Multi-dimensional comprehensive evaluation system and method for offshore wind turbine generator and key components

Abstract

The invention discloses a multi-dimensional comprehensive evaluation system and method for an offshore wind turbine generator and key components, belongs to the technical field of offshore wind power, and adopts a multi-level fuzzy comprehensive evaluation method. According to the multi-level fuzzy comprehensive evaluation method, firstly, a multi-level index system needs to be established; then comprehensive evaluation is carried out on each index factor of each hierarchy from the bottommost layer from bottom to top, iteration is carried out in sequence, multi-dimensional data fusion is achieved, an evaluation vector of the final hierarchy is obtained, multi-dimensional comprehensive high-precision evaluation of the offshore wind turbine generator and key components is achieved, and the problem that in the prior art, when the number of evaluation indexes is large, the evaluation efficiency is high is solved. And the resolution of the evaluation result is poor.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of offshore wind power, and relates to a multi-dimensional comprehensive evaluation system and method for offshore wind turbine units and key components. BACKGROUND

[0002] Offshore wind power technology refers to a technology of generating power by using offshore wind power resources. In recent years, with the increasing demand for renewable energy sources worldwide, offshore wind power technology has developed rapidly; the current offshore units show the trend of larger and larger single machine capacity, larger and larger impeller diameter, and deeper and deeper installation depth. In addition, the offshore environment where the offshore wind turbine units are located is complex and changeable, the atmospheric area has high humidity and high salt spray, the splash area has frequent dry and wet alternation, the underwater area has long-time immersion and serious attachment of aquatic organisms, which all bring serious challenges to the long-term safe and stable operation of offshore wind power equipment.

[0003] With the continuous development of computer network technology, big data and artificial intelligence technologies are also applied to offshore wind farms. These technologies can monitor and analyze the state of wind power equipment, and give early warning of faults to realize intelligent management such as fault warning and state monitoring. Each fault has its mechanism, and the existing technology analyzes the fault mechanism, selects parameters or parameter combinations with high sensitivity to fault generation to form evaluation indexes, and uses single-level fuzzy comprehensive evaluation to evaluate the state of wind power equipment. However, when there are many evaluation indexes, using single-level fuzzy comprehensive evaluation will make the weight of each factor small, resulting in poor resolution of the evaluation result. SUMMARY

[0004] The purpose of the present application is to solve the problems in the prior art and provide a multi-dimensional comprehensive evaluation system and method for offshore wind turbine units and key components to solve the technical problem of poor resolution of the evaluation result when there are many evaluation indexes in the prior art.

[0005] To achieve the above-mentioned purpose, the following technical solutions are adopted in the present application:

[0006] A multi-dimensional comprehensive evaluation method for offshore wind turbine units and key components, comprising the following steps:

[0007] Obtaining the main indexes of each subsystem; establishing a multi-level index system according to the main indexes of each subsystem;

[0008] For the multi-level index system, starting from the bottom layer, each main index of each level is respectively subjected to fuzzy comprehensive evaluation from bottom to top, and the evaluation vector of the final level is obtained by iteration.

[0009] Preferably, the subsystems include blades, bolts, transmission chains, frequency converters and component fatigue indexes.

[0010] Preferably, the main indicators of the blade include a crack detection indicator and an icing detection indicator;

[0011] The main indicators of the bolt include a bolt fracture indicator;

[0012] The main indicators of the transmission chain include a gearbox damage indicator, a toothed belt damage indicator, and a stator support crack indicator;

[0013] The main indicators of the frequency converter include a frequency converter anomaly indicator and an IGBT operation anomaly indicator.

[0014] Preferably, the multi-level indicator system is established, specifically as follows:

[0015] Suppose that the bottom layer has n indicators, denoted as X = {x1, x2, … x n},

[0016] According to the attributes of the bottom layer indicators, they are divided into u subsets, i.e. X = {X1, X2, … X u},where any X i and X j have no intersection;

[0017] The total number of indicators in the next layer is n, i.e.

[0018] Preferably, the fuzzy comprehensive evaluation is performed on each main indicator of each level, specifically including:

[0019] The weight distribution is performed on the lower indicators of each main indicator in the second level to obtain a weight vector and calculate the indicator weight;

[0020] After the initial data of each main indicator in the second level is normalized, the membership degree matrix is calculated using the membership function distribution; the evaluation vector of the second level is calculated according to the indicator weight and the membership degree matrix;

[0021] The weighting is performed on each main indicator in the second level to obtain a weighted indicator, and the evaluation matrix is calculated according to the evaluation vector of the second level; the evaluation vector of the next level is obtained according to the weighted indicator and the evaluation matrix;

[0022] Iterate in sequence to obtain the evaluation vector of the final level.

[0023] Preferably, the correlation coefficient method in the objective weighting method is used to calculate the indicator weight, and the weight distribution is performed on the lower indicators of each main indicator in the second level.

