Fault diagnosis method and device for offshore wind turbine generator converter

Abstract

The invention provides a fault diagnosis method and device for an offshore wind turbine generator converter, and relates to the technical field of offshore power generation. Real-time operation data of the offshore wind turbine generator converter are acquired, the real-time operation data are acquired by a sensor installed on the offshore wind turbine generator converter, and the real-time operation data at least comprise temperature data, vibration data and electrical related data; abnormal identification is carried out on the real-time operation data based on a machine learning algorithm, a fault diagnosis result of the offshore wind turbine generator converter is output in response to identification that the offshore wind turbine generator converter has a fault, and the fault diagnosis result comprises a fault position, a fault type and a fault level; and generating abnormal alarm information based on the fault diagnosis result. According to the method, data analysis is carried out by utilizing a machine learning algorithm, the root of a potential problem can be identified more accurately, a detailed fault diagnosis result is provided, and compared with traditional manual inspection, the method is more efficient and accurate.

Description

Technical Field

[0001] The present application relates to the field of offshore power generation technology, and in particular to a fault diagnosis method and device for an offshore wind turbine converter. Background Art

[0002] As an important part of renewable energy, offshore wind turbines are widely used in marine areas to generate electricity using wind energy. As offshore wind turbines are often in complex and harsh environmental conditions, their internal converters, as one of the core power electronic devices, face great working challenges. The marine environment is characterized by high humidity and high salt fog, which poses a severe test to the normal operation of the converter. The high humidity environment makes it easy for water vapor in the air to condense inside the converter to form water droplets, thereby affecting the insulation performance and stability of electrical components. High salt fog contains a large amount of salt such as sodium chloride, which is easy to adhere to the surface of the converter and the internal circuit, causing problems such as corrosion and short circuit, seriously affecting the service life and reliability of the equipment. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, one purpose of the present application is to propose a fault diagnosis method for an offshore wind turbine converter, by acquiring real-time operating data of the offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data includes at least temperature data, vibration data and electrical related data; performing abnormality identification on the real-time operating data based on a machine learning algorithm, and in response to identifying a fault in the offshore wind turbine converter, outputting a fault diagnosis result of the offshore wind turbine converter, the fault diagnosis result including the fault location, fault type and fault level; and generating abnormal alarm information based on the fault diagnosis result.

[0005] The second objective of the present application is to provide a fault diagnosis device for an offshore wind turbine converter.

[0006] The third objective of the present application is to provide an electronic device.

[0007] A fourth object of the present application is to provide a non-transitory computer-readable storage medium.

[0008] A fifth object of the present application is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present application proposes a fault diagnosis method for an offshore wind turbine converter, comprising: obtaining real-time operating data of the offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data includes at least temperature data, vibration data and electrical-related data; performing abnormality identification on the real-time operating data based on a machine learning algorithm, and in response to identifying a fault in the offshore wind turbine converter, outputting a fault diagnosis result of the offshore wind turbine converter, the fault diagnosis result including the fault location, fault type and fault level; generating abnormal alarm information based on the fault diagnosis result.

[0010] According to one embodiment of the present application, anomaly identification is performed on real-time operation data based on a machine learning algorithm, including: inputting the real-time operation data into a trained anomaly identification model; and performing anomaly identification on the real-time operation data based on the anomaly identification model.

[0011] According to one embodiment of the present application, a training method for an abnormality recognition model includes: determining a training sample set, the training sample set includes positive samples and negative samples, each negative sample includes historical operating data, historical fault locations, historical fault types and historical fault levels of an offshore wind turbine converter; iteratively training the abnormality recognition model to be trained based on the training sample set to obtain a trained abnormality recognition model.

[0012] According to one embodiment of the present application, the anomaly recognition model adopts a support vector machine or a neural network algorithm.

[0013] According to an embodiment of the present application, the fault diagnosis method for an offshore wind turbine converter further includes: determining a target strategy from a preset strategy library based on the fault diagnosis result; and sending abnormal alarm information and the target strategy to a terminal device corresponding to the operation and maintenance personnel.

