Wind power plant fault linkage early warning method and system based on digital twinning
Through the combination of the digital twin platform and the Internet of Things monitoring platform, accurate detection and early warning of wind farm faults is achieved, the problem of low accuracy of wind farm fault detection is solved, and the operational safety and stability of wind farms is improved.
Patent Information
- Application Number
- CN202410981961.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-26
AI Technical Summary
The accuracy of wind farm fault detection is low, which often causes the fault to be detected after the impact is caused. It is difficult to ensure that relevant personnel obtain key information in a timely manner and take effective measures.
Based on the digital twin platform, the wind farm is modeled, combined with the real-time data and control plan information of the Internet of Things monitoring platform, state prediction and fault detection are carried out, and the linkage warning device is activated to achieve early warning.
It improves the operating safety and stability of wind farms, and through accurate fault detection and early warning, the time for the impact of faults is reduced, and the timeliness and effectiveness of management is improved.
Smart Images

Figure CN119028094A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of wind energy technology, and in particular to a wind farm fault linkage early warning method and system based on digital twins. Background Art
[0002] In the field of wind farm operation and management, the continuous expansion of its scale has made the operation and management more and more complex, especially in terms of fault warning and handling, the challenges faced are more severe. The contradiction between the demand for safe and stable operation and the lack of management means is becoming increasingly acute, and it is imperative to seek more efficient and intelligent wind farm management methods. Traditional wind farm management methods usually have many limitations. For example, the acquisition of monitoring data is not comprehensive and the real-time performance is poor, which makes it difficult to accurately reflect the actual operating status of the wind farm; the ability to predict the future status of the wind farm is weak, and it is impossible to make effective response preparations in advance; the fault detection method is relatively lagging, and it is often detected only after the fault has caused a greater impact; the early warning means are single and the effect is not good, and it is difficult to ensure that relevant personnel can obtain key information in time and take effective measures.
[0003] In the current related technologies, there is a technical problem of low accuracy in wind farm fault detection. Summary of the invention
[0004] The present application provides a wind farm fault linkage warning method and system based on digital twins, which adopts a wind farm modeling based on a digital twin platform to obtain a model; obtains a real-time data set based on an Internet of Things monitoring platform; obtains control scheme information, and predicts the wind farm status in combination with the model to obtain a prediction result; detects faults based on the real-time data set and the prediction result to obtain a detection report; activates a linkage warning device, and combines the report warning to achieve the technical effect of improving the safety and stability of wind farm operation.
[0005] This application provides a wind farm fault linkage early warning method based on digital twins, including:
[0006] The wind farm is modeled based on the digital twin platform to obtain a wind farm model; based on the Internet of Things monitoring platform, a real-time monitoring data set of the wind farm is obtained; the control scheme information of the wind farm is obtained, and the state of the wind farm is predicted in combination with the wind farm model to obtain a wind farm state prediction result; fault detection is performed on the wind farm based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report; the linkage early warning device is activated, and an early warning is issued to the wind farm in combination with the wind farm fault detection report.
[0007] This application also provides a wind farm fault linkage early warning system based on digital twins, including:
[0008] A wind farm model acquisition module, the wind farm model acquisition module is used to model the wind farm based on the digital twin platform to obtain a wind farm model; a real-time monitoring data set acquisition module, the real-time monitoring data set acquisition module is used to obtain a real-time monitoring data set of the wind farm based on the Internet of Things monitoring platform; a wind farm state prediction result acquisition module, the wind farm state prediction result acquisition module is used to obtain the control scheme information of the wind farm, and perform state prediction on the wind farm in combination with the wind farm model to obtain a wind farm state prediction result; a wind farm fault detection report acquisition module, the wind farm fault detection report acquisition module is used to perform fault detection on the wind farm based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report; a linkage warning device activation module, the linkage warning device activation module is used to activate the linkage warning device, and warn the wind farm in combination with the wind farm fault detection report.
[0009] The wind farm fault linkage early warning method and system based on digital twin proposed in this application first models the wind farm based on the digital twin platform to obtain a model; obtains a real-time data set based on the Internet of Things monitoring platform; obtains control scheme information, and predicts the wind farm status in combination with the model to obtain a prediction result; detects faults based on the real-time data set and the prediction result to obtain a detection report; activates the linkage early warning device, and combines the report warning to achieve the technical effect of improving the safety and stability of wind farm operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.
[0011] Figure 1 A schematic diagram of a flow chart of a wind farm fault linkage warning method based on digital twins provided in an embodiment of the present application;
[0012] Figure 2 A schematic diagram of the structure of a wind farm fault linkage warning system based on digital twins provided in an embodiment of the present application.
