Wind power generation remote operation and maintenance monitoring system based on Internet of Things

Abstract

The invention relates to the technical field of wind power generation operation and maintenance monitoring, and discloses a wind power generation remote operation and maintenance monitoring system based on the Internet of Things, and the system comprises an acquisition module which is used for building a plurality of monitoring areas, setting the monitoring parameters of each monitoring area, and collecting the real-time monitoring data of each monitoring area according to the monitoring parameters, calculating a real-time operation evaluation value; the judgment module is used for judging whether the corresponding monitoring area needs operation and maintenance or not according to the real-time operation evaluation value, and if yes, a plurality of first operation and maintenance strategies are generated; and the operation and maintenance module is used for performing coupling analysis on each first operation and maintenance strategy, determining a second operation and maintenance strategy according to a coupling analysis result, sending an operation and maintenance instruction according to the second operation and maintenance strategy, and improving the monitoring precision and the operation and maintenance efficiency of wind power generation.

Description

Technical Field

[0001] This application relates to the field of wind power operation and maintenance monitoring technology, and in particular to a wind power remote operation and maintenance monitoring system based on the Internet of Things. Background Technology

[0002] As an important component of renewable energy, wind power has seen its installed capacity and coverage continue to expand. However, wind turbines are mostly deployed in complex environments such as the field and the sea. The equipment has a complex structure and operates under high load conditions for a long time, which can easily lead to problems such as component wear, low efficiency, and sudden failures, placing extremely high demands on operation and maintenance.

[0003] To address the aforementioned issues, IoT technology has been introduced to enable remote monitoring. However, existing technologies still have limitations: in the data acquisition phase, only basic parameters can be collected and alarms triggered, lacking refined regional division and differentiated parameter configuration for wind farms, thus reducing monitoring accuracy; in the operation and maintenance phase, the coupling effects between different strategies have not been fully considered, significantly reducing the efficiency of the operation and maintenance solution. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides an IoT-based remote operation and maintenance monitoring system for wind power generation. By dividing the wind farm into multiple monitoring areas and setting monitoring parameters, the system collects real-time monitoring data and calculates real-time operation evaluation values. Based on the real-time operation evaluation values, it determines whether operation and maintenance is required. If so, it generates several first operation and maintenance strategies and performs coupled analysis. Based on the analysis results, it determines a second operation and maintenance strategy, thereby improving the monitoring accuracy and operation and maintenance efficiency of wind power generation.

[0005] In some embodiments of this application, an IoT-based remote operation and maintenance monitoring system for wind power generation is provided, including: The data acquisition module is used to establish several monitoring areas and set monitoring parameters for each monitoring area, collect real-time monitoring data for each monitoring area according to the monitoring parameters, and calculate the real-time operation evaluation value. The judgment module is used to determine whether the corresponding monitoring area needs maintenance based on the real-time operation evaluation value. If it does, it generates several first maintenance strategies. The operation and maintenance module is used to perform coupling analysis on each first operation and maintenance strategy, determine the second operation and maintenance strategy based on the coupling analysis results, and issue operation and maintenance instructions according to the second operation and maintenance strategy.

[0006] In some embodiments of this application, several monitoring areas are established and monitoring parameters for each monitoring area are set, including: Establish multiple monitoring areas; Generate a historical monitoring data packet for each monitoring area, wherein the historical monitoring data packet includes historical monitoring data for each monitoring area in several historical monitoring periods; Several equipment evaluation indicators and several status evaluation indicators are pre-set; The historical monitoring data packets of each monitoring area are evaluated according to several equipment evaluation indicators and several status evaluation indicators to obtain the first evaluation value and the second evaluation value corresponding to each historical monitoring cycle. The weight is then calculated to obtain the third evaluation value. The average value of the third evaluation value of several historical monitoring periods in the same monitoring area is calculated to obtain the comprehensive evaluation value of the corresponding monitoring area. The monitoring parameters for the corresponding monitoring area are set according to the comprehensive evaluation value. The monitoring parameters include monitoring points, monitoring sensors, monitoring time intervals, and monitoring cycles.

[0007] In some embodiments of this application, real-time operational data for each monitoring area is collected according to monitoring parameters, and a real-time operational evaluation value is calculated, including: Real-time operational data for each monitoring area is collected according to the monitoring parameters, and combined with the corresponding monitoring sources to form a device-location-data mapping table; Compare the real-time operating data in the device-location-data mapping table with the corresponding first standard operating data range and second standard operating data range. If both are within the first standard operating data range and second standard operating data range, calculate the first standard coefficient of the corresponding real-time operating data. If it is not within the first standard operating data range, calculate the first deviation coefficient of the corresponding real-time operating data; If the data falls within the first standard operating data range but not within the second standard operating data range, calculate the second standard coefficient and the second deviation coefficient for the corresponding real-time operating data. Generate the operational sub-coefficients for each monitoring point; The operating coefficient of the corresponding equipment is generated based on the operating sub-coefficients of several monitoring points of the same equipment and the reliability coefficient of the monitoring points. Real-time operational evaluation values ​​are generated based on the operating coefficients of several devices with the same monitoring coefficient and the importance coefficient of the devices.

