Online monitoring system for blades of wind generating set

Abstract

The invention relates to the technical field of wind turbine generator blades, in particular to a wind turbine generator blade online monitoring system. Comprising a central control unit used for setting a plurality of monitoring points according to blade parameters; the monitoring unit comprises a plurality of monitoring sub-modules, and the monitoring sub-modules are arranged at the monitoring points; the inspection unit is used for collecting infrared data and image data of the fan blade; multi-dimensional data of the fan blade are acquired by establishing a plurality of monitoring points, so that abnormal states such as internal damage and defects of the wind power blade are pre-warned, infrared data and image data of the fan blade are acquired by combining an unmanned aerial vehicle inspection technology, potential fault risks of the fan blade are pre-warned and overhauled in time, fault expansion is avoided, and the working efficiency is improved. The maintenance cost is reduced, and safe operation of the fan is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine blades, and in particular to an online monitoring system for wind turbine blades. Background Art

[0002] Wind energy is the most widely used renewable energy at present. However, the working environment of wind turbines is harsh and various system failures occur frequently. In particular, the wind turbine blades, as the core equipment of the unit, account for 15%-20% of the total equipment cost of the whole unit. They are easily damaged by external impacts such as thermal stress, hygroscopicity and lightning strikes, and have relatively high operation and maintenance costs.

[0003] At present, remote online monitoring systems have been installed on the generators, gearboxes, pitch and yaw mechanisms of wind turbines, which can monitor the operating status of components in real time. However, the wind turbine blades are one of the components that are easily damaged by lightning strikes and wind erosion, and faults such as blade cracking and delamination will occur. At present, the remote real-time status monitoring means are not complete. If problems are not discovered in time and the unit is started up and operated, it may lead to catastrophic consequences. Summary of the Invention

[0004] The purpose of the present application is: to solve the above technical problems, the present application provides an online monitoring system for wind turbine blades, aiming to improve the monitoring efficiency of wind turbine blades and ensure the safe and efficient operation of wind turbines.

[0005] In some embodiments of the present application, multi-dimensional data of wind turbine blades are collected by establishing multiple monitoring points, so as to give early warnings of abnormal states such as internal damage and defects of wind power blades. By combining the drone inspection technology, infrared data and image data of wind turbine blades are obtained, and potential fault risks of wind turbine blades are timely warned and repaired, so as to avoid the expansion of faults, reduce maintenance costs, and ensure the safe operation of the fan.

[0006] In some embodiments of the present application, an online monitoring system for wind turbine blades is provided, including: A central control unit for setting multiple monitoring points according to blade parameters; A monitoring unit including multiple monitoring sub-modules, and the monitoring sub-modules are arranged at each monitoring point; An inspection unit for collecting infrared data and image data of wind turbine blades; The central control unit includes: A first processing module for establishing a monitoring point sequence A, A = (a1, a2... a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; A second processing module, configured to obtain monitoring data packets of each monitoring point, and generate an anomaly evaluation value according to a preset status evaluation model and all the monitoring data packets.

[0007] In some embodiments of the present application, the central control unit further includes: A third processing module, configured to set an inspection strategy for the inspection unit; The third processing module is further configured to obtain an inspection data packet according to the inspection strategy, and generate a risk evaluation value according to the inspection data packet; The third processing module is further configured to determine whether to generate a maintenance instruction according to the risk evaluation value.

[0008] In some embodiments of the present application, the second processing module is further configured to: Set a plurality of monitoring characteristic indexes and simulation sub-models according to the historical operation parameters of the fan blade; Construct a status evaluation model according to all the monitoring characteristic indexes; Set a feedback time axis, and the feedback time axis includes a plurality of feedback time nodes; Obtain the monitoring data packets of all the monitoring points at the current feedback time node, and generate an operation data packet and a characteristic data packet according to all the monitoring data packets; Establish a compensation coefficient sequence R according to the simulation sub-model and the operation data packet; R = (r1, r2…r i …r θ1 ), where r i is the compensation coefficient of the i-th monitoring characteristic index at the current feedback time node; θ1 is the number of monitoring characteristic indexes; Generate an anomaly evaluation value f at the current feedback time node according to the characteristic data packet and the status evaluation model.

[0009] In some embodiments of the present application, when generating the anomaly evaluation value f, it includes: f = e1 * Q1 * β i * (j i - j' i ) 2 + e2 * Q2 * β i * (r i * j i - j' i ) 2 ; