Wind power generation system, early warning method of wind turbine generator unit thereof, and readable storage medium

Abstract

The application discloses a wind power generation system and a warning method of a wind turbine generator thereof and a readable storage medium. The method comprises the following steps: when it is monitored based on a preset detection model that a power curve of a generator of a wind turbine generator in a wind power generation system is abnormal, obtaining a rotating speed value and a power value in an abnormal period, and a wind speed value collected by a wind speed meter of the wind turbine generator in the abnormal period; generating the wind speed value and the power value into a wind power curve comparison graph, and generating the rotating speed value and the power value into a scatter comparison graph; determining a risk value and a reference repair measure of the generator according to the wind power curve comparison graph and the scatter comparison graph; generating the obtained historical warning information, the risk value and the reference repair measure of the generator into warning information, and warning the generator of the power curve abnormality. In this way, the power curve abnormality of the generator is warned in advance through the warning information, and the repair is more convenient, and the repair efficiency is improved.

Description

Early warning methods and readable storage media for wind power generation systems and their wind turbines Technical Field

[0001] This invention relates to the field of wind power generation technology, and in particular to a wind power generation system and its wind turbine generator early warning method, as well as a readable storage medium. Background Technology

[0002] Wind power generation is receiving increasing attention due to the clean, environmentally friendly, and renewable nature of wind energy. Its basic working principle is to convert wind energy into mechanical energy, then convert that mechanical energy into electrical energy via a generator, and finally output it to the power grid. A wind power generation system mainly consists of multiple wind turbine units, including a wind turbine rotor, main shaft, gearbox, generator, and supporting tower. The wind turbine is equipped with blades; when these blades rotate under the influence of wind, they convert wind energy into mechanical energy.

[0003] The power generation of a wind turbine is closely related to the normal operation of its internal components, such as the generator and the main shaft. However, some abnormalities are unavoidable, such as excessive generator temperature rise, abnormal power curves, and abnormal main shaft lubrication. Currently, there is a lack of early warning mechanisms for generators exhibiting abnormal power curves. Maintenance personnel only address the issue when the wind turbine fails to operate normally due to abnormal power curves, failing to provide early warning. Furthermore, maintenance personnel cannot directly identify the specific abnormality causing the turbine's malfunction; they must individually inspect each component to determine the cause. This results in difficult and inefficient maintenance. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, and readable storage medium for early warning of wind power generation systems and their wind turbine units. This aims to solve the technical problems in the prior art where wind turbine units in wind power generation systems fail to provide early warning of anomalies due to the lack of an early warning mechanism for abnormal generator power curves, resulting in difficulties in fault repair and low repair efficiency.

[0005] To achieve the above objectives, the present invention provides an early warning method for wind turbine generators in a wind power generation system, the early warning method comprising:

[0006] When an abnormal power curve is detected in any wind turbine generator in the wind power generation system based on a preset detection model, the rotational speed and power value of the generator during the abnormal period are obtained, as well as the wind speed value collected by the anemometer of the wind turbine generator where the generator is located during the abnormal period.

[0007] The wind speed value and the power value are generated into a wind power curve comparison chart, and the rotational speed value and the power value are generated into a scatter plot comparison chart;

[0008] Based on the wind power curve comparison chart and scatter plot comparison chart, determine the risk value and reference maintenance measures for the generator;

[0009] The system acquires historical early warning information of the generator, and generates early warning information by combining the historical early warning information, the risk value, and the reference maintenance measures. Based on the early warning information, it issues an early warning for abnormal power curves of the generator.

[0010] Optionally, the step of generating a wind power curve comparison graph from the wind speed value and the power value includes:

[0011] Acquire sample wind speed data and sample power generation data, and fit the sample wind speed data and sample power generation data into a data curve to generate a reference wind speed power curve.

[0012] The wind speed value and the power value are used to generate a wind speed-power curve, and the wind speed-power curve and the reference wind speed-power curve are added to a preset template diagram to generate a wind power curve comparison diagram.

[0013] Optionally, the step of generating a scatter plot of the rotational speed value and the power value includes:

[0014] Obtain the reference speed and reference power values ​​of the non-abnormal generators in the wind power generation system during the abnormal period;

[0015] The reference speed value and the reference power value of each of the non-abnormal generators are used to generate a reference scatter plot of each of the non-abnormal generators;

[0016] The rotational speed value and the power value are generated as a scatter plot to be compared, and the scatter plot to be compared and each of the reference scatter plots are used to form the scatter plot comparison chart.

[0017] Optionally, the scatter plot comparison chart includes a multi-fan scatter plot comparison chart and a single-fan scatter plot comparison chart. The step of forming the scatter plot comparison chart based on the scatter plot to be compared and each of the reference scatter plots includes:

[0018] The scatter plot to be compared is arranged and compared with each of the reference scatter plots to generate the multi-fan scatter plot;

[0019] Select any target scatter plot from each of the reference scatter plots, and merge the scatter plot to be compared with the target scatter plot to form the single wind turbine scatter comparison plot.

[0020] Optionally, the step of determining the risk value and reference maintenance measures of the generator based on the wind power curve comparison chart and scatter plot comparison chart includes:

[0021] Based on the wind power curve comparison chart, as well as the multi-fan scatter comparison chart and single-fan scatter comparison chart in the scatter comparison chart, the authenticity of the abnormal power curve of the generator is verified.

[0022] If the authenticity of the abnormal power curve of the generator is verified, then according to the wind power curve comparison chart, the multi-wind turbine scatter comparison chart and the single-wind turbine scatter comparison chart, a first risk value, a second risk value and a third risk value are generated respectively, as well as a first maintenance measure, a second maintenance measure and a third maintenance measure are generated respectively.