[0008] In some embodiments of this application, generating the operating sub-coefficient for each monitoring point includes: Based on the relationship between real-time monitoring data and standard data range, real-time monitoring data is divided into three categories: Category I data, Category II data, and Category III data. The formula for calculating the running sub-coefficient is as follows: ; Where Y is the sub-coefficient, y1 is the first operational transformation coefficient, y2 is the second operational transformation coefficient, y3 is the third operational transformation coefficient, and n1 is the number of data in the first category. The first standard coefficient is the i1th data point of the first class. Let n1 be the weight coefficient of the i1th data point in the first category, and n2 be the number of data points in the second category. The first deviation coefficient is the i2th second-class data. n is the weight coefficient of the i2th second-class data, and n3 is the number of third-class data. The second standardized coefficient is the i3rd third-class data point. The second deviation coefficient is the third type of data for the i3rd data point. is the weight coefficient of the i3rd third-class data.

[0009] In some embodiments of this application, determining whether a corresponding monitoring area requires maintenance based on real-time operational evaluation values ​​includes: Pre-set the operational evaluation threshold for each monitoring area; If the real-time performance evaluation value is not less than the corresponding performance evaluation value threshold, then it is determined that the corresponding monitoring area does not require maintenance. If the real-time performance evaluation value is less than the corresponding performance evaluation value threshold, then the corresponding monitoring area is determined to require maintenance. Analyze the equipment in the monitoring area that requires maintenance, screen out the equipment whose operating coefficient is less than the preset operating coefficient threshold, and set it as the equipment to be maintained; Analyze the monitoring points of the equipment to be maintained, screen out the monitoring points whose operating sub-coefficient is less than the preset operating sub-coefficient threshold, and calculate the first occurrence ratio of each second type of data and the second occurrence ratio of each third type of data at all screened monitoring points. Set the second type of data, whose first occurrence ratio is greater than the first preset occurrence ratio, and the third type of data, whose second occurrence ratio is greater than the second preset occurrence ratio, as the maintenance data of the corresponding equipment to be maintained; The devices to be maintained and the data to be maintained in the monitoring area that need to be maintained are set as the maintenance factors for the corresponding monitoring area that needs to be maintained.

[0010] In some embodiments of this application, several first operation and maintenance strategies are generated, including: Obtain historical maintenance data and historical maintenance policies from the historical maintenance logs of each device, and construct a mapping table of historical maintenance data and historical maintenance policies for each device; The similarity score is obtained by comparing the devices to be maintained and the data to be maintained in the monitoring area that need to be maintained with the historical data to be maintained in the historical maintenance strategy mapping table of the corresponding devices. The historical maintenance strategies corresponding to the historical maintenance data with a similarity greater than a preset similarity threshold are constructed into a maintenance strategy reference library for the corresponding maintenance device. The maintenance strategy reference library includes several maintenance strategies. Generate a reference library of maintenance strategies for all devices in the monitoring area that require maintenance; Randomly select one maintenance strategy from the maintenance strategy reference library for each device to be maintained, and combine them to obtain several first maintenance strategies for the monitoring area that needs maintenance.

[0011] In some embodiments of this application, before performing coupling analysis on each first operation and maintenance strategy and determining the second operation and maintenance strategy based on the coupling analysis results, the following steps are included: Generate predictive maintenance data packages for each first maintenance strategy; Pre-set several operation and maintenance evaluation indicators; The predicted operation and maintenance data package for each first operation and maintenance strategy is evaluated based on several operation and maintenance evaluation indicators to obtain the predicted operation and maintenance evaluation value for each first operation and maintenance strategy. The first maintenance strategy is removed from the list of maintenance strategies whose predicted maintenance evaluation value is less than the preset maintenance evaluation value threshold. Then, a coupling analysis is performed on each of the remaining first maintenance strategies.

[0012] In some embodiments of this application, a coupling analysis is performed on each of the remaining first operation and maintenance strategies, including: Each of the remaining first operation and maintenance strategies includes several operation and maintenance strategies, and each operation and maintenance strategy is mapped to a device to be operated and maintained. A coupling analysis is performed on several operation and maintenance strategies with the same first operation and maintenance strategy to obtain the first coupling degree of the corresponding first operation and maintenance strategy; Select the first operation and maintenance strategy with a first coupling degree less than a preset coupling threshold; Construct a sequence of first operation and maintenance strategies for the monitoring areas that require operation and maintenance based on the selected first operation and maintenance strategy; A coupling analysis is performed sequentially on several first operation and maintenance strategies in the first operation and maintenance strategy sequence for different monitoring areas that require operation and maintenance, to obtain the second coupling degree between different first operation and maintenance strategies. If all second coupling degrees are less than the preset coupling degree threshold, then a second operation and maintenance strategy is constructed based on the corresponding multiple first operation and maintenance strategies.

