An expert guidance and support method and system for offshore wind power.
By establishing an expert guidance standard library and calculating fault similarity, a fault handling solution for offshore wind power is provided, which solves the problems of low efficiency and high cost in offshore wind power fault handling and achieves efficient and low-cost fault handling.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUANENG GROUP TECHNOLOGY INNOVATION CENTER CO LTD
- Filing Date
- 2022-07-29
- Publication Date
- 2026-07-17
AI Technical Summary
Offshore wind power fault handling is time-consuming and requires a high level of expertise, resulting in low efficiency and high cost.
Establish an expert guidance standard library based on the causes of failures. By calculating the similarity between the current failure and historical failures, obtain expert guidance assistance solutions and provide failure handling solutions.
It improved the efficiency of troubleshooting, reduced labor costs, and simplified the difficulty of troubleshooting.
Smart Images
Figure CN115270969B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of wind turbine fault diagnosis auxiliary technology, specifically involving an expert guidance auxiliary method and system for offshore wind power. Background Technology
[0002] Compared to onshore wind power, offshore wind power has advantages such as superior wind resources, larger installed capacity per turbine, higher power generation, and suitability for large-scale development. Currently, offshore wind power is entering a period of rapid development, but offshore wind farms face a series of challenges, including sudden equipment failures, high requirements for specialized troubleshooting, high maintenance costs, long maintenance cycles, and significant downtime losses.
[0003] Judging from the handling of faults by on-site personnel at offshore wind farms in recent years, it is often impossible to directly link the fault with the solution. Repeated consultations with experts are required, which greatly increases the time required for fault handling, reduces the efficiency of fault handling, and raises the cost of handling faults in wind turbine units. Summary of the Invention
[0004] In order to overcome the shortcomings of the existing technology, the present invention aims to provide an expert guidance and assistance method and system for offshore wind power, which improves the efficiency of fault handling, reduces the difficulty of fault handling, and reduces labor costs.
[0005] This invention is achieved through the following technical solution:
[0006] An expert-guided support method for offshore wind power includes:
[0007] S1: Establish an expert guidance standard library based on the causes of failures. This library is created and entered by relevant experts based on current technology and historical experience.
[0008] S2: Calculate the similarity between the current fault and the historical fault in terms of operating parameters and fault phenomena at the time of the fault occurrence, and determine the cause of the historical fault based on the similarity calculation results;
[0009] S3: Use the fault causes of historical faults to associate with the expert guidance standard library established in S1, and obtain the expert guidance assistance scheme corresponding to the current fault.
[0010] Preferably, in S1, the information in the expert guidance standard library includes: fault name, fault cause, handling method and steps, replacement spare parts information, tool information, safety information, personnel configuration information, and drawings.
[0011] Preferably, in S2, the fault phenomenon of the current fault includes the fault name and fault phenomenon description of the current fault, and the operating parameters of the current fault include the operating parameter information of the wind turbine corresponding to the time when the current fault occurred; the fault phenomenon of the historical fault includes the fault name and fault phenomenon description of the historical fault, and the operating parameters of the historical fault include the operating parameter information of the wind turbine corresponding to the time when the historical fault occurred.
[0012] Preferably, in S2, when obtaining the operating parameters of the current fault, the alternating factor elimination algorithm is used to eliminate data factors in the operating parameters at the fault time that did not affect the occurrence of the fault, so as to obtain the operating parameters of the current fault; when obtaining the operating parameters of historical faults, the alternating factor elimination algorithm is used to eliminate data factors in the operating parameters at the fault time that did not affect the occurrence of the fault, so as to obtain the operating parameters of historical faults.
[0013] More preferably, in S2, the similarity calculation between the operating parameters of the current fault and the operating parameters of the historical fault is specifically as follows: based on the obtained operating parameters of the current fault and the operating parameters of the historical fault, the similarity between the current fault and the historical fault in terms of the operating parameters at the time of the fault is calculated respectively; the calculated similarity is ranked from largest to smallest to obtain a set of historical faults in which the similarity between the current fault and the historical fault in terms of the operating parameters at the time of the fault is ranked from largest to smallest.
[0014] More preferably, in S2, the similarity calculation between the fault phenomenon of the current fault and the fault phenomenon of the historical fault is specifically as follows: based on semantic content, the fault phenomenon of the historical fault is retrieved and calculated to obtain a set of historical faults in which the similarity between the current fault and the historical fault in terms of fault phenomenon is ranked from large to small.