[0023] The risk value and the reference maintenance measure are determined based on the first risk value, the second risk value, the third risk value, the first maintenance measure, the second maintenance measure, and the third maintenance measure.

[0024] Optionally, the step of verifying the authenticity of the generator's power curve anomaly based on the wind power curve comparison chart, and the multi-fan scatter comparison chart and single-fan scatter comparison chart in the scatter comparison chart, includes:

[0025] Obtain the average deviation and deviation ratio of the wind speed power curve relative to the reference wind speed power curve in the wind power curve comparison graph, and determine whether there is an anomaly in the wind speed power curve based on the average deviation and the deviation ratio;

[0026] Obtain the interval power corresponding to the preset speed range in the multi-fan scatter comparison chart, and determine whether there is an anomaly in the target interval power of the scatter chart to be compared in the multi-fan scatter comparison chart based on the interval power;

[0027] Determine whether the first data point of the scatter plot to be compared in the single fan scatter plot is more dispersed than the second data point of the target scatter plot, and whether the average value of the first data point is less than the average value of the second data point.

[0028] If the wind speed-power curve is abnormal, and / or the power in the target range is abnormal, and / or the first data points are more dispersed than the second data points and the average value of the first data points is less than the average value of the second data points, then the authenticity of the abnormality of the generator's power curve is verified.

[0029] Optionally, the step of determining the risk value and the reference maintenance measure based on the first risk value, the second risk value, the third risk value, and the first maintenance measure, the second maintenance measure, and the third maintenance measure includes:

[0030] The first risk value, the second risk value, and the third risk value are compared, and the maximum value is determined as the risk value.

[0031] Perform a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and use the result of the union operation as the reference maintenance measure.

[0032] Optionally, the reference maintenance measures include at least checking whether there is a lubrication abnormality in the main bearing of the wind turbine where the generator is located, checking whether there is a problem with the pitch of the wind turbine, and checking whether the control strategy corresponding to the generator is abnormal.

[0033] Furthermore, to achieve the above objectives, the present invention also provides a wind power generation system, the wind power generation system comprising: a memory, a processor, a communication bus, and a control program stored in the memory:

[0034] The communication bus is used to enable communication between the processor and the memory;

[0035] The processor is used to execute the control program to implement the steps of the early warning method for wind turbine units in a wind power generation system as described above.

[0036] Furthermore, to achieve the above objectives, the present invention also provides a readable storage medium storing a control program, which, when executed by a processor, implements the steps of the early warning method for wind turbine units in a wind power generation system as described above.

[0037] The wind power generation system and its generator early warning method, as well as the readable storage medium of the present invention, are equipped with a preset detection model. When the preset detection model detects an abnormal power curve in any generator of any wind turbine in the wind power generation system, the system acquires the rotational speed and power values ​​of the generator during the abnormal period. Simultaneously, it acquires the wind speed values ​​collected by the anemometer of the wind turbine unit where the generator is located during the abnormal period. Based on the wind speed and power values, a wind-power curve comparison chart and a scatter plot comparison chart are generated. Subsequently, based on the wind-power curve comparison chart and the scatter plot comparison chart, the risk value and reference maintenance measures for the generator with the abnormal power curve are determined. The risk value reflects the degree of abnormality in the power curve, while the reference maintenance measures reflect the possible maintenance measures to be taken for the generator with the abnormal power curve. Subsequently, historical early warning information of the generator with the abnormal power curve is acquired, and this historical early warning information, risk value, and reference maintenance measures are combined to generate an early warning output for the generator with the abnormal power curve. Therefore, early warning information can be used to detect potential generator anomalies, avoiding the situation where wind turbines fail to generate electricity normally only after abnormal generator power curves occur, thus enabling early warning of anomalies. Furthermore, maintenance personnel can easily identify potential causes of anomalies and corresponding repair measures by reviewing the reference maintenance procedures in the early warning information, facilitating rapid troubleshooting and making maintenance more convenient and efficient. Attached Figure Description

[0038] Figure 1 is a flowchart illustrating the first embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention.

[0039] Figure 2 is a flowchart illustrating the second embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention.

[0040] Figure 3 is a comparison diagram of wind power curves generated by an embodiment of the early warning method for wind turbines in the wind power generation system of the present invention.

[0041] Figure 4 is a scatter comparison diagram of multiple wind turbines generated by an embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention.

[0042] Figure 5 is a scatter comparison diagram of a single wind turbine generated by an embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention.

[0043] Figure 6 is a flowchart illustrating the third embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention.

[0044] Figure 7 is a schematic diagram of the hardware operating environment involved in an embodiment of the wind power generation system of the present invention.

[0045] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0046] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0047] This invention provides an early warning method for wind turbine units in a wind power generation system. Please refer to Figure 1, which is a schematic flowchart of the first embodiment of the early warning method for wind turbine units in a wind power generation system according to this invention.

[0048] This invention provides an embodiment of an early warning method for wind turbine generators in a wind power generation system. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order. Specifically, the early warning method for wind turbine generators in this embodiment includes:

[0049] Step S10: When the power curve of any wind turbine generator in the wind power generation system is found to be abnormal based on the preset detection model, the rotational speed and power value of the generator during the abnormal period are obtained, as well as the wind speed value collected by the anemometer of the wind turbine generator where the generator is located during the abnormal period.

