbine in an embodiment of the present invention is shown;

[0069] Figure 2 The schematic diagram of the structure of the life prediction system of the mechanical wearing parts of the wind turbine in the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0070] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0071] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0072] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0073] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0074] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0075] like Figure 1 As shown, an embodiment of the present invention discloses a life prediction method for mechanical wearing parts of a wind turbine, comprising:

[0076] S110: Acquire life influencing factors corresponding to mechanical wearing parts, and determine target life influencing factors from all life influencing factors based on a pre-trained life influencing value model;

[0077] In some embodiments of the present application, when obtaining the life influencing factors corresponding to the mechanical wearing parts and determining the target life influencing factors from all the life influencing factors based on the pre-trained life influencing value model, it includes:

[0078] Output the life impact value corresponding to each life impact factor based on the pre-trained life impact value model;

[0079] All life impact values ​​are sorted by numerical size, and all life impact values ​​are combined in pairs based on a position jump combination method to obtain multiple life impact value series, wherein the position jump combination method is to combine the nth life impact value and the n+2th life impact value;

[0080] Calculate the life impact difference between two life impact values ​​in the series of all life impact values;

[0081] All life impact differences that are less than a preset life impact difference are retained, and a target life impact factor tag is generated for the corresponding life impact value series;

[0082] Generate a target life impact factor tag for the larger life impact value in the remaining life impact value series;

[0083] The life influencing factor corresponding to the generated target life influencing factor mark is determined as the target life influencing factor.

[0084] In this embodiment, factors affecting the lifespan include the number of uses, the duration of use, the ambient temperature, the corrosion resistance, the stress level, etc.

[0085] In this embodiment, the life impact value model is trained based on historical life impact factors, and can output the life impact value corresponding to each life impact factor.

[0086] In this embodiment, when the life impact value is less than the preset life impact value, there are two corresponding life impact values. When the life impact value is greater than or equal to the preset life impact value, the larger life impact value of the two corresponding life impact values ​​is obtained.

[0087] The beneficial effect of the above technical solution is that the present invention can lay a foundation for life prediction of mechanical wearing parts and ensure the accuracy of life prediction by determining the factors affecting the target life.

[0088] In some embodiments of the present application, the lifespan impact value model is trained according to the following method:

[0089] Preprocess and standardize the factors affecting life span, where preprocessing includes data cleaning, elimination of invalid data, elimination of abnormal data and format unification;

[0090] Construct a data set based on factors affecting life span after treatment;

[0091] Sampling the data set according to a preset ratio to obtain a training subset and a test subset;

[0092] A pre-selected neural network model is obtained, and the neural network model is iteratively trained according to the training subset, and the iteratively trained neural network model is evaluated according to the test subset to obtain the life impact value model.

[0093] In this embodiment, the preset ratio may be 1:1, 1:3, etc., and may be specifically set according to actual conditions.

[0094] The beneficial effect of the above technical solution is that the present invention can accurately obtain the life impact value model and ensure the training accuracy of the life impact value model.

[0095] S120: Analyze the factors affecting the target life, and calculate the single influencing factor and the comprehensive influencing factor of the mechanical wearing parts based on the analysis results;

[0096] In some embodiments of the present application, when analyzing the factors affecting the target life and calculating the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results, it includes:

[0097] Determine a target life influencing factor and an adjacent target life influencing factor, and obtain the corresponding historical impact value and historical adjacent impact value;

[0098] Calculate the absolute value of the influence value difference between the historical influence value and the historical adjacent influence value;

[0099] Determine the maximum impact value and the minimum impact value corresponding to all target life influencing factors, and calculate the impact value difference between the maximum impact value and the minimum impact value;

[0100] Calculate the absolute value of the impact value difference and the impact value difference ratio of the impact difference;

[0101] Calculate the absolute value of the target life influencing factor difference between the target life influencing factor and the adjacent target life influencing factor;

[0102] Determine a maximum target life influencing factor and a minimum target life influencing factor from all target life influencing factors, and calculate a target life influencing factor difference between the maximum target life influencing factor and the minimum target life influencing factor;

[0103] Calculate the absolute value of the target life influencing factor difference and the influencing factor difference ratio of the target life influencing factor difference;

[0104] Calculate the product of the impact value difference ratio and the impact factor difference ratio, and perform normalization processing to obtain a single impact factor;

[0105] The remaining influencing factors of the target life are processed to obtain multiple single influencing factors;

[0106] Calculate the average of all single impact factors to get the comprehensive impact factor.