[0015] More preferably, S3 specifically involves: based on the obtained set of historical faults with the highest similarity to the current fault in terms of operating parameters at the time of the fault and the set of historical faults with the highest similarity in terms of fault phenomena, querying the expert guidance standard library established in S1 using the fault cause association of historical faults to obtain the expert guidance assistance scheme corresponding to the current fault.
[0016] More preferably, the expert guidance and assistance scheme includes: fault code, fault name, wind turbine system, fault cause, handling method and steps, spare parts replacement information, tool information, safety information, personnel configuration information and relevant drawings and documents.
[0017] This invention discloses an expert guidance and assistance system for offshore wind power, comprising:
[0018] The module for establishing an expert guidance standard library creates an expert guidance standard library based on the causes of failures. This library is created and entered by relevant experts based on current technology and historical experience.
[0019] The similarity calculation module calculates the similarity between the current fault and historical faults in terms of both operating parameters and fault phenomena at the time of the fault occurrence.
[0020] The fault cause determination module determines the fault cause of historical faults based on similarity calculation results;
[0021] The expert guidance and assistance solution determination module uses the fault causes of historical faults to associate with the expert guidance standard library and obtains the expert guidance and assistance solution corresponding to the current fault.
[0022] Preferably, it further includes:
[0023] The maintenance and update module maintains and updates the expert guidance standards library;
[0024] The expert guidance and assistance solution recommendation module provides reference and basis for troubleshooting personnel to carry out troubleshooting work based on the currently provided expert guidance and assistance solutions. When multiple guidance solutions are involved, they are tried in descending order of recommendation until the fault is finally resolved.
[0025] Compared with the prior art, the present invention has the following beneficial technical effects:
[0026] This invention discloses an expert guidance and assistance method for offshore wind power, which fully considers the high complexity, high cost, and high timeliness requirements in handling offshore wind turbine failures. From an expert's perspective, it provides recommended guidance solutions to assist in failure handling. First, based on the current failure phenomenon and operating parameters at the time of the failure, data processing and cleaning are performed. Then, for the current failure and historical failures, the similarity of failure phenomena and the similarity of operating parameters at the time of the failure are calculated, and the cause of the historical failure with the highest similarity is obtained. By associating the failure cause with an expert guidance database, guidance solutions are obtained for failure handling personnel to refer to, greatly improving failure handling efficiency, reducing failure handling difficulty, and reducing labor costs. Attached Figure Description
[0027] Figure 1 This is a flowchart illustrating the method for calculating the similarity between current faults and historical faults in this invention. Detailed Implementation
[0028] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments. These descriptions are intended to explain the invention and not to limit it.
[0029] The expert guidance and assistance method and system for offshore wind power of the present invention includes:
[0030] Data interface module
[0031] The data interface module provides the recommendation algorithm module with the necessary data, including: current fault symptoms, operating parameters at the time of the current fault, historical fault symptoms, operating parameters at the time of historical faults, and an expert guidance library.
[0032] The current fault symptoms include: the fault name and a description of the fault symptoms.
[0033] The operating parameters at the time of the current fault include: the operating parameter information of the wind turbine at the time the current fault occurred.
[0034] Historical fault phenomena include: fault name and fault phenomenon description.
[0035] The operating parameters at the time of the historical fault include: the operating parameter information of the wind turbine at the time the historical fault occurred.
[0036] The expert guidance database includes: fault name, fault cause, handling methods and steps, replacement parts information, tool information, safety information, personnel configuration information, and relevant drawings and documents.
[0037] Recommendation algorithm module
[0038] The recommendation algorithm is the core of this invention. The data input through the data interface module is used for algorithm operation and processing analysis. It calculates the similarity between the current fault and historical faults from two aspects: fault phenomena and operating parameters at the time of the fault. This allows it to obtain the fault causes of historical faults with high similarity. By associating with the expert guidance standard library, it finally outputs the guidance scheme with the highest recommendation degree to assist fault handling personnel in troubleshooting and handling faults in offshore wind turbines.
[0039] Suppose there exists a fault set F = {F0, F1, F2, ..., Fn} consisting of one unprocessed current fault and n processed historical faults. n}, where F0 represents the current fault, F1, F2, ..., F n Representing historical faults, the calculation steps of the recommendation algorithm are as follows: Figure 1 As shown:
[0040] The detailed steps and principles are as follows:
[0041] Step 1: Processing operating parameters at the current time of the fault
[0042] Enter the name of the current fault, the time of the current fault, and the operating parameters.
[0043] For the operating parameters at the time of the fault, an alternating factor elimination algorithm is used to remove data factors from the operating parameters at the time of the fault that did not affect the occurrence of the fault. For the operating parameter P at the time of the fault, G(P) represents the data factors it contains, and the calculation of the elimination algorithm is shown in the following formula:
[0044]
[0045] In the formula, s represents the type of data factors affecting the operating parameters at the time of the fault, and u j The value represents the proportion of data factors influencing the operating parameters at the time of failure within the original operating parameters at the time of failure. When the calculated result of the data factor influencing the operating parameters at the time of failure is greater than the influence value of the operating parameters at the time of failure, the operating parameter P at that time of failure is removed, and the influence value s of the operating parameters at the time of failure is determined. j The calculation is shown in the following formula:
[0046] s j =(s j -mins j ) / (maxs j -mins j )
[0047] By eliminating data factors from the operating parameters at the time of the fault that did not affect the occurrence of the fault, the accuracy and completeness of the operating parameters at the time of the offshore wind turbine fault are ensured. After eliminating data factors from the operating parameters at the time of the fault that did not affect the occurrence of the fault, the operating parameters at the time of the fault are calculated as follows:
[0048] L(u) = -(u1 × log2(u1) + ... + u n ×log2(u n ))
[0049] In the formula, n represents the types of data factors affecting the operating parameters at the time of the fault after removal, L(u) represents the number of times the operating parameters occur at the time of the fault, and u n This represents the proportion of the operating parameters at each fault moment to the total operating parameters at all fault moments.
[0050] Using the above formula, the processing of the operating parameters at the current fault time is completed, resulting in the operating parameters at the current fault time as P_F0(f 01 ,f 02 ,f 03 ,f 04 ,...,f 0m ), where m is the number of preprocessed fault time operation parameters.
[0051] Step 2: Processing operating parameters at the time of historical faults
[0052] Using the calculation formula in step 1, the operating parameters at the time of the historical fault are processed to obtain the operating parameters at the time of the nth historical fault as P_F. n (f n1 ,fn2 ,f n3 ,f n4 ,...,f nm ).
[0053] Step 3: Calculation of similarity of operating parameters at the time of failure
[0054] Based on the operating parameters at the time of the current fault obtained from step 1 and the operating parameters at the time of the historical fault obtained from step 3, the similarity between the current fault and the historical fault in terms of operating parameters at the time of the fault is calculated. The calculation of the similarity is shown in the following formula:
[0055]
[0056] The calculated similarity scores are ranked from highest to lowest to obtain a set of historical faults whose similarity to the current fault and historical faults in terms of operating parameters at the time of the fault is ranked from highest to lowest. in The historical fault with the highest similarity in operating parameters at the time of the fault. The historical fault with the lowest similarity in operating parameters at the time of the fault.
[0057] Step 4: Calculation of similarity of fault phenomena
[0058] For the current fault symptom C, the fault symptom of historical faults is retrieved based on semantic content as shown in the following formula:
[0059]
[0060] Where N represents the total number of semantic content entries in the fault phenomena of historical faults, a and z represent the attribute sets of the fault phenomena of the current fault and the fault phenomena of historical faults, respectively, and F O F q F v This represents the frequency of attributes o, q, and v in the content. o indicates the shared attributes between the current fault's symptoms and those of historical faults; q indicates attributes included in historical fault symptoms but not in the current fault's symptoms; and v indicates attributes included in the current fault's symptoms but not in historical fault symptoms. Thus, a set of historical faults with decreasing similarity to the current fault in terms of symptoms is calculated. in These are the historical faults with the highest similarity in their fault symptoms. The historical faults with the least similarity in fault symptoms.
[0061] Step 5: Recommended Guidance Plan
[0062] Based on the historical fault set obtained from step 3 The historical fault set obtained from step 4 An expert guidance standard library is established by associating historical fault causes with other faults. Guidance solutions for the corresponding fault causes are obtained. The similarity between the current fault and historical faults is the recommendation degree of the guidance solution. The information in the guidance solution includes: relevant drawings, relevant documents, operation steps, safety information, and personnel and spare parts configuration information.
[0063] Application Function Module
[0064] The application features include an expert guidance library and recommended guidance solutions.
[0065] The expert guidance module allows experts to maintain and update guidance plans.
[0066] The guidance solution recommendation module provides system-recommended guidance solutions for the current fault, offering reference and guidance for troubleshooting personnel. When multiple guidance solutions are involved, they can be tried in descending order of recommendation level until the fault is finally resolved.
[0067] Result Output Module
[0068] It has a data service interface, which allows other systems to call the guidance scheme recommendation function of this invention.
