A fault positioning method, a fault processing method, a device, and an electronic device

Abstract

The embodiment of the application provides a fault positioning method, a fault processing method, a device and electronic equipment, relates to the wind power generation technical field, and the method is applied to a wind power prediction system. The wind power prediction system respectively communicates with a data acquisition device and a data processing device. The method comprises the following steps: when it is detected that the wind power prediction system processes wind farm data abnormally, determining an abnormal type of the abnormality based on whether the wind power prediction system receives wind farm data sent by the data processing device in a target data acquisition period; when the abnormal type is a communication abnormality, performing fault positioning based on communication information between the wind power prediction system and the data acquisition device and the data processing device to obtain a fault positioning result; and when the abnormal type is a first type of data abnormality, determining that an abnormal data in the wind farm data belongs to a target device which is faulty, so that the stability of the wind power prediction system can be improved.

Description

Technical Field

[0001] This application relates to the field of wind power generation technology, and in particular to a fault location method, fault handling method, device and electronic equipment. Background Technology

[0002] Wind power prediction technology uses wind farm data, such as wind turbine (Wind Turbine) operation data and wind farm meteorological data, to predict the power of a wind farm and report the predicted power to the dispatching platform. This enables power dispatching departments to perform power dispatching based on the power received from the dispatching platform.

[0003] A wind farm is equipped with wind turbines, wind measurement equipment, a SCADA (Supervisory Control and Data Acquisition) system, a data transceiver server, and a wind power prediction system. The SCADA system acquires wind turbine operating data and reports it to the wind power prediction system. The data transceiver server acquires meteorological data measured by the wind measurement equipment and forecast meteorological data obtained from a meteorological platform, and reports it to the wind power prediction system. Then, the wind power prediction system determines the predicted power data of the wind farm based on the wind farm data reported by the SCADA system and the data transceiver server.

[0004] Because the wind power prediction system and its interconnected equipment are deployed in different areas of the wind farm—for example, the wind power prediction system is deployed in the non-control area of ​​the wind farm, while the wind turbines and SCADA system are deployed in the control area—various instabilities can occur when the wind power prediction system interacts with other equipment. These instabilities include network fluctuations, network interruptions, data loss, and data reporting failures, all of which can affect the normal operation of the wind power prediction system and reduce its stability. Summary of the Invention

[0005] The purpose of this application is to provide a fault location method, fault handling method, apparatus, and electronic device to locate faults and handle abnormalities when an anomaly is detected in the wind power prediction system's processing of wind farm data. This reduces the impact on the normal operation of the wind power prediction system and improves its stability. The specific technical solution is as follows:

[0006] Firstly, to achieve the above objectives, embodiments of this application provide a fault location method, which is applied to a wind power prediction system. The wind power prediction system communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measurement device, and the data processing device includes SCADA and a data transceiver server. The method includes:

[0007] When an anomaly is detected in the wind power prediction system's processing of wind farm data, the anomaly type is determined based on whether the wind power prediction system received wind farm data sent by the data processing device within the target data acquisition period.

[0008] When the anomaly type is a communication anomaly, the fault location result is obtained by performing fault location based on the communication information between the wind power prediction system and the data acquisition device and the data processing device, respectively.

[0009] When the anomaly type is the first type of data anomaly, the device to which the abnormal data in the wind farm data belongs is determined to be the target device that has failed.

[0010] Optionally, the method for determining the anomaly type based on whether the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period includes:

[0011] If the wind power prediction system does not receive wind farm data sent by the data processing device within the target data acquisition period, the abnormality type of the abnormality is determined to be a communication abnormality.

[0012] If the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period, and detects that the wind farm data is abnormal, the abnormality type of the abnormality is determined to be the first type of data abnormality.

[0013] Optionally, when the anomaly type is a communication anomaly, the fault location result is obtained by performing fault location based on the communication information between the wind power prediction system and the data acquisition device and the data processing device, respectively, including:

[0014] From the data acquisition device and the data processing device, the device that did not send a heartbeat detection request during the heartbeat detection cycle is identified as the target device that has malfunctioned;

[0015] If a heartbeat detection request is received from the data acquisition device and the data processing device during the heartbeat detection cycle, data update information is obtained from the data acquisition device and the data processing device respectively; wherein, the data update information includes: the update time of the most recent data update, and / or, the data increment information of the most recent data update;

[0016] If the data update information of the data acquisition device matches that of the data processing device, then a network anomaly is determined between the wind power prediction system and the data processing device.

[0017] If the data update information of the data acquisition device and the data processing device do not match, then a network anomaly is determined between the data acquisition device and the data processing device.

[0018] Wherein, when the data acquisition device is a wind turbine, the data processing device is SCADA; when the data acquisition device is a wind measurement device, the data processing device is a data transceiver server.

[0019] Optionally, the data acquisition device matches the data update information with the data processing device, including:

[0020] The first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the duration between the first update time and the second update time is less than the first preset duration.

[0021] And / or,

[0022] The wind farm data cached by the data acquisition device increased during the most recent data update, and the wind farm data cached by the data processing device also increased during the most recent data update.

[0023] Optionally, the wind power prediction system communicates with the dispatching platform, and the method further includes:

[0024] If the predicted power data output by the wind power prediction system is abnormal, the abnormality type is determined to be the second type of data abnormality, and the wind power prediction system is determined to be the target device that has failed; wherein, the predicted power data is obtained by the wind power prediction system based on the received wind farm data;

[0025] If the wind power prediction system fails to report predicted power data to the scheduling platform, the anomaly type is determined to be a reporting anomaly, and the wind power prediction system is identified as the target device that has failed.

[0026] Optionally, if the wind power prediction system fails to report predicted power data to the scheduling platform, the anomaly type of the detected anomaly is determined to be a reporting anomaly, including:

[0027] If the wind power prediction system does not receive a response message from the scheduling platform within a first preset time period after sending the predicted power data to the scheduling platform, or if it receives a response message from the scheduling platform carrying a status code indicating a reporting error, it determines that the reporting of the predicted power data to the scheduling platform has failed, and determines that the anomaly type is a reporting anomaly.

[0028] Secondly, to achieve the above objectives, embodiments of this application provide a fault handling method. This method is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measurement device, and the data processing device includes SCADA and a data transceiver server. The method includes:

[0029] When an anomaly is detected in the wind power prediction system's processing of wind farm data, the anomaly type and fault location result are obtained; wherein, the anomaly type and the fault location result are determined based on the fault location method described in the first aspect above;

[0030] When the anomaly type is a communication anomaly and the fault location result indicates that the target device in the data acquisition device and the data processing device has malfunctioned, a control command is sent to the target device so that the target device can perform fault handling according to a preset self-test procedure.

[0031] When the anomaly type is communication anomaly, and the fault location result indicates a network anomaly in the wind power prediction system, the data acquisition device, and the data processing device, an alarm message is output.

[0032] When the anomaly type is the first type of data anomaly, the abnormal data that has occurred is repaired.

[0033] Optionally, the repair of the abnormal data includes:

[0034] If the abnormal data is the turbine operation data of the first wind turbine, the turbine operation data of the first wind turbine is determined based on the data collection period before the target data collection period, and / or the turbine operation data of the second wind turbine in the target data collection period that meets the preset screening conditions.

[0035] If the abnormal data is the meteorological measurement data of the wind measuring device, the repaired meteorological measurement data of the wind measuring device is determined based on at least one of the meteorological measurement data of the wind measuring device in the data collection period before the target data collection period, the meteorological measurement data of the wind turbine in the target data collection period, and the predicted meteorological data of the meteorological platform.