[0013] In some embodiments of this application, a feedback module is also included, comprising: The feedback module is used to set the feedback time interval for the corresponding monitoring area based on the predicted operation and maintenance evaluation value of the first operation and maintenance strategy in the second operation and maintenance strategy. Several feedback time nodes are generated according to the feedback time interval; Collect actual operation and maintenance data for the corresponding monitoring area according to the feedback time node, calculate the actual application coefficient of the second operation and maintenance strategy for the corresponding monitoring area based on the actual operation and maintenance data, and determine whether to generate optimization instructions for the second operation and maintenance strategy.

[0014] In some embodiments of this application, the feedback time interval for setting the second operation and maintenance strategy based on the predicted operation and maintenance assessment value includes: The first predicted maintenance assessment value range, the second predicted maintenance assessment value range, the third predicted maintenance assessment value range, and the fourth predicted maintenance assessment value range are preset. When the predicted operation and maintenance assessment value is within the first predicted operation and maintenance assessment value range, the feedback time interval is set to the first preset time interval; When the predicted operation and maintenance assessment value is within the second predicted operation and maintenance assessment value range, the feedback time interval is set to the second preset time interval. When the predicted operation and maintenance assessment value is within the third predicted operation and maintenance assessment value range, the feedback time interval is set to the third preset time interval; When the predicted operation and maintenance assessment value is within the fourth predicted operation and maintenance assessment value range, the feedback time interval is set to the fourth preset time interval.

[0015] The wind power generation remote operation and maintenance monitoring system based on the Internet of Things (IoT) of this application has the following advantages compared with the prior art: By dividing the wind farm into multiple monitoring areas and setting monitoring parameters, real-time monitoring data is collected and real-time operation evaluation values ​​are calculated. Based on the real-time operation evaluation values, it is determined whether operation and maintenance are required. If so, several first operation and maintenance strategies are generated and coupled analysis is performed. Based on the analysis results, a second operation and maintenance strategy is determined, thereby improving the monitoring accuracy and operation and maintenance efficiency of wind power generation. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of a remote operation and maintenance monitoring system for wind power generation based on the Internet of Things, as described in an embodiment of this application. Detailed Implementation

[0017] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0018] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0021] like Figure 1 As shown in the figure, an embodiment of this application provides a remote operation and maintenance monitoring system for wind power generation based on the Internet of Things, comprising: The data acquisition module is used to establish several monitoring areas and set monitoring parameters for each monitoring area, collect real-time monitoring data for each monitoring area according to the monitoring parameters, and calculate the real-time operation evaluation value. The judgment module is used to determine whether the corresponding monitoring area needs maintenance based on the real-time operation evaluation value. If it does, it generates several first maintenance strategies. The operation and maintenance module is used to perform coupling analysis on each first operation and maintenance strategy, determine the second operation and maintenance strategy based on the coupling analysis results, and issue operation and maintenance instructions according to the second operation and maintenance strategy.

[0022] In this embodiment, the real-time monitoring data of each monitoring area is input to the Internet of Things (IoT) platform through the network layer. The IoT platform generates a real-time monitoring evaluation value based on the pre-set monitoring evaluation indicators for each monitoring area and determines whether maintenance is required. If so, a first maintenance strategy is generated and applied to the corresponding monitoring area. By feeding back the changes in the operating status and efficiency of the equipment units in the corresponding area displayed on the large screen, the application coefficient is obtained, and it is determined whether to optimize, thereby further improving the efficiency of remote maintenance.

[0023] In some embodiments of this application, several monitoring areas are established and monitoring parameters for each monitoring area are set, including: Establish multiple monitoring areas; Generate a historical monitoring data packet for each monitoring area, wherein the historical monitoring data packet includes historical monitoring data for each monitoring area in several historical monitoring periods; Several equipment evaluation indicators and several status evaluation indicators are pre-set; The historical monitoring data packets of each monitoring area are evaluated according to several equipment evaluation indicators and several status evaluation indicators to obtain the first evaluation value and the second evaluation value corresponding to each historical monitoring cycle. The weight is then calculated to obtain the third evaluation value. The average value of the third evaluation value of several historical monitoring periods in the same monitoring area is calculated to obtain the comprehensive evaluation value of the corresponding monitoring area. The monitoring parameters for the corresponding monitoring area are set according to the comprehensive evaluation value. The monitoring parameters include monitoring points, monitoring sensors, monitoring time intervals, and monitoring cycles.

[0024] In this embodiment, the wind farm is evenly divided into multiple monitoring areas. The equipment evaluation indicators include, but are not limited to, equipment importance, number of equipment, number of important equipment, equipment operation time, and equipment utilization coefficient. Equipment importance is set according to the degree of influence of each equipment on the functional requirements of the wind turbine and the degree of correlation between different equipment. Equipment with an importance greater than a preset importance threshold is set as important equipment. The equipment utilization coefficient refers to the length of time that the equipment participates in the demand command.