[0069] It should be noted that the above description is only a part of the embodiments of the present invention, and all equivalent changes made to the system described in this invention are included within the protection scope of this invention. Those skilled in the art can make similar substitutions to the specific examples described, as long as they do not deviate from the structure of the invention or exceed the scope defined in these claims, all of which fall within the protection scope of this invention.
Claims
1. An expert guidance and assistance method for offshore wind power, characterized in that, include: S1: Establish an expert guidance standard library based on the causes of failures. This library is created and entered by relevant experts based on current technology and historical experience. S2: Calculate the similarity between the current fault and the historical fault in terms of operating parameters and fault phenomena at the time of the fault occurrence, and determine the cause of the historical fault based on the similarity calculation results; S3: Use the causes of historical faults to associate with the expert guidance standard library established in S1 to obtain the expert guidance assistance scheme corresponding to the current fault; In S2, when obtaining the operating parameters of the current fault, the interleaved factor elimination algorithm is used to eliminate data factors in the operating parameters at the fault time that did not affect the occurrence of the fault, so as to obtain the operating parameters of the current fault. When obtaining the operating parameters of historical faults, the interleaved factor elimination algorithm is used to eliminate data factors in the operating parameters at the fault time that did not affect the occurrence of the fault, so as to obtain the operating parameters of historical faults. In S2, the similarity calculation between the operating parameters of the current fault and the operating parameters of the historical fault is as follows: based on the obtained operating parameters of the current fault and the operating parameters of the historical fault, the similarity between the current fault and the historical fault in terms of the operating parameters at the time of the fault is calculated respectively; the calculated similarity is ranked from large to small to obtain the set of historical faults in which the similarity between the current fault and the historical fault in terms of the operating parameters at the time of the fault is ranked from large to small. In S2, the similarity calculation between the fault phenomena of the current fault and the fault phenomena of historical faults is as follows: based on semantic content, the fault phenomena of historical faults are retrieved and calculated to obtain a set of historical faults in which the similarity between the current fault and historical faults in terms of fault phenomena is ranked from large to small.
2. The expert guidance and assistance method for offshore wind power as described in claim 1, characterized in that, In S1, the information in the expert guidance standard library includes: fault name, fault cause, handling method and steps, replacement spare parts information, tool information, safety information, personnel configuration information, and drawings.
3. The expert guidance and assistance method for offshore wind power as described in claim 1, characterized in that, In S2, the current fault phenomenon includes the fault name and fault phenomenon description, and the current fault operating parameters include the operating parameter information of the wind turbine corresponding to the time when the current fault occurred. The fault phenomena of historical faults include the fault name and fault phenomenon description, and the operating parameters of historical faults include: the operating parameter information of the wind turbine corresponding to the time when the historical fault occurred.
4. The expert guidance and assistance method for offshore wind power as described in claim 3, characterized in that, Specifically, S3 involves: based on the set of historical faults obtained from the current fault and the set of historical faults with the same similarity in terms of operating parameters at the time of the fault, ranked from largest to smallest, and the set of historical faults with the same similarity in terms of fault phenomena, querying the expert guidance standard library established in S1 using the fault cause association of historical faults, and obtaining the expert guidance assistance scheme corresponding to the current fault.
5. The expert guidance and assistance method for offshore wind power as described in claim 1, characterized in that, The expert guidance and assistance plan includes: fault code, fault name, wind turbine system, fault cause, handling method and steps, replacement spare parts information, tool information, safety information, personnel configuration information and relevant drawings and documents.
6. An expert guidance and assistance system for offshore wind power that implements the expert guidance and assistance method for offshore wind power as described in any one of claims 1-5, characterized in that, include: The module for establishing an expert guidance standard library creates an expert guidance standard library based on the causes of failures. This library is created and entered by relevant experts based on current technology and historical experience. The similarity calculation module calculates the similarity between the current fault and historical faults in terms of both operating parameters and fault phenomena at the time of the fault occurrence. The fault cause determination module determines the fault cause of historical faults based on similarity calculation results; The expert guidance and assistance solution determination module uses the causes of historical faults to associate with the expert guidance standard library to obtain the expert guidance and assistance solution corresponding to the current fault.
7. The expert guidance and assistance system for offshore wind power as described in claim 6, characterized in that, Also includes: The maintenance and update module maintains and updates the expert guidance standards library; The expert guidance and assistance solution recommendation module provides reference and basis for troubleshooting personnel to carry out troubleshooting and handling work based on the currently provided expert guidance and assistance solutions. When multiple guidance options are involved, try them in descending order of recommendation until the fault is finally resolved.