Running state detection method and device, storage medium, electronic device and computer program product
By establishing the mapping relationship between wind turbine operation data and power, and using the target model to judge the status of the wind turbine, the problem of low fault detection efficiency of wind turbine sets is solved, and faster fault detection is achieved.
Patent Information
- Application Number
- CN202411229940.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-12
AI Technical Summary
The fault detection efficiency of wind turbine units is low. In the prior art, manual methods are relied on and data back-passing speed is slow, so the fault status cannot be discovered in time.
By obtaining the operation-related data of the wind turbine, using the target model to establish a mapping relationship between data and power, and then judging the operating status of the wind turbine, including the fault status and normal status, avoiding the fusion and analysis of a large amount of data.
It improves the efficiency of wind turbine fault detection, can judge the operating status of wind turbine more quickly, and solves the problem of low detection efficiency.
Smart Images

Figure CN118934500A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of fault detection of wind turbine generator sets, and more specifically, to a method and device for detecting an operating state, a storage medium, an electronic device, and a computer program product. Background Art
[0002] Wind power generation is a renewable energy technology that converts wind energy into electrical energy. Wind energy has become the fastest growing renewable energy source in the world, and the installation of wind turbines has increased rapidly in the past decade. The main equipment for wind power generation includes wind turbines, wind towers, impellers, etc., among which wind turbines are its core components. In order to ensure that wind turbines can operate stably and efficiently, regular inspection and monitoring of them is essential.
[0003] Among the related technologies, most still use manual methods to perform fault detection on wind turbines. During the detection process, drones and other equipment are used to scan wind turbines for faults and transmit data back. However, wind turbines are mostly built in places with complex environments, making it difficult for drones to fly, and affected by signal strength, the speed of data transmission is slow. After the data is transmitted back, a large amount of fusion and analysis of various types of data is required, resulting in low efficiency in fault detection of wind turbines and inability to promptly detect whether the status of the wind turbine is faulty or not.
[0004] With regard to the problem of low detection efficiency of fault detection of wind turbine generator sets in related technologies, no effective solution has been proposed so far.
[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention
[0006] The embodiments of the present application provide a method and device for detecting an operating status, a storage medium, an electronic device, and a computer program product, so as to at least solve the problem of low detection efficiency of fault detection of a wind turbine generator set.
[0007] According to one aspect of an embodiment of the present application, a method for detecting an operating status is provided, comprising: obtaining Q groups of operating-related data corresponding to a wind turbine at Q moments, wherein each group of operating-related data includes parameter values of M operating parameters; determining, through a target model, Q powers corresponding to the wind turbine at the Q moments according to the Q groups of operating-related data, wherein the target model is used to determine the power of the wind turbine according to the operating-related data of the wind turbine; establishing a mapping relationship between the Q groups of data and the Q powers, and determining the operating status of the wind turbine according to the mapping relationship, wherein the operating status includes: a fault state and a normal state.
[0008] In an exemplary embodiment, through the target model, according to the Q groups of operation-related data, before the Q powers of the wind turbine corresponding to the Q moments are determined, the method also includes: obtaining sample training data, wherein each group of data in the sample training data includes parameter values of the M operating parameters and the corresponding power of the wind turbine; using the sample training data to train D general models to obtain D trained models, wherein the algorithms used by any two models of the D general models are different; and determining the target model from the D trained models.
[0009] In an exemplary embodiment, the target model is determined from the D trained models, including: when the difference of the same prediction capabilities of the D trained models is less than or equal to a preset threshold, any one of the D trained models is determined as the target model; when the difference of the same prediction capabilities of the D trained models is greater than the preset threshold, the model with the excellent prediction capability closest to 1 among the D trained models is determined as the target model.
[0010] In an exemplary embodiment, the method further includes: determining the value of Q by the following formula 1 and formula 2: Wherein, the value of Q is equal to n, N is equal to the number of groups of all operation-related data of the wind turbine, Z is the quantile of the standard normal distribution at the confidence level e, e is the natural index, and P is a preset value.