[0036] Optionally, the method further includes:

[0037] When the anomaly type is the second type of data anomaly, the predicted power data after repair is determined based on the predicted power data output by the wind power prediction system in the data acquisition cycle before the target data acquisition cycle.

[0038] When the exception type is reporting exception, if no response message is received from the scheduling platform, predictive power data is sent to the scheduling platform; if a response message carrying a reporting error status code is received, predictive power data is generated according to the status code, and the generated predictive power data is sent to the scheduling platform.

[0039] Thirdly, to achieve the above objectives, embodiments of this application provide a fault location device, which is applied to a wind power prediction system. The wind power prediction system communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measuring device, and the data processing device includes SCADA and a data transceiver server. The device includes:

[0040] An anomaly type determination module is used to determine the anomaly type of the anomaly when an anomaly is detected in the wind power prediction system's processing of wind farm data, based on whether the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period.

[0041] The first fault location module is used to locate the fault and obtain the fault location result based on the communication information between the wind power prediction system and the data acquisition device and the data processing device when the anomaly type is a communication anomaly.

[0042] The second fault location module is used to determine, when the anomaly type is the first type of data anomaly, the device to which the abnormal data in the wind farm data belongs is the target device that has experienced a fault.

[0043] Optionally, the anomaly type determination module is specifically used to determine the anomaly type of the anomaly as a communication anomaly if the wind power prediction system does not receive wind farm data sent by the data processing device within the target data acquisition period.

[0044] If the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period, and detects that the wind farm data is abnormal, the abnormality type of the abnormality is determined to be the first type of data abnormality.

[0045] Optionally, the first fault location module is specifically used to determine, from the data acquisition device and the data processing device, the device that did not send a heartbeat detection request during the heartbeat detection cycle as the target device that has malfunctioned;

[0046] If a heartbeat detection request is received from the data acquisition device and the data processing device during the heartbeat detection cycle, data update information is obtained from the data acquisition device and the data processing device respectively; wherein, the data update information includes: the update time of the most recent data update, and / or, the data increment information of the most recent data update;

[0047] If the data update information of the data acquisition device matches that of the data processing device, then a network anomaly is determined between the wind power prediction system and the data processing device.

[0048] If the data update information of the data acquisition device and the data processing device do not match, then a network anomaly is determined between the data acquisition device and the data processing device.

[0049] Wherein, when the data acquisition device is a wind turbine, the data processing device is SCADA; when the data acquisition device is a wind measurement device, the data processing device is a data transceiver server.

[0050] Optionally, the data acquisition device matches the data update information with the data processing device, including:

[0051] The first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the duration between the first update time and the second update time is less than the first preset duration.

[0052] And / or,

[0053] The wind farm data cached by the data acquisition device increased during the most recent data update, and the wind farm data cached by the data processing device also increased during the most recent data update.

[0054] Optionally, the wind power prediction system communicates with the dispatching platform, and the device further includes:

[0055] The third fault location module is specifically used to determine the type of abnormality as a second type of data abnormality if the predicted power data output by the wind power prediction system is abnormal data, and to determine the wind power prediction system as the target device that has failed; wherein, the predicted power data is obtained by the wind power prediction system based on the received wind farm data;

[0056] The fourth fault location module is specifically used to determine the type of the abnormality as a reporting abnormality if the wind power prediction system fails to report predicted power data to the scheduling platform, and to determine the wind power prediction system as the target device that has failed.

[0057] Optionally, the fourth fault location module is specifically used to determine that reporting the predicted power data to the scheduling platform has failed if the wind power prediction system does not receive a response message from the scheduling platform within a first preset time period after sending the predicted power data to the scheduling platform, or if it receives a response message from the scheduling platform carrying a status code indicating a reporting error, and determines that the anomaly type of the anomaly is a reporting anomaly.

[0058] Fourthly, to achieve the above objectives, this application provides a fault handling device applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measurement device, and the data processing device includes SCADA and a data transceiver server. The device includes:

[0059] The data acquisition module is used to acquire the anomaly type and fault location result when an anomaly is detected in the wind power prediction system's processing of wind farm data; wherein the anomaly type and the fault location result are determined by the fault location device described in the third aspect above;

[0060] The first fault handling module is used to send a control command to the target device when the abnormality type is a communication abnormality and the fault location result indicates that the target device in the data acquisition device and the data processing device has failed, so that the target device can perform fault handling according to a preset self-test procedure.

[0061] The second fault handling module is used to output alarm information when the anomaly type is communication anomaly and the fault location result indicates a network anomaly in the wind power prediction system, the data acquisition device and the data processing device.

[0062] The third fault handling module is used to repair the abnormal data when the abnormality type is the first type of data abnormality.

[0063] Optionally, the third fault handling module is specifically used to determine the repaired turbine operation data of the first wind turbine based on the turbine operation data of the first wind turbine in the data acquisition period before the target data acquisition period, and / or the turbine operation data of the second wind turbine in the target data acquisition period that meets the preset screening conditions, if the abnormal data is the turbine operation data of the first wind turbine.

[0064] If the abnormal data is the meteorological measurement data of the wind measuring device, the repaired meteorological measurement data of the wind measuring device is determined based on at least one of the meteorological measurement data of the wind measuring device in the data collection period before the target data collection period, the meteorological measurement data of the wind turbine in the target data collection period, and the predicted meteorological data of the meteorological platform.

[0065] Optionally, the device further includes:

[0066] The fourth fault handling module is used to determine the repaired predicted power data based on the predicted power data output by the wind power prediction system in the data acquisition cycle before the target data acquisition cycle when the anomaly type is the second type of data anomaly.

[0067] When the exception type is reporting exception, if no response message is received from the scheduling platform, predictive power data is sent to the scheduling platform; if a response message carrying a reporting error status code is received, predictive power data is generated according to the status code, and the generated predictive power data is sent to the scheduling platform.

[0068] This application also provides an electronic device, including:

[0069] Memory, used to store computer programs;

[0070] When a processor executes a program stored in a memory, it implements either the fault location method described in the first aspect above, or the fault handling method described in either the second aspect above.

[0071] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the fault location method described in any of the first aspects above, or the fault handling method described in any of the second aspects above.

[0072] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the fault location method described in any of the first aspects above, or the fault handling method described in any of the second aspects above.

[0073] Beneficial effects of the embodiments in this application:

[0074] This application provides a fault location method, fault handling method, apparatus, and electronic device. The method is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measurement device, and the data processing device includes SCADA and a data transceiver server. The method includes: when an anomaly is detected in the wind power prediction system's processing of wind farm data, determining the anomaly type based on whether the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period; when the anomaly type is a communication anomaly, performing fault location based on the communication information between the wind power prediction system and the data acquisition device and the data processing device to obtain a fault location result; and when the anomaly type is a first-type data anomaly, determining the device to which the abnormal data in the wind farm data belongs as the target device that has experienced the fault.

[0075] Based on the above processing, fault location can be performed when anomalies are detected in the wind power prediction system's processing of wind farm data. Subsequently, processing of the anomalies based on the fault location results can reduce the impact on the normal operation of the wind power prediction system and improve its stability.