[0050] The wind power generation system in this embodiment includes multiple wind turbine units. Each wind turbine unit includes at least a wind rotor, main shaft, gearbox, generator, and supporting tower. The main shaft is equipped with a main bearing, and the wind rotor includes at least blades, a hub, bearings, and a rotor. The blades generate torque under the action of wind, causing the shaft to rotate and converting the wind rotor into mechanical energy. This mechanical energy is then transmitted to the generator through a transmission device such as a gearbox, coupling, and bearings, and the generator converts it into alternating current through electromagnetic induction.

[0051] This generator's early warning method can be applied to the entire wind power generation system or to individual wind turbines within the system. A wind power generation system inevitably includes a control device to ensure the orderly operation of its components and achieve wind power generation. This control device can be a centralized, overall control system or a distributed system with localized control. For the former, the generator's early warning method is applied to the overall control device, i.e., the system's control device. For the latter, the generator's early warning method can be applied to either the overall control device or localized control devices, i.e., the individual control devices of each wind turbine. This embodiment preferably uses the system's control device as an example for explanation.

[0052] Furthermore, to monitor the operation of various components in the wind turbine, multiple detection models are pre-set. For example, detection models can be set for main bearing lubrication, generator temperature rise, power curve, etc., and various types of detection models can also be set for anemometers, gearboxes, etc. In this embodiment, all kinds of detection models can be unified into a preset detection model, or various detection models can be set separately as multiple detection models.

[0053] Furthermore, the preset detection model generates reference data reflecting the normality of the generator power curve through pre-training. This reference data allows for real-time monitoring of whether the generator's power curve is abnormal. When an abnormal power curve is detected in a wind turbine generator within the wind power generation system, indicating a potential problem with the generator's power curve, a mechanism is implemented to verify the accuracy of the detection by combining the generator's speed, power, and wind speed values ​​collected by the corresponding anemometer. This requires acquiring the speed and power values ​​of the generator exhibiting the abnormal power curve during the abnormal period, as well as the wind speed values ​​collected by the anemometer of the wind turbine unit containing that generator during that abnormal period. Of course, the acquired speed, power, and wind speed values ​​can also be values ​​over a longer period, including the abnormal period; in this case, the speed, power, and wind speed values ​​within the abnormal period need to be selected.

[0054] Step S20: Generate a wind power curve comparison chart for the wind speed value and the power value, and generate a scatter comparison chart for the rotational speed value and the power value;

[0055] Furthermore, the wind speed and power generation values ​​acquired during the abnormal period are used to generate a wind power curve comparison chart based on the normal power values ​​of other generators without wind power curve anomalies during the abnormal period and the normal wind speed values ​​of their respective wind turbine units. Simultaneously, for the speed and power values ​​of generators with abnormal power curves during the abnormal period, these are used to generate a scatter plot based on the normal speed and power values ​​of other generators without power curve anomalies during the abnormal period. The wind power curve comparison chart and the scatter plot demonstrate the anomaly of the generators with abnormal power curves.

[0056] Step S30: Determine the risk value and reference maintenance measures for the generator based on the wind power curve comparison chart and scatter comparison chart;

[0057] Understandably, the severity of generator power curve anomalies affects wind turbine power generation differently. Some anomalies may have a more serious impact on wind turbines, such as directly causing turbine shutdowns, while others have a less severe impact. Therefore, to determine the severity of generator power curve anomalies, after confirming the existence of anomalies in generators monitored by the preset detection model through wind power curve comparison charts and scatter plots, it is necessary to determine the risk value of the generator with the abnormal power curve based on these charts to reflect the severity of the risk. Furthermore, a warning level can be determined based on the risk value. A pre-defined correspondence between risk value ranges and warning levels can be established. For example, if the risk value range is set to 0-1, where 0-0.3 corresponds to a low warning level, 0.3-0.7 to a medium warning level, and 0.7-1 to a high warning level, then the corresponding warning level can be determined based on the range in which the risk value falls.

[0058] Furthermore, corresponding maintenance measures can be pre-set for various faults and anomalies. By comparing wind power curves and scatter plots, potential anomalies can be identified, and corresponding maintenance measures can be found as reference measures. This allows maintenance personnel to quickly and accurately repair generators exhibiting abnormal power curves. The reference maintenance measures determined by the pre-set measures include at least checking the lubricating grease level in the main bearing of the wind turbine, whether the grease injection pipe is cracked, and whether there is grease leakage at the injection point to determine if there is a lubrication abnormality in the main bearing; checking the operation status of the blade angle encoder and signal transmission channel of the wind turbine, as well as the normal operation status of the pitch system of the wind turbine, to determine if there is an abnormality in the pitch of the wind turbine where the generator exhibits an abnormal power curve; and checking whether the control strategy controlling the generator's operation is abnormal.

[0059] Step S40: Obtain historical early warning information of the generator, and generate early warning information by combining the historical early warning information, the risk value, and the reference maintenance measures, and issue an early warning for abnormal power curve of the generator based on the early warning information.

[0060] Furthermore, generators within the same wind turbine unit may experience multiple power curve anomalies, with an early warning issued before each anomaly. A mechanism is in place to combine previous warnings into a single warning message for each new one, providing a comprehensive overview of the power curve anomalies within the wind turbine unit. Specifically, historical warning information for the generator currently experiencing a power curve anomaly is acquired. This historical warning information includes the number of previous warnings and their levels. For example, warning levels may be high, medium, and low; this generator's power curve has previously received 8 warnings: 3 high-level warnings, 3 medium-level warnings, and 2 low-level warnings. The historical warning information may also include detailed descriptions of previous warnings, the time of each warning, and the warning curve itself. The warning curve is generated from the number of historical warnings, their levels, and their times, allowing maintenance personnel to easily view the overall warning situation of the generator's power curve.