[0107] In this embodiment, the normalization process is complicated and mature, and will not be introduced in detail here.

[0108] The beneficial effect of the above technical solution is that the present invention can calculate the single influencing factor and the comprehensive influencing factor according to the target life influencing factor and the historical influencing value, which can not only ensure the calculation accuracy of the single influencing factor and the comprehensive influencing factor, but also lay the foundation for the life prediction of mechanical wearing parts and provide reliable data support.

[0109] S130: Calculating a target life influencing factor of the mechanical wearing part based on the single influencing factor and the comprehensive influencing factor;

[0110] In some embodiments of the present application, when calculating the target life influencing factor of the mechanical wearing part according to the single influencing factor and the comprehensive influencing factor, it includes:

[0111] Determine the maximum single impact factor and the minimum single impact factor from all single impact factors;

[0112] The target life influencing factor of the mechanical wearing parts is calculated according to the following formula:

[0113]

[0114] Among them, w is the factor affecting the target life, m is the number of single influencing factors, e i is the i-th single impact factor, tmin is the minimum single impact factor, tmax is the maximum single impact factor, For all The maximum value among them, r is the adjustment coefficient of the factor affecting the target life.

[0115] In some embodiments of the present application, the adjustment coefficient r of the target life influencing factor is determined according to the following method:

[0116] Presetting a first preset target lifespan influencing factor factor and a second preset target lifespan influencing factor factor;

[0117] Presetting a first adjustment coefficient, a second adjustment coefficient, and a third adjustment coefficient;

[0118] When the first preset condition is identified, the adjustment coefficient r of the target life influencing factor is set to the first adjustment coefficient;

[0119] When the second preset condition is identified, the adjustment coefficient r of the target life influencing factor is set to the second adjustment coefficient;

[0120] When the third preset condition is identified, the adjustment coefficient r of the target life influence factor is set to the third adjustment coefficient, wherein the first preset condition is that the target life influence factor is less than the first preset target life influence factor, the second preset condition is that the target life influence factor is greater than or equal to the first preset target life influence factor and less than the second preset target life influence factor, and the third preset condition is that the target life influence factor is greater than or equal to the second preset target life influence factor.

[0121] In this embodiment, the first preset target lifespan influencing factor is smaller than the second preset target lifespan influencing factor.

[0122] In this embodiment, the first adjustment coefficient is smaller than the second adjustment coefficient and smaller than the third adjustment coefficient.

[0123] The beneficial effect of the above technical solution is that the present invention can realize dynamic adjustment of the target life influencing factor according to the target life influencing factor, the first preset target life influencing factor and the second preset target life influencing factor, thereby ensuring the adjustment accuracy and the comprehensiveness of the calculation of the target life influencing factor.

[0124] S140: collecting historical maintenance records of the mechanical wearing parts, and calculating historical maintenance factors of the mechanical wearing parts according to the historical maintenance records;

[0125] In some embodiments of the present application, when collecting the historical maintenance records of the mechanical wearing parts and calculating the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records, it includes:

[0126] Analyze the historical maintenance records to determine the historical maintenance duration corresponding to each historical maintenance record;

[0127] Obtain a preset standard maintenance duration, and classify all historical maintenance durations that are less than or equal to the standard maintenance duration into a standard maintenance set;

[0128] Classify all historical maintenance durations that are greater than the standard maintenance duration into an overtime maintenance set;

[0129] A historical maintenance factor of the mechanical wearing part is calculated according to the standard maintenance set and the overdue maintenance set.

[0130] The beneficial effect of the above technical solution is that the present invention obtains a standard maintenance set and an overdue maintenance set by division, thereby further laying a foundation for calculating the historical maintenance factor of mechanical wearing parts.

[0131] In some embodiments of the present application, when calculating the historical maintenance factor of the mechanical wearing part according to the standard maintenance set and the overdue maintenance set, it includes:

[0132] Calculating an average value of the standard maintenance set and calculating an average value of the overdue maintenance set;

[0133] The historical maintenance factor of the mechanical wearing parts is calculated according to the following formula:

[0134]

[0135] Among them, q is the historical maintenance factor of mechanical wearing parts, g1 is the first calculation coefficient, b is the average value of the standard maintenance set, y1 is the number of historical maintenance hours in the standard maintenance set, k1 is the number of historical maintenance hours in the overtime maintenance set, g2 is the second calculation coefficient, and p is the average value of the overtime maintenance set.

[0136] The beneficial effect of the above technical solution is that the present invention can effectively ensure the calculation accuracy of the historical maintenance factor, avoid errors caused by human participation, and provide a basis for the predicted life of mechanical wearing parts.

