Yaw brake device anomaly determination method and device, electronic device, and storage medium

Abstract

The present application relates to the technical field of wind power generator, and particularly relates to yaw brake equipment abnormality determination method and device, electronic equipment and storage medium. A current vibration value corresponding to a yaw moment of a target wind power generator is acquired, and a current current value corresponding to at least one motor in the target wind power generator is acquired; a preset current range corresponding to the yaw moment of the target wind power generator is acquired, and a preset vibration threshold value is acquired; each current current value is compared with the preset current range, and the current vibration value is compared with the preset vibration threshold value; according to the comparison result, it is determined that the yaw brake equipment of the target wind power generator is abnormal. The technical problem of how to determine that the yaw brake equipment is abnormal is solved. The efficiency of determining that the yaw brake equipment of the target wind power generator is abnormal is improved. The yaw brake equipment of the target wind power generator can be found to be abnormal in time, and the failure rate of the target wind power generator is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generators, in particular to a yaw brake device abnormality determination method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Due to the particularity of the yaw brake device (including the yaw brake disc and the yaw brake pad), the surface cannot be stuck with grease, oil or have abnormal wear. If the above abnormal conditions of the yaw brake device are not handled in time, the target wind power generator will have problems such as abnormal noise, vibration, and contaminated yaw brake pad.

[0003] Currently, there is no effective automatic identification method for the sticking of oil and abnormal wear of the yaw brake device in the industry, and only routine on-site inspection and maintenance or inspection after problems occur. The sticking of oil or abnormal wear of the yaw brake device cannot be found and handled in time, which further causes the friction pad to be deeply contaminated or the brake disc to be abnormally worn, resulting in unnecessary losses.

[0004] Therefore, how to determine the abnormality of the yaw brake device has become a problem to be solved. SUMMARY

[0005] Therefore, the present application provides a yaw brake device abnormality determination method, device, electronic equipment and storage medium to solve the problem of how to determine the abnormality of the yaw brake device.

[0006] In a first aspect, the present application provides a yaw brake device abnormality determination method, which comprises:

[0007] obtaining a current vibration value corresponding to a yaw time of a target wind power generator, and a current current value corresponding to at least one motor in the target wind power generator;

[0008] obtaining a preset current range and a preset vibration threshold value corresponding to the yaw time of the target wind power generator;

[0009] comparing each current current value with the preset current range, and comparing the current vibration value with the preset vibration threshold value;

[0010] determining that the yaw brake device of the target wind power generator is abnormal according to the comparison result.

[0011] The yaw brake equipment abnormality determination method provided in the embodiments of the present application obtains the current vibration value corresponding to the yaw moment of the target wind turbine and the current current value corresponding to at least one motor in the target wind turbine, so as to ensure that the obtained current vibration value and each current current value are for the yaw moment of the target wind turbine, thereby ensuring the accuracy of the obtained current vibration value and each current current value. The preset current range corresponding to the yaw moment of the target wind turbine and the preset vibration threshold value are obtained, each current current value is compared with the preset current range, and the current vibration value is compared with the preset vibration threshold value; according to the comparison result, it is determined that the yaw brake equipment of the target wind turbine is abnormal, thereby solving the technical problem of how to determine that the yaw brake equipment is abnormal. The above method does not need to identify the current vibration value and each current current value artificially, thereby improving the efficiency of determining that the yaw brake equipment of the target wind turbine is abnormal. In addition, the above method can realize timely detection of the abnormality of the yaw brake equipment of the target wind turbine, reduce the probability of replacing the yaw friction plate, and reduce the risk of abnormal wear of the yaw brake equipment and long shutdown of the target wind turbine, thereby reducing the failure rate of the target wind turbine.

[0012] In an optional implementation, obtaining the preset current range corresponding to the yaw moment of the target wind turbine and the preset vibration threshold value comprises:

[0013] Obtaining the current working parameter corresponding to the yaw moment of the target wind turbine; the current working parameter comprises at least one of a current wind speed value, a current wind direction value, a current yaw speed value, a current power value, and a current yaw back pressure value;

[0014] Inputting the current working parameter into a preset data model;

[0015] The preset data model identifies the current working parameter to determine the preset current range and the preset vibration threshold value corresponding to the current working parameter of the target wind turbine at the yaw moment.

[0016] The yaw brake equipment abnormality determination method provided in the embodiments of the present application obtains the current working parameter corresponding to the yaw moment of the target wind turbine. The current working parameter is input into a preset data model; the preset data model identifies the current working parameter to determine the preset current range and the preset vibration threshold value corresponding to the current working parameter of the target wind turbine at the yaw moment, so as to ensure that the output preset current range and the preset vibration threshold value match the current working parameter of the target wind turbine, avoid the situation that the preset current range and the preset vibration threshold value do not match the current working parameter of the target wind turbine, resulting in inaccurate comparison results, and thereby inaccurate results of determining that the yaw brake equipment of the target wind turbine is abnormal.

[0017] In an alternative embodiment, the training process of the preset data model comprises:

[0018] The historical working parameters corresponding to the yaw moment of the target wind turbine, the historical preset current range and the historical preset vibration threshold are obtained; the historical working parameters include at least one of the historical wind speed value, the historical front wind direction value, the historical yaw speed value, the historical power value and the historical yaw back pressure value;

[0019] The historical working parameters, the historical preset current range and the historical preset vibration threshold are input into the initial data network;

[0020] The initial data network extracts features from the historical working parameters, and outputs virtual preset current range and virtual preset vibration threshold;

[0021] Based on the relationship between the virtual preset current range and the historical preset current range, and the relationship between the virtual preset vibration threshold and the historical preset vibration threshold, the initial data network is updated to obtain the preset data model.