[0076] Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0077] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0078] Figure 1 A flowchart illustrating the first fault location method provided in this application embodiment;

[0079] Figure 2 A flowchart illustrating the second fault location method provided in this application embodiment;

[0080] Figure 3 A flowchart of the first fault handling method provided in the embodiments of this application;

[0081] Figure 4 A flowchart illustrating the second fault handling method provided in this application embodiment;

[0082] Figure 5 A structural diagram of a fault location device provided in an embodiment of this application;

[0083] Figure 6A structural diagram of a fault handling device provided in an embodiment of this application;

[0084] Figure 7 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0085] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of this application.

[0086] In related technologies, wind power prediction systems and their interconnected devices are deployed in different areas of wind farms. For example, the wind power prediction system is deployed in the non-control area of ​​the wind farm, while the wind turbines and SCADA system are deployed in the control area. When the wind power prediction system interacts with other devices, various instabilities can occur, such as network fluctuations, network interruptions, data loss, and data reporting failures. These can all affect the normal operation of the wind power prediction system and reduce its stability.

[0087] To address the aforementioned issues, this application provides a fault location method applied to a wind power prediction system. When an anomaly is detected in the wind power prediction system's processing of wind farm data, the fault location result is determined according to the fault location method provided in this application. This application also provides a fault handling method applied to the wind power prediction system. After determining the fault location result of the anomaly in the wind power prediction system's processing of wind farm data, fault handling is performed according to the fault handling method provided in this application. This can reduce the impact on the normal operation of the wind power prediction system and improve its stability.

[0088] The following describes the fault location method provided in the embodiments of this application.

[0089] See Figure 1 , Figure 1 A flowchart of a fault location method provided in this application embodiment is shown. This method is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measurement device, and the data processing device includes SCADA and a data transceiver server. The method includes the following steps:

[0090] S101: When an anomaly is detected in the wind power prediction system's processing of wind farm data, the anomaly type is determined based on whether the wind power prediction system receives wind farm data sent by the data processing equipment within the target data acquisition period.

[0091] S102: When the anomaly type is communication anomaly, the fault location result is obtained by performing fault location based on the communication information between the wind power prediction system and the data acquisition equipment and the data processing equipment.

[0092] S103: When the anomaly type is the first type of data anomaly, determine the equipment to which the abnormal data in the wind farm data belongs as the target equipment that has failed.

[0093] The fault location method provided in this application can locate faults when an anomaly is detected in the wind power prediction system's processing of wind farm data. Subsequently, processing the anomaly based on the fault location results can reduce the impact on the normal operation of the wind power prediction system and improve its stability.

[0094] For step S101, the wind farm is equipped with wind turbines, wind measurement equipment, SCADA, data transceiver servers and wind power prediction systems.

[0095] The operating data of a wind turbine includes: the power of the wind turbine generator, the amount of electricity generated, and the meteorological data measured by the wind turbine generator.

[0096] Anemometers can be wind-measuring lidar. The meteorological data measured by anemometers include wind speed, wind direction, temperature, humidity, and air pressure.

[0097] Forecasted meteorological data includes forecasted meteorological data obtained from meteorological platforms. Examples include wind speed, wind direction, temperature, humidity, and air pressure.

[0098] When the wind turbine reaches the time corresponding to the target data acquisition cycle, it reports the turbine operation data collected within the target data acquisition cycle to SCADA. After receiving the turbine operation data reported by the wind turbine, SCADA reports the turbine operation data to the wind power prediction system. The duration of the data acquisition cycle can be set according to requirements; for example, the duration of the data acquisition cycle can be 5 minutes, or it can also be 3 minutes.

[0099] When the wind measuring equipment reaches the time corresponding to the target data collection period, it reports the measured meteorological data collected within the target data collection period to the data transceiver server. When the data transceiver server reaches the time corresponding to the data collection period, it obtains the predicted meteorological data from the meteorological platform, and after receiving the measured meteorological data reported by the wind measuring equipment, it reports both the measured meteorological data and the predicted meteorological data to the wind power prediction system.

[0100] The wind power prediction system determines the predicted power data of the wind farm based on the wind farm data reported by the SCADA system and the data transceiver server.

[0101] In some embodiments, step S101 may include the following steps: if the wind power prediction system does not receive wind farm data sent by the data processing device within the target data acquisition period, determine that the anomaly type is a communication anomaly. If the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period and detects that the wind farm data is abnormal data, determine that the anomaly type is a first type of data anomaly.

[0102] When an anomaly is detected in the wind power prediction system's processing of wind farm data, if the wind power prediction system does not receive wind farm data sent by the data processing equipment within the target data acquisition period, it indicates that the wind farm data collected by the data acquisition equipment has not been successfully reported to the wind power prediction system. In this case, it can be determined that there is a communication anomaly between the data acquisition equipment, the data processing equipment, and the wind power prediction system, and the anomaly type is determined to be a communication anomaly.

[0103] If the wind power prediction system receives wind farm data from the data processing equipment within the target data acquisition period, it indicates that the wind farm data collected by the data acquisition equipment has been successfully reported to the wind power prediction system. Furthermore, it can detect whether the wind farm data falls within a preset data range. If the wind farm data exceeds the preset data range, it is determined that the wind farm data is abnormal. For example, the preset data range for wind turbine power is not less than 0. If the wind turbine power is negative, it can be determined that the wind turbine power is abnormal data.

[0104] Furthermore, when wind farm data is detected as abnormal, the abnormality type is determined to be the first type of data abnormality.

[0105] For step S102, the anomaly types include: communication anomaly, first-type data anomaly, second-type data anomaly, and reporting anomaly. Communication anomalies include equipment anomalies and network anomalies. Equipment anomalies indicate malfunctions in wind turbines, wind measurement equipment, SCADA systems, data transceiver servers, etc. Network anomalies indicate abnormal network connections between wind turbines, wind measurement equipment, SCADA systems, data transceiver servers, etc. First-type data anomalies indicate abnormal wind farm data reported by wind turbines and wind measurement equipment. Second-type data anomalies indicate abnormal predicted power data output by the wind power prediction system. Reporting anomalies indicate abnormalities in the predicted power data reported by the wind power prediction system to the dispatch platform.

[0106] For the second type of data anomalies and reporting anomalies, please refer to the relevant descriptions in the subsequent embodiments.

[0107] In some embodiments, Figure 1 Based on this, see Figure 2 Step S102 may include the following steps:

[0108] S1021: When the anomaly type is communication anomaly, identify the device that did not send a heartbeat detection request during the heartbeat detection cycle from the data acquisition device and the data processing device as the target device that has failed.

[0109] S1022: When the exception type is communication exception, if a heartbeat detection request is received from the data acquisition device and the data processing device during the heartbeat detection cycle, data update information is obtained from the data acquisition device and the data processing device respectively.

[0110] The data update information includes: the update time of the most recent data update, and / or, the data increment information of the most recent data update.

[0111] S1023: If the data update information of the data acquisition device and the data processing device match, then a network anomaly is determined between the wind power prediction system and the data processing device.

[0112] S1024: If the data update information of the data acquisition device and the data processing device do not match, then a network anomaly is determined between the data acquisition device and the data processing device.

[0113] When the data acquisition device is a wind turbine, the data processing device is SCADA; when the data acquisition device is a wind measurement device, the data processing device is a data transceiver server.

[0114] The wind turbine, wind measurement equipment, SCADA system, and data transceiver server each perform periodic heartbeat checks with the wind power prediction system to determine if any of these components are malfunctioning. The following explanation uses a wind turbine as an example; the heartbeat check method between other devices and the wind power prediction system can be referenced in the same manner.