[0014] According to an embodiment of the present application, obtaining real-time operating data of an offshore wind turbine converter includes: receiving real-time collected data from a sensor installed on the offshore wind turbine converter by wireless transmission.

[0015] To achieve the above-mentioned purpose, the second aspect embodiment of the present application proposes a fault diagnosis device for an offshore wind turbine converter, including: an acquisition module, used to obtain real-time operating data of the offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data includes at least temperature data, vibration data and electrical related data; an identification module, used to identify abnormalities in the real-time operating data based on a machine learning algorithm, and in response to identifying that there is a fault in the offshore wind turbine converter, output a fault diagnosis result of the offshore wind turbine converter, the fault diagnosis result including the fault location, fault type and fault level; an alarm module, used to issue an abnormal alarm signal based on the fault diagnosis result.

[0016] According to one embodiment of the present application, the identification module is further used to: input the real-time operation data into a trained abnormality identification model; and perform abnormality identification on the real-time operation data based on the abnormality identification model.

[0017] According to one embodiment of the present application, the fault diagnosis device of the offshore wind turbine converter also includes a training module, which is used to: determine a training sample set, the training sample set includes positive samples and negative samples, each negative sample includes historical operating data, historical fault locations, historical fault types and historical fault levels of the offshore wind turbine converter; iteratively train the abnormality recognition model to be trained based on the training sample set to obtain a trained abnormality recognition model.

[0018] According to one embodiment of the present application, the anomaly recognition model adopts a support vector machine or a neural network algorithm.

[0019] According to one embodiment of the present application, the alarm module is also used to: determine the target strategy from a preset strategy library according to the fault diagnosis result; and send the abnormal alarm information and the target strategy to the terminal device corresponding to the operation and maintenance personnel.

[0020] According to an embodiment of the present application, the acquisition module is further used to: receive real-time collected data from sensors installed on the offshore wind turbine converter via wireless transmission.

[0021] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the fault diagnosis method for the offshore wind turbine converter as described in the first aspect embodiment of the present application.

[0022] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the fault diagnosis method of the offshore wind turbine converter as described in the first aspect embodiment of the present application.

[0023] To achieve the above-mentioned purpose, the fifth aspect embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the fault diagnosis method for the offshore wind turbine converter as described in the first aspect embodiment of the present application.

[0024] The present application achieves at least the following beneficial effects: by acquiring the operating data of the converter in real time, the present application can monitor the operating status of the offshore wind turbine converter in real time, and promptly detect any abnormalities or potential faults, thereby reducing the occurrence of sudden faults and improving the reliability of the unit; using machine learning algorithms for data analysis can more accurately identify the root causes of potential problems and provide detailed fault diagnosis results, which is more efficient and accurate than traditional manual inspections; by identifying and diagnosing faults in advance, operation and maintenance personnel can take preventive maintenance measures before the fault occurs, reducing the downtime of the wind turbine caused by the fault, thereby improving the overall operating efficiency of the unit and reducing downtime losses; timely alarm information can help operation and maintenance personnel respond quickly and avoid more serious equipment damage due to long delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0026] Figure 1 It is a schematic diagram of an exemplary implementation of a fault diagnosis method for an offshore wind turbine converter shown in one embodiment of the present application.

[0027] Figure 2 It is a schematic diagram of an exemplary implementation of a fault diagnosis method for an offshore wind turbine converter shown in one embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of a fault diagnosis device for an offshore wind turbine converter shown in one embodiment of the present application.

[0029] Figure 4 It is a schematic diagram of an electronic device shown in one embodiment of the present application. DETAILED DESCRIPTION

[0030] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] Figure 1 is a schematic diagram of an exemplary implementation of a fault diagnosis method for an offshore wind turbine converter shown in the present application, such as Figure 1 As shown, the fault diagnosis method of the offshore wind turbine converter comprises the following steps:

[0032] S101, obtaining real-time operating data of an offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data at least includes temperature data, vibration data and electrical related data.