[0061] Furthermore, historical early warning information, along with risk values ​​and reference maintenance measures, is combined to generate early warning information. A template for generating early warning information is pre-set; by adding various information from historical early warning information, risk values, and reference maintenance measures to the corresponding positions in the template, an early warning message is formed. This early warning information is then output to the monitoring center of the wind power system or to the smart terminals of maintenance personnel connected to the wind power system, allowing maintenance personnel to view the information and promptly repair generators exhibiting abnormal power curves.

[0062] Understandably, after maintenance personnel repair a generator exhibiting an abnormal power curve based on the early warning information, the generator's power curve returns to normal. The anomaly in this warning is resolved and becomes a historical warning, requiring updating. Specifically, a preset detection model analyzes data from generators currently exhibiting abnormal power curves that have been repaired by maintenance personnel to determine if the generator still exhibits an abnormal power curve. If it does not, it indicates that the detected anomaly has been eliminated, and an early warning clearance notification is output. Simultaneously, the historical early warning information is updated based on this latest warning information to facilitate maintenance and repair of the generator the next time an abnormal power curve occurs.

[0063] The early warning method for wind turbine generators in this wind power generation system includes a preset detection model. When the model detects an anomaly in the power curve of any wind turbine generator in the system, it acquires the rotational speed and power values ​​of the generator during the abnormal period. Simultaneously, it acquires the wind speed values ​​collected by the anemometer of the wind turbine generator during the abnormal period. Based on the wind speed and power values, a wind-power curve comparison chart and a scatter plot comparison chart are generated. Then, based on the wind-power curve comparison chart and the scatter plot comparison chart, the risk value and reference maintenance measures for the generator with the abnormal power curve are determined. The risk value reflects the degree of power curve anomaly, while the reference maintenance measures represent possible maintenance actions for the generator with the abnormal power curve. Subsequently, historical early warning information for generators with abnormal power curves is acquired, and this historical early warning information, risk value, and reference maintenance measures are combined to generate an early warning output for generators with abnormal power curves. Therefore, early warning information can be used to detect potential generator anomalies, avoiding the situation where wind turbines fail to generate electricity normally only after abnormal generator power curves occur, thus enabling early warning of anomalies. Furthermore, maintenance personnel can easily identify potential causes of anomalies and corresponding repair measures by reviewing the reference maintenance procedures in the early warning information, facilitating rapid troubleshooting and making maintenance more convenient and efficient.

[0064] Furthermore, referring to Figure 2, based on the first embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention, a second embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention is proposed.

[0065] The difference between the second embodiment of the early warning method for wind turbine units in the wind power generation system and the first embodiment of the early warning method for wind turbine units in the wind power generation system is that the step of generating a wind power curve comparison graph from the wind speed value and the power value includes:

[0066] Step S21: Obtain sample wind speed data and sample power generation data, and fit the sample wind speed data and sample power generation data into a data curve to generate a reference wind speed power curve.

[0067] Step S22: Generate a wind speed-power curve from the wind speed value and the power value, and add the wind speed-power curve and the reference wind speed-power curve to a preset template diagram to generate the wind power curve comparison diagram;

[0068] Furthermore, the normal power values ​​of other generators that did not exhibit abnormal wind power curves during the abnormal period, along with the normal wind speed values ​​of their respective wind turbine units, are obtained as sample power generation data and sample wind speed data. These sample power generation data and sample wind speed data are then combined to form data curves. Specifically, sample power generation data and sample wind speed data from the same generator form a single data curve. These data curves are then fitted to obtain a reference wind speed-power curve. Simultaneously, a pre-set template is used to generate a wind power curve comparison chart. The wind speed and power values ​​acquired during the abnormal period are used to generate a wind speed-power curve, which, along with the reference wind speed-power curve, is added to the template to create the wind power curve comparison chart. The difference between the wind speed-power curve and the reference wind speed-power curve in the comparison chart reflects the degree of abnormality of the generator exhibiting the abnormal power curve. See Figure 3 for details; curve ① is the reference wind speed-power curve, and curve ② is the wind speed-power curve, both of which are used to generate the wind power curve comparison chart.

[0069] Furthermore, the step of generating a scatter plot of the rotational speed value and the power value includes:

[0070] Step S23: Obtain the reference speed and reference power values ​​of the non-abnormal generators in the wind power generation system during the abnormal period;

[0071] Step S24: Generate a reference scatter plot of each of the non-abnormal generators by taking the reference speed value and the reference power value of each non-abnormal generator.

[0072] Step S25: Generate a scatter plot to be compared from the rotational speed value and the power value, and form the scatter plot comparison chart based on the scatter plot to be compared and each of the reference scatter plots.

[0073] Furthermore, the normal speed and power values ​​of other generators that did not exhibit power curve anomalies during the abnormal period are obtained as reference speed and power values. A two-dimensional coordinate axis of power and speed is established, with one axis representing power and the other representing the target speed; for example, the horizontal axis represents speed and the vertical axis represents power. The reference speed and reference power values ​​of each generator that did not exhibit power curve anomalies are used to form their own reference value pairs, and each reference value pair is added to the two-dimensional coordinate axis to form a reference scatter plot for each generator that did not exhibit wind power curve anomalies, with one reference scatter plot for each generator. Simultaneously, the speed and power values ​​of generators exhibiting wind power curve anomalies are used to form abnormal value pairs, and these abnormal value pairs are added to the two-dimensional coordinate axis to form a scatter plot to be compared. This scatter plot to be compared and the various reference scatter plots together form a scatter comparison plot. The resulting scatter plot comparison chart includes a multi-fan scatter plot comparison chart and a single-fan scatter plot comparison chart. Specifically, the step of forming the scatter plot comparison chart based on the scatter plot to be compared and each of the reference scatter plots includes:

[0074] Step a1: Arrange and compare the scatter plot to be compared with each of the reference scatter plots to generate the multi-fan scatter plot comparison chart;

[0075] Step a2: Select any target scatter plot from each of the reference scatter plots, and merge the scatter plot to be compared with the target scatter plot to form the single wind turbine scatter comparison plot.