[0115] When the preset heartbeat detection cycle is reached, the wind turbine sends a heartbeat detection request to the wind power prediction system. Upon receiving the heartbeat detection request, the wind power prediction system returns a heartbeat detection response to the wind turbine to confirm that the wind turbine is not malfunctioning. Conversely, if the wind power prediction system does not receive a heartbeat detection request from the wind turbine within the heartbeat detection cycle, it can determine that the wind turbine is the target device that has malfunctioned.

[0116] Similarly, if the wind power prediction system does not receive a heartbeat detection request from the wind measurement device within the heartbeat detection period, the wind measurement device can be identified as the faulty target device. If the wind power prediction system does not receive a heartbeat detection request from the SCADA system within the heartbeat detection period, the SCADA system can be identified as the faulty target device. If the wind power prediction system does not receive a heartbeat detection request from the data transceiver server within the heartbeat detection period, the data transceiver server can be identified as the faulty target device.

[0117] In some embodiments, a wireless network is deployed in the wind farm for heartbeat detection between the wind turbines, wind measurement equipment, SCADA system, data transceiver server, and wind power prediction system. The SCADA system, data transceiver server, and wind power prediction system transmit data via a wired network.

[0118] If the wind power prediction system receives a heartbeat detection request from the data acquisition device and the data processing device during the heartbeat detection cycle, it indicates that the data acquisition device and the data processing device are not malfunctioning. The problem may be a network anomaly between the wind power prediction system and the data processing device, or a network anomaly between the data acquisition device and the data processing device.

[0119] In addition to reporting the wind farm data to the data processing equipment, the data acquisition equipment also caches the data locally. This means that both the data acquisition and processing equipment update the data. Therefore, the wind power prediction system obtains updated data information from both the data acquisition and processing equipment.

[0120] Data update information includes the update time of the most recent data update and / or the data increment information of the most recent data update. The data increment information of the most recent data update includes whether the locally cached wind farm data has been increased.

[0121] Furthermore, the wind power prediction system determines whether the data update information from the data acquisition equipment and the data processing equipment matches.

[0122] In some embodiments, matching the data update information between the data acquisition device and the data processing device includes:

[0123] The first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the duration between the first update time and the second update time is less than the first preset duration.

[0124] And / or,

[0125] The wind farm data cached by the data acquisition equipment increased during the most recent data update, and the wind farm data cached by the data processing equipment also increased during the most recent data update.

[0126] Since the data acquisition equipment collects wind farm data and then reports it to the data processing equipment, the second update time of the data processing equipment is later than the first update time of the data acquisition equipment. Furthermore, because the time required for the data acquisition equipment to report the collected wind farm data to the data processing equipment is relatively short, the duration between the first and second update times is less than the first preset duration. The first preset duration is set by technical personnel according to requirements.

[0127] Therefore, if the first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the time between the first update time and the second update time is less than the first preset time, it can be determined that the data update information of the data acquisition device and the data processing device are matched.

[0128] For example, if the first update time of the most recent update data of the wind turbine is earlier than the second update time of the most recent update data of SCADA, and the time between the first update time and the second update time is less than the first preset time, then it is determined that the data update information of the wind turbine matches the data update information of SCADA.

[0129] If the first update time of the most recent data update by the wind measurement device is earlier than the second update time of the most recent data update by the data transceiver server, and the time between the first update time and the second update time is less than the first preset time, then it is determined that the data update information of the wind measurement device matches the data update information of the data transceiver server.

[0130] Furthermore, assuming the data acquisition equipment is functioning correctly, the wind farm data collected by the equipment is continuously cached locally, thus increasing the cached wind farm data. Similarly, the wind farm data collected by the equipment is continuously reported to the data processing equipment, thus increasing the cached wind farm data.

[0131] Therefore, if the wind farm data cached by the data acquisition device increases during the most recent data update, and the wind farm data cached by the data processing device also increases during the most recent data update, then it is determined that the data update information of the data acquisition device matches the data update information of the data processing device.

[0132] For example, if the wind farm data cached when the wind turbine last updated its data increased, and the wind farm data cached when the SCADA last updated its data also increased, then it is determined that the wind turbine's data update information matches the SCADA's data update information.

[0133] If the data update information of the data acquisition device matches the data update information of the data processing device, it indicates that the wind farm data collected by the data acquisition device has been successfully reported to the data processing device, and it can be determined that the network between the data acquisition device and the data processing device is normal. However, since the wind power prediction system has not received the wind farm data, it indicates that the data processing device has not successfully reported the wind farm data to the wind power prediction system, and it can be determined that the network between the wind power prediction system and the data processing device is abnormal.

[0134] For example, the first update time of the most recent data update by the wind turbine is earlier than the second update time of the most recent data update by SCADA, and the time between the first and second update times is less than a first preset time. Alternatively, the wind farm data cached during the most recent data update by the wind turbine increased, and the wind farm data cached during the most recent data update by SCADA also increased. In this case, it indicates that the wind farm data collected by the wind turbine was successfully reported to SCADA, meaning the network between the wind turbine and SCADA is normal. However, if SCADA failed to successfully report the wind farm data to the wind power prediction system, then the network between SCADA and the wind power prediction system is abnormal.

[0135] If the data update information from the data acquisition device does not match the data update information from the data processing device, it indicates that the wind farm data collected by the data acquisition device has not been successfully reported to the data processing device, which can determine that there is a network anomaly between the data acquisition device and the data processing device.

[0136] For example, if the wind turbine's cached wind farm data increased during its most recent data update, but the SCADA's cached wind farm data did not increase during its most recent data update, this indicates that the wind turbine's collected wind farm data was not successfully reported to the SCADA, suggesting a network anomaly between the wind turbine and the SCADA.

[0137] Regarding step S103, when the anomaly type is the first type of data anomaly, that is, the wind farm data reported to the wind power prediction system is abnormal data, it can be determined that the device to which the abnormal data in the wind farm data belongs is the target device that has failed.

[0138] For example, if the power output of a wind turbine is negative, it indicates that the power data collected by the wind turbine is abnormal, thus determining that the wind turbine has malfunctioned; the wind turbine is the target device with the malfunction. Similarly, if the wind speed measured by the anemometer is negative, it indicates that the wind speed measured by the anemometer is abnormal, thus determining that the anemometer has malfunctioned; the anemometer is the target device with the malfunction. Or, if the wind speed obtained from the meteorological platform is negative, it indicates that the wind speed predicted by the meteorological platform is abnormal, thus determining that the meteorological platform has malfunctioned; the meteorological platform is the target device with the malfunction.

[0139] In some embodiments, the wind power prediction system communicates with the scheduling platform and reports predicted power data to the scheduling platform. The wind power prediction system can also detect whether it has malfunctioned based on its own data processing and the predicted power data reported to the scheduling platform.

[0140] Accordingly, the method may further include the following steps: If the predicted power data output by the wind power prediction system is abnormal data, determine that the abnormality type is a second type of data abnormality, and determine that the wind power prediction system is the target device that has failed. Here, the predicted power data is obtained by the wind power prediction system based on received wind farm data. If the wind power prediction system fails to report predicted power data to the dispatch platform, determine that the abnormality type is a reporting abnormality, and determine that the wind power prediction system is the target device that has failed.

[0141] The wind power prediction system determines the predicted power data based on the received wind farm data. The system checks whether the predicted power data falls within a preset data range. If the predicted power data does not fall within the preset range, it is considered abnormal. For example, if the preset data range for predicted power data is greater than 0, a negative predicted power data is considered abnormal.