[0013] Description of the accompanying drawings: wind farm model acquisition module 10, real-time monitoring data set acquisition module 20, wind farm state prediction result acquisition module 30, wind farm fault detection report acquisition module 40, linkage warning device activation module 50. DETAILED DESCRIPTION
[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.
[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.
[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.
[0017] The embodiment of the present application provides a wind farm fault linkage warning method based on digital twins, such as Figure 1 As shown, the method includes:
[0018] Step S100, modeling the wind farm based on the digital twin platform to obtain a wind farm model. Specifically, the wind farm modeling work covers the comprehensive construction and shaping of the wind farm on the digital twin platform, aiming to obtain an accurate wind farm model that can truthfully reflect the actual situation. First, various basic information of the wind farm is widely collected, such as the geographical conditions of the wind farm, including topography, landforms and altitude, detailed parameters of wind turbines, such as model, power, blade length and tower height, configuration details of the power transmission system, such as the direction of cable lines, layout of substations, etc., and relevant data of the surrounding environment, such as the distribution of wind speed and wind direction throughout the year, etc. After obtaining these basic information, relying on the modeling tools and functions of the digital twin platform, the physical model of the wind farm is constructed. For the wind turbines, accurate three-dimensional shaping is carried out in strict accordance with their actual physical structure and size, covering blades, towers, nacelles and other components. At the same time, each component is given corresponding physical properties, such as material properties, weight, moment of inertia, etc. After completing the construction of the physical model , further establish the logical model of the wind farm, which includes clarifying the operating logic of the wind turbine, such as start-up, shutdown, speed control, etc., the logic of power transmission, such as the distribution of electric energy, loss calculation, etc., as well as the interaction logic between the entire wind farm and the external power grid. In order to make the model closer to reality and more accurate, dynamic data will be introduced, such as incorporating historical wind speed and wind direction data into the model to simulate the operating status of wind turbines under different wind conditions. At the same time, considering factors such as equipment aging and wear, the model is dynamically adjusted and optimized. In the process of modeling, the model verification and calibration work is continuously carried out, and the results of the model output are compared with the actual wind farm operating data, such as power generation, equipment failure rate, etc. If there is a deviation, the cause is analyzed and the model is corrected to ensure that the model can accurately reflect the actual operation of the wind farm. The wind farm model finally obtained on the digital twin platform has laid a solid foundation for subsequent monitoring, prediction, fault detection and other operations.
[0019] In a possible implementation, a wind farm is modeled based on a digital twin platform to obtain a wind farm model, and step S100 further includes step S110, wherein the wind farm includes a primary system and a secondary system. Specifically, it is clarified that a wind farm includes a primary system and a secondary system, and the primary system generally includes wind turbines, transformers, transmission lines and other equipment directly involved in the production and transmission of electric energy; the secondary system covers measurement, control, protection, communication and other equipment and systems used to monitor and manage the primary system.
[0020] Step S120, modeling the primary system based on the digital twin platform to obtain a primary wind farm model. Specifically, when modeling the primary system based on the digital twin platform, the detailed parameters and operating characteristics of each device in the primary system are collected, such as the mechanical structure, blade characteristics, and generator parameters of the wind turbine; the capacity, ratio, and impedance of the transformer; the length, model, resistance, and reactance of the transmission line, etc., and the modeling tools and algorithms of the digital twin platform are used to construct a digital model of each device in the primary system based on these parameters, and the connection and interaction between them are taken into account, so as to obtain a primary wind farm model.
[0021] Step S130, modeling the secondary system based on the digital twin platform to obtain a secondary wind farm model. Specifically, the secondary system is modeled based on the digital twin platform to obtain technical specifications, control logic, communication protocols and other information of various types of equipment in the secondary system, such as the accuracy and range of the measuring device, the action setting value and logic of the protection device, the transmission rate and protocol of the communication device, etc., and by setting the corresponding model parameters and logical relationships in the digital twin platform, a digital model of the secondary system is constructed to obtain a secondary wind farm model.
[0022] Step S140, fuse the primary wind farm model and the secondary wind farm model to generate the wind farm model. Specifically, after obtaining the primary wind farm model and the secondary wind farm model respectively, a fusion operation is performed. During the fusion process, it is necessary to establish an association and interaction relationship between the primary system and the secondary system, such as matching the measurement data in the secondary system with the equipment operating status in the primary system, accurately transmitting the control instructions from the secondary system to the corresponding equipment in the primary system, realizing seamless connection of data and control signals, coordinating and integrating the two models in terms of interface, data format, time synchronization, etc., to ensure that the fused model can accurately reflect the overall operating status and control logic of the wind farm, and finally generate a complete wind farm model.