[0022] The yaw brake equipment abnormality determination method provided by the embodiment of the application obtains the historical working parameters corresponding to the yaw moment of the target wind turbine, the historical preset current range and the historical preset vibration threshold. The historical working parameters, the historical preset current range and the historical preset vibration threshold are input into the initial data network; the initial data network extracts features from the historical working parameters, and outputs virtual preset current range and virtual preset vibration threshold. Based on the relationship between the virtual preset current range and the historical preset current range, and the relationship between the virtual preset vibration threshold and the historical preset vibration threshold, the initial data network is updated to obtain the preset data model. The accuracy of the obtained preset data model is ensured, and the accuracy of the preset current range and the preset vibration threshold output based on the preset data model is ensured.

[0023] In an alternative embodiment, based on the relationship between the virtual preset current range and the historical preset current range, and the relationship between the virtual preset vibration threshold and the historical preset vibration threshold, the initial data network is updated to obtain the preset data model, comprising:

[0024] A first loss function between the virtual preset current range and the historical preset current range is calculated;

[0025] A second loss function between the virtual preset vibration threshold and the historical preset vibration threshold is calculated;

[0026] The first loss function and the second loss function are fused to generate a target loss function;

[0027] Based on the target loss function, the initial data network is updated to obtain the preset data model.

[0028] The yaw brake equipment abnormity determination method provided by the embodiments of the present application calculates a first loss function between the virtual preset current range and the historical preset current range, ensures that the preset data model can learn the difference between the virtual preset current range and the historical preset current range. A second loss function between the virtual preset vibration threshold and the historical preset vibration threshold is calculated, which ensures that the preset data model can learn the difference between the virtual preset vibration threshold and the historical preset vibration threshold. The first loss function and the second loss function are fused to generate a target loss function, which ensures that the preset data model can determine the difference between the virtual preset current range and the historical preset current range and the difference between the virtual preset vibration threshold and the historical preset vibration threshold based on the target loss function. Based on the target loss function, the initial data network is updated to obtain the preset data model, which ensures the accuracy of the generated preset data model.

[0029] In an optional implementation, before the current vibration value corresponding to the yaw moment of the target wind turbine and the current current value corresponding to at least one motor in the target wind turbine are acquired, the method comprises:

[0030] Acquiring the current yaw angle corresponding to the target wind turbine based on the yaw sensor;

[0031] Comparing the current yaw angle with the historical yaw angle to calculate a yaw angle change value;

[0032] If the yaw angle change value is greater than a preset yaw angle change value, it is determined that the target wind turbine is at the yaw moment.

[0033] The yaw brake equipment abnormity determination method provided by the embodiments of the present application acquires the current yaw angle corresponding to the target wind turbine based on the yaw sensor; compares the current yaw angle with the historical yaw angle to calculate a yaw angle change value; and if the yaw angle change value is greater than a preset yaw angle change value, it is determined that the target wind turbine is at the yaw moment, so that it can be determined whether the yaw brake equipment of the target wind turbine is abnormal when the target wind turbine is at the yaw moment.

[0034] In an optional implementation, if the yaw angle change value is greater than a preset yaw angle change value, it is determined that the target wind turbine is at the yaw moment, comprising:

[0035] If the yaw angle change value is greater than a preset yaw angle change value, acquiring the yaw state identification information corresponding to the target wind turbine sent by the monitoring system of the target wind turbine;

[0036] If the yaw state identification information represents that the target wind turbine is in a yaw state, it is determined that the target wind turbine is at the yaw moment.

[0037] The yaw brake equipment abnormality determination method provided in the embodiments of the present application includes: if the yaw angle change value is greater than the preset yaw angle change value, obtaining yaw state identification information corresponding to the target wind turbine sent by a monitoring system of the target wind turbine; and if the yaw state identification information indicates that the target wind turbine is in a yaw state, determining that the target wind turbine is in a yaw moment. The double conditions are used for constraint, so as to ensure the accuracy of the determined yaw moment of the target wind turbine and avoid the inaccuracy of the yaw sensor in determining the yaw moment of the target wind turbine.

[0038] In an optional embodiment, according to the comparison result, it is determined that the yaw brake equipment of the target wind turbine is abnormal, including:

[0039] If the current vibration value is greater than the preset vibration threshold value, and at least one current current value is not in the preset current range, it is determined that the yaw brake equipment of the target wind turbine is abnormal, and prompt information is output.

[0040] The yaw brake equipment abnormality determination method provided in the embodiments of the present application includes: if the current vibration value is greater than the preset vibration threshold value, it is determined that the current vibration value is large, and at least one current current value is not in the preset current range, it is determined that the yaw brake equipment of the target wind turbine is abnormal, and prompt information is output. The above method determines that the yaw brake equipment of the target wind turbine is abnormal through the comparison result of the current vibration value and the preset vibration threshold value and the comparison result of each current current value and the preset current range, double constraint conditions, ensures the accuracy of the determined yaw brake equipment of the target wind turbine, and enables the user to obtain the message that the yaw brake equipment of the target wind turbine is abnormal in time, thereby reducing the failure rate of the target wind turbine.