[0137] S150: Predicting the life of the mechanical wearing parts according to the target life influencing factor and the historical maintenance factor.

[0138] In some embodiments of the present application, the predicted life of the mechanical wearing parts is calculated according to the following formula:

[0139] s=17.56-5.12×((1+w) q +(1+q) w );

[0140] Where s is the predicted life of mechanical wearing parts.

[0141] The beneficial effect of the above technical solution is: by continuously collecting and analyzing the operating data of wearing parts, accurate life prediction of wind turbine mechanical wearing parts can be achieved, and the reliability and safety of wind power generation equipment can be improved, which is of great significance to improving the technical level and maintenance efficiency of the wind power industry.

[0142] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0143] Correspondingly, such as Figure 2 As shown, the present application also provides a life prediction system for mechanical wearing parts of a wind turbine, comprising:

[0144] The first module is used to obtain life influencing factors corresponding to mechanical wearing parts, and determine target life influencing factors from all life influencing factors based on a pre-trained life influencing value model;

[0145] The second module is used to analyze the factors affecting the target life, and calculate the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results;

[0146] The third module is used to calculate the target life influencing factor of the mechanical wearing parts based on the single influencing factor and the comprehensive influencing factor;

[0147] The fourth module is used to collect the historical maintenance records of the mechanical wearing parts and calculate the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records;

[0148] The fifth module is used to predict the life of the mechanical wearing parts according to the target life influencing factors and the historical maintenance factors.

[0149] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0150] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0151] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting the life of mechanical wearing parts of a wind turbine, characterized in that: include: Obtain life influencing factors corresponding to mechanical wearing parts, and determine target life influencing factors from all life influencing factors based on a pre-trained life influencing value model; Analyze the factors affecting the target life, and calculate the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results; Calculating the target life influencing factor of the mechanical wearing parts based on the single influencing factor and the comprehensive influencing factor; Collecting historical maintenance records of the mechanical wearing parts, and calculating historical maintenance factors of the mechanical wearing parts according to the historical maintenance records; The life of the mechanical wearing parts is predicted according to the target life influencing factor and the historical maintenance factor.

2. The life prediction method of mechanical wearing parts of a wind turbine according to claim 1, characterized in that: When obtaining the life influencing factors corresponding to the mechanical wearing parts and determining the target life influencing factors from all the life influencing factors based on the pre-trained life influencing value model, it includes: Output the life impact value corresponding to each life impact factor based on the pre-trained life impact value model; All life impact values ​​are sorted by numerical size, and all life impact values ​​are combined in pairs based on a position jump combination method to obtain multiple life impact value series, wherein the position jump combination method is to combine the nth life impact value and the n+2th life impact value; Calculate the life impact difference between two life impact values ​​in the series of all life impact values; All life impact differences that are less than a preset life impact difference are retained, and a target life impact factor tag is generated for the corresponding life impact value series; Generate a target life impact factor tag for the larger life impact value in the remaining life impact value series; The life influencing factor corresponding to the generated target life influencing factor mark is determined as the target life influencing factor.

3. The life prediction method of mechanical wearing parts of a wind turbine according to claim 1, characterized in that: The life impact value model is trained according to the following method: Preprocess and standardize the factors affecting life span, where preprocessing includes data cleaning, eliminating invalid data, eliminating abnormal data and format unification; Construct a data set based on factors affecting life span after treatment; Sampling the data set according to a preset ratio to obtain a training subset and a test subset; A pre-selected neural network model is obtained, and the neural network model is iteratively trained according to the training subset, and the iteratively trained neural network model is evaluated according to the test subset to obtain the life impact value model.

4. The life prediction method of mechanical wearing parts of a wind turbine according to claim 1, characterized in that: When analyzing the factors affecting the target life and calculating the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results, it includes: Determine a target life influencing factor and an adjacent target life influencing factor, and obtain the corresponding historical impact value and historical adjacent impact value; Calculate the absolute value of the influence value difference between the historical influence value and the historical adjacent influence value; Determine the maximum impact value and the minimum impact value corresponding to all target life influencing factors, and calculate the impact value difference between the maximum impact value and the minimum impact value; Calculate the absolute value of the impact value difference and the impact value difference ratio of the impact difference; Calculate the absolute value of the target life influencing factor difference between the target life influencing factor and the adjacent target life influencing factor; Determine a maximum target life influencing factor and a minimum target life influencing factor from all target life influencing factors, and calculate a target life influencing factor difference between the maximum target life influencing factor and the minimum target life influencing factor; Calculate the absolute value of the target life influencing factor difference and the influencing factor difference ratio of the target life influencing factor difference; Calculate the product of the impact value difference ratio and the impact factor difference ratio, and perform normalization processing to obtain a single impact factor; The remaining influencing factors of the target life are processed to obtain multiple single influencing factors; Calculate the average of all single impact factors to get the comprehensive impact factor.