[0023] In a possible implementation, the primary system is modeled based on the digital twin platform to obtain a primary wind farm model, and step S120 further includes step S121, collecting basic information of the primary system according to the Internet of Things monitoring platform to obtain a primary wind farm information set. Specifically, the basic information of the primary system is collected with the help of the Internet of Things monitoring platform. The sensors and monitoring equipment in the Internet of Things monitoring platform will collect data related to the primary system. The data covers the operating parameters of the wind turbine (such as speed, power, temperature, etc.), the working status of the transformer (voltage, current, oil temperature, etc.), the electrical parameters of the transmission line (resistance, reactance, capacitance, etc.) and the performance indicators and operating conditions of other related equipment, etc. The collected raw data are integrated to form a primary wind farm information set.
[0024] Step S122, data cleaning is performed according to the primary wind farm information set to obtain a primary wind farm basic data set. Specifically, the acquired primary wind farm information set is cleaned. At this stage, the integrity and accuracy of the data are checked, duplicate, erroneous or missing data are removed, abnormal values are processed, such as data points that obviously deviate from the normal range, and are corrected or eliminated through reasonable methods (such as average value replacement, interpolation, etc.), and the format of the data is unified and standardized for subsequent processing and analysis. After the cleaning steps, a high-quality, accurate and uniformly formatted primary wind farm basic data set is obtained.
[0025] Step S123, construct the primary wind farm model based on the digital twin platform and the primary wind farm basic data set. Specifically, the primary wind farm model is constructed based on the digital twin platform and the cleaned primary wind farm basic data set. The digital twin platform provides a powerful modeling environment and tools, which combines the data in the basic data set with the modeling elements and algorithms in the platform. According to the physical structure and working principle of each device in the primary system, the corresponding model parameters and logical relationships are set in the platform. Mathematical models and simulation technology are used to simulate the operating behavior of the devices in the primary system and the dynamic interaction between them. Through continuous debugging and optimization, the constructed model can accurately reflect the actual operating characteristics and performance of the primary system, and finally form an accurate and reliable primary wind farm model.
[0026] Step S200: obtaining a real-time monitoring data set of the wind farm according to the Internet of Things monitoring platform. Specifically, the wind farm real-time monitoring data set refers to a collection of various real-time data of the wind farm obtained through the Internet of Things monitoring platform. Numerous sensors and monitoring equipment deployed in the wind farm, such as speed sensors, power sensors, temperature sensors, vibration sensors, etc. on wind turbines, as well as current transformers and voltage transformers on transmission lines, and anemometers and wind vanes used to measure the environment, continuously collect real-time data of key parts and equipment in the wind farm. The data collected by the sensors are quickly transmitted to the data concentrator or gateway through wired or wireless communication methods such as Ethernet. The data concentrator or gateway preliminarily organizes and summarizes these raw data to ensure the integrity and consistency of the data. The organized data is then transmitted to the server side of the Internet of Things monitoring platform with the help of networks such as 4G / 5G networks and dedicated communication lines. The database system on the server side receives and stores these real-time data to form a continuously updated data set. Security measures such as data encryption and identity authentication are adopted during data transmission and storage to ensure the confidentiality, integrity and availability of the data to prevent the data from being illegally accessed or tampered with. Finally, users can access and obtain this real-time monitoring data set at any time on the user interface of the Internet of Things monitoring platform for further analysis, processing and decision-making.
[0027] Step S300, obtain the control scheme information of the wind farm, perform state prediction on the wind farm in combination with the wind farm model, and obtain the wind farm state prediction result. Specifically, the control scheme information of the wind farm refers to various detailed regulations and parameters covering the operation control of the wind farm. Obtain relevant control scheme information, integrate it with the constructed wind farm model, implement state prediction on the wind farm, and thus obtain the wind farm state prediction result. Among them, the control scheme information includes the start-up and shutdown strategy of the wind turbine, power regulation criteria, operation mode settings under different wind speeds, and control strategies for interaction with the power grid. Then, input such control scheme information into the wind farm model, combined with current or expected environmental conditions, such as wind speed, wind direction, temperature, etc., as well as external factors such as the demand and restrictions of the power grid. Relying on the algorithm and simulation mechanism in the model, the control scheme and these input conditions are comprehensively considered, and the operation state of the wind farm in the future period is calculated and speculated. This process covers many aspects such as the power output of the wind turbine, the operating efficiency of the equipment, the potential risk of failure, and the stability of power transmission. After a series of complex calculations and analyses, the wind farm status prediction results are finally obtained. The results are presented in the form of data, charts or reports, providing valuable references for the operation and management of wind farms, helping to formulate optimization strategies and response measures in advance to ensure the efficient and stable operation of wind farms.
[0028] Step S400, based on the real-time monitoring data set and the wind farm state prediction result, the wind farm is detected for faults, and a wind farm fault detection report is obtained. Specifically, the wind farm fault detection refers to the fault detection work implemented on the wind farm based on the real-time monitoring data set and the state prediction result, and the corresponding fault detection report is obtained. The real-time monitoring data set is obtained, which covers the detailed data of various equipment and systems in the wind farm at the current operating moment, such as the speed, temperature, vibration amplitude of the wind turbine, and the current and voltage of the transmission line. At the same time, the wind farm state prediction result previously obtained by model prediction is obtained. Subsequently, the various parameters in the real-time monitoring data set are compared and analyzed with the corresponding data in the state prediction result, and the difference between the actual value and the predicted value of each parameter is carefully checked to explore possible abnormal situations. For parameters with large deviations, the reasons behind them are further explored, and the working principle of wind farm equipment, historical fault data, and relevant professional knowledge and experience are combined to determine whether such deviations mean potential faults. During the analysis process, special fault detection algorithms and models are used. These algorithms and models can evaluate whether they are in the normal working range and the severity of the abnormality based on the characteristics of different types of equipment and parameters. Comprehensive and systematic detection and evaluation are carried out on all key equipment and systems in the entire wind farm, and the correlation between multiple parameters and factors is comprehensively considered to determine whether there is a fault and the type, location and possible impact range of the fault. After a series of rigorous analysis and judgment, the test results are sorted and summarized to generate a detailed wind farm fault detection report. The report clearly indicates the specific status of the fault, including the name of the faulty equipment, the type of fault, the location of occurrence, the severity and other key information, providing an accurate and clear basis for subsequent maintenance and processing.
[0029] In a possible implementation, the wind farm is fault-detected based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report, and step S400 further includes step S410, performing feature recognition based on the real-time monitoring data set to obtain a primary wind farm monitoring data set and a secondary wind farm monitoring data set. Specifically, in-depth feature recognition is performed on the real-time monitoring data set, and through data analysis, key features and data related to the primary wind farm are extracted from the huge real-time monitoring data set to form a primary wind farm monitoring data set; at the same time, the features and data related to the secondary wind farm are separated to form a secondary wind farm monitoring data set.
[0030] Step S420, feature recognition is performed based on the wind farm state prediction result to obtain a primary state prediction result and a secondary state prediction result. Specifically, feature recognition is performed on the wind farm state prediction result to identify the portion corresponding to the primary wind farm from the overall prediction result, thereby obtaining a primary state prediction result; and the prediction content corresponding to the secondary wind farm is found to obtain a secondary state prediction result.
[0031] Step S430, performing fault detection based on the primary wind farm monitoring data set and the primary state prediction result to generate a primary fault detection result. Specifically, the primary wind farm monitoring data set is combined with the primary state prediction result to perform fault detection, using an advanced fault detection model to compare the differences and rules between the monitoring data and the prediction results, carefully analyzing possible anomalies and deviations therein, so as to determine whether there is a fault in the primary wind farm, and generate a detailed primary fault detection result.
[0032] Step S440, performing fault detection according to the secondary wind farm monitoring data set and the secondary state prediction result to generate a secondary fault detection result. Specifically, similar fault detection operations are performed on the secondary wind farm monitoring data set and the secondary state prediction result, and corresponding detection means and techniques are used to comprehensively check potential faults in the secondary wind farm, and finally generate a secondary fault detection result.
[0033] Step S450, sorting the primary fault detection results and the secondary fault detection results, and generating the wind farm fault detection report. Specifically, the primary fault detection results and the secondary fault detection results are systematically sorted and summarized, considering the fault conditions of the primary and secondary wind farms, analyzing the correlation and mutual influence between them, and by sorting and analyzing these results, generating a comprehensive, accurate and integrated wind farm fault detection report, providing strong support and decision-making basis for subsequent wind farm maintenance and management.