[0011] In an exemplary embodiment, determining the operating state of the wind turbine generator according to the mapping relationship includes: determining the operating state of the wind turbine generator according to the mapping relationship based on a KS distribution test.
[0012] In an exemplary embodiment, Q groups of operation-related data corresponding to a wind turbine at Q moments are obtained, including: obtaining multiple groups of monitored operation-related data from a monitoring and data acquisition system of the wind turbine; filtering the multiple groups of operation-related data based on a quantile filtering method to obtain multiple groups of filtered operation-related data; and obtaining Q groups of operation-related data corresponding to the wind turbine at Q moments from the multiple groups of operation-related data.
[0013] According to another aspect of an embodiment of the present application, a device for detecting an operating status is also provided, including: an acquisition module, used to acquire Q groups of operating-related data corresponding to the wind turbine at Q moments, wherein each group of operating-related data includes parameter values of M operating parameters; a first determination module, used to determine, through a target model, Q powers corresponding to the wind turbine at the Q moments according to the Q groups of operating-related data, wherein the target model is used to determine the power of the wind turbine according to the operating-related data of the wind turbine; a second determination module, used to establish a mapping relationship between the Q groups of data and the Q powers, and determine the operating status of the wind turbine according to the mapping relationship, wherein the operating status includes: a fault state and a normal state.
[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for detecting the running state when running.
[0015] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the operating status detection method through the computer program.
[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and the method for detecting the above-mentioned running state when the computer program is executed by a processor.
[0017] Through the present application, the operation-related data of the wind turbine at multiple moments are obtained, and the target model is used to determine the power corresponding to the wind turbine at each moment according to the obtained multiple sets of operation-related data, thereby establishing a mapping relationship between the multiple sets of operation-related data and the power, and then judging the operation state of the wind turbine according to the established mapping relationship. Since the target model is used to determine the power of the wind turbine according to the operation-related data, and the operation state of the wind turbine can be determined only according to the mapping relationship between the operation-related data and the power, the fusion and analysis of a large amount of data is avoided, thereby improving the detection efficiency of the fault detection of the wind turbine set, and solving the problem of low detection efficiency of the fault detection of the wind turbine set. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0020] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for detecting an operating state in an embodiment of the present application;
[0021] Figure 2 is a flow chart of a method for detecting an operating state according to an embodiment of the present application;
[0022] Figure 3 is a schematic diagram of another optional method for detecting an operating state according to an embodiment of the present application;
[0023] Figure 4 It is a structural block diagram of a detection device for an operating state according to an embodiment of the present application. DETAILED DESCRIPTION
[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for detecting an operating state according to an embodiment of the present application. Figure 1As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (Central Processing Unit, MCU) or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the detection method of the running state in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.
[0028] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0029] In this embodiment, a method for detecting an operating state is provided, and the execution subject includes but is not limited to a fault detection module. Figure 2 is a flow chart of a method for detecting an operating state according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps S202-S206:
[0030] Step S202: acquiring Q groups of operation-related data corresponding to the wind turbine at Q moments, wherein each group of operation-related data includes parameter values of M operation parameters;
[0031] Optionally, the M operating parameters include, but are not limited to: wind speed, ambient temperature, air density, blade structure, pitch angle, and bearing temperature.
[0032] It should be noted that Q is a positive integer and M is a positive integer.
[0033] In an exemplary embodiment, the above step S202 can be implemented by the following steps S11-S13:
[0034] Step S11: acquiring a plurality of groups of operation-related data monitored from a monitoring and data acquisition system of the wind turbine;
[0035] It should be noted that the Supervisory Control and Data Acquisition (SCADA) system is a system used to monitor and control the power generation process of wind turbines. The SCADA system usually consists of a main computer and multiple remote terminal units or remote terminal stations, which can realize remote monitoring and control of wind turbines, without the need for manual or drone data collection on site, thus improving data collection efficiency.