[0142] Alternatively, the wind power prediction system can check whether the predicted power data matches the wind turbine operating data. If the predicted power data does not match the wind turbine operating data, the predicted power data can be determined to be abnormal. For example, wind speed and predicted power data are positively correlated. If the wind speed in the target data acquisition period is greater than the wind speed in the previous data acquisition period, and the predicted power data in the target data acquisition period is less than the predicted power data in the previous data acquisition period, the predicted power data can be determined to be abnormal.

[0143] Furthermore, the anomaly occurring in the wind power prediction system was determined to be a Type II data anomaly. Type II data anomalies indicate that the predicted power data output by the wind power prediction system is abnormal. Since the predicted power data is output by the wind power prediction system, it can be determined that the wind power prediction system is the target device experiencing the malfunction.

[0144] If the predicted power data output by the wind power prediction system is not abnormal, the wind power prediction system will report the predicted power data to the dispatch platform. The wind power prediction system can detect whether there is an anomaly in the reported predicted power data to the dispatch platform. If the wind power prediction system fails to report the predicted power data to the dispatch platform, it determines that the anomaly type is a reporting anomaly.

[0145] In some embodiments, if the wind power prediction system does not receive a response message from the scheduling platform within a first preset time period after sending the predicted power data, it indicates that the scheduling platform has not received the predicted power data. Therefore, it can be determined that the wind power prediction system failed to report the predicted power data to the scheduling platform, and the anomaly type is identified as a reporting anomaly. The first preset time period is set by technical personnel according to requirements.

[0146] Alternatively, the wind power prediction system receives a response message from the dispatch platform carrying a status code indicating a reporting error. This message indicates that the dispatch platform received an abnormality in the predicted power data, confirms that the reporting of the predicted power data to the dispatch platform failed, and identifies the type of the abnormality as a reporting error.

[0147] The status code indicates the type of anomaly that occurred in the predicted power data received by the scheduling platform. For example, the status code might indicate that the amount of predicted power data received by the scheduling platform is too large. Alternatively, the status code might indicate that the format of the predicted power data received by the scheduling platform is not a format that the scheduling platform can process. Or, the status code might indicate that the reporting path for the predicted power data reported by the wind power prediction system is incorrect.

[0148] Since the predicted power data is output by the wind power prediction system and reported to the dispatch platform by the wind power prediction system, when the anomaly type is the second type of data anomaly or reporting anomaly, the wind power prediction system can be identified as the target device that has failed.

[0149] The following describes the fault handling method provided in the embodiments of this application.

[0150] In some embodiments, see Figure 3 , Figure 3 The flowchart illustrates a fault handling method provided in this application embodiment. This method is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measurement device, and the data processing device includes SCADA and a data transceiver server. The method may include the following steps:

[0151] S301: When an anomaly is detected in the wind power prediction system's processing of wind farm data, obtain the anomaly type and fault location results.

[0152] The anomaly type and fault location result are determined based on the fault location method in the aforementioned embodiments.

[0153] S302: When the anomaly type is communication anomaly and the fault location result indicates that the target device in the data acquisition device and data processing device has failed, a control command is sent to the target device so that the target device can perform fault handling according to the preset self-test procedure.

[0154] S303: When the anomaly type is communication anomaly and the fault location result indicates a network anomaly in the wind power prediction system, data acquisition equipment, and data processing equipment, an alarm message is output.

[0155] S304: When the anomaly type is Class I data anomaly, repair the abnormal data that has occurred.

[0156] Based on the fault handling method provided in the embodiments of this application, when an anomaly is detected in the wind power prediction system's processing of wind farm data, anomaly handling is performed based on the anomaly type and fault location results, which can reduce the impact on the normal operation of the wind power prediction system and improve the stability of the wind power prediction system.

[0157] Regarding steps S301 and S302, the wind power prediction system performs anomaly detection when processing wind farm data. If an anomaly is detected in the processing of wind farm data, the system obtains the anomaly type and fault location result. The method by which the wind power prediction system obtains the anomaly type and fault location result can be found in the relevant descriptions of the foregoing embodiments.

[0158] If the anomaly type is communication anomaly, and the fault location result indicates a fault in the target device within the data acquisition and data processing equipment, the wind power prediction system sends a control command to the target device. This control command is used to instruct the target device to perform a self-check.

[0159] Accordingly, upon receiving the control command, the target device performs fault handling according to a preset self-test procedure. This preset self-test procedure is pre-set by technicians on the target device. For example, the target device can use the preset self-test procedure to check for faults in its sensor module, data forwarding module, and data storage module.

[0160] If the target device detects a specific module malfunctioning according to its preset self-test procedure—for example, a sensor module malfunction—the device can be restarted. Then, if the target device is a data acquisition device (e.g., a wind turbine), it continues data acquisition. Subsequently, when the wind power prediction system receives wind farm data from the target device, it can determine that the fault handling is complete. If the target device is a data processing device (e.g., a data transceiver server), it continues to report the received wind farm data to the wind power prediction system. Subsequently, when the wind power prediction system receives the reported wind farm data from the target device, it determines that the fault handling is complete.

[0161] If the target device fails to detect a specific faulty module according to the preset self-test procedure, it sends a notification message to the wind power prediction system indicating that the target device cannot handle the fault. Correspondingly, upon receiving this notification message, the wind power prediction system outputs an alarm message indicating that the target device cannot handle the fault. Subsequently, technicians can use this alarm message to perform fault handling.

[0162] Regarding step S303, since the wind power prediction system, data acquisition equipment, and data processing equipment transmit data via a wired network, if the anomaly type is communication anomaly and the fault location result indicates a network anomaly in the wind power prediction system, data acquisition equipment, and data processing equipment, it indicates a physical fault in the wired network between the wind power prediction system, data acquisition equipment, and data processing equipment. For example, the network cable between the wind turbine and SCADA may be disconnected, or the network cable between SCADA and the wind power prediction system may be disconnected.

[0163] Correspondingly, if the wind power prediction system is unable to process the data, it outputs an alarm message indicating a network anomaly in the wind power prediction system, data acquisition equipment, and data processing equipment. Subsequently, technicians can use this alarm message to troubleshoot and improve the stability of the wind power prediction system.

[0164] Regarding step S304, when the anomaly type is the first type of data anomaly, if the anomaly data is wind turbine operation data or measured meteorological data, the wind power prediction system performs data repair. If the anomaly data is predicted meteorological data, since the predicted meteorological data is not collected by the data acquisition equipment in the wind farm, fault handling cannot be performed, and the wind power prediction system can output an alarm message indicating that the predicted meteorological data is abnormal.

[0165] In some embodiments, Figure 3 Based on this, see Figure 4 Step S304 may include the following steps:

[0166] S3041: When the anomaly type is the first type of data anomaly, if the abnormal data is the turbine operation data of the first wind turbine, the turbine operation data of the first wind turbine in the data acquisition period before the target data acquisition period, and / or the turbine operation data of the second wind turbine in the target data acquisition period that meets the preset screening conditions, are used to determine the repaired turbine operation data of the first wind turbine.

[0167] S3042: When the anomaly type is Class I data anomaly, if the anomaly data is the meteorological measurement data of the wind measuring equipment, the repaired meteorological measurement data of the wind measuring equipment shall be determined based on at least one of the meteorological measurement data of the wind measuring equipment in the data collection period before the target data collection period, the meteorological measurement data of the wind turbine in the target data collection period, and the predicted meteorological data of the meteorological platform.