[0041] In a second aspect, the present application provides a yaw brake equipment abnormality determination device, which includes:

[0042] A first acquisition module is configured to acquire a current vibration value corresponding to a yaw moment of a target wind turbine and a current current value corresponding to at least one motor in the target wind turbine;

[0043] A second acquisition module is configured to acquire a preset current range and a preset vibration threshold value corresponding to the yaw moment of the target wind turbine;

[0044] A comparison module is configured to compare each current current value with the preset current range respectively, and compare the current vibration value with the preset vibration threshold value;

[0045] A first determination module is configured to determine that the yaw brake equipment of the target wind turbine is abnormal according to the comparison result.

[0046] The yaw brake equipment abnormality determination device provided by the embodiment of the application obtains the current vibration value corresponding to the yaw moment of the target wind turbine and the current current value corresponding to at least one motor in the target wind turbine, so that the current vibration value and the current current value obtained are ensured to be at the yaw moment of the target wind turbine, and the accuracy of the current vibration value and the current current value obtained is ensured. The preset current range corresponding to the yaw moment of the target wind turbine and the preset vibration threshold are obtained, each current current value is compared with the preset current range, and the current vibration value is compared with the preset vibration threshold; according to the comparison result, it is determined that the yaw brake equipment of the target wind turbine is abnormal. The above method does not need to identify the current vibration value and the current current value artificially, and the efficiency of determining that the yaw brake equipment of the target wind turbine is abnormal is improved. In addition, the above method can realize timely discovery of the yaw brake equipment of the target wind turbine being abnormal, reduce the probability of replacing the yaw friction plate, and reduce the risk of yaw brake equipment abnormal wear and long stop of the target wind turbine, thereby reducing the failure rate of the target wind turbine.

[0047] In a third aspect, the application provides an electronic device, comprising a memory and a processor, the memory and the processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the yaw brake equipment abnormality determination method of the first aspect or any of the corresponding embodiments thereof.

[0048] In a fourth aspect, the application provides a computer readable storage medium, the computer readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the yaw brake equipment abnormality determination method of the first aspect or any of the corresponding embodiments thereof.

[0049] In a fifth aspect, the application provides a computer program product, comprising computer instructions, and the computer instructions are used to make a computer execute the yaw brake equipment abnormality determination method of the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the specific embodiments of the application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0051] Figure 1 is a flowchart of the yaw brake equipment abnormality determination method according to the embodiment of the application;

[0052] Figure 2 Fig. 6 is a flowchart of another yaw brake device abnormality determination method according to an embodiment of the present application;

[0053] Figure 3 Fig. 7 is a flowchart of yet another yaw brake device abnormality determination method according to an embodiment of the present application;

[0054] Figure 4 Fig. 8 is a structural block diagram of a yaw brake device abnormality determination apparatus according to an embodiment of the present application;

[0055] Figure 5 Fig. 9 is a structural block diagram of another yaw brake device abnormality determination apparatus according to an embodiment of the present application;

[0056] Figure 6 Fig. 10 is a hardware structure schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0058] Due to the particularity of the yaw brake device (including yaw brake disc and yaw brake pad), the surface cannot stick with grease, oil or have abnormal wear. If the above abnormal conditions of the yaw brake device are not handled in time, the target wind turbine will have abnormal noise, vibration, yaw friction pad pollution and other problems.

[0059] At present, there is no effective automatic identification method for the yaw brake device sticking oil and abnormal wear in the industry. Only through daily on-site inspection and maintenance, or after the problem occurs, the inspection can be carried out. The yaw brake device sticking oil or abnormal wear cannot be found and handled in time, which further causes the friction pad to be deeply contaminated, or the brake disc to be abnormally worn, resulting in unnecessary loss.

[0060] Therefore, how to determine the yaw brake device abnormality has become a problem to be solved.

[0061] Based on this, the embodiment of the present application provides a yaw brake device abnormality determination method, obtaining a current vibration value corresponding to a yaw moment of a target wind turbine, and a current current value corresponding to at least one motor in the target wind turbine, ensuring that the obtained current vibration value and each current current value are for the target wind turbine at the yaw moment, thereby ensuring the accuracy of the obtained current vibration value and each current current value. Obtain a preset current range and a preset vibration threshold value corresponding to the yaw moment of the target wind turbine, compare each current current value with the preset current range, and compare the current vibration value with the preset vibration threshold value; according to the comparison result, determine that the yaw brake device of the target wind turbine is abnormal. The above method does not need to identify the current vibration value and each current current value artificially, because it improves the efficiency of determining that the yaw brake device of the target wind turbine is abnormal. In addition, the above method can realize timely discovery of the yaw brake device of the target wind turbine, reduce the probability of replacing the yaw friction plate, and reduce the risk of yaw brake device abnormal wear and long stop of the target wind turbine, thereby reducing the failure rate of the target wind turbine.

[0062] It should be noted that the yaw brake device abnormality determination method provided by the embodiment of the present application can be a yaw brake device abnormality determination device, which can be realized by software, hardware or a combination of software and hardware to become part or all of an electronic device. The electronic device can be an electronic device inside the target wind turbine, or an electronic device independent of the target wind turbine. When the electronic device is independent of the target wind turbine, the electronic device can be a server or a terminal. The server in the embodiment of the present application can be a server, or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, a wearable device, a smart robot and other smart hardware devices. In the following method embodiment, the execution subject is taken as an example to illustrate.