[0036] Step S12: filtering the multiple sets of operation-related data based on the quantile filtering method to obtain multiple sets of filtered operation-related data;
[0037] Optionally, each set of operation-related data includes parameter values of M operation parameters, each operation parameter includes 100 parameter values, and the quantile is applied to each 100 parameter values, and the 100 parameters are filtered using a normal distribution method to detect and remove outliers, wherein the formula of the normal distribution is: Wherein, X is the parameter value, x is the preset value, P is the probability of X<x, t is the corresponding time, and e is the natural exponent.
[0038] Optionally, after filtering each set of operation-related data based on the above method, all data sets are merged.
[0039] Step S13: acquiring Q groups of operation-related data corresponding to the wind turbine at Q moments from the multiple groups of operation-related data.
[0040] Step S204: determining, by means of a target model, Q powers of the wind turbine generator corresponding to the Q moments according to the Q groups of operation-related data, wherein the target model is used to determine the power of the wind turbine generator according to the operation-related data of the wind turbine generator;
[0041] That is, the input of the target model is: Q groups of operation-related data, and the output is: the power corresponding to the Q groups of operation-related data.
[0042] Step S206: establishing a mapping relationship between the Q groups of data and the Q powers, and determining the operating state of the wind turbine generator according to the mapping relationship, wherein the operating state includes: a fault state and a normal state.
[0043] Optionally, the above step S206 may be implemented by a target model, that is, the target model is also used to determine the operating state of the wind turbine generator, that is, the output of the target model may also include: the operating state of the wind turbine generator.
[0044] In the above steps, the operation-related data of the wind turbine at multiple moments are obtained, and the target model is used to determine the power corresponding to the wind turbine at each moment according to the multiple sets of operation-related data obtained, thereby establishing a mapping relationship between the multiple sets of operation-related data and the power, and then judging the operation status of the wind turbine according to the established mapping relationship. Since the target model is used to determine the power of the wind turbine according to the operation-related data, and the operation status of the wind turbine can be determined only according to the mapping relationship between the operation-related data and the power, the fusion and analysis of a large amount of data is avoided, thereby improving the detection efficiency of the fault detection of the wind turbine set, and solving the problem of low detection efficiency of the fault detection of the wind turbine set.
[0045] In an exemplary embodiment, before determining the Q powers of the wind turbine corresponding to the Q moments according to the Q groups of operation-related data through the target model, the method further includes the following steps S11-S13:
[0046] Step S11: acquiring sample training data, wherein each set of data in the sample training data includes parameter values of the M operating parameters and the power of the corresponding wind turbine generator;
[0047] Optionally, the sample training data may include Q groups of data.
[0048] Optionally, when the above step S206 is implemented by a target model, the sample training data further includes: the operating status of the wind turbine generator corresponding to the Q group data.
[0049] Step S12: using the sample training data to train D general models to obtain D trained models, wherein algorithms used by any two models in the D general models are different;
[0050] Optionally, the algorithm includes but is not limited to: radial basis function (RBF), multi-layer perceptron neural networks (MLP) and gradient boosting regressor (GBR).
[0051] It should be noted that D is a positive integer.
[0052] Step S13: Determine the target model from the D trained models.
[0053] In an exemplary embodiment, the above step S13 can be implemented by the following steps S131 to S132:
[0054] Step S131: when the difference of the same prediction ability of the D trained models is less than or equal to a preset threshold, determining any one of the D trained models as the target model;
[0055] It should be noted that when the difference in equal predictive ability (EPA) of D trained models is less than or equal to a preset threshold, it means that the difference in predictive ability of the D trained models is small, and any one of the models can be determined as the target model.
[0056] Step S132: When the difference of the equal prediction capabilities of the D trained models is greater than the preset threshold, the model with the excellent prediction capability closest to 1 among the D trained models is determined as the target model.
[0057] That is to say, when the difference of the same predictive ability of the D trained models is greater than the preset threshold, it means that the predictive ability of the D trained models is quite different, and it is necessary to compare the superior predictive ability (SPA) of the models, and select the model with the correlation coefficient closest to 1 as the target model.