[0076] Furthermore, the multi-wind turbine scatter plot comparison compares scatter plots formed by multiple wind turbine units. For the reference scatter plot and the scatter plot to be compared, the scatter plot to be compared and each reference scatter plot are arranged one by one to form the multi-wind turbine scatter plot comparison. See Figure 4 for details. The wind turbine units are referred to simply as wind turbines. In Figure 4, the generator of wind turbine 43 shows an abnormal power curve, while the generators of wind turbines 39, 41, and 62 do not show any abnormal power curves. The upper left corner shows the reference scatter plot formed by wind turbine 39, the upper right corner shows the reference scatter plot formed by wind turbine 41, the lower right corner shows the reference scatter plot formed by wind turbine 62, and the lower left corner shows the scatter plot to be compared formed by wind turbine 43. The single-wind turbine scatter plot comparison compares a single reference scatter plot with the scatter plot to be compared. One reference scatter plot is randomly selected as the target scatter plot, and then the scatter plot to be compared is merged with this target scatter plot to form the single-wind turbine scatter plot comparison. Please refer to Figure 5 for details. The points concentrated on curve ① are the reference scatter plot formed by wind turbine No. 39, while the points scattered around curve ① are the comparison scatter plot formed by wind turbine No. 43. Together, they form a single wind turbine scatter comparison plot, showing the differences in speed and power between wind turbines with abnormal power curves and those without.

[0077] In this embodiment, the reference wind speed-power curve and reference scatter plot generated by the generator that does not show any power curve anomalies are used as references for the wind speed-power curve and the scatter plot to be compared, forming a wind power curve comparison chart and a scatter comparison chart. The scatter comparison chart is further divided into a multi-wind turbine scatter comparison chart and a single-wind turbine scatter comparison chart, realizing a comprehensive comparison between the wind speed-power curve and the scatter plot to be compared, thereby making the judgment of generator power curve anomalies more accurate.

[0078] Furthermore, referring to Figure 6, based on the first or second embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention, a third embodiment of the early warning method for wind turbine units in the wind power generation system of the present invention is proposed.

[0079] The difference between the third embodiment of the early warning method for wind turbine generators in the wind power generation system and the first or second embodiment of the early warning method for wind turbine generators in the wind power generation system is that the step of determining the risk value and reference maintenance measures of the generator based on the wind power curve comparison chart and scatter plot comparison chart includes:

[0080] Step S31: Based on the wind power curve comparison chart, and the multi-fan scatter comparison chart and single-fan scatter comparison chart in the scatter comparison chart, verify the authenticity of the abnormal power curve of the generator.

[0081] In this embodiment, the anomalies in the wind power curve comparison chart, the multi-wind turbine scatter plot comparison chart, and the single-wind turbine single-point comparison chart can all be used to reflect the severity of the generator power curve anomaly and to verify the accuracy of the preset detection model. Specifically, the authenticity of the generator power curve anomaly is first verified based on the wind power curve comparison chart, the multi-wind turbine scatter plot comparison chart, and the single-wind turbine scatter plot comparison chart. If the wind power curve comparison chart, the multi-wind turbine scatter plot comparison chart, or the single-wind turbine scatter plot comparison chart shows anomalies, it can be determined that the generator has indeed experienced a power curve anomaly. The step of verifying the authenticity of the generator power curve anomaly based on the wind power curve comparison chart, and the multi-wind turbine scatter plot comparison chart and the single-wind turbine scatter plot comparison chart, includes:

[0082] Step b1: Obtain the average deviation and deviation ratio of the wind speed power curve relative to the reference wind speed power curve in the wind power curve comparison graph, and determine whether the wind speed power curve is abnormal based on the average deviation and the deviation ratio.

[0083] Step b2: Obtain the interval power corresponding to the preset speed range in the multi-fan scatter comparison chart, and determine whether there is any abnormality in the target interval power of the scatter chart to be compared in the multi-fan scatter comparison chart based on the interval power;

[0084] Step b3: Determine whether the first data points of the scatter plot to be compared in the single fan scatter plot are more dispersed than the second data points of the target scatter plot, and whether the average value of the first data points is less than the average value of the second data points.

[0085] Step b4: If the wind speed power curve is abnormal, and / or the power in the target interval is abnormal, and / or the first data points are more dispersed than the second data points and the average value of the first data points is less than the average value of the second data points, then the authenticity of the abnormality of the generator's power curve is verified.

[0086] Understandably, for a wind power curve comparison chart, the power difference between the wind speed power curve and the reference wind speed power curve varies at different wind speed points. To reflect the magnitude of the deviation, multiple wind speed points in the comparison chart can be selected, and the power difference corresponding to each wind speed point can be calculated. Then, the average of these power differences can be calculated to obtain the average deviation. Simultaneously, the slopes of the wind speed power curve and the reference wind speed power curve are calculated, and the difference between the two slopes is obtained as the deviation ratio. The larger the deviation from the average value and the larger the deviation ratio, the greater the difference between the wind speed power curve and the reference wind speed power curve. Therefore, based on the average deviation and the deviation ratio, it can be determined whether the wind speed power curve is abnormal. A first threshold and a second threshold are set to characterize the abnormality. The average deviation is compared to the first threshold, and the deviation ratio is compared to the second threshold. If the average deviation is greater than the first threshold, or the deviation ratio is greater than the second threshold, then the wind speed power curve is determined to deviate significantly from the reference wind speed power curve, indicating an anomaly; otherwise, no anomaly is found.