[0063] According to the embodiment of the present application, a yaw brake device abnormality determination method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0064] In the present embodiment, a yaw brake device abnormality determination method is provided, which can be used in the above-mentioned electronic device, Figure 1 is a flowchart of the yaw brake device abnormality determination method according to the embodiment of the present application, as Figure 1 shown, the flowchart includes the following steps:

[0065] In step S101, a current vibration value corresponding to a yaw moment of the target wind turbine and a current current value corresponding to at least one motor of the target wind turbine are acquired.

[0066] Specifically, the electronic device can acquire the current vibration value corresponding to the yaw moment of the target wind turbine based on the vibration sensor. The electronic device can acquire the current current value corresponding to the at least one motor of the target wind turbine based on the motor current transformer.

[0067] In step S102, a preset current range and a preset vibration threshold value corresponding to the yaw moment of the target wind turbine are acquired.

[0068] Specifically, the electronic device can acquire the preset current range and the preset vibration threshold value corresponding to the yaw moment of the target wind turbine input by a user, or receive the preset current range and the preset vibration threshold value corresponding to the yaw moment of the target wind turbine sent by another device. The preset current range and the preset vibration threshold value can also be set according to the actual working condition of the target wind turbine.

[0069] The manner in which the electronic device acquires the preset current range and the preset vibration threshold value is not limited in the embodiments of the present application.

[0070] This step will be described in detail below.

[0071] In step S103, each current current value is compared with the preset current range, and the current vibration value is compared with the preset vibration threshold value.

[0072] Specifically, the electronic device can compare each current current value corresponding to the motor with the preset current range, and compare the current vibration value corresponding to the target wind turbine with the preset vibration threshold value.

[0073] In step S104, it is determined that the yaw brake device of the target wind turbine is abnormal according to the comparison result.

[0074] Specifically, when the current current values are all not in the preset current range, that is, each current current value is greater than the maximum value in the preset current range or less than the minimum value in the preset current range, and the current vibration value corresponding to the target wind turbine is greater than the preset vibration threshold value, the electronic device determines that the yaw brake device of the target wind turbine is abnormal.

[0075] The yaw brake equipment abnormity determination method provided in the embodiments of the present application comprises the following steps: obtaining a current vibration value corresponding to a yaw moment of a target wind turbine and a current current value corresponding to at least one motor in the target wind turbine, ensuring that the obtained current vibration value and each current current value are at the yaw moment of the target wind turbine, and further ensuring the accuracy of the obtained current vibration value and each current current value; obtaining a preset current range and a preset vibration threshold value corresponding to the yaw moment of the target wind turbine, comparing each current current value with the preset current range, and comparing the current vibration value with the preset vibration threshold value; and determining that the yaw brake equipment of the target wind turbine is abnormal according to the comparison result. The above method does not require manual identification of the current vibration value and each current current value, thereby improving the efficiency of determining that the yaw brake equipment of the target wind turbine is abnormal. In addition, the above method can realize timely detection of the abnormality of the yaw brake equipment of the target wind turbine, reduce the probability of replacing the yaw friction plate, and reduce the risk of abnormal wear of the yaw brake equipment and long-term shutdown of the target wind turbine, thereby reducing the failure rate of the target wind turbine.

[0076] In the embodiments, a yaw brake equipment abnormity determination method is provided, which can be used for the electronic device described above, Figure 2 is a flowchart of the yaw brake equipment abnormity determination method according to the embodiments of the present application, as Figure 2 shown, the flowchart comprises the following steps:

[0077] In step S201, a current vibration value corresponding to a yaw moment of a target wind turbine and a current current value corresponding to at least one motor in the target wind turbine are obtained.

[0078] For this step, please refer to the description of step S101 above, which will not be repeated here.

[0079] In step S202, a preset current range and a preset vibration threshold value corresponding to the yaw moment of the target wind turbine are obtained.

[0080] Specifically, the above step S202 can comprise the following steps:

[0081] In step S2021, a current working parameter corresponding to the yaw moment of the target wind turbine is obtained.

[0082] The current working parameter comprises at least one of a current wind speed value, a current wind direction value, a current yaw speed value, a current power value, and a current yaw back pressure value.

[0083] Specifically, the electronic device can obtain the current wind speed value and the current wind direction value of the target wind turbine at the yaw moment based on the anemorumbometer; the electronic device can detect the current yaw speed value of the target wind turbine at the yaw moment based on the yaw position sensor; the electronic device can detect the current power value of the target wind turbine at the yaw moment based on the power detection module; and the electronic device can detect the current yaw back pressure value of the target wind turbine at the yaw moment based on the hydraulic station pressure sensor.

[0084] In step S2022, the current working parameter is input into the preset data model.

[0085] Specifically, the electronic device can receive a preset data model input by a user, can receive a preset data model sent by another device, and can also obtain a preset data model through training data. The embodiments of the present application do not limit the way in which the electronic device obtains the preset data model.

[0086] Then, the electronic device inputs the current working parameter into the preset data model.

[0087] The preset data model can be any one of a radial basis function (RBF) network, a feedforward neural network (FFNN), a convolutional neural network (CNN), a deconvolutional network (DN), a deep convolutional inverse graphics network (DCIGN), a generative adversarial network (GAN), a recurrent neural network (RNN), a long / short term memory (LSTM), a deep residual network (DRN), and an extreme learning machine (ELM). The embodiments of the present application do not limit the preset data model.

[0088] In step S2023, the preset data model identifies the current working parameter to determine the preset current range and the preset vibration threshold corresponding to the current working parameter of the target wind turbine at the yaw moment.