[0025] In this embodiment, the status evaluation indicators include, but are not limited to, the probability of status anomalies, the degree of frequency status anomalies, and the degree of impact on unit operation.

[0026] In this embodiment, the first evaluation value is calculated based on several equipment evaluation indicators. The greater the importance of the equipment, the greater the number of important equipment, and the greater the equipment utilization coefficient, the greater the first evaluation value. The second evaluation value is calculated based on several status evaluation indicators. The greater the probability of status abnormality, the greater the degree of frequency status abnormality, and the greater the degree of impact on unit operation, the greater the second evaluation value. The third evaluation value = first evaluation value * 0.4 + second evaluation value * 0.6. The greater the third evaluation value, the greater the comprehensive evaluation value.

[0027] In this embodiment, the monitoring points and sensors are set by the main equipment in each monitoring area and the points with a high probability of anomalies in the main equipment. The monitoring time interval is set according to the magnitude of the comprehensive evaluation value. When the comprehensive evaluation value is larger, the monitoring cycle length and the monitoring time interval are shorter, and vice versa.

[0028] In some embodiments of this application, real-time operational data for each monitoring area is collected according to monitoring parameters, and a real-time operational evaluation value is calculated, including: Real-time operational data for each monitoring area is collected according to the monitoring parameters, and combined with the corresponding monitoring sources to form a device-location-data mapping table; Compare the real-time operating data in the device-location-data mapping table with the corresponding first standard operating data range and second standard operating data range. If both are within the first standard operating data range and second standard operating data range, calculate the first standard coefficient of the corresponding real-time operating data. If it is not within the first standard operating data range, calculate the first deviation coefficient of the corresponding real-time operating data; If the data falls within the first standard operating data range but not within the second standard operating data range, calculate the second standard coefficient and the second deviation coefficient for the corresponding real-time operating data. Generate the operational sub-coefficients for each monitoring point; The operating coefficient of the corresponding equipment is generated based on the operating sub-coefficients of several monitoring points of the same equipment and the reliability coefficient of the monitoring points. Real-time operational evaluation values ​​are generated based on the operating coefficients of several devices with the same monitoring coefficient and the importance coefficient of the devices.

[0029] In this embodiment, the first standard operating data range refers to the monitoring data range of the corresponding monitoring point that can ensure the normal operation of the equipment, and the second standard operating data range refers to the monitoring data range of the corresponding monitoring point that can ensure the equipment is operating at high efficiency. The first standard operating data range includes the second standard operating data range.

[0030] In this embodiment, the first standard coefficient refers to the data difference between the real-time running data and the center point of the second standard running data interval when the data is within the second standard running data interval. The smaller the data difference, the larger the first standard coefficient, and vice versa. The value range of the first standard coefficient is (1,2).

[0031] In this embodiment, the first deviation coefficient refers to the data difference between the real-time running data and the data endpoint closest to the first standard running data range when the data difference is not within the first standard running data range. The smaller the data difference, the smaller the first deviation coefficient, and vice versa. The value range of the first deviation coefficient is (-1, 0).

[0032] In this embodiment, the second standard coefficient refers to the data difference between the real-time running data and the center point of the first standard running data interval when the data is within the first standard running data interval but not within the second standard running data interval. The smaller the data difference, the larger the second standard coefficient, and vice versa. The value range of the second standard coefficient is (0,1). The second deviation coefficient refers to the data difference between the real-time running data and the data endpoint closest to the second standard running data interval. The larger the data difference, the larger the second deviation coefficient, and vice versa. The value range of the second deviation coefficient is (0,1).

[0033] In this embodiment, the confidence coefficient is set based on the accuracy of the assessment of the corresponding equipment operating status generated from the historical monitoring data of the monitoring points. The higher the assessment accuracy, the larger the confidence coefficient, and vice versa.

[0034] In this embodiment, the importance coefficient is calculated based on the number of associated devices and the degree of impact on the overall operating status of the wind turbine.

[0035] In some embodiments of this application, generating the operating sub-coefficient for each monitoring point includes: Based on the relationship between real-time monitoring data and standard data range, real-time monitoring data is divided into three categories: Category I data, Category II data, and Category III data. The formula for calculating the running sub-coefficient is as follows: ; Where Y is the sub-coefficient, y1 is the first operational transformation coefficient, y2 is the second operational transformation coefficient, y3 is the third operational transformation coefficient, and n1 is the number of data in the first category. The first standard coefficient is the i1th data point of the first class. Let n1 be the weight coefficient of the i1th data point in the first category, and n2 be the number of data points in the second category. The first deviation coefficient is the i2th second-class data. n is the weight coefficient of the i2th second-class data, and n3 is the number of third-class data. The second standardized coefficient is the i3rd third-class data point. The second deviation coefficient is the third type of data for the i3rd data point. is the weight coefficient of the i3rd third-class data.

[0036] In this embodiment, the first type of data refers to real-time running data that is in both the first standard running data range and the second standard running data range; the second type of data refers to real-time running data that is not in the first standard running data range; and the third type of data refers to real-time running data that is in both the first standard running data range and the second standard running data range.