[0168] When the abnormal data is the operating data of the first wind turbine, it can be handled in the following way:

[0169] In one implementation, because the data acquisition cycle is short—for example, wind farm data collected every 5 minutes is reported to the wind power prediction system—the wind farm data in two adjacent data acquisition cycles are quite similar. Therefore, when the abnormal data is the turbine operation data of the first wind turbine, the turbine operation data of the first wind turbine in the data acquisition cycle preceding the target data acquisition cycle can be used as the corrected turbine operation data of the first wind turbine. The data acquisition cycle preceding the target data acquisition cycle can be the previous data acquisition cycle.

[0170] In another implementation, a wind farm deploys multiple wind turbines. Among these turbines, some have similar wind resources; for example, wind turbines physically close to each other have similar wind speeds. Therefore, the operating data of these turbines with similar wind resources are also similar. Thus, when the abnormal data is from the first wind turbine, a second wind turbine with similar wind resources can be identified as the one that meets the preset screening criteria. The operating data of this second wind turbine is then used as the corrected operating data for the first wind turbine.

[0171] In another implementation, the weighted sum of the wind turbine operation data of the first wind turbine and the wind turbine operation data of the second wind turbine in the data acquisition period prior to the target data acquisition period is calculated as the repaired wind turbine operation data of the first wind turbine.

[0172] When the abnormal data is meteorological data measured by an anemometer, it can be handled in the following ways:

[0173] In one implementation, because the data acquisition cycle is short, wind farm data within two adjacent data acquisition cycles are quite similar. Therefore, when the abnormal data is meteorological data measured by the wind measuring equipment, the meteorological data measured by the wind measuring equipment in the data acquisition cycle prior to the target data acquisition cycle can be used as the meteorological data measured by the repaired wind measuring equipment.

[0174] In another implementation, sensors are installed in the wind turbines deployed in the wind farm. These turbines can then measure the meteorological data of the wind farm and report it to the wind power prediction system via SCADA. Therefore, the meteorological data from the wind turbines during the target data acquisition period is used as the meteorological data for the repaired wind measurement equipment.

[0175] In another implementation, the predicted meteorological data from the meteorological platform within the target data collection period can be directly used as the measured meteorological data of the repaired wind measuring equipment.

[0176] In another implementation, the weighted sum of the meteorological data measured by the wind measuring equipment during the data acquisition period prior to the target data acquisition period, the meteorological data measured by the wind turbine during the target data acquisition period, and the predicted meteorological data from the meteorological platform is used as the meteorological data measured by the repaired wind measuring equipment.

[0177] In some embodiments, when the wind power prediction system detects a fault, it may handle the fault in the following manner.

[0178] Accordingly, the method may further include the following steps: When the anomaly type is the second type of data anomaly, determine the repaired predicted power data based on the predicted power data output by the wind power prediction system in the data acquisition cycle before the target data acquisition cycle. When the anomaly type is a reporting anomaly, if no response message is received from the scheduling platform, send the predicted power data to the scheduling platform; if a response message carrying a reporting error status code is received, generate the predicted power data according to the status code, and send the generated predicted power data to the scheduling platform.

[0179] When the anomaly type is Category 2 (i.e., the predicted power data output by the wind power prediction system is anomalous), the wind power prediction system can re-determine the predicted power data for the target data acquisition period based on the wind farm data received during the target data acquisition period. If the re-determined predicted power data is still anomalous, the corrected predicted power data can be determined based on the predicted power data output during data acquisition periods prior to the target data acquisition period.

[0180] For example, predictive power data from multiple data acquisition cycles preceding the target data acquisition cycle is acquired, and this predictive power data from these multiple data acquisition cycles is input into a pre-trained deep learning model, which outputs the repaired predictive power data for the target data acquisition cycle. The pre-trained deep learning model is trained using the predictive power data from multiple data acquisition cycles as input parameters and the predictive power data from the next data acquisition cycle as output parameters.

[0181] When the anomaly type is "reported anomaly," it indicates that the wind power prediction system has reported an anomaly in the predicted power data to the dispatch platform. In this case, the anomaly will be handled according to the response message from the dispatch platform.

[0182] If no response message is received from the scheduling platform, the predicted power data is resent directly to the scheduling platform.

[0183] If a response message carrying a reported error status code is received, new predicted power data is generated according to the status code. Specifically, if the status code indicates that the amount of predicted power data received by the scheduling platform is too large, the predicted power data is compressed to obtain new predicted power data with a smaller data volume. Alternatively, if the status code indicates that the format of the predicted power data received by the scheduling platform is not a format that the scheduling platform can process, new predicted power data in a format that the scheduling platform can process is generated. Then, the generated predicted power data is sent to the scheduling platform.

[0184] and Figure 1 For the corresponding method implementation examples, see [link to relevant documentation]. Figure 5 , Figure 5This is a structural diagram of a fault location device provided in an embodiment of this application. The device is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measuring device, and the data processing device includes SCADA and a data transceiver server. The device includes:

[0185] The anomaly type determination module 501 is used to determine the anomaly type of the anomaly when an anomaly is detected in the wind power prediction system processing wind farm data, based on whether the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period.

[0186] The first fault location module 502 is used to perform fault location based on the communication information between the wind power prediction system and the data acquisition device and the data processing device when the anomaly type is a communication anomaly.

[0187] The second fault location module 503 is used to determine, when the anomaly type is the first type of data anomaly, the device to which the abnormal data in the wind farm data belongs is the target device that has experienced a fault.

[0188] Optionally, the anomaly type determination module 501 is specifically used to determine the anomaly type of the anomaly as a communication anomaly if the wind power prediction system does not receive wind farm data sent by the data processing device within the target data acquisition period.

[0189] If the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period, and detects that the wind farm data is abnormal, the abnormality type of the abnormality is determined to be the first type of data abnormality.

[0190] Optionally, the first fault location module 502 is specifically used to determine, from the data acquisition device and the data processing device, the device that did not send a heartbeat detection request during the heartbeat detection cycle as the target device that has malfunctioned;

[0191] If a heartbeat detection request is received from the data acquisition device and the data processing device during the heartbeat detection cycle, data update information is obtained from the data acquisition device and the data processing device respectively; wherein, the data update information includes: the update time of the most recent data update, and / or, the data increment information of the most recent data update;

[0192] If the data update information of the data acquisition device matches that of the data processing device, then a network anomaly is determined between the wind power prediction system and the data processing device.

[0193] If the data update information of the data acquisition device and the data processing device do not match, then a network anomaly is determined between the data acquisition device and the data processing device.

[0194] Wherein, when the data acquisition device is a wind turbine, the data processing device is SCADA; when the data acquisition device is a wind measurement device, the data processing device is a data transceiver server.

[0195] Optionally, the data acquisition device matches the data update information with the data processing device, including:

[0196] The first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the duration between the first update time and the second update time is less than the first preset duration.

[0197] And / or,

[0198] The wind farm data cached by the data acquisition device increased during the most recent data update, and the wind farm data cached by the data processing device also increased during the most recent data update.

[0199] Optionally, the wind power prediction system communicates with the dispatching platform, and the device further includes:

[0200] The third fault location module is specifically used to determine the type of abnormality as a second type of data abnormality if the predicted power data output by the wind power prediction system is abnormal data, and to determine the wind power prediction system as the target device that has failed; wherein, the predicted power data is obtained by the wind power prediction system based on the received wind farm data;

[0201] The fourth fault location module is specifically used to determine the type of the abnormality as a reporting abnormality if the wind power prediction system fails to report predicted power data to the scheduling platform, and to determine the wind power prediction system as the target device that has failed.