[0089] Specifically, the preset data model calculates key statistics (including mean, standard deviation, minimum value, maximum value, etc.) for the current working parameters. Then, the electronic device uses visualization techniques such as scatter plots, box plots, histograms, etc. to explore the data distribution and relationship, and the electronic device uses correlation coefficients (such as Pearson or Spearman) to determine the correlation between different parameters in the current working parameters.

[0090] Next, a univariate feature selection method (such as chi-square test, ANOVA, etc.) is used to evaluate the correlation of each parameter in the current working parameters with the target variable (preset current range and preset vibration threshold). In addition, a machine learning model (such as random forest, Lasso regression, etc.) is used to evaluate the importance of each parameter in the current working parameters.

[0091] Then, based on the importance evaluation of each parameter in the current working parameters, the parameters that have the greatest impact on the target variable (preset current range and preset vibration threshold) are selected for combination. For example, two parameters are multiplied, multiple parameters are added, parameters are grouped according to their specific ranges, etc. Then, based on the combined parameters, the preset current range and the preset vibration threshold are output.

[0092] The training process of the preset data model can include the following steps:

[0093] Step a1, obtaining the historical working parameters corresponding to the yaw moment of the target wind turbine and the historical preset current range and the historical preset vibration threshold.

[0094] The historical working parameters include at least one of historical wind speed value, historical front wind direction value, historical yaw speed value, historical power value, and historical yaw back pressure value.

[0095] The historical preset current range and the historical preset vibration threshold are obtained according to experimental data.

[0096] Specifically, the electronic device can find the historical working parameters corresponding to the yaw moment of the target wind turbine and the historical preset current range and the historical preset vibration threshold from the storage space, or receive the historical working parameters corresponding to the yaw moment of the target wind turbine and the historical preset current range and the historical preset vibration threshold input by the user. The way the electronic device obtains the historical working parameters corresponding to the yaw moment of the target wind turbine and the historical preset current range and the historical preset vibration threshold is not limited in the embodiments of the present application.

[0097] Step a2, inputting the historical working parameters and the historical preset current range and the historical preset vibration threshold into the initial data network.

[0098] Step a3, the initial data network extracts features from the historical working parameters, and outputs a virtual preset current range and a virtual preset vibration threshold.

[0099] Specifically, the initial data network calculates key statistics (including mean, standard deviation, minimum value, maximum value, etc.) from the historical working parameters. Then, the electronic device uses visualization techniques such as scatter plots, box plots, and histograms to explore data distribution and relationships, and the electronic device uses correlation coefficients (such as Pearson or Spearman) to determine the correlation between different parameters in the historical working parameters.

[0100] Next, a univariate feature selection method (such as chi-square test, ANOVA, etc.) is used to evaluate the correlation of each parameter in the historical working parameters with the target variable (historical preset current range and historical preset vibration threshold). In addition, a machine learning model (such as random forest, Lasso regression, etc.) is used to evaluate the importance of each parameter in the historical working parameters.

[0101] Then, based on the importance evaluation of each parameter in the historical working parameters, the parameters that have the greatest impact on the target variable (historical preset current range and historical preset vibration threshold) are selected and combined. For example, two parameters are multiplied, multiple parameters are added, parameters are grouped according to their specific ranges, etc. Then, based on the combined parameters, the virtual preset current range and the virtual preset vibration threshold are output.

[0102] Step a4, based on the relationship between the virtual preset current range and the historical preset current range, and the relationship between the virtual preset vibration threshold and the historical preset vibration threshold, the initial data network is updated to obtain a preset data model.

[0103] Specifically, the above step a4 can include the following steps:

[0104] Step a41, calculate the first loss function between the virtual preset current range and the historical preset current range.

[0105] Specifically, the electronic device can calculate the first loss function between the virtual preset current range and the historical preset current range.

[0106] Wherein, the first loss function can be any one of mean square error loss function, mean absolute error loss function, cross entropy loss function.

[0107] Step a42, calculate the second loss function between the virtual preset vibration threshold and the historical preset vibration threshold.

[0108] Specifically, the electronic device can calculate the second loss function between the virtual preset vibration threshold and the historical preset vibration threshold.

[0109] The second loss function can be any one of a mean square error loss function, a mean absolute error loss function, and a cross-entropy loss function.

[0110] In step a43, the first loss function and the second loss function are fused to generate a target loss function.

[0111] Optionally, the electronic device can average the first loss function and the second loss function to generate the target loss function.

[0112] Optionally, the electronic device can also weight-average the first loss function and the second loss function to generate the target loss function.

[0113] In step a44, the initial data network is updated based on the target loss function to obtain a preset data model.

[0114] Specifically, the electronic device can use gradient descent or other optimization algorithms (such as Adam, SGD, etc.) to update the initial data network based on the target loss function to obtain the preset data model.

[0115] In step S203, each current current value is compared with a preset current range, and a current vibration value is compared with a preset vibration threshold.

[0116] For this step, please refer to the description of step S103 above, which will not be repeated here.

[0117] In step S204, according to the comparison result, it is determined that the yaw brake device of the target wind turbine is abnormal.

[0118] For this step, please refer to the description of step S104 above, which will not be repeated here.

[0119] The yaw brake device abnormality determination method provided by the embodiments of the present application obtains the current working parameters of the target wind turbine at the yaw time. The current working parameters are input into the preset data model. The preset data model identifies the current working parameters to determine the preset current range and the preset vibration threshold corresponding to the current working parameters of the target wind turbine at the yaw time, ensuring that the output preset current range and the preset vibration threshold match the current working parameters of the target wind turbine, avoiding the situation that the preset current range and the preset vibration threshold do not match the current working parameters of the target wind turbine, resulting in inaccurate comparison results and further inaccurate results of determining that the yaw brake device of the target wind turbine is abnormal.