[0087] Furthermore, for the multi-fan scatter plot, a preset speed range is established, such as the range less than 6 revolutions per minute in Figure 4. The power of each reference scatter plot and the scatter plot to be compared within the preset speed range is obtained. The power of the scatter plot to be compared is used as the target power, and then compared with the power of each range. This comparison determines whether there is an anomaly in the target power of the scatter plot to be compared. If the differences in power between ranges are small, but the difference between the target power and the power of each range is large, then an anomaly exists. For example, in Figure 4, the power of fans 39, 41, and 62 is 0 in the range less than 6 revolutions per minute, while the target power of fan 43 is not 0 in the range less than 6 revolutions per minute, indicating that the target power of fan 43 is abnormal.

[0088] Furthermore, for the single-fan scatter plot comparison, the data points of the scatter plot to be compared are taken as the first data points, and the data points of the target scatter plot are taken as the second data plot. The first and second data plots are then compared to determine whether the first data points are more dispersed than the second data points. Additionally, the first and second data points are averaged to obtain their average values, and then compared to determine whether the average value of the first and second data points is less than the average value of the second data points. If the first data points are more dispersed than the second data points, and the average value of the first data points is less than the average value of the second data points, it indicates that the scatter plot to be compared is more dispersed than the target scatter plot and has lower power, suggesting an anomaly in the scatter plot to be compared.

[0089] Furthermore, if the wind speed-power curve is determined to be abnormal, or the power in the target range is abnormal, or the first data point is more dispersed than the second data point and the average value of the first data point is less than the average value of the second data point, or two or three of these are abnormal, then it indicates that the generator does indeed have an abnormal power curve, and the verification of the generator power curve abnormality is passed. Conversely, if the wind speed-power curve is determined to be normal, the power in the target range is normal, and the first data point is not dispersed than the second data point and the average value of the first data point is not less than the average value of the second data point, then it indicates that the generator power curve is normal, and the verification of the generator power curve abnormality is failed. This indicates that the preset detection model for detecting generator power curve abnormalities is inaccurate, and a prompt message for optimizing the preset detection model is output to improve its detection accuracy.

[0090] Step S32: If the authenticity of the abnormal power curve of the generator is verified, then according to the wind power curve comparison chart, the multi-wind turbine scatter comparison chart and the single-wind turbine scatter comparison chart, the first risk value, the second risk value and the third risk value are generated respectively, and the first maintenance measure, the second maintenance measure and the third maintenance measure are generated respectively.

[0091] Step S33: Determine the risk value and the reference maintenance measure based on the first risk value, the second risk value, the third risk value, the first maintenance measure, the second maintenance measure, and the third maintenance measure.

[0092] Furthermore, for generators whose power curve anomalies have been verified, a first risk value and a first maintenance measure are generated based on the wind power curve comparison chart. The risk value corresponding to the wind power curve comparison chart reflects the degree of anomaly in the generator's power curve and the possible maintenance measures. Simultaneously, a second risk value and a second maintenance measure are generated based on a multi-wind turbine scatter plot comparison chart. The risk value corresponding to the multi-wind turbine scatter plot comparison chart reflects the degree of anomaly in the generator's power curve and the possible maintenance measures. In addition, a third risk value and a third maintenance measure are generated based on a single-wind turbine scatter plot comparison chart. The risk value corresponding to the single-wind turbine scatter plot comparison chart reflects the degree of anomaly in the generator's power curve and the possible maintenance measures.

[0093] Furthermore, since the risks embodied by the first risk value, the second risk value, and the third risk value are different, it is necessary to determine the overall risk value based on all three. Similarly, the maintenance methods embodied by the first maintenance measure, the second maintenance measure, and the third maintenance measure are also different, and it is also necessary to determine the overall reference maintenance measure based on all three. Specifically, the steps of determining the risk value and the reference maintenance measure based on the first risk value, the second risk value, the third risk value, and the first maintenance measure, the second maintenance measure, and the third maintenance measure include:

[0094] Step c1: Compare the first risk value, the second risk value, and the third risk value, and determine the maximum value as the risk value;

[0095] Step c2: Perform a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and use the union operation result as the reference maintenance measure.

[0096] Furthermore, the first, second, and third risk values ​​represent different levels of risk, with higher values ​​indicating greater risk. Therefore, a comparison can be made among the first, second, and third risk values ​​to determine the largest value as the overall risk value. The first, second, and third maintenance measures represent the maintenance methods for potential faults. For comprehensive maintenance, the first, second, and third maintenance measures are combined to obtain the overall comprehensive reference maintenance measures.

[0097] This embodiment establishes a verification mechanism for generator power curve anomalies based on wind power curve comparison charts, multi-wind turbine scatter plot comparison charts, and single-wind turbine scatter plot comparison charts, thereby making the prediction and detection model more accurate. Furthermore, for generators that are verified to have power curve anomalies, the overall risk value is determined using wind power curve comparison charts, multi-wind turbine scatter plot comparison charts, and single-wind turbine scatter plot comparison charts to accurately reflect the risk of generators with power curve anomalies, and to determine comprehensive reference maintenance measures for maintenance personnel to quickly eliminate anomalies and carry out maintenance, thus improving the accuracy of generator power curve anomaly early warning.

[0098] Furthermore, this embodiment of the invention also provides a wind power generation system. Referring to Figure 7, Figure 7 is a structural schematic diagram of the equipment hardware operating environment involved in the wind power generation system embodiment of the present invention.