[0033] Among them, in this application, real-time collected data from sensors installed on offshore wind turbine converters are received by wireless transmission.

[0034] Among them, temperature is one of the important indicators to determine whether the converter is working properly. Too high temperature may mean that the internal electrical components of the converter are overloaded or the heat dissipation system fails, so temperature data needs to be collected in this application.

[0035] Among them, vibration is an important data to judge whether the converter is operating normally. Abnormal vibration may indicate that the converter internal or connecting parts are loose, worn or damaged, so vibration data needs to be collected in this application.

[0036] Among them, electrical related data include electrical parameters such as current, voltage, power factor, frequency, etc. These data can be used to monitor the electrical performance of the converter and detect faults in the electrical system (such as short circuit, open circuit, etc.).

[0037] All these real-time operation data are transmitted in real time via wireless transmission, ensuring that the data can be transmitted from the site to the ground diagnostic device in a timely and reliable manner. This wireless transmission method can effectively overcome the difficulties of laying out traditional wired communication facilities in the offshore wind turbine environment.

[0038] S102, performing abnormality identification on real-time operating data based on a machine learning algorithm, and in response to identifying a fault in an offshore wind turbine converter, outputting a fault diagnosis result of the offshore wind turbine converter, wherein the fault diagnosis result includes a fault location, a fault type, and a fault level.

[0039] After obtaining the real-time operation data, the real-time operation data is processed and analyzed using machine learning algorithms (such as decision trees, random forests, neural networks, etc.). Machine learning algorithms can automatically identify potential abnormal patterns in a large amount of real-time operation data, which usually indicate converter failure or abnormal operation.

[0040] Once an anomaly is detected, the machine learning algorithm will automatically identify and give the fault location, fault type (such as electrical fault, mechanical fault, etc.), and fault level (such as minor fault, major fault, etc.) based on real-time operating data.

[0041] S103, generating abnormal warning information based on the fault diagnosis result.

[0042] Abnormal alarm information will be pushed to the operation and maintenance personnel or monitoring center in time so that relevant personnel can take countermeasures quickly. Alarm information can also be notified via SMS, email, or dedicated operation and maintenance platform.

[0043] An embodiment of the present application proposes a fault diagnosis method for an offshore wind turbine converter, by acquiring real-time operating data of the offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data includes at least temperature data, vibration data, and electrical-related data; anomalies are identified on the real-time operating data based on a machine learning algorithm, and in response to identifying that a fault exists in the offshore wind turbine converter, a fault diagnosis result of the offshore wind turbine converter is output, the fault diagnosis result including the fault location, fault type, and fault level; and abnormal alarm information is generated based on the fault diagnosis result. By acquiring the operating data of the converter in real time, the present application can monitor the operating status of the converter of the offshore wind turbine in real time, and promptly detect any abnormalities or potential faults, thereby reducing the occurrence of sudden faults and improving the reliability of the unit; using machine learning algorithms for data analysis can more accurately identify the root causes of potential problems and provide detailed fault diagnosis results, which is more efficient and accurate than traditional manual inspections; by identifying and diagnosing faults in advance, operation and maintenance personnel can take preventive maintenance measures before the fault occurs, reducing the downtime of the wind turbine caused by the fault, thereby improving the overall operating efficiency of the unit and reducing downtime losses; timely alarm information can help operation and maintenance personnel respond quickly to avoid more serious equipment damage due to long delays.

[0044] Figure 2 is a schematic diagram of an exemplary implementation of a fault diagnosis method for an offshore wind turbine converter shown in the present application, such as Figure 2 As shown, the fault diagnosis method of the offshore wind turbine converter comprises the following steps:

[0045] S201, obtaining real-time operating data of an offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data includes at least temperature data, vibration data, and electrical related data.