[0120] In addition, the training process of the preset data model comprises: obtaining historical working parameters corresponding to the yaw moment of the target wind turbine, and historical preset current ranges and historical preset vibration thresholds; inputting the historical working parameters, the historical preset current ranges and the historical preset vibration thresholds into an initial data network; performing feature extraction on the historical working parameters by the initial data network, and outputting virtual preset current ranges and virtual preset vibration thresholds; updating the initial data network based on a relationship between the virtual preset current ranges and the historical preset current ranges, and a relationship between the virtual preset vibration thresholds and the historical preset vibration thresholds, to obtain the preset data model. The accuracy of the obtained preset data model is ensured, and thus the accuracy of the preset current ranges and the preset vibration thresholds output based on the preset data model is ensured.

[0121] In the embodiment, a yaw brake equipment abnormality determination method is provided, which can be used for the electronic device described above, Figure 3 is a flowchart of the yaw brake equipment abnormality determination method according to the embodiment of the present application, as Figure 3 shown, the flowchart comprises the following steps:

[0122] Step S301: obtaining a current yaw angle corresponding to the target wind turbine based on a yaw sensor.

[0123] Specifically, the electronic device can obtain the current yaw angle corresponding to the target wind turbine based on the yaw sensor.

[0124] Step S302: comparing the current yaw angle with a historical yaw angle, and calculating a yaw angle change value.

[0125] Specifically, the electronic device can find the historical yaw angle in the storage space. It should be noted that the historical yaw angle can be the yaw angle at a time point before the current time point, or the yaw angle at a time point before the current time point and a time point before the current time point, or the yaw angle at a time point before the current time point, a time point before the current time point and a time point before the current time point, and the present application does not limit the historical yaw angle.

[0126] The electronic device can calculate the yaw angle change value by subtracting the historical yaw angle from the current yaw angle.

[0127] Step S303: if the yaw angle change value is greater than a preset yaw angle change value, determining that the target wind turbine is at a yaw moment.

[0128] In an optional embodiment, if the yaw angle change value is greater than the preset yaw angle change value, it is determined that the target wind turbine is at a yaw moment.

[0129] In another optional embodiment, the step S303 can comprise the following steps:

[0130] In step S3031, if the yaw angle change value is greater than the preset yaw angle change value, the yaw state identification information corresponding to the target wind turbine sent by the monitoring system of the target wind turbine is acquired.

[0131] Specifically, if the yaw angle change value is greater than the preset yaw angle change value, the electronic device acquires the yaw state identification information corresponding to the target wind turbine sent by the monitoring system of the target wind turbine based on the communication connection between the electronic device and the monitoring system.

[0132] In the above step, the yaw state identification information can be acquired by the electronic device based on the communication connection between the electronic device and the monitoring system.

[0133] In step S3032, if the yaw state identification information indicates that the target wind turbine is in the yaw state, it is determined that the target wind turbine is in the yaw state.

[0134] Specifically, the electronic device identifies the yaw state identification information, and if the identification result is that the yaw state identification information indicates that the target wind turbine is in the yaw state, it is determined that the target wind turbine is in the yaw state.

[0135] In step S304, the current vibration value corresponding to the yaw state of the target wind turbine and the current current value corresponding to at least one motor in the target wind turbine are acquired.

[0136] For this step, please refer to the description of step S201 above, which will not be repeated here.

[0137] In step S305, the preset current range corresponding to the yaw state of the target wind turbine and the preset vibration threshold value are acquired.

[0138] For this step, please refer to the description of step S202 above, which will not be repeated here.

[0139] In step S306, each current value is compared with the preset current range, and the current vibration value is compared with the preset vibration threshold value.

[0140] For this step, please refer to the description of step S203 above, which will not be repeated here.

[0141] In step S307, according to the comparison result, it is determined that the yaw brake device of the target wind turbine is abnormal.

[0142] Specifically, the above step S307 can include the following steps:

[0143] In step S3071, if the current vibration value is greater than the preset vibration threshold value, and at least one current value is not within the preset current range, it is determined that the yaw brake device of the target wind turbine is abnormal, and a prompt information is outputted.

[0144] Specifically, if the current vibration value is greater than the preset vibration threshold value, and at least one of the current current values is not within the preset current range, i.e., at least one of the current current values is greater than the maximum value in the preset current range or less than the minimum value in the preset current range, the electronic device determines that the yaw brake device of the target wind turbine is abnormal, and outputs prompt information.

[0145] The yaw brake device abnormality determination method provided in the embodiments of the present application acquires the current yaw angle corresponding to the target wind turbine based on the yaw sensor; compares the current yaw angle with the historical yaw angle to calculate a yaw angle change value; if the yaw angle change value is greater than a preset yaw angle change value, acquires the yaw state identification information corresponding to the target wind turbine sent by the monitoring system of the target wind turbine; and if the yaw state identification information indicates that the target wind turbine is in a yaw state, determines that the target wind turbine is in a yaw moment. The double conditions are used for constraint, which ensures the accuracy of the determination that the target wind turbine is in a yaw moment, and avoids the inaccuracy of the determination that the target wind turbine is in a yaw moment caused by the yaw sensor.