[0099] As shown in Figure 7, the wind power generation system may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0100] Those skilled in the art will understand that the hardware structure of the wind power generation system shown in Figure 7 does not constitute a limitation on the wind power generation system, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0101] As shown in Figure 7, the memory 1005, which serves as a readable storage medium, may include an operating system, a network communication module, a user interface module, and a control program. The operating system is a program that manages and controls the wind power generation system and software resources, supporting the operation of the network communication module, the user interface module, the control program, and other programs or software. The network communication module manages and controls the network interface 1004, and the user interface module manages and controls the user interface 1003.

[0102] In the wind power generation system hardware structure shown in Figure 7, the network interface 1004 is mainly used to connect to the backend server and communicate with it; the user interface 1003 is mainly used to connect to the client (user terminal) and communicate with it; the processor 1001 can call the control program stored in the memory 1005 and perform the following operations:

[0103] When an abnormal power curve is detected in any wind turbine generator in the wind power generation system based on a preset detection model, the rotational speed and power value of the generator during the abnormal period are obtained, as well as the wind speed value collected by the anemometer of the wind turbine generator where the generator is located during the abnormal period.

[0104] The wind speed value and the power value are generated into a wind power curve comparison chart, and the rotational speed value and the power value are generated into a scatter plot comparison chart;

[0105] Based on the wind power curve comparison chart and scatter plot comparison chart, determine the risk value and reference maintenance measures for the generator;

[0106] The system acquires historical early warning information of the generator, and generates early warning information by combining the historical early warning information, the risk value, and the reference maintenance measures. Based on the early warning information, it issues an early warning for abnormal power curves of the generator.

[0107] Furthermore, the step of generating a wind power curve comparison graph from the wind speed value and the power value includes:

[0108] Acquire sample wind speed data and sample power generation data, and fit the sample wind speed data and sample power generation data into a data curve to generate a reference wind speed power curve.

[0109] The wind speed value and the power value are used to generate a wind speed-power curve, and the wind speed-power curve and the reference wind speed-power curve are added to a preset template diagram to generate a wind power curve comparison diagram.

[0110] Further, the step of generating a scatter plot of the rotational speed value and the power value includes:

[0111] Obtain the reference speed and reference power values ​​of the non-abnormal generators in the wind power generation system during the abnormal period;

[0112] The reference speed value and the reference power value of each of the non-abnormal generators are used to generate a reference scatter plot of each of the non-abnormal generators;

[0113] The rotational speed value and the power value are generated as a scatter plot to be compared, and the scatter plot to be compared and each of the reference scatter plots are used to form the scatter plot comparison chart.

[0114] Furthermore, the scatter plot comparison chart includes a multi-fan scatter plot comparison chart and a single-fan scatter plot comparison chart. The step of forming the scatter plot comparison chart based on the scatter plot to be compared and each of the reference scatter plots includes:

[0115] The scatter plot to be compared is arranged and compared with each of the reference scatter plots to generate the multi-fan scatter plot;

[0116] Select any target scatter plot from each of the reference scatter plots, and merge the scatter plot to be compared with the target scatter plot to form the single wind turbine scatter comparison plot.

[0117] Furthermore, the step of determining the risk value and reference maintenance measures of the generator based on the wind power curve comparison chart and scatter plot comparison chart includes:

[0118] Based on the wind power curve comparison chart, as well as the multi-fan scatter comparison chart and single-fan scatter comparison chart in the scatter comparison chart, the authenticity of the abnormal power curve of the generator is verified.

[0119] If the authenticity of the abnormal power curve of the generator is verified, then according to the wind power curve comparison chart, the multi-wind turbine scatter comparison chart and the single-wind turbine scatter comparison chart, a first risk value, a second risk value and a third risk value are generated respectively, as well as a first maintenance measure, a second maintenance measure and a third maintenance measure are generated respectively.

[0120] The risk value and the reference maintenance measure are determined based on the first risk value, the second risk value, the third risk value, the first maintenance measure, the second maintenance measure, and the third maintenance measure.

[0121] Furthermore, the step of verifying the authenticity of the generator's power curve anomaly based on the wind power curve comparison chart, and the multi-fan scatter comparison chart and single-fan scatter comparison chart in the scatter comparison chart, includes:

[0122] Obtain the average deviation and deviation ratio of the wind speed power curve relative to the reference wind speed power curve in the wind power curve comparison graph, and determine whether there is an anomaly in the wind speed power curve based on the average deviation and the deviation ratio;

[0123] Obtain the interval power corresponding to the preset speed range in the multi-fan scatter comparison chart, and determine whether there is an anomaly in the target interval power of the scatter chart to be compared in the multi-fan scatter comparison chart based on the interval power;

[0124] Determine whether the first data point of the scatter plot to be compared in the single fan scatter plot is more dispersed than the second data point of the target scatter plot, and whether the average value of the first data point is less than the average value of the second data point.

[0125] If the wind speed-power curve is abnormal, and / or the power in the target range is abnormal, and / or the first data points are more dispersed than the second data points and the average value of the first data points is less than the average value of the second data points, then the authenticity of the abnormality of the generator's power curve is verified.

[0126] Further, the step of determining the risk value and the reference maintenance measure based on the first risk value, the second risk value, the third risk value, and the first maintenance measure, the second maintenance measure, and the third maintenance measure includes:

[0127] The first risk value, the second risk value, and the third risk value are compared, and the maximum value is determined as the risk value.

[0128] Perform a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and use the result of the union operation as the reference maintenance measure.

[0129] Furthermore, the reference maintenance measures include at least checking whether there is any lubrication abnormality in the main bearing of the wind turbine where the generator is located, checking whether there is any abnormality in the pitch of the wind turbine, and checking whether there is any abnormality in the control strategy corresponding to the generator.