[0058] It should be noted that the above-mentioned step S131 and step S132 are steps executed in two different situations respectively, and there is no order of execution when implementing the embodiment of the present application.
[0059] In an exemplary embodiment, the method further includes the following steps: determining the value of Q by the following formula 1 and formula 2: Wherein, the value of Q is equal to n, N is equal to the number of groups of all operation-related data of the wind turbine, Z is the quantile of the standard normal distribution at the confidence level e, e is the natural index, and P is a preset value.
[0060] Optionally, in general, P is 50% of N.
[0061] It should be noted that if the amount of data is too large, it will easily lead to overfitting of the model. If the amount of data is too small, the model will not fully simulate the on-site status of the wind turbine. Therefore, it is necessary to determine the appropriate amount of data to optimize the model's judgment ability and improve the accuracy of the results.
[0062] In an exemplary embodiment, determining the operating state of the wind turbine generator according to the mapping relationship may be achieved through the following steps: determining the operating state of the wind turbine generator according to the mapping relationship based on a KS distribution test.
[0063] Obviously, the embodiments described above are only some embodiments of the present application, not all embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:
[0064] Optionally, the following combination Figure 3 To explain:
[0065] 1. Collect and process data;
[0066] Operational data is collected from SCADA from wind turbines containing necessary process parameters (such as wind speed, density, blades, pitch angle and bearing temperature as mentioned above), and quantile-based filtering techniques are used to detect and remove abnormal data.
[0067] The collected data is cut into groups of 100 numbers and the probability distribution is defined. Quantiles are applied to the probability distribution of each group in order to detect and remove outliers. All data groups are merged.
[0068] The defined probability distribution takes the normal distribution as an example, where the formula of the normal distribution is:
[0069]
[0070] 2. Use hybrid algorithms to build models;
[0071] The above multiple variables (such as the above wind speed, density, blades, pitch angle and bearing temperature, etc.) are input for model development to better capture the actual field conditions, thereby optimizing the model's judgment ability and improving the accuracy of the results.
[0072] Secondly, the general model is trained using algorithms such as RBF, MLP and GBR respectively to obtain multiple trained models, and then the target model is obtained through subsequent steps.
[0073] 3. Determine the target model;
[0074] The EPA loss distribution of the trained models based on the above three algorithms is calculated using the Mariano-Preve EPA test, and the EPA loss distribution of the models based on the above three algorithms is compared.
[0075] The null hypothesis states that all competing models have EPA, the alternative hypothesis states that the expected loss difference between models is not equal to zero at a significance level of 0.05, and a trained model is randomly selected as the target model.
[0076] It should be noted that the significance level is usually called α (Greek letter alpha), and in most cases, α is set to 0.05. The confidence level is (1-α), or 100×(1-α)%. Therefore, if α=0.05, the confidence level is 0.95 or 95%. It means that the results of the three models are similar, and you can randomly choose a trained model.
[0077] If the null hypothesis is rejected, the algorithm compares the SPA of the models and selects the model with the correlation coefficient closest to one as the target model.
[0078] 4. Estimation of significance level;
[0079] The target model determined above is used to generate power values corresponding to various wind speeds, so as to further determine the mapping relationship between the operation-related data and the corresponding power, and then based on the KS distribution test, the operating state of the wind turbine is determined according to the mapping relationship, and the normally operating wind turbine (including: turbine) is inferred.
[0080] It should be noted that the data set is divided into bins of wind speed intervals to represent the data distribution under normal operating conditions of the wind turbine, and the graph of wind speed and power output is used to generate the significance level of a specific bin to help the KS test decision.
[0081] It should be noted that the most appropriate sample size is calculated using the Cochran formula. This sample size represents the number of SCADA temporary instances required for a KS test with similar distribution. The Cochran formula is as follows: Where N represents the size of the finite population, Z represents the Z score at the confidence interval e, and P represents the portion of the population that is assumed to represent the characteristics of the population. In general, the P value is generally considered to be 50% of the population.
[0082] Use the KS test to determine whether a sample comes from a specific distribution to distinguish between normal and / or faulty states.