[0034] In a possible implementation, fault detection is performed based on the primary wind farm monitoring data set and the primary state prediction result to generate a primary fault detection result, and step S430 further includes step S431, loading a primary wind farm fault record library based on the Internet of Things monitoring platform. Specifically, a primary wind farm fault record library is obtained based on the Internet of Things monitoring platform, and the fault record library stores various fault information that occurred in the primary wind farm in the past, including the time of the fault, equipment type, fault description, maintenance processing method and other detailed contents.
[0035] Step S432, perform standardization processing on the primary wind farm fault record library to obtain a primary wind farm fault record set. Specifically, the obtained primary wind farm fault record library is standardized, and the data format, encoding method, unit, etc. in the fault record need to be unified and standardized, duplicate, erroneous or incomplete records need to be removed, and text information such as fault description need to be classified and encoded to form a standardized and structured primary wind farm fault record set.
[0036] Step S433, construct a primary wind farm fault detection model based on the primary wind farm fault record set. Specifically, the primary wind farm fault detection model is constructed using the standardized primary wind farm fault record set. During the construction process, data analysis and machine learning algorithms are used to extract key features and rules in the fault record set, such as the failure modes that are prone to occur in certain equipment under specific operating conditions, the association between different fault types, etc. Based on these features and rules, a model that can identify and predict primary wind farm faults is established.
[0037] Step S434, based on the primary wind farm monitoring data set and the primary state prediction result, according to the primary wind farm fault detection model, output the primary fault detection result. Specifically, based on the acquired primary wind farm monitoring data set and the primary state prediction result, they are input into the constructed primary wind farm fault detection model, and the model will analyze and calculate the input data, compare the monitoring data and prediction results with the fault modes and laws learned in the model, and determine whether there are abnormalities or conform to known fault characteristics, thereby outputting accurate primary fault detection results, which will provide the wind farm operation and maintenance personnel with important information such as whether the primary wind farm equipment has a fault, the type of fault, and the severity of the fault, so that corresponding maintenance and preventive measures can be taken in a timely manner.
[0038] In a possible implementation, fault detection is performed based on the secondary wind farm monitoring data set and the secondary state prediction result to generate a secondary fault detection result. Step S440 further includes step S441, building a secondary wind farm fault detection model. Specifically, a secondary wind farm fault detection model is built to collect and analyze a large amount of fault data and operating characteristic information related to the secondary wind farm, determine key indicators and parameters for fault detection, such as the operating temperature, current change, voltage fluctuation, etc. of the equipment, select a suitable modeling method, based on statistical methods, machine learning algorithms, or models based on physical principles. In the modeling process, the collected data is preprocessed, including data cleaning, feature engineering and other operations, and representative features are extracted to provide effective input for model training and optimization, and the parameters and structure of the model are continuously adjusted. The model is evaluated and verified using a validation set to ensure the accuracy and reliability of the model.
[0039] Step S442, based on the secondary wind farm monitoring data set and the secondary state prediction result, according to the secondary wind farm fault detection model, obtain the secondary fault detection result. Specifically, after the secondary wind farm fault detection model is built, the model is applied based on the secondary wind farm monitoring data set and the secondary state prediction result, and the detailed data in the monitoring data set, such as the real-time operating parameters and environmental conditions of each device, and the relevant information in the secondary state prediction result, are input into the fault detection model. After receiving these inputs, the model will analyze and compare the input data according to its internal calculation logic and learned mode, and determine whether the data conforms to the normal operation mode, or whether there are features that match the known fault mode, and finally output the secondary fault detection result, clearly indicating whether there is a fault in the secondary wind farm, as well as important information such as the possible fault type, location and severity, to provide powerful guidance for subsequent maintenance and repair work.
[0040] In a possible implementation, the primary fault detection result and the secondary fault detection result are collated to generate the wind farm fault detection report, and step S450 further includes step S451, obtaining a predetermined fault report template. Specifically, the predetermined fault report template is obtained, and the template is usually designed in advance according to the specifications and requirements of the wind farm fault report, and contains fixed sections and formats such as basic fault information, detection methods, possible causes, etc.
[0041] Step S452, according to the predetermined fault report template, the primary fault detection result and the secondary fault detection result are sorted to obtain an initial fault detection report. Specifically, according to the predetermined fault report template, the primary fault detection result and the secondary fault detection result are sorted, and the detailed information such as the specific faulty equipment, fault type, occurrence time, severity, etc. obtained in the primary and secondary fault detections are classified and filled in according to the requirements of the template, thereby forming an initial fault detection report.