[0024] Preferably, the initial data of each main indicator in the second level is normalized using the degradation degree analysis method.

[0025] A multi-dimensional comprehensive evaluation system for offshore wind turbine and key components, comprising:

[0026] A multi-level index system establishment unit is configured to obtain main indexes of each subsystem and establish a multi-level index system according to the main indexes of each subsystem.

[0027] An iterative calculation unit is configured to perform fuzzy comprehensive evaluation on each main index of each level from the bottom up according to the multi-level index system, and obtain an evaluation vector of the final level through iteration.

[0028] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the multi-dimensional comprehensive evaluation method for offshore wind turbine and key components.

[0029] A computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the multi-dimensional comprehensive evaluation method for offshore wind turbine and key components.

[0030] Compared with the prior art, the present application has the following beneficial effects:

[0031] 1) When there are many evaluation indexes, using single-level fuzzy comprehensive evaluation will make the weight of each factor small, resulting in poor resolution of the evaluation result. Therefore, when there are many indexes, it is suitable to use multi-level fuzzy comprehensive evaluation method. The multi-level fuzzy comprehensive evaluation method first establishes a multi-level index system, and then performs comprehensive evaluation on each index factor of each level from the bottom up, and obtains an evaluation vector of the final level through iteration, realizing multi-dimensional data fusion, and realizing high-precision evaluation of offshore wind turbine and key components, solving the technical problem of poor resolution of the evaluation result in the prior art when there are many evaluation indexes.

[0032] 2) Each fault has its mechanism, and by analyzing the fault mechanism, selecting parameters or parameter combinations with high sensitivity to fault generation, and establishing the association between fault and selected parameters / parameter combinations, the running state of the wind turbine can be better evaluated, and the main indexes representing the running state of each subsystem are selected according to the running characteristics of different components of the offshore wind turbine, forming the association between the structural ontology characteristics of the wind turbine and key components and the environmental parameters, avoiding single evaluation, and improving the effectiveness of the evaluation method.

[0033] 3) The weight of the evaluation index reflects the importance of each index to the evaluation object. The weight of each layer index needs to be reasonably assigned, and the correlation coefficient method is used to determine the weight between each level factor, so that the weight assignment is more objective and accurate. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0035] Figure 1 The flow chart of the method of the present application;

[0036] Figure 2 The system block diagram of the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical scheme in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0038] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments in the present application without creative labor are within the scope of protection of the present application.

[0039] It should be noted that: similar numbers and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0040] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship of the product in use, only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0041] In addition, if the term "horizontal" is used, it is not meant to require absolutely horizontal surfaces, but rather can be slightly inclined. As such, the term "horizontal" is used to mean that the direction is more horizontal than vertical, and is not meant to require a perfectly horizontal surface.

[0042] In the description of the embodiments of the application, it should also be noted that, unless specifically defined and limited, if the terms "set", "install", "connect", "connect" appear, it should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the application can be understood according to the specific circumstances.

[0043] The application will be described in further detail below with reference to the drawings:

[0044] From the technical point of view of the transmission system, the current domestic mainstream machine type has double-fed wind turbine, direct-drive wind turbine, in order to better evaluate the operation condition of wind turbine, from the structure of offshore wind turbine and power grid factors, a multi-level fuzzy comprehensive evaluation index system is established for offshore wind turbine with different structures. Referring to Figure 1 The application discloses a kind of offshore wind turbine and key component multi-dimension comprehensive evaluation method, comprising the following steps:

[0045] S1: obtain the main index of each subsystem;According to the main index of each subsystem, a multi-level index system is established;

[0046] S2: for multi-level index system, starting from the bottom layer, each main index of each level is respectively evaluated from bottom to top, and the evaluation vector of the final level is obtained by iteration.

[0047] When there are many evaluation indexes, using single-level fuzzy comprehensive evaluation will make the weight of each factor smaller, resulting in poor resolution of evaluation results. Therefore, when there are many indexes, multi-level fuzzy comprehensive evaluation method is suitable. Multi-level fuzzy comprehensive evaluation method first establishes a multi-level index system;Then starting from the bottom layer, each index factor of each level is respectively evaluated from bottom to top, and the evaluation vector of the final level is obtained by iteration, realizing multi-dimension data fusion, realizing high-precision evaluation of offshore wind turbine and key component multi-dimension comprehensive.

[0048] In some embodiments, each failure has its mechanism, by analyzing the failure mechanism, selecting parameters or parameter combinations with high sensitivity to failure, establishing the association between failure and selected parameters / parameter combinations, in order to better evaluate the operation status of the wind turbine, starting from the structure of the offshore wind turbine and the grid factors, according to the operation characteristics of different components of the wind turbine, the main indicators representing the operation state of each subsystem are selected, the association between the structure of the wind turbine and the key components and the environmental parameters is formed, the single evaluation is avoided, and the effectiveness of the evaluation method is improved. The subsystems include blades, bolts, transmission chain, frequency converter and component fatigue index.