[0083] 5. Use the target model to detect the operating status of the wind turbine and output the results.
[0084] Based on the KS distribution test, the operating status of the wind turbine is determined using a target model.
[0085] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.
[0086] In the present embodiment, a detection device for operating status is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the equipment described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.
[0087] Figure 4 : is a structural block diagram of a running state detection device according to an embodiment of the present application, the device comprising:
[0088] An acquisition module 42 is used to acquire Q groups of operation-related data corresponding to the wind turbine at Q moments, wherein each group of operation-related data includes parameter values of M operation parameters;
[0089] A first determination module 44 is configured to determine, by means of a target model, Q powers of the wind turbine corresponding to the Q moments according to the Q groups of operation-related data, wherein the target model is configured to determine the power of the wind turbine according to the operation-related data of the wind turbine;
[0090] The second determination module 46 is used to establish a mapping relationship between the Q groups of data and the Q powers, and determine the operating state of the wind turbine according to the mapping relationship, wherein the operating state includes: a fault state and a normal state.
[0091] The above device obtains the operation-related data of the wind turbine at multiple moments, and uses the target model to determine the power corresponding to the wind turbine at each moment based on the multiple sets of operation-related data obtained, thereby establishing a mapping relationship between the multiple sets of operation-related data and the power, and then judging the operation state of the wind turbine based on the established mapping relationship. Since the target model is used to determine the power of the wind turbine based on the operation-related data, and the operation state of the wind turbine can be determined only based on the mapping relationship between the operation-related data and the power, the fusion and analysis of a large amount of data is avoided, thereby improving the detection efficiency of the fault detection of the wind turbine set, and solving the problem of low detection efficiency of the fault detection of the wind turbine set.
[0092] In an exemplary embodiment, the above-mentioned device also includes: a training module, which is used to obtain sample training data before determining the Q powers of the wind turbine corresponding to the Q moments based on the Q groups of operation-related data through the target model, wherein each group of data in the sample training data includes the parameter values of the M operating parameters and the corresponding power of the wind turbine; use the sample training data to train D general models to obtain D trained models, wherein the algorithms used by any two models of the D general models are different; determine the target model from the D trained models.
[0093] In an exemplary embodiment, the above-mentioned training module includes: a determination unit, which is used to determine any one of the D trained models as the target model when the difference of the same prediction capabilities of the D trained models is less than or equal to a preset threshold; when the difference of the same prediction capabilities of the D trained models is greater than the preset threshold, determine the model among the D trained models whose excellent prediction capability is closest to 1 as the target model.
[0094] In an exemplary embodiment, the apparatus further includes: a third determination module, configured to determine the value of Q by using the following formula 1 and formula 2: Wherein, the value of Q is equal to n, N is equal to the number of groups of all operation-related data of the wind turbine, Z is the quantile of the standard normal distribution at the confidence level e, e is the natural index, and P is a preset value.
[0095] In an exemplary embodiment, the second determination module 46 is further configured to determine the operating state of the wind turbine according to the mapping relationship based on a KS distribution test.
[0096] In an exemplary embodiment, the acquisition module 42 is also used to acquire multiple groups of monitored operation-related data from the monitoring and data acquisition system of the wind turbine; filter the multiple groups of operation-related data based on a quantile filtering method to obtain multiple groups of filtered operation-related data; and acquire Q groups of operation-related data corresponding to the wind turbine at Q moments from the multiple groups of operation-related data.
[0097] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.
[0098] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:
[0099] S1, obtaining Q groups of operation-related data corresponding to the wind turbine at Q moments, wherein each group of operation-related data includes parameter values of M operation parameters;
[0100] S2, determining, by means of a target model, Q powers of the wind turbine corresponding to the Q moments according to the Q groups of operation-related data, wherein the target model is used to determine the power of the wind turbine according to the operation-related data of the wind turbine;
[0101] S3, establishing a mapping relationship between the Q groups of data and the Q powers, and determining the operating state of the wind turbine according to the mapping relationship, wherein the operating state includes: a fault state and a normal state.