[0146] In addition, if the current vibration value is greater than the preset vibration threshold value, it is determined that the current vibration value is large, and at least one of the current current values is not within the preset current range, it is determined that the yaw brake device of the target wind turbine is abnormal, and prompt information is output. The above method determines that the yaw brake device of the target wind turbine is abnormal through the comparison result of the current vibration value and the preset vibration threshold value and the comparison result of each current value and the preset current range, double constraint conditions, ensures the accuracy of the determination that the yaw brake device of the target wind turbine is abnormal, and enables the user to timely obtain the message that the yaw brake device of the target wind turbine is abnormal, thereby reducing the failure rate of the target wind turbine.

[0147] In the embodiments, a yaw brake device abnormality determination apparatus is also provided, which is used to implement the above embodiments and preferred embodiments, and will not be described herein. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0148] The embodiments provide a yaw brake device abnormality determination apparatus, as shown in Figure 4 The yaw brake device abnormality determination apparatus includes:

[0149] The first acquisition module 401 is configured to acquire a current vibration value corresponding to a yaw moment of a target wind turbine, and a current current value corresponding to at least one motor in the target wind turbine;

[0150] The second acquisition module 402 is configured to acquire a preset current range corresponding to the yaw moment of the target wind turbine and a preset vibration threshold.

[0151] The comparison module 403 is configured to compare each current value with the preset current range respectively, and compare the current vibration value with the preset vibration threshold.

[0152] The first determination module 404 is configured to determine that the yaw brake device of the target wind turbine is abnormal according to the comparison result.

[0153] In some optional embodiments, the second acquisition module 402 is specifically configured to acquire a current working parameter corresponding to the yaw moment of the target wind turbine; the current working parameter includes at least one of a current wind speed value, a current wind direction value, a current yaw speed value, a current power value and a current yaw back pressure value; and the current working parameter is input to a preset data model. The preset data model identifies the current working parameter to determine the preset current range corresponding to the current working parameter of the target wind turbine at the yaw moment and the preset vibration threshold.

[0154] In some optional embodiments, the second acquisition module 402 is specifically configured to acquire a historical working parameter corresponding to the yaw moment of the target wind turbine and a historical preset current range and a historical preset vibration threshold; the historical working parameter includes at least one of a historical wind speed value, a historical wind direction value, a historical yaw speed value, a historical power value and a historical yaw back pressure value; and the historical working parameter, the historical preset current range and the historical preset vibration threshold are input to an initial data network. The initial data network extracts features of the historical working parameter to output a virtual preset current range and a virtual preset vibration threshold. The initial data network is updated based on a relationship between the virtual preset current range and the historical preset current range and a relationship between the virtual preset vibration threshold and the historical preset vibration threshold to obtain the preset data model.

[0155] In some optional embodiments, the second acquisition module 402 is specifically configured to calculate a first loss function between the virtual preset current range and the historical preset current range; calculate a second loss function between the virtual preset vibration threshold and the historical preset vibration threshold; perform fusion processing on the first loss function and the second loss function to generate a target loss function; and update the initial data network based on the target loss function to obtain the preset data model.

[0156] In some optional embodiments, the yaw brake device abnormality determination apparatus, as shown in Figure 5 , further includes:

[0157] The third acquisition module 405 is configured to acquire a current yaw angle of the target wind turbine based on a yaw sensor.

[0158] The computing module 406 is configured to compare the current yaw angle with the historical yaw angle, and calculate a yaw angle change value;

[0159] The second determining module 407 is configured to determine that the target wind turbine is in the yaw moment if the yaw angle change value is greater than a preset yaw angle change value.

[0160] In some optional embodiments, the second determining module 407 is specifically configured to acquire yaw state identification information corresponding to the target wind turbine sent by a monitoring system of the target wind turbine if the yaw angle change value is greater than the preset yaw angle change value; and determine that the target wind turbine is in the yaw moment if the yaw state identification information represents that the target wind turbine is in a yaw state.

[0161] In some optional embodiments, the first determining module 404 is specifically configured to determine that the yaw brake device of the target wind turbine is abnormal and output prompt information if the current vibration value is greater than the preset vibration threshold value and the at least one current current value is not within the preset current range.

[0162] Further function descriptions of the above-mentioned various modules and units are the same as those of the above-mentioned corresponding embodiments, and will not be described here.

[0163] The yaw brake device abnormality determination apparatus in the embodiment is presented in the form of a functional unit. The unit herein refers to an ASIC (Application Specific Integrated Circuit, Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0164] The embodiment of the present application also provides an electronic device with the yaw brake device abnormality determination apparatus shown in the above Figure 4 and Figure 5 .

[0165] Please refer to Figure 6 , Figure 6 is a structural schematic diagram of an electronic device provided by an optional embodiment of the present application, as shown in Figure 6As shown, the electronic device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate via one or more buses and can be mounted on a common motherboard or in other manners as appropriate. The processor can process instructions for execution within the electronic device, including instructions stored in the memory or on storage to display graphical information for a GUI on an external input / output device, such as a display device coupled to the interface. In some alternative implementations, multiple processors and / or multiple buses can be employed as appropriate, as well as multiple memories and types of memory. Also, various components can be connected by various interfaces, not necessarily by a bus. In some implementations, for example, the interfaces can be wires or wireless connections. Figure 6 The processor 10 is taken as an example.

[0166] The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0167] The memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods illustrated in the above embodiments.