[0049] In some embodiments, each subsystem selects main indicators representing the operation state of the subsystem.

[0050] (1) Blade

[0051] 1) Crack detection: by analyzing the relevant monitoring parameters of the blade, variable pitch, and nacelle vibration, and combining the peak ratio algorithm, the blade is predicted.

[0052] 2) Icing detection: by fitting the relevant monitoring parameters of the blade and the environmental parameters, and then predicting the icing of the blade through difference analysis.

[0053] (3) Bolt

[0054] By analyzing the relevant monitoring parameters of the blade, variable pitch, and nacelle vibration, using discrete probability analysis and abnormal point distribution analysis, the bolt fracture is predicted.

[0055] (3) Transmission chain

[0056] 1) Gearbox damage: by using the TF-IDF statistical analysis method on the relevant monitoring data of the gearbox (front and rear shaft temperature and temperature difference, gearbox oil temperature, oil pressure, and vibration).

[0057] 2) Belt damage: data cleaning is performed on the relevant monitoring parameters such as blade speed and angle, variable pitch, and then discrete probability analysis is performed.

[0058] 3) Stator support cracking: using the relevant monitoring parameters of nacelle acceleration and environmental data, abnormal point distribution measurement is used for prediction.

[0059] (4) Frequency converter

[0060] 1) Frequency converter anomaly: by using difference analysis on the relevant monitoring data of the frequency converter (RMIO, ISU, INU, control cabinet, cooling system), and then using discrete anomaly analysis to predict the abnormality of the frequency converter.

[0061] 2) IGBT operation abnormality: through the converter environment monitoring parameters, and current voltage monitoring parameters, using abnormal point distribution to predict IGBT problem.

[0062] (5) Component fatigue index

[0063] Fatigue prediction is performed on large components, different monitoring parameters are used for different components, and neural network algorithm is used to predict fatigue index.

[0064] In some embodiments, the multi-level index system is established, specifically:

[0065] Let the first bottom layer have n indexes, denoted as X = {x1, x2, … x n},

[0066] According to the attributes of the first bottom layer indexes, they are divided into u subsets, that is, X = {X1, X2, … X u},where any X i and X j have no intersection;

[0067] The upper layer index is the total number of lower layer indexes n, that is

[0068] In some embodiments, the fuzzy comprehensive evaluation is performed on each main index of each level respectively, specifically including:

[0069] S201: Weight distribution is performed on the lower level indexes of each main index in the second level, a weight vector is obtained, and the index weight is calculated;

[0070] S202: After the initial data of each main index in the second level is normalized, the membership degree matrix is calculated using the membership function distribution; the evaluation vector of the second level is calculated according to the index weight and the membership degree matrix;

[0071] S203: The weighting index is obtained by weighting each main index in the second level, and the evaluation matrix is calculated according to the evaluation vector of the second level; the evaluation vector of the next level is obtained according to the weighting index and the evaluation matrix;

[0072] S204: Iteration is performed in sequence to obtain the evaluation vector of the final level.

[0073]

Embodiment

[0074] The following takes a two-layer fuzzy comprehensive evaluation model as an example to illustrate the establishment process.

[0075] (1) Establish a multi-level index system

[0076] Let the first layer have n indexes, denoted as X = {x1, x2, … xn}, then it can be divided into u subsets according to the attributes of the index of this layer, that is, X = {X1, X2, ..., X}. u}, where any X i and X j There is no overlap. This is the second-level indicator, and the total number of indicators in the lower level is n, that is...

[0077] (2) Assigning weights

[0078] For each index X in the second layer i Sub-indicators We perform weight allocation to obtain u weight vectors. The correlation coefficient method in the objective weighting method is used to calculate the index weights.

[0079] (3) Calculate the membership matrix

[0080] Choose an appropriate method to calculate the membership degree, and obtain the single-factor membership matrix R corresponding to each second-level indicator. i When the physical meanings and units of the indicator parameters differ, it is necessary to normalize the initial data values ​​in order to conduct a comprehensive comparative analysis of these indicator factors. This normalization process utilizes a degradation degree analysis method. Then, an appropriate membership function distribution is selected to calculate the membership matrix.

[0081] (4) Calculate the evaluation vector

[0082] Assuming there are m evaluation levels, then by Obtain all second-level evaluation vectors.

[0083] (5) Continue iterative calculation

[0084] Each X in the second layer i Let it be denoted as an index, i.e., X = {X1, X2, ..., Xu}, and let X be an index. i Weighting, i.e., A = (a1, a2, ... a2) u The evaluation matrix for X can be obtained from the following matrix:

[0085]

[0086] Thus, the final evaluation vector is obtained:

[0087] B = AR = (b1, b2, ... b m (2)

[0088] Therefore, multi-level fuzzy comprehensive evaluation models with three, four, or more layers can be derived similarly.