[0102] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.
[0103] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.
[0104] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are performed.
[0105] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0106] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0107] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0108] S1, obtaining Q groups of operation-related data corresponding to the wind turbine at Q moments, wherein each group of operation-related data includes parameter values of M operation parameters;
[0109] S2, determining, by means of a target model, Q powers of the wind turbine corresponding to the Q moments according to the Q groups of operation-related data, wherein the target model is used to determine the power of the wind turbine according to the operation-related data of the wind turbine;
[0110] S3, establishing a mapping relationship between the Q groups of data and the Q powers, and determining the operating state of the wind turbine according to the mapping relationship, wherein the operating state includes: a fault state and a normal state.
[0111] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0112] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.
[0113] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.
[0114] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A method for detecting an operating state, It is characterized in that include: Acquire Q groups of operation-related data corresponding to the wind turbine at Q moments, wherein each group of operation-related data includes parameter values of M operation parameters; Determine, by means of a target model, Q powers of the wind turbine generator corresponding to the Q moments according to the Q groups of operation-related data, wherein the target model is used to determine the power of the wind turbine generator according to the operation-related data of the wind turbine generator; A mapping relationship between the Q groups of data and the Q powers is established, and the operating state of the wind turbine is determined according to the mapping relationship, wherein the operating state includes: a fault state and a normal state.
2. The method according to claim 1, It is characterized in that Before determining, by means of a target model, Q powers of the wind turbine generator corresponding to the Q moments according to the Q groups of operation-related data, the method further comprises: Acquire sample training data, wherein each set of data in the sample training data includes parameter values of the M operating parameters and the power of the corresponding wind turbine generator; Using the sample training data to train D general models to obtain D trained models, wherein algorithms used by any two models in the D general models are different; The target model is determined from the D trained models.
3. The method according to claim 2, It is characterized in that Determining the target model from the D trained models includes: When the difference of the same prediction abilities of the D trained models is less than or equal to a preset threshold, any one of the D trained models is determined as the target model; when the difference of the same prediction abilities of the D trained models is greater than the preset threshold, the model among the D trained models whose excellent prediction ability is closest to 1 is determined as the target model.
4. The method according to claim 1, It is characterized in that The method further comprises: The value of Q is determined by the following formula 1 and formula 2: Wherein, the value of Q is equal to n, N is equal to the number of groups of all operation-related data of the wind turbine, Z is the quantile of the standard normal distribution at confidence level e, where e is the natural exponent and P is a preset value.
5. The method according to claim 1, It is characterized in that Determining the operating state of the wind turbine generator according to the mapping relationship includes: Based on the KS distribution test, the operating state of the wind turbine is determined according to the mapping relationship.
6. The method according to claim 1, It is characterized in that Obtain Q groups of operation-related data corresponding to the wind turbine at Q moments, including: Acquiring multiple groups of monitored operation-related data from a monitoring and data acquisition system of the wind turbine; Filtering the multiple sets of operation-related data based on a quantile filtering method to obtain multiple sets of filtered operation-related data; Q groups of operation-related data corresponding to the wind turbine at Q moments are obtained from the multiple groups of operation-related data.
7. A device for detecting the running status, It is characterized in that include: An acquisition module, used to acquire Q groups of operation-related data corresponding to the wind turbine at Q moments, wherein each group of operation-related data includes parameter values of M operation parameters; A first determination module is used to determine Q powers of the wind turbine generator corresponding to the Q moments according to the Q groups of operation-related data through a target model, wherein the target model is used to determine the power of the wind turbine generator according to the operation-related data of the wind turbine generator; The second determination module is used to establish a mapping relationship between the Q groups of data and the Q powers, and determine the operating state of the wind turbine according to the mapping relationship, wherein the operating state includes: a fault state and a normal state.
8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.
9. An electronic device comprising a memory and a processor, It is characterized in that A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.
10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
Citation Information
Cited By
State detection method and device of wind generating set and storage medium
CN119593966A
Method and device for detecting state of wind turbine generator system and storage medium
CN119593966B