[0042] Step S453, performing fault linkage analysis based on the primary fault detection result and the secondary fault detection result to obtain the wind farm fault linkage analysis result. Specifically, performing fault linkage analysis based on the primary fault detection result and the secondary fault detection result, considering the relevant equipment and fault conditions involved in the two detection results, analyzing the cause-effect relationship, mutual influence and possible chain reactions between them. For example, whether the failure of a certain primary equipment will affect the operation of the secondary system, or whether the failure in the secondary system is indirectly caused by the problem of the primary equipment. Through in-depth analysis and reasoning, the wind farm fault linkage analysis result is obtained.
[0043] Step S454, optimize the initial fault detection report according to the wind farm fault linkage analysis result to obtain the wind farm fault detection report. Specifically, the initial fault detection report is optimized according to the wind farm fault linkage analysis result, and on the basis of the initial report, the correlation information between faults, possible development trends, and comprehensive suggestions and response strategies for the overall fault situation are supplemented, so that the report can more comprehensively and accurately reflect the fault status and potential risks of the wind farm, and finally obtain a complete wind farm fault detection report, which provides valuable reference and guidance for the maintenance, repair and subsequent operation of the wind farm.
[0044] Step S500, activate the linkage early warning device, and warn the wind farm in combination with the wind farm fault detection report. Specifically, the activation operation of the linkage early warning device refers to a series of early warning actions performed after the wind farm fault detection report is generated and confirmed. The linkage early warning device covers a variety of forms, such as sound and light alarms, electronic display screens, SMS push systems, email sending systems, etc. Once the activation command is received, the linkage early warning device immediately obtains key information in the wind farm fault detection report. This key information includes the severity of the fault, the specific location, the possible scope of impact, and the expected development trend. Then, according to the acquired fault detection report information, the linkage early warning device carries out early warning actions according to preset rules and logic. For example, if the severity of the fault is quite high, the sound and light alarm will send a strong sound and light signal to attract the immediate attention of the on-site staff; the electronic display screen will scroll to display the details of the fault so that relevant personnel can quickly know. For situations that require remote notification, the SMS push system will send SMS messages containing fault details to relevant managers and technicians, and the email sending system will send detailed fault detection reports to specific mailboxes so that they can promptly understand the fault conditions of the wind farm even if they are not on site. During the entire early warning process, the linkage early warning device continues to operate to ensure that the early warning information can be conveyed to all those who need to know in a timely and accurate manner. At the same time, according to changes in fault conditions and new detection results, the content and method of early warning are continuously updated and adjusted to ensure the safe and stable operation of the wind farm.
[0045] The embodiment of the present application adopts a digital twin platform to model the wind farm and obtain a model; obtains a real-time data set based on the Internet of Things monitoring platform; obtains control scheme information, and predicts the state of the wind farm in combination with the model to obtain a prediction result; detects faults based on the real-time data set and the prediction result to obtain a detection report; activates the linkage early warning device, and combines the report with the early warning, thereby achieving the technical effect of improving the safety and stability of the wind farm operation.
[0046] In the above, refer to Figure 1 The wind farm fault linkage warning method based on digital twin according to an embodiment of the present invention is described in detail. Figure 2A wind farm fault linkage warning system based on digital twin according to an embodiment of the present invention is described.
[0047] The wind farm fault linkage warning system based on digital twins according to the embodiment of the present invention is used to solve the technical problem of low accuracy of fault detection in existing wind farms, and achieve the technical effect of improving the safety and stability of wind farm operation. The wind farm fault linkage warning system based on digital twins includes: a wind farm model acquisition module 10, a real-time monitoring data set acquisition module 20, a wind farm state prediction result acquisition module 30, a wind farm fault detection report acquisition module 40, and a linkage warning device activation module 50.
[0048] The wind farm model acquisition module 10 is used to model the wind farm based on the digital twin platform to obtain the wind farm model;
[0049] The real-time monitoring data set acquisition module 20 is used to obtain the real-time monitoring data set of the wind farm according to the Internet of Things monitoring platform;
[0050] The wind farm state prediction result acquisition module 30 is used to obtain the control scheme information of the wind farm, perform state prediction on the wind farm in combination with the wind farm model, and obtain the wind farm state prediction result;
[0051] The wind farm fault detection report acquisition module 40 is used to perform fault detection on the wind farm based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report;
[0052] The linkage warning device activation module 50 is used to activate the linkage warning device and issue a warning to the wind farm in combination with the wind farm fault detection report.