[0089] Weighted evaluation:

[0090] The weight of the evaluation index reflects the importance of each index to the evaluation object, and the corresponding weight needs to be reasonably allocated to each layer index. The method for determining the weight of the evaluation index can be divided into two categories: subjective weighting method and objective weighting method. The subjective weighting method mainly relies on the experience of experts to determine the weight, which is easy to implement but has strong subjectivity. The objective weighting method obtains the weight of the index by calculation according to the data information of each subsystem in the actual operation of the system, and the weight determined is more objective. The objective weighting method can use the correlation coefficient method to calculate the index weight, and use the correlation coefficient method to determine the weight between each level factor, so that the weight assignment is more objective and accurate.

[0091] Referring to Figure 2 The offshore wind turbine and key component multi-dimensional comprehensive evaluation system also discloses a multi-level index system establishment unit, which is configured to obtain main indexes of each subsystem and establish a multi-level index system according to the main indexes of each subsystem.

[0092] The multi-level index system establishment unit is configured to obtain main indexes of each subsystem and establish a multi-level index system according to the main indexes of each subsystem.

[0093] The iteration calculation unit is configured to perform comprehensive evaluation on each main index of each level respectively from the bottom layer to the top layer according to the multi-level index system, and obtain an evaluation vector of the final level through iteration.

[0094] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the offshore wind turbine and key component multi-dimensional comprehensive evaluation method according to any one of the above.

[0095] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the offshore wind turbine and key component multi-dimensional comprehensive evaluation method according to any one of the above.

[0096] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0097] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0099] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0100] Finally, it should be noted that the above-mentioned embodiments are merely intended to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A multi-dimensional comprehensive evaluation method for offshore wind turbine units and key components, characterized in that, Includes the following steps: Obtain the key indicators for each subsystem; establish a multi-level indicator system based on the key indicators of each subsystem; For the multi-level indicator system, starting from the bottom level, fuzzy comprehensive evaluation is performed on each major indicator of each level from bottom to top, and the evaluation vector of the final level is obtained by iterating in sequence.

2. The multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to claim 1, characterized in that, The subsystem includes blades, bolts, transmission chains, frequency converters, and component fatigue indices.

3. The multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to claim 2, characterized in that, The main indicators of the blades include crack detection indicators and icing detection indicators; The main indicators of the bolt include bolt fracture indicators; The main indicators of the transmission chain include gearbox damage indicators, toothed belt damage indicators, and stator support cracking indicators. The main indicators of the frequency converter include frequency converter abnormality indicators and IGBT operation abnormality indicators.

4. The multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to claim 1, characterized in that, The establishment of a multi-level indicator system specifically includes: Let the bottom layer have n indices, represented as X = {x1, x2, ..., xn}. n }, Based on the attributes of the lowest-level index, it is divided into u subsets, namely X = {X1, X2, ..., X}. u }, where any X i and X j No intersection; The upper-level indicator is n, and the total number of lower-level indicators is n, that is 5. The multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to claim 1, characterized in that, The fuzzy comprehensive evaluation of each key indicator at each level specifically includes: Weights are assigned to the sub-indicators of each major indicator in the second level to obtain a weight vector and the indicator weights are calculated. After normalizing the initial data of each major indicator in the second level, the membership degree matrix is ​​calculated using the membership function distribution; the evaluation vector of the second level is calculated based on the indicator weights and the membership degree matrix. Weighted indicators are assigned to each major indicator in the second level to obtain weighted indicators, and the evaluation matrix is ​​calculated based on the evaluation vector of the second level; the evaluation vector of the next level is obtained based on the weighted indicators and the evaluation matrix. By iterating sequentially, the final evaluation vector for each level is obtained.

6. The multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to claim 5, characterized in that, The correlation coefficient method in the objective weighting method is used to calculate the index weights, and the weights are allocated to the sub-indicators of each major indicator in the second level.

7. The multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to claim 5, characterized in that, The initial data of each major indicator in the second level were normalized using the degradation analysis method.

8. A multi-dimensional comprehensive evaluation system for offshore wind turbines and key components, characterized in that, include: A multi-level indicator system establishment unit is used to obtain the main indicators of each subsystem; and to establish a multi-level indicator system based on the main indicators of each subsystem. The iterative calculation unit is used to perform fuzzy comprehensive evaluation of each major indicator at each level from the bottom up according to the multi-level indicator system, starting from the bottom level, and iterates in sequence to obtain the evaluation vector of the final level.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the multi-dimensional comprehensive evaluation method for offshore wind turbines and key components according to any one of claims 1-7.

Images