[0046] S202, performing abnormality identification on real-time operating data based on a machine learning algorithm, and in response to identifying a fault in an offshore wind turbine converter, outputting a fault diagnosis result of the offshore wind turbine converter, wherein the fault diagnosis result includes a fault location, a fault type, and a fault level.

[0047] The real-time operation data is input into a trained anomaly recognition model; and anomalies are recognized on the real-time operation data based on the anomaly recognition model.

[0048] Optionally, the anomaly recognition model uses a support vector machine or a neural network algorithm.

[0049] The training method of the anomaly recognition model includes: determining a training sample set, the training sample set includes positive samples and negative samples, each negative sample includes historical operation data, historical fault locations, historical fault types and historical fault levels of an offshore wind turbine converter; iteratively training the anomaly recognition model to be trained based on the training sample set to obtain a trained anomaly recognition model.

[0050] S203: Generate abnormal warning information based on the fault diagnosis result.

[0051] S204: Determine a target strategy from a preset strategy library according to the fault diagnosis result.

[0052] Among them, the strategy library can be preset with target strategies corresponding to various fault diagnosis results, and experts can predict in advance and give corresponding strategies to generate the strategy library.

[0053] S205, sending the abnormal alarm information and the target strategy to the terminal device corresponding to the operation and maintenance personnel.

[0054] The embodiments of the present application can monitor the operating status of the offshore wind turbine inverter in real time by acquiring the operating data of the inverter in real time, and promptly discover any abnormalities or potential faults, thereby reducing the occurrence of sudden faults and improving the reliability of the unit; using machine learning algorithms for data analysis can more accurately identify the root causes of potential problems and provide detailed fault diagnosis results, which is more efficient and accurate than traditional manual inspections; by identifying and diagnosing faults in advance, operation and maintenance personnel can take preventive maintenance measures before the fault occurs, reducing the downtime of the wind turbine caused by the fault, thereby improving the overall operating efficiency of the unit and reducing downtime losses; timely alarm information can help operation and maintenance personnel respond quickly to avoid more serious equipment damage due to long delays.

[0055] Figure 3 is a schematic diagram of a fault diagnosis device for an offshore wind turbine converter shown in the present application, such as Figure 3 As shown, the fault diagnosis device 300 of the offshore wind turbine converter includes an acquisition module 301, an identification module 302 and an alarm module 303, wherein:

[0056] The acquisition module 301 is used to acquire real-time operating data of the offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data at least includes temperature data, vibration data and electrical related data.

[0057] The identification module 302 is used to identify anomalies in real-time operating data based on a machine learning algorithm, and in response to identifying that there is a fault in the offshore wind turbine converter, output a fault diagnosis result of the offshore wind turbine converter, wherein the fault diagnosis result includes a fault location, a fault type and a fault level.

[0058] The alarm module 303 is used to issue an abnormal alarm signal based on the fault diagnosis result.

[0059] By acquiring the operating data of the converter in real time, the device can monitor the operating status of the offshore wind turbine converter in real time and detect any abnormalities or potential faults in time, thereby reducing the occurrence of sudden faults and improving the reliability of the unit; using machine learning algorithms for data analysis can more accurately identify the root causes of potential problems and provide detailed fault diagnosis results, which is more efficient and accurate than traditional manual inspections; by identifying and diagnosing faults in advance, operation and maintenance personnel can take preventive maintenance measures before the fault occurs, reducing the downtime of the wind turbine caused by the fault, thereby improving the overall operating efficiency of the unit and reducing downtime losses; timely alarm information can help operation and maintenance personnel respond quickly to avoid more serious equipment damage due to long delays.

[0060] Furthermore, the identification module 302 is also used to: input the real-time operation data into a trained abnormality identification model; and perform abnormality identification on the real-time operation data based on the abnormality identification model.