[0202] Optionally, the fourth fault location module is specifically used to determine that reporting the predicted power data to the scheduling platform has failed if the wind power prediction system does not receive a response message from the scheduling platform within a first preset time period after sending the predicted power data to the scheduling platform, or if it receives a response message from the scheduling platform carrying a status code indicating a reporting error, and determines that the anomaly type of the anomaly is a reporting anomaly.

[0203] Based on the fault location device provided in this application embodiment, fault location can be performed when an anomaly is detected in the wind power prediction system's processing of wind farm data. Subsequently, the anomaly can be processed based on the fault location result, which can reduce the impact on the normal operation of the wind power prediction system and improve its stability.

[0204] and Figure 3 For the corresponding method implementation examples, see [link to relevant documentation]. Figure 6 , Figure 6 This is a structural diagram of a fault handling device provided in an embodiment of this application. The device is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition device includes a wind turbine and a wind measuring device, and the data processing device includes SCADA and a data transceiver server. The device includes:

[0205] The data acquisition module 601 is used to acquire the anomaly type and fault location result when an anomaly is detected in the wind power prediction system processing wind farm data; wherein the anomaly type and the fault location result are determined by the fault location device described in the third aspect above.

[0206] The first fault handling module 602 is used to send a control command to the target device when the abnormality type is a communication abnormality and the fault location result indicates that the target device in the data acquisition device and the data processing device has failed, so that the target device can perform fault handling according to a preset self-test procedure.

[0207] The second fault handling module 603 is used to output alarm information when the anomaly type is communication anomaly and the fault location result indicates a network anomaly in the wind power prediction system, the data acquisition device and the data processing device.

[0208] The third fault handling module 604 is used to repair the abnormal data when the abnormality type is the first type of data abnormality.

[0209] Optionally, the third fault handling module 604 is specifically used to determine the repaired wind turbine operation data of the first wind turbine based on the wind turbine operation data of the first wind turbine in the data acquisition period before the target data acquisition period, and / or the wind turbine operation data of the second wind turbine in the target data acquisition period that meets the preset screening conditions, if the abnormal data is the wind turbine operation data of the first wind turbine.

[0210] If the abnormal data is the meteorological measurement data of the wind measuring device, the repaired meteorological measurement data of the wind measuring device is determined based on at least one of the meteorological measurement data of the wind measuring device in the data collection period before the target data collection period, the meteorological measurement data of the wind turbine in the target data collection period, and the predicted meteorological data of the meteorological platform.

[0211] Optionally, the device further includes:

[0212] The fourth fault handling module is used to determine the repaired predicted power data based on the predicted power data output by the wind power prediction system in the data acquisition cycle before the target data acquisition cycle when the anomaly type is the second type of data anomaly.

[0213] When the exception type is reporting exception, if no response message is received from the scheduling platform, predictive power data is sent to the scheduling platform; if a response message carrying a reporting error status code is received, predictive power data is generated according to the status code, and the generated predictive power data is sent to the scheduling platform.

[0214] Based on the fault handling device provided in the embodiments of this application, when an anomaly is detected in the wind power prediction system's processing of wind farm data, the anomaly handling is performed based on the anomaly type and fault location results, which can reduce the impact on the normal operation of the wind power prediction system and improve the stability of the wind power prediction system.

[0215] This application also provides an electronic device, such as... Figure 7 As shown, it includes:

[0216] Memory 701 is used to store computer programs;

[0217] When the processor 702 executes the program stored in the memory 701, it implements the steps of the fault location and handling method in the above embodiments, or the steps of the fault handling method in the above embodiments.

[0218] Furthermore, the aforementioned electronic device may also include a communication bus and / or a communication interface, with the processor 702, the communication interface, and the memory 701 communicating with each other via the communication bus.

[0219] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0220] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0221] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0222] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0223] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above-described fault location methods or the steps of a fault handling method.

[0224] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the fault location methods or fault handling methods described above.

[0225] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a solid-state drive (SSD), etc.

[0226] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0227] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, electronic devices, computer-readable storage media, and computer program products are basically similar to the method embodiments, and therefore the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0228] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. A fault location method, characterized in that, The method is applied to a wind power prediction system, which communicates with data acquisition equipment and data processing equipment. The data acquisition equipment includes a wind turbine and a wind measuring device, and the data processing equipment includes a data acquisition and monitoring control system (SCADA) and a data transceiver server. The method includes: When an anomaly is detected in the wind power prediction system's processing of wind farm data, the anomaly type is determined based on whether the wind power prediction system received wind farm data sent by the data processing device within the target data acquisition period. When the anomaly type is a communication anomaly, the fault location result is obtained by performing fault location based on the communication information between the wind power prediction system and the data acquisition device and the data processing device, respectively. When the anomaly type is the first type of data anomaly, the device to which the abnormal data in the wind farm data belongs is determined to be the target device that has malfunctioned; The method for determining the anomaly type based on whether the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period includes: If the wind power prediction system does not receive wind farm data sent by the data processing device within the target data acquisition period, the abnormality type of the abnormality is determined to be a communication abnormality. If the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period, and detects that the wind farm data is abnormal, the abnormality type of the abnormality is determined to be the first type of data abnormality. When the anomaly type is a communication anomaly, based on the communication information between the wind power prediction system and the data acquisition device and the data processing device, respectively, fault location is performed to obtain the fault location result, including: From the data acquisition device and the data processing device, the device that did not send a heartbeat detection request during the heartbeat detection cycle is identified as the target device that has malfunctioned; If a heartbeat detection request is received from the data acquisition device and the data processing device during the heartbeat detection cycle, data update information is obtained from the data acquisition device and the data processing device respectively; wherein, the data update information includes: the update time of the most recent data update, and / or, the data increment information of the most recent data update; If the data update information of the data acquisition device matches that of the data processing device, then a network anomaly is determined between the wind power prediction system and the data processing device. If the data update information of the data acquisition device and the data processing device do not match, then a network anomaly is determined between the data acquisition device and the data processing device. Wherein, when the data acquisition device is a wind turbine, the data processing device is SCADA; when the data acquisition device is a wind measurement device, the data processing device is a data transceiver server.

2. The method according to claim 1, characterized in that, The data acquisition device matches the data update information with the data processing device, including: The first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the duration between the first update time and the second update time is less than the first preset duration. And / or, The wind farm data cached by the data acquisition device increased during the most recent data update, and the wind farm data cached by the data processing device also increased during the most recent data update.

3. The method according to claim 1, characterized in that, The wind power prediction system communicates with the dispatch platform, and the method further includes: If the predicted power data output by the wind power prediction system is abnormal, the abnormality type is determined to be the second type of data abnormality, and the wind power prediction system is determined to be the target device that has failed; wherein, the predicted power data is obtained by the wind power prediction system based on the received wind farm data; If the wind power prediction system fails to report predicted power data to the scheduling platform, the anomaly type is determined to be a reporting anomaly, and the wind power prediction system is identified as the target device that has failed.

4. The method according to claim 3, characterized in that, If the wind power prediction system fails to report predicted power data to the dispatch platform, the anomaly type is determined to be a reporting anomaly, including: If the wind power prediction system does not receive a response message from the scheduling platform within a first preset time period after sending the predicted power data to the scheduling platform, or if it receives a response message from the scheduling platform carrying a status code indicating a reporting error, it determines that the reporting of the predicted power data to the scheduling platform has failed, and determines that the anomaly type is a reporting anomaly.