[0037] In this embodiment, the operation conversion coefficient refers to converting the deviation coefficient or standard coefficient into a value with the same dimension as the operation sub-coefficient. When the first standard coefficient is larger, the operation sub-coefficient is larger; when the first deviation coefficient is larger, the operation sub-coefficient is smaller; when the second standard coefficient is larger and the second deviation coefficient is smaller, the operation sub-coefficient is larger.

[0038] In this embodiment, when the running sub-coefficient is larger and the confidence coefficient is larger, the running coefficient is larger; when the running coefficient is larger and the importance coefficient is larger, the real-time running evaluation value is larger, and vice versa.

[0039] In this embodiment, by evaluating the operating sub-coefficient of each monitoring point, the accuracy of judging the operating status of the equipment and the corresponding monitoring area is improved, laying the foundation for subsequent operation and maintenance strategies and improving operation and maintenance efficiency.

[0040] In some embodiments of this application, determining whether a corresponding monitoring area requires maintenance based on real-time operational evaluation values ​​includes: Pre-set the operational evaluation threshold for each monitoring area; If the real-time performance evaluation value is not less than the corresponding performance evaluation value threshold, then it is determined that the corresponding monitoring area does not require maintenance. If the real-time performance evaluation value is less than the corresponding performance evaluation value threshold, then the corresponding monitoring area is determined to require maintenance. Analyze the equipment in the monitoring area that requires maintenance, screen out the equipment whose operating coefficient is less than the preset operating coefficient threshold, and set it as the equipment to be maintained; Analyze the monitoring points of the equipment to be maintained, screen out the monitoring points whose operating sub-coefficient is less than the preset operating sub-coefficient threshold, and calculate the first occurrence ratio of each second type of data and the second occurrence ratio of each third type of data at all screened monitoring points. Set the second type of data, whose first occurrence ratio is greater than the first preset occurrence ratio, and the third type of data, whose second occurrence ratio is greater than the second preset occurrence ratio, as the maintenance data of the corresponding equipment to be maintained; The devices to be maintained and the data to be maintained in the monitoring area that need to be maintained are set as the maintenance factors for the corresponding monitoring area that needs to be maintained.

[0041] In this embodiment, the occurrence ratio is calculated by comparing the number of times each type of data appears in the selected monitoring points with the total number of selected monitoring points. The first preset occurrence ratio is 50%, and the second preset occurrence ratio is 80%.

[0042] In some embodiments of this application, several first operation and maintenance strategies are generated, including: Obtain historical maintenance data and historical maintenance policies from the historical maintenance logs of each device, and construct a mapping table of historical maintenance data and historical maintenance policies for each device; The similarity score is obtained by comparing the devices to be maintained and the data to be maintained in the monitoring area that need to be maintained with the historical data to be maintained in the historical maintenance strategy mapping table of the corresponding devices. The historical maintenance strategies corresponding to the historical maintenance data with a similarity greater than a preset similarity threshold are constructed into a maintenance strategy reference library for the corresponding maintenance device. The maintenance strategy reference library includes several maintenance strategies. Generate a reference library of maintenance strategies for all devices in the monitoring area that require maintenance; Randomly select one maintenance strategy from the maintenance strategy reference library for each device to be maintained, and combine them to obtain several first maintenance strategies for the monitoring area that needs maintenance.

[0043] In this embodiment, similarity refers to the degree of similarity between the maintenance data of the same device and the historical maintenance data in the historical maintenance strategy mapping table of the corresponding device, that is, the degree of similarity between the deviation coefficient or the second standard coefficient of the same maintenance data.

[0044] In this embodiment, the first maintenance strategy is obtained by combining a maintenance strategy randomly selected from all the devices to be maintained.

[0045] In some embodiments of this application, before performing coupling analysis on each first operation and maintenance strategy and determining the second operation and maintenance strategy based on the coupling analysis results, the following steps are included: Generate predictive maintenance data packages for each first maintenance strategy; Pre-set several operation and maintenance evaluation indicators; The predicted operation and maintenance data package for each first operation and maintenance strategy is evaluated based on several operation and maintenance evaluation indicators to obtain the predicted operation and maintenance evaluation value for each first operation and maintenance strategy. The first maintenance strategy is removed from the list of maintenance strategies whose predicted maintenance evaluation value is less than the preset maintenance evaluation value threshold. Then, a coupling analysis is performed on each of the remaining first maintenance strategies.

[0046] In this embodiment, the operation and maintenance evaluation indicators include, but are not limited to, operation and maintenance accuracy, operation and maintenance cost, operation and maintenance success probability, and operation and maintenance timeliness. Operation and maintenance timeliness is determined based on the length of time that the operation and maintenance strategy will affect the operation and maintenance data. The predicted operation and maintenance strategy package of the first operation and maintenance strategy is determined based on the actual historical operation and maintenance data of the historical operation and maintenance strategy that is highly similar to the second operation and maintenance strategy.