[0061] Furthermore, the fault diagnosis device for the offshore wind turbine converter also includes a training module, which is used to: determine a training sample set, the training sample set includes positive samples and negative samples, each negative sample includes historical operating data, historical fault locations, historical fault types and historical fault levels of the offshore wind turbine converter; iteratively train the abnormality recognition model to be trained based on the training sample set to obtain a trained abnormality recognition model.

[0062] Furthermore, the anomaly recognition model uses a support vector machine or a neural network algorithm.

[0063] Furthermore, the alarm module 303 is also used to: determine a target policy from a preset policy library according to the fault diagnosis result; and send abnormal alarm information and the target policy to a terminal device corresponding to the operation and maintenance personnel.

[0064] Furthermore, the acquisition module 301 is also used to: receive real-time collected data from sensors installed on the converter of the offshore wind turbine generator set by wireless transmission.

[0065] In order to implement the above embodiment, the present application embodiment also proposes an electronic device 400, such as Figure 4 As shown, the electronic device 400 includes: a processor 401 and a memory 402 that is communicatively connected to the processor, the memory 402 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 401 to implement the fault diagnosis method for the offshore wind turbine converter as shown in the above embodiment.

[0066] In order to implement the above embodiments, the embodiments of the present application also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to implement the fault diagnosis method for an offshore wind turbine converter as shown in the above embodiments.

[0067] In order to implement the above embodiments, the embodiments of the present application further provide a computer program product, including a computer program, which, when executed by a processor, implements the fault diagnosis method for an offshore wind turbine converter as shown in the above embodiments.

[0068] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0069] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0070] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0071] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A fault diagnosis method for an offshore wind turbine converter, characterized in that: include: Acquire real-time operating data of an offshore wind turbine converter, wherein the real-time operating data is collected by sensors installed on the offshore wind turbine converter, and the real-time operating data includes at least temperature data, vibration data, and electrical related data; Identify anomalies of the real-time operation data based on a machine learning algorithm, and in response to identifying that a fault exists in the offshore wind turbine converter, output a fault diagnosis result of the offshore wind turbine converter, wherein the fault diagnosis result includes a fault location, a fault type, and a fault level; Generate abnormal warning information based on the fault diagnosis result.

2. The method according to claim 1, characterized in that: The performing abnormality identification on the real-time operation data based on a machine learning algorithm includes: Inputting the real-time operation data into a trained anomaly recognition model; Anomalies are identified on the real-time operation data based on the anomaly identification model.

3. The method according to claim 2, characterized in that The training method of the anomaly recognition model comprises: Determine a training sample set, the training sample set includes positive samples and negative samples, each of the negative samples includes historical operation data, historical fault locations, historical fault types and historical fault levels of the offshore wind turbine converter; The anomaly recognition model to be trained is iteratively trained based on the training sample set to obtain a trained anomaly recognition model.

4. The method according to claim 3, characterized in that The anomaly recognition model adopts a support vector machine or a neural network algorithm.

5. The method according to claim 4, characterized in that The method further comprises: Determining a target strategy from a preset strategy library according to the fault diagnosis result; The abnormal alarm information and the target strategy are sent to the terminal device corresponding to the operation and maintenance personnel.

6. The method according to claim 5, characterized in that The real-time operation data of the offshore wind turbine converter is obtained, including: The real-time collected data of the sensor installed on the converter of the offshore wind turbine generator set is received by wireless transmission.

7. A fault diagnosis device for an offshore wind turbine converter, characterized in that: include: An acquisition module, used for acquiring real-time operation data of an offshore wind turbine converter, wherein the real-time operation data is collected by sensors installed on the offshore wind turbine converter, and the real-time operation data at least includes temperature data, vibration data and electrical related data; an identification module, configured to identify anomalies of the real-time operation data based on a machine learning algorithm, and output a fault diagnosis result of the offshore wind turbine converter in response to identifying that a fault exists in the offshore wind turbine converter, wherein the fault diagnosis result includes a fault location, a fault type, and a fault level; An alarm module is used to issue an abnormal alarm signal based on the fault diagnosis result.

8. An electronic device, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images