5. A fault handling method, characterized in that, The method is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition equipment includes a wind turbine and a wind measurement device; the data processing equipment includes SCADA and a data transceiver server; the method includes: When an anomaly is detected in the wind power prediction system's processing of wind farm data, the anomaly type and fault location result are obtained; wherein, the anomaly type and the fault location result are determined based on the fault location method according to any one of claims 1 to 4; When the anomaly type is a communication anomaly and the fault location result indicates that the target device in the data acquisition device and the data processing device has malfunctioned, a control command is sent to the target device so that the target device can perform fault handling according to a preset self-test procedure. When the anomaly type is communication anomaly, and the fault location result indicates a network anomaly in the wind power prediction system, the data acquisition device, and the data processing device, an alarm message is output. When the anomaly type is the first type of data anomaly, the abnormal data that has occurred is repaired.

6. The method according to claim 5, characterized in that, The repair of abnormal data includes: If the abnormal data is the turbine operation data of the first wind turbine, the turbine operation data of the first wind turbine is determined based on the data collection period before the target data collection period, and / or the turbine operation data of the second wind turbine in the target data collection period that meets the preset screening conditions. If the abnormal data is the meteorological measurement data of the wind measuring device, the repaired meteorological measurement data of the wind measuring device is determined based on at least one of the meteorological measurement data of the wind measuring device in the data collection period before the target data collection period, the meteorological measurement data of the wind turbine in the target data collection period, and the predicted meteorological data of the meteorological platform.

7. The method according to claim 5, characterized in that, The method further includes: When the anomaly type is the second type of data anomaly, the predicted power data after repair is determined based on the predicted power data output by the wind power prediction system in the data acquisition cycle before the target data acquisition cycle. When the exception type is reporting exception, if no response message is received from the scheduling platform, the predicted power data is sent to the scheduling platform; if a response message carrying a reporting error status code is received, the predicted power data is generated according to the status code, and the generated predicted power data is sent to the scheduling platform.

8. A fault location device, characterized in that, The device is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition equipment includes a wind turbine and a wind measurement device; the data processing equipment includes SCADA and a data transceiver server; the device includes: An anomaly type determination module is used to determine the anomaly type of the anomaly when an anomaly is detected in the wind power prediction system's processing of wind farm data, based on whether the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period. The first fault location module is used to locate the fault and obtain the fault location result based on the communication information between the wind power prediction system and the data acquisition device and the data processing device when the anomaly type is a communication anomaly. The second fault location module is used to determine the device to which the abnormal data in the wind farm data belongs as the target device that has failed when the anomaly type is the first type of data anomaly. The anomaly type determination module is specifically used to determine the anomaly type as a communication anomaly if the wind power prediction system does not receive wind farm data sent by the data processing device within the target data acquisition period. If the wind power prediction system receives wind farm data sent by the data processing device within the target data acquisition period, and detects that the wind farm data is abnormal, the abnormality type of the abnormality is determined to be the first type of data abnormality. The first fault location module is specifically used to determine, from the data acquisition device and the data processing device, the device that did not send a heartbeat detection request during the heartbeat detection cycle as the target device that has malfunctioned; If a heartbeat detection request is received from the data acquisition device and the data processing device during the heartbeat detection cycle, data update information is obtained from the data acquisition device and the data processing device respectively; wherein, the data update information includes: the update time of the most recent data update, and / or, the data increment information of the most recent data update; If the data update information of the data acquisition device matches that of the data processing device, then a network anomaly is determined between the wind power prediction system and the data processing device. If the data update information of the data acquisition device and the data processing device do not match, then a network anomaly is determined between the data acquisition device and the data processing device. Wherein, when the data acquisition device is a wind turbine, the data processing device is SCADA; when the data acquisition device is a wind measurement device, the data processing device is a data transceiver server.

9. The apparatus according to claim 8, characterized in that, The data acquisition device matches the data update information with the data processing device, including: The first update time of the most recent data update by the data acquisition device is earlier than the second update time of the most recent data update by the data processing device, and the duration between the first update time and the second update time is less than the first preset duration. And / or, The wind farm data cached by the data acquisition device increased during the most recent data update, and the wind farm data cached by the data processing device also increased during the most recent data update. The device further includes: The third fault location module is specifically used to determine the type of abnormality as a second type of data abnormality if the predicted power data output by the wind power prediction system is abnormal data, and to determine the wind power prediction system as the target device that has failed; wherein, the predicted power data is obtained by the wind power prediction system based on the received wind farm data; The fourth fault location module is specifically used to determine the type of the abnormality as a reporting abnormality if the wind power prediction system fails to report the predicted power data to the dispatch platform, and to determine the wind power prediction system as the target device that has failed. The fourth fault location module is specifically used to determine that reporting the predicted power data to the scheduling platform has failed if the wind power prediction system does not receive a response message from the scheduling platform within a first preset time period after sending the predicted power data to the scheduling platform, or if it receives a response message from the scheduling platform carrying a status code indicating a reporting error, and determines that the abnormality type of the abnormality is a reporting abnormality.

10. A fault handling device, characterized in that, The device is applied to a wind power prediction system, which communicates with a data acquisition device and a data processing device. The data acquisition equipment includes a wind turbine and a wind measurement device; the data processing equipment includes SCADA and a data transceiver server; the device includes: The data acquisition module is used to acquire the anomaly type and fault location result when an anomaly is detected in the wind power prediction system's processing of wind farm data; wherein the anomaly type and the fault location result are determined based on the fault location device according to any one of claims 8 to 9. The first fault handling module is used to send a control command to the target device when the abnormality type is a communication abnormality and the fault location result indicates that the target device in the data acquisition device and the data processing device has failed, so that the target device can perform fault handling according to a preset self-test procedure. The second fault handling module is used to output alarm information when the anomaly type is communication anomaly and the fault location result indicates a network anomaly in the wind power prediction system, the data acquisition device and the data processing device. The third fault handling module is used to repair the abnormal data when the abnormality type is the first type of data abnormality.

11. The apparatus according to claim 10, characterized in that, The third fault handling module is specifically used to determine the repaired wind turbine operation data of the first wind turbine based on the wind turbine operation data of the first wind turbine in the data acquisition period before the target data acquisition period, and / or the wind turbine operation data of the second wind turbine in the target data acquisition period that meets the preset screening conditions, if the abnormal data is the wind turbine operation data of the first wind turbine. If the abnormal data is the meteorological measurement data of the wind measuring device, the repaired meteorological measurement data of the wind measuring device is determined based on at least one of the meteorological measurement data of the wind measuring device in the data collection period before the target data collection period, the meteorological measurement data of the wind turbine in the target data collection period, and the predicted meteorological data of the meteorological platform. The device further includes: The fourth fault handling module is used to determine the repaired predicted power data based on the predicted power data output by the wind power prediction system in the data acquisition cycle before the target data acquisition cycle when the anomaly type is the second type of data anomaly. When the exception type is reporting exception, if no response message is received from the scheduling platform, the predicted power data is sent to the scheduling platform; if a response message carrying a reporting error status code is received, the predicted power data is generated according to the status code, and the generated predicted power data is sent to the scheduling platform.

12. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of claims 1-4, or any one of claims 5-7.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in claims 1-4 or any one of claims 5-7.

Images