[0047] In this embodiment, the lower the accuracy of operation and maintenance, the higher the cost of operation and maintenance, the lower the probability of success of operation and maintenance, and the lower the timeliness of operation and maintenance, the smaller the predicted operation and maintenance assessment value, and vice versa.

[0048] In some embodiments of this application, before performing coupling analysis on each first operation and maintenance strategy and determining the second operation and maintenance strategy based on the coupling analysis results, the method further includes: Each of the remaining first operation and maintenance strategies includes several operation and maintenance strategies, and each operation and maintenance strategy is mapped to a device to be operated and maintained. A coupling analysis is performed on several operation and maintenance strategies with the same first operation and maintenance strategy to obtain the first coupling degree of the corresponding first operation and maintenance strategy; Select the first operation and maintenance strategy with a first coupling degree less than a preset coupling threshold; Construct a sequence of first operation and maintenance strategies for the monitoring areas that require operation and maintenance based on the selected first operation and maintenance strategy; A coupling analysis is performed sequentially on several first operation and maintenance strategies in the first operation and maintenance strategy sequence for different monitoring areas that require operation and maintenance, to obtain the second coupling degree between different first operation and maintenance strategies. If all second coupling degrees are less than the preset coupling degree threshold, then a second operation and maintenance strategy is constructed based on the corresponding multiple first operation and maintenance strategies.

[0049] In this embodiment, coupling analysis is used to analyze the correlation and degree of influence between different operation and maintenance strategies under the same first operation and maintenance strategy. If the coupling degree is high, it means that one operation and maintenance strategy may significantly affect the effect of another strategy, or even cause the effects of the two strategies to cancel each other out or produce a superposition effect. If the coupling degree is low, it means that each strategy is relatively independent and the influence between them is small.

[0050] In this embodiment, the first operation and maintenance strategy sequence is constructed according to the first coupling degree, that is, the first operation and maintenance strategy ranked first has the smallest first coupling degree.

[0051] In this embodiment, a coupling analysis is performed between the first first maintenance strategy in the first maintenance strategy sequence for different monitoring areas that need maintenance, to obtain a second coupling degree. If there is a second coupling degree that is not less than a preset coupling degree threshold, then a coupling analysis is performed on the second second maintenance strategy in the corresponding sequence. For example, if the different monitoring areas that need maintenance are a, b, and c, and the corresponding first first maintenance strategy is a1, b1, c1, and d1, the second coupling degree between the two first maintenance strategies is calculated respectively. If both are less than the preset coupling evaluation value threshold, then a second maintenance strategy is constructed based on a1, b1, c1, and d1. If the second coupling degree between a1, b1 and a1, c1 is not less than the preset coupling degree threshold, then a2 is selected and the coupling analysis is performed again until both are less than the preset coupling degree threshold.

[0052] In this embodiment, by incorporating coupling analysis, it is ensured that the second operation and maintenance strategy is the optimal operation and maintenance solution after comprehensively considering the mutual influence of each first operation and maintenance strategy, thereby providing more scientific and reliable operation and maintenance suggestions for the equipment operation status and power generation efficiency of wind turbine units and improving operation and maintenance efficiency.

[0053] In some embodiments of this application, a feedback module is also included, comprising: The feedback module is used to set the feedback time interval for the corresponding monitoring area based on the predicted operation and maintenance evaluation value of the first operation and maintenance strategy in the second operation and maintenance strategy. Several feedback time nodes are generated according to the feedback time interval; Collect actual operation and maintenance data for the corresponding monitoring area according to the feedback time node, calculate the actual application coefficient of the second operation and maintenance strategy for the corresponding monitoring area based on the actual operation and maintenance data, and determine whether to generate optimization instructions for the second operation and maintenance strategy.

[0054] In this embodiment, the actual operation and maintenance data includes the change characteristics of the data to be operated and maintained for each device. The change characteristics include the change trend, the change value, and the change rate. When the change trend is a normal trend or an abnormal trend, the actual application coefficient is larger when it is a normal trend and the change value and change rate are both standard changes, and vice versa.

[0055] In this embodiment, when the actual application coefficient is less than the preset application coefficient threshold, an optimization instruction is generated to improve the operational reliability and power generation efficiency of the wind turbine generator set.

[0056] In some embodiments of this application, the feedback time interval for setting the second operation and maintenance strategy based on the predicted operation and maintenance assessment value includes: The first predicted maintenance assessment value range, the second predicted maintenance assessment value range, the third predicted maintenance assessment value range, and the fourth predicted maintenance assessment value range are preset. When the predicted operation and maintenance assessment value is within the first predicted operation and maintenance assessment value range, the feedback time interval is set to the first preset time interval; When the predicted operation and maintenance assessment value is within the second predicted operation and maintenance assessment value range, the feedback time interval is set to the second preset time interval. When the predicted operation and maintenance assessment value is within the third predicted operation and maintenance assessment value range, the feedback time interval is set to the third preset time interval; When the predicted operation and maintenance assessment value is within the fourth predicted operation and maintenance assessment value range, the feedback time interval is set to the fourth preset time interval.