[0168] The memory 20 can include a program region and a data region. The program region can store an operating system and application programs required by at least one function. The data region can store data created according to the use of the electronic device, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some alternative implementations, the memory 20 can optionally include a memory disposed remotely from the processor 10, and these remote memories can be connected to the electronic device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0169] The memory 20 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned types of memories.

[0170] The electronic device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 can be connected by a bus or other means,Figure 6 The bus connection is taken as an example.

[0171] The input device 30 can receive inputted digital or character information, and generate key signal inputs related to user settings and function controls of the electronic device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), etc. The display device includes, but is not limited to, a liquid crystal display, a light emitting diode, a display, and a plasma display. In some alternative embodiments, the display device can be a touch screen.

[0172] The embodiments of the present application also provide a computer readable storage medium, the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded from a network and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk or a solid state disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that the computer, processor, microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, processor or hardware, the method shown in the above embodiments is implemented.

[0173] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, the method and / or technical solutions according to the present application can be called or provided. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source file, executable file, installation package file, etc., and accordingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0174] While embodiments of the application have been described in connection with the preferred embodiments of the various figures, those of ordinary skill in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the application, and that such modifications and changes fall within the scope of the appended claims.

Claims

1. A yaw brake device abnormality determination method characterized by comprising: The method comprises: obtaining a current yaw angle corresponding to a target wind turbine based on a yaw sensor; comparing the current yaw angle with a historical yaw angle to calculate a yaw angle change value; if the yaw angle change value is greater than a preset yaw angle change value, determining that the target wind turbine is in the yaw moment; obtaining a current vibration value corresponding to the target wind turbine in the yaw moment, and a current current value corresponding to at least one motor in the target wind turbine; obtaining a preset current range and a preset vibration threshold corresponding to the target wind turbine in the yaw moment; comparing each of the current current values with the preset current range, and comparing the current vibration value with the preset vibration threshold; determining that the yaw brake device of the target wind turbine is abnormal according to the comparison result.

2. The method of claim 1, wherein, The method comprises: obtaining a current working parameter corresponding to the target wind turbine in the yaw moment; the current working parameter comprises at least one of a current wind speed value, a current wind direction value, a current yaw speed value, a current power value, and a current yaw back pressure value; inputting the current working parameter into a preset data model; the preset data model identifies the current working parameter to determine the preset current range and the preset vibration threshold corresponding to the current working parameter of the target wind turbine in the yaw moment.

3. The method of claim 2, wherein, The training process of the preset data model comprises: obtaining a historical working parameter, a historical preset current range, and a historical preset vibration threshold corresponding to the target wind turbine in the yaw moment; the historical working parameter comprises at least one of a historical wind speed value, a historical wind direction value, a historical yaw speed value, a historical power value, and a historical yaw back pressure value; inputting the historical working parameter, the historical preset current range, and the historical preset vibration threshold into an initial data network; the initial data network extracts features from the historical working parameter to output a virtual preset current range and a virtual preset vibration threshold; updating the initial data network based on the relationship between the virtual preset current range and the historical preset current range, and the relationship between the virtual preset vibration threshold and the historical preset vibration threshold, to obtain the preset data model.

4. The method of claim 3, wherein, The updating of the initial data network based on the relationship between the virtual preset current range and the historical preset current range, and the relationship between the virtual preset vibration threshold and the historical preset vibration threshold, to obtain the preset data model, comprises: calculating a first loss function between the virtual preset current range and the historical preset current range; calculating a second loss function between the virtual preset vibration threshold and the historical preset vibration threshold; fusing the first loss function and the second loss function to generate a target loss function; updating the initial data network based on the target loss function to obtain the preset data model.

5. The method of claim 1, wherein, If the yaw angle change value is greater than a preset yaw angle change value, it is determined that the target wind turbine is in the yaw moment. If the yaw angle change value is greater than a preset yaw angle change value, yaw state identification information corresponding to the target wind turbine sent by a monitoring system of the target wind turbine is acquired. If the yaw state identification information indicates that the target wind turbine is in a yaw state, it is determined that the target wind turbine is in the yaw moment.

6. The method of claim 1, wherein, According to the comparison result, it is determined that the yaw brake device of the target wind turbine is abnormal. If the current vibration value is greater than the preset vibration threshold value, and at least one of the current current values is not within the preset current range, it is determined that the yaw brake device of the target wind turbine is abnormal, and prompt information is output.

7. A yaw brake device abnormality determination apparatus characterized by comprising: The device comprises: A first acquisition module is configured to acquire a current yaw angle corresponding to a target wind turbine based on a yaw sensor, compare the current yaw angle with a historical yaw angle, calculate a yaw angle change value, and if the yaw angle change value is greater than a preset yaw angle change value, determine that the target wind turbine is in the yaw moment. A current vibration value corresponding to the moment when the target wind turbine is in the yaw moment, and a current current value corresponding to at least one motor in the target wind turbine are acquired. A second acquisition module is configured to acquire a preset current range and a preset vibration threshold value corresponding to the target wind turbine at the yaw moment. A comparison module is configured to compare each of the current current values with the preset current range, and compare the current vibration value with the preset vibration threshold value. A first determination module is configured to determine, according to the comparison result, that the yaw brake device of the target wind turbine is abnormal.

8. An electronic device, comprising: It comprises: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the yaw brake device abnormality determination method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for making a computer execute the yaw brake device abnormality determination method of any one of claims 1 to 6.

10. A computer program product, characterised in that, It comprises computer instructions for making a computer execute the yaw brake device abnormality determination method of any one of claims 1 to 6.

Images