[0053] The specific configuration of the wind farm model acquisition module 10 will be described in detail below. As described above, the wind farm is modeled based on the digital twin platform to obtain a wind farm model. The wind farm model acquisition module 10 may further include: a wind farm composition unit for the wind farm including a primary system and a secondary system; a primary wind farm model unit for modeling the primary system based on the digital twin platform to obtain a primary wind farm model; a secondary wind farm model unit for modeling the secondary system based on the digital twin platform to obtain a secondary wind farm model; and a wind farm model generation unit for fusing the primary wind farm model and the secondary wind farm model to generate the wind farm model.
[0054] Among them, the primary system is modeled based on the digital twin platform to obtain a primary wind farm model, and the primary wind farm model unit may further include: a primary wind farm information set acquisition subunit is used to collect basic information of the primary system according to the Internet of Things monitoring platform to obtain a primary wind farm information set; a primary wind farm basic data set acquisition subunit is used to perform data cleaning according to the primary wind farm information set to obtain a primary wind farm basic data set; a primary wind farm model construction subunit is used to construct the primary wind farm model based on the digital twin platform and the primary wind farm basic data set.
[0055] The specific configuration of the wind farm fault detection report acquisition module 40 will be described in detail below. As described above, the wind farm is fault-detected based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report. The wind farm fault detection report acquisition module 40 may further include: a monitoring data set acquisition unit for performing feature recognition based on the real-time monitoring data set to obtain a primary wind farm monitoring data set and a secondary wind farm monitoring data set; a result recognition feature unit for performing feature recognition based on the wind farm state prediction result to obtain a primary state prediction result and a secondary state prediction result; a primary fault detection result generation unit for performing fault detection based on the primary wind farm monitoring data set and the primary state prediction result to generate a primary fault detection result; a secondary fault detection result generation unit for performing fault detection based on the secondary wind farm monitoring data set and the secondary state prediction result to generate a secondary fault detection result; and a wind farm fault detection report generation unit for collating the primary fault detection result and the secondary fault detection result to generate the wind farm fault detection report.
[0056] Among them, fault detection is performed according to the primary wind farm monitoring data set and the primary state prediction result to generate a primary fault detection result, and the primary fault detection result generating unit may further include: a fault record library loading subunit is used to load the primary wind farm fault record library according to the Internet of Things monitoring platform; a primary wind farm fault record set acquisition subunit is used to perform standardized processing according to the primary wind farm fault record library to obtain a primary wind farm fault record set; a primary wind farm fault detection model construction subunit is used to construct a primary wind farm fault detection model according to the primary wind farm fault record set; a primary fault detection result output subunit is used to output the primary fault detection result according to the primary wind farm fault detection model based on the primary wind farm monitoring data set and the primary state prediction result.
[0057] Among them, fault detection is performed according to the secondary wind farm monitoring data set and the secondary state prediction result to generate a secondary fault detection result. The secondary fault detection result generation unit may further include: a secondary wind farm fault detection model construction subunit for building a secondary wind farm fault detection model; a secondary fault detection result acquisition subunit for obtaining the secondary fault detection result according to the secondary wind farm fault detection model based on the secondary wind farm monitoring data set and the secondary state prediction result.
[0058] Among them, the primary fault detection result and the secondary fault detection result are collated to generate the wind farm fault detection report, and the wind farm fault detection report generating unit may further include: a fault report template acquisition subunit for obtaining a predetermined fault report template; an initial fault detection report acquisition subunit for collating the primary fault detection result and the secondary fault detection result according to the predetermined fault report template to obtain an initial fault detection report; a wind farm fault linkage analysis result acquisition subunit for performing fault linkage analysis according to the primary fault detection result and the secondary fault detection result to obtain a wind farm fault linkage analysis result; a wind farm fault detection report acquisition subunit for optimizing the initial fault detection report according to the wind farm fault linkage analysis result to obtain the wind farm fault detection report.
[0059] The wind farm fault linkage warning system based on digital twin provided in the embodiment of the present invention can execute the wind farm fault linkage warning method based on digital twin provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0060] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0061] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims
1. A wind farm fault linkage early warning method based on digital twins, characterized in that: The method comprises: Model the wind farm based on the digital twin platform to obtain the wind farm model; According to the Internet of Things monitoring platform, a real-time monitoring data set of the wind farm is obtained; Obtaining control scheme information of the wind farm, performing state prediction on the wind farm in combination with the wind farm model, and obtaining a wind farm state prediction result; Performing fault detection on the wind farm based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report; The linkage early warning device is activated to issue an early warning to the wind farm in combination with the wind farm fault detection report.