[0057] In this embodiment, the first predicted maintenance assessment value range < the second predicted maintenance assessment value range < the third predicted maintenance assessment value range < the fourth predicted maintenance assessment value range, and the first preset time interval < the second preset time interval < the third preset time interval < the fourth preset time interval.

[0058] In this embodiment, the larger the predicted operation and maintenance assessment value, the higher the operation and maintenance accuracy, the lower the cost, the higher the probability of operation and maintenance success, and the higher the operation and maintenance timeliness. The feedback time interval can be increased accordingly, and vice versa, so as to accurately feed back the actual operation and maintenance data, evaluate the application coefficient and optimize it in a timely manner, and improve the efficiency of remote operation and maintenance.

[0059] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.

Claims

1. A remote operation and maintenance monitoring system for wind power generation based on the Internet of Things, characterized in that, include: The data acquisition module is used to establish several monitoring areas and set monitoring parameters for each monitoring area, collect real-time monitoring data for each monitoring area according to the monitoring parameters, and calculate the real-time operation evaluation value. The judgment module is used to determine whether the corresponding monitoring area needs maintenance based on the real-time operation evaluation value. If it does, it generates several first maintenance strategies. The operation and maintenance module is used to perform coupling analysis on each first operation and maintenance strategy, determine the second operation and maintenance strategy based on the coupling analysis results, and issue operation and maintenance instructions according to the second operation and maintenance strategy.

2. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 1, characterized in that, Establish several monitoring areas and set monitoring parameters for each monitoring area, including: Establish multiple monitoring areas; Generate a historical monitoring data packet for each monitoring area, wherein the historical monitoring data packet includes historical monitoring data for each monitoring area in several historical monitoring periods; Several equipment evaluation indicators and several status evaluation indicators are pre-set; The historical monitoring data packets of each monitoring area are evaluated according to several equipment evaluation indicators and several status evaluation indicators to obtain the first evaluation value and the second evaluation value corresponding to each historical monitoring cycle. The weight is then calculated to obtain the third evaluation value. The average value of the third evaluation value of several historical monitoring periods in the same monitoring area is calculated to obtain the comprehensive evaluation value of the corresponding monitoring area. The monitoring parameters for the corresponding monitoring area are set according to the comprehensive evaluation value. The monitoring parameters include monitoring points, monitoring sensors, monitoring time intervals, and monitoring cycles.

3. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 2, characterized in that, Real-time operational data for each monitoring area is collected according to the monitoring parameters, and real-time operational evaluation values ​​are calculated, including: Real-time operational data for each monitoring area is collected according to the monitoring parameters, and combined with the corresponding monitoring sources to form a device-location-data mapping table; Compare the real-time operating data in the device-location-data mapping table with the corresponding first standard operating data range and second standard operating data range. If both are within the first standard operating data range and second standard operating data range, calculate the first standard coefficient of the corresponding real-time operating data. If it is not within the first standard operating data range, calculate the first deviation coefficient of the corresponding real-time operating data; If the data falls within the first standard operating data range but not within the second standard operating data range, calculate the second standard coefficient and the second deviation coefficient for the corresponding real-time operating data. Generate the operational sub-coefficients for each monitoring point; The operating coefficient of the corresponding equipment is generated based on the operating sub-coefficients of several monitoring points of the same equipment and the reliability coefficient of the monitoring points. Real-time operational evaluation values ​​are generated based on the operating coefficients of several devices with the same monitoring coefficient and the importance coefficient of the devices.

4. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 3, characterized in that, Generate the operational sub-coefficients for each monitoring point, including: Based on the relationship between real-time monitoring data and standard data range, real-time monitoring data is divided into three categories: Category I data, Category II data, and Category III data. The formula for calculating the running sub-coefficient is as follows: ； Where Y is the sub-coefficient, y1 is the first operational transformation coefficient, y2 is the second operational transformation coefficient, y3 is the third operational transformation coefficient, and n1 is the number of data in the first category. The first standard coefficient is the i1th data point of the first class. Let n1 be the weight coefficient of the i1th data point in the first category, and n2 be the number of data points in the second category. The first deviation coefficient is the i2th second-class data. n is the weight coefficient of the i2th second-class data, and n3 is the number of third-class data. The second standardized coefficient is the i3rd third-class data point. The second deviation coefficient is the third type of data for the i3rd data point. is the weight coefficient of the i3rd third-class data.

5. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 4, characterized in that, Determine whether the corresponding monitored area requires maintenance based on real-time operational evaluation values, including: Pre-set the operational evaluation threshold for each monitoring area; If the real-time performance evaluation value is not less than the corresponding performance evaluation value threshold, then it is determined that the corresponding monitoring area does not require maintenance. If the real-time performance evaluation value is less than the corresponding performance evaluation value threshold, then the corresponding monitoring area is determined to require maintenance. Analyze the equipment in the monitoring area that requires maintenance, screen out the equipment whose operating coefficient is less than the preset operating coefficient threshold, and set it as the equipment to be maintained; Analyze the monitoring points of the equipment to be maintained, screen out the monitoring points whose operating sub-coefficient is less than the preset operating sub-coefficient threshold, and calculate the first occurrence ratio of each second type of data and the second occurrence ratio of each third type of data at all screened monitoring points. Set the second type of data, whose first occurrence ratio is greater than the first preset occurrence ratio, and the third type of data, whose second occurrence ratio is greater than the second preset occurrence ratio, as the maintenance data of the corresponding equipment to be maintained; The devices to be maintained and the data to be maintained in the monitoring area that need to be maintained are set as the maintenance factors for the corresponding monitoring area that needs to be maintained.

6. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 5, characterized in that, Several primary operation and maintenance strategies are generated, including: Obtain historical maintenance data and historical maintenance policies from the historical maintenance logs of each device, and construct a mapping table of historical maintenance data and historical maintenance policies for each device; The similarity score is obtained by comparing the devices to be maintained and the data to be maintained in the monitoring area that need to be maintained with the historical data to be maintained in the historical maintenance strategy mapping table of the corresponding devices. The historical maintenance strategies corresponding to the historical maintenance data with a similarity greater than a preset similarity threshold are constructed into a maintenance strategy reference library for the corresponding maintenance device. The maintenance strategy reference library includes several maintenance strategies. Generate a reference library of maintenance strategies for all devices in the monitoring area that require maintenance; Randomly select one maintenance strategy from the maintenance strategy reference library for each device to be maintained, and combine them to obtain several first maintenance strategies for the monitoring area that needs maintenance.

7. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 6, characterized in that, Before determining the second operation and maintenance strategy based on the results of the coupling analysis for each first operation and maintenance strategy, the following steps are also included: Generate predictive maintenance data packages for each first maintenance strategy; Pre-set several operation and maintenance evaluation indicators; The predicted operation and maintenance data package for each first operation and maintenance strategy is evaluated based on several operation and maintenance evaluation indicators to obtain the predicted operation and maintenance evaluation value for each first operation and maintenance strategy. The first maintenance strategy is removed from the list of maintenance strategies whose predicted maintenance evaluation value is less than the preset maintenance evaluation value threshold. Then, a coupling analysis is performed on each of the remaining first maintenance strategies.

8. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 7, characterized in that, Calculate the coupling evaluation value of the remaining first maintenance strategy for the monitored area requiring maintenance, and determine the second maintenance strategy, including: Each of the remaining first operation and maintenance strategies includes several operation and maintenance strategies, and each operation and maintenance strategy is mapped to a device to be operated and maintained. A coupling analysis is performed on several operation and maintenance strategies with the same first operation and maintenance strategy to obtain the first coupling degree of the corresponding first operation and maintenance strategy; Select the first operation and maintenance strategy with a first coupling degree less than a preset coupling threshold; Construct a sequence of first operation and maintenance strategies for the monitoring areas that require operation and maintenance based on the selected first operation and maintenance strategy; A coupling analysis is performed sequentially on several first operation and maintenance strategies in the first operation and maintenance strategy sequence for different monitoring areas that require operation and maintenance, to obtain the second coupling degree between different first operation and maintenance strategies. If all second coupling degrees are less than the preset coupling degree threshold, then a second operation and maintenance strategy is constructed based on the corresponding multiple first operation and maintenance strategies.

9. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 8, characterized in that, It also includes a feedback module, including: The feedback module is used to set the feedback time interval for the corresponding monitoring area based on the predicted operation and maintenance evaluation value of the first operation and maintenance strategy in the second operation and maintenance strategy. Several feedback time nodes are generated according to the feedback time interval; Collect actual operation and maintenance data for the corresponding monitoring area according to the feedback time node, calculate the actual application coefficient of the second operation and maintenance strategy for the corresponding monitoring area based on the actual operation and maintenance data, and determine whether to generate optimization instructions for the second operation and maintenance strategy.

10. The IoT-based remote operation and maintenance monitoring system for wind power generation as described in claim 9, characterized in that, The feedback time interval for the second maintenance strategy is set based on the predicted maintenance assessment value, including: The first predicted maintenance assessment value range, the second predicted maintenance assessment value range, the third predicted maintenance assessment value range, and the fourth predicted maintenance assessment value range are preset. When the predicted operation and maintenance assessment value is within the first predicted operation and maintenance assessment value range, the feedback time interval is set to the first preset time interval; When the predicted operation and maintenance assessment value is within the second predicted operation and maintenance assessment value range, the feedback time interval is set to the second preset time interval. When the predicted operation and maintenance assessment value is within the third predicted operation and maintenance assessment value range, the feedback time interval is set to the third preset time interval; When the predicted operation and maintenance assessment value is within the fourth predicted operation and maintenance assessment value range, the feedback time interval is set to the fourth preset time interval.

Images