[0130] The specific implementation of the wind power generation system of the present invention is basically the same as the various embodiments of the early warning method for wind turbine units in the above-mentioned wind power generation system, and will not be repeated here.

[0131] This invention also proposes a readable storage medium. The readable storage medium stores a control program, which, when executed by a processor, implements the steps of the early warning method for wind turbine generators in a wind power generation system as described above.

[0132] The readable storage medium of the present invention can be a computer-readable storage medium, and its specific implementation is basically the same as the various embodiments of the early warning method for wind turbine units in the above-mentioned wind power generation system, and will not be repeated here.

[0133] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many modifications under the guidance of the present invention without departing from the spirit and scope of the claims. All equivalent structural or procedural transformations made using the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are within the protection scope of the present invention.

Claims

1. A method for early warning of wind turbine units in a wind power generation system, characterized in that, The early warning method includes: when an abnormal power curve is detected in any wind turbine generator in the wind power generation system based on a preset detection model, acquiring the rotational speed and power value of the generator during the abnormal period, and the wind speed value collected by the anemometer of the wind turbine generator during the abnormal period; generating a wind-power curve comparison chart, and generating a scatter plot of the rotational speed and power value; the step of generating a scatter plot of the rotational speed and power value includes: acquiring the reference rotational speed and reference power value of the non-abnormal generators in the wind power generation system during the abnormal period; generating the reference rotational speed and reference power value of each non-abnormal generator as a reference curve for each non-abnormal generator. The process involves generating a scatter plot using the rotational speed and power values, creating a comparison plot based on the comparison plot and the reference scatter plots, and then determining the risk value and reference maintenance measures for the generator according to the wind power curve comparison plot and the scatter plot. This includes verifying the authenticity of the generator's power curve anomaly based on the wind power curve comparison plot, as well as the multi-fan scatter plot and single-fan scatter plot in the scatter plot comparison. This includes obtaining the average deviation and deviation ratio of the wind speed-power curve relative to the reference wind speed-power curve in the wind power curve comparison plot, and determining whether the wind speed-power curve is abnormal based on the average deviation and the deviation ratio. The power of the interval corresponding to the preset speed range in the multi-fan scatter plot is used to determine whether the target interval power of the scatter plot to be compared in the multi-fan scatter plot is abnormal. It is also determined whether the first data point of the scatter plot to be compared in the single-fan scatter plot is more dispersed than the second data point of the target scatter plot, and whether the average value of the first data point is less than the average value of the second data point. If the wind speed-power curve is abnormal, and / or the target interval power is abnormal, and / or the first data point is more dispersed than the second data point and the average value of the first data point is less than the average value of the second data point, then the authenticity of the generator power curve abnormality is determined. Verification: If the authenticity of the abnormal power curve of the generator is verified, then based on the wind power curve comparison chart, the multi-wind turbine scatter comparison chart, and the single-wind turbine scatter comparison chart, a first risk value, a second risk value, and a third risk value are generated, as well as a first maintenance measure, a second maintenance measure, and a third maintenance measure. Based on the first risk value, the second risk value, the third risk value, and the first maintenance measure, the second maintenance measure, and the third maintenance measure, the risk value and the reference maintenance measure are determined. Historical early warning information of the generator is obtained, and the historical early warning information, the risk value, and the reference maintenance measure are generated as early warning information. Based on the early warning information, an early warning of abnormal power curve of the generator is issued.

2. The early warning method as described in claim 1, characterized in that, The steps for generating the wind power curve comparison chart include: acquiring sample wind speed data and sample power generation data, and fitting the sample wind speed data and sample power generation data into a data curve to generate a reference wind speed power curve; generating the wind speed value and the power value into a wind speed power curve, and adding the wind speed power curve and the reference wind speed power curve to a preset template chart to generate the wind power curve comparison chart.

3. The early warning method as described in claim 1, characterized in that, The scatter plot comparison chart includes a multi-fan scatter plot comparison chart and a single-fan scatter plot comparison chart. The step of forming the scatter plot comparison chart based on the scatter plot to be compared and each of the reference scatter plots includes: arranging and comparing the scatter plot to be compared with each of the reference scatter plots to generate the multi-fan scatter plot comparison chart; selecting any target scatter plot from each of the reference scatter plots, and merging the scatter plot to be compared with the target scatter plot to form the single-fan scatter plot comparison chart.

4. The early warning method as described in claim 1, characterized in that, The step of determining the risk value and the reference maintenance measure based on the first risk value, the second risk value, the third risk value, and the first maintenance measure, the second maintenance measure, and the third maintenance measure includes: comparing the first risk value, the second risk value, and the third risk value to determine the maximum value as the risk value; and performing a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure to obtain the union operation result as the reference maintenance measure.

5. The early warning method according to any one of claims 1-4, characterized in that, The reference maintenance measures include at least checking whether there is any lubrication abnormality in the main bearing of the wind turbine where the generator is located, checking whether there is any abnormality in the pitch of the wind turbine, and checking whether there is any abnormality in the control strategy corresponding to the generator.

6. A wind power generation system, characterized in that, The wind power generation system includes: a memory, a processor, a communication bus, and a control program stored in the memory; the communication bus is used to enable communication between the processor and the memory; the processor is used to execute the control program to implement the steps of the early warning method for wind turbine generators in the wind power generation system as described in any one of claims 1-4.

7. A readable storage medium, characterized in that, The readable storage medium stores a control program, which, when executed by a processor, implements the steps of the early warning method for wind turbine units in a wind power generation system as described in any one of claims 1-4.

Images