5. The life prediction method of mechanical wearing parts of a wind turbine according to claim 4, characterized in that: When calculating the target life influencing factor of the mechanical wearing parts according to the single influencing factor and the comprehensive influencing factor, it includes: Determine the maximum single impact factor and the minimum single impact factor from all single impact factors; The target life influencing factor of the mechanical wearing parts is calculated according to the following formula: Among them, w is the factor affecting the target life, m is the number of single influencing factors, e i is the i-th single impact factor, tmin is the minimum single impact factor, tmax is the maximum single impact factor, For all The maximum value among them, r is the adjustment coefficient of the factor affecting the target life.

6. The life prediction method of mechanical wearing parts of a wind turbine according to claim 5, characterized in that: Determine the adjustment coefficient r of the factor affecting the target life according to the following method: Preset a first preset target lifespan influencing factor factor and a second preset target lifespan influencing factor factor; Presetting a first adjustment coefficient, a second adjustment coefficient, and a third adjustment coefficient; When the first preset condition is identified, the adjustment coefficient r of the target life influencing factor is set to the first adjustment coefficient; When the second preset condition is identified, the adjustment coefficient r of the target life influencing factor is set to the second adjustment coefficient; When the third preset condition is identified, the adjustment coefficient r of the target life influence factor is set to the third adjustment coefficient, wherein the first preset condition is that the target life influence factor is less than the first preset target life influence factor, the second preset condition is that the target life influence factor is greater than or equal to the first preset target life influence factor and less than the second preset target life influence factor, and the third preset condition is that the target life influence factor is greater than or equal to the second preset target life influence factor.

7. The life prediction method of mechanical wearing parts of a wind turbine according to claim 1, characterized in that: When collecting the historical maintenance records of the mechanical wearing parts and calculating the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records, it includes: Analyze the historical maintenance records to determine the historical maintenance duration corresponding to each historical maintenance record; Obtain a preset standard maintenance duration, and classify all historical maintenance durations that are less than or equal to the standard maintenance duration into a standard maintenance set; Classify all historical maintenance durations that are greater than the standard maintenance duration into an overtime maintenance set; A historical maintenance factor of the mechanical wearing part is calculated according to the standard maintenance set and the overdue maintenance set.

8. The life prediction method of mechanical wearing parts of a wind turbine according to claim 7, characterized in that: When calculating the historical maintenance factor of the mechanical wearing part according to the standard maintenance set and the overdue maintenance set, it includes: Calculating an average value of the standard maintenance set and calculating an average value of the overdue maintenance set; The historical maintenance factor of the mechanical wearing parts is calculated according to the following formula: Among them, q is the historical maintenance factor of mechanical wearing parts, g1 is the first calculation coefficient, b is the average value of the standard maintenance set, y1 is the number of historical maintenance hours in the standard maintenance set, k1 is the number of historical maintenance hours in the overtime maintenance set, g2 is the second calculation coefficient, and p is the average value of the overtime maintenance set.

9. The life prediction method of mechanical wearing parts of a wind turbine according to claim 8, characterized in that: When predicting the life of the mechanical wearing parts according to the target life influencing factor and the historical maintenance factor, it includes: The predicted life of the mechanical wearing parts is calculated according to the following formula: s=17.56-5.12×((1+w) q +(1+q) w ); Where s is the predicted life of mechanical wearing parts.

10. A life prediction system for mechanical wearing parts of a wind turbine, characterized in that: include: The first module is used to obtain life influencing factors corresponding to mechanical wearing parts, and determine target life influencing factors from all life influencing factors based on a pre-trained life influencing value model; The second module is used to analyze the factors affecting the target life, and calculate the single influencing factors and comprehensive influencing factors of the mechanical wearing parts based on the analysis results; The third module is used to calculate the target life influencing factor of the mechanical wearing parts based on the single influencing factor and the comprehensive influencing factor; The fourth module is used to collect the historical maintenance records of the mechanical wearing parts and calculate the historical maintenance factors of the mechanical wearing parts according to the historical maintenance records; The fifth module is used to predict the life of the mechanical wearing parts according to the target life influencing factors and the historical maintenance factors.

Images