2. The wind farm fault linkage early warning method based on digital twin according to claim 1, characterized in that: The wind farm is modeled based on the digital twin platform to obtain a wind farm model, including: The wind farm includes a primary system and a secondary system; Modeling the primary system based on the digital twin platform to obtain a primary wind farm model; Modeling the secondary system based on the digital twin platform to obtain a secondary wind farm model; The primary wind farm model and the secondary wind farm model are integrated to generate the wind farm model.
3. The wind farm fault linkage early warning method based on digital twin according to claim 2, characterized in that: Modeling the primary system based on the digital twin platform to obtain a primary wind farm model includes: Collecting basic information of the primary system according to the Internet of Things monitoring platform to obtain a primary wind farm information set; Performing data cleaning according to the primary wind farm information set to obtain a primary wind farm basic data set; Based on the digital twin platform and the primary wind farm basic data set, a primary wind farm model is constructed.
4. The wind farm fault linkage early warning method based on digital twin according to claim 1, characterized in that: Performing fault detection on the wind farm based on the real-time monitoring data set and the wind farm state prediction result to obtain a wind farm fault detection report includes: Perform feature recognition according to the real-time monitoring data set to obtain a primary wind farm monitoring data set and a secondary wind farm monitoring data set; Perform feature recognition according to the wind farm state prediction result to obtain a primary state prediction result and a secondary state prediction result; Performing fault detection according to the primary wind farm monitoring data set and the primary state prediction result to generate a primary fault detection result; Performing fault detection according to the secondary wind farm monitoring data set and the secondary state prediction result to generate a secondary fault detection result; The primary fault detection result and the secondary fault detection result are collated to generate the wind farm fault detection report.
5. The wind farm fault linkage early warning method based on digital twin according to claim 4, characterized in that: Performing fault detection according to the primary wind farm monitoring data set and the primary state prediction result to generate a primary fault detection result includes: According to the Internet of Things monitoring platform, a wind farm fault record library is loaded; Performing standardization processing according to the primary wind farm fault record library to obtain a primary wind farm fault record set; constructing a primary wind farm fault detection model according to the primary wind farm fault record set; Based on the primary wind farm monitoring data set and the primary state prediction result, and according to the primary wind farm fault detection model, the primary fault detection result is output.
6. The wind farm fault linkage early warning method based on digital twin according to claim 4, characterized in that: Performing fault detection according to the secondary wind farm monitoring data set and the secondary state prediction result to generate a secondary fault detection result includes: Build a secondary wind farm fault detection model; Based on the secondary wind farm monitoring data set and the secondary state prediction result, the secondary fault detection result is obtained according to the secondary wind farm fault detection model.
7. The wind farm fault linkage early warning method based on digital twin according to claim 4, characterized in that: Arranging the primary fault detection result and the secondary fault detection result to generate the wind farm fault detection report includes: Get the scheduled fault report template; Arranging the primary fault detection result and the secondary fault detection result according to the predetermined fault report template to obtain an initial fault detection report; Performing fault linkage analysis according to the primary fault detection result and the secondary fault detection result to obtain a wind farm fault linkage analysis result; The initial fault detection report is optimized according to the wind farm fault linkage analysis result to obtain the wind farm fault detection report.
8. The wind farm fault linkage early warning system based on digital twin is characterized by: The system is used to implement the wind farm fault linkage early warning method based on digital twins according to any one of claims 1 to 7, and the system includes: A wind farm model acquisition module, wherein the wind farm model acquisition module is used to model the wind farm based on the digital twin platform to obtain a wind farm model; A real-time monitoring data set acquisition module, wherein the real-time monitoring data set acquisition module is used to obtain a real-time monitoring data set of the wind farm according to an Internet of Things monitoring platform; A wind farm state prediction result acquisition module, the wind farm state prediction result acquisition module is used to obtain the control scheme information of the wind farm, perform state prediction on the wind farm in combination with the wind farm model, and obtain the wind farm state prediction result; A wind farm fault detection report acquisition module, the wind farm fault detection report acquisition module is used to perform fault detection on the wind farm based on the real-time monitoring data set and the wind farm state prediction result, and obtain a wind farm fault detection report; A linkage warning device activation module is used to activate the linkage warning device and to issue a warning to the wind farm in combination with the wind farm fault detection report.
Citation Information
Patent Citations
Wind turbine generator power prediction modeling method and device
CN114139778A
Wind power fan monitoring method, device and system and computer readable storage medium
CN115288950A
Fault diagnosis method, device, system and equipment and storage medium
CN115310265A
Wind turbine generator operation and maintenance method and device, electronic equipment and storage medium
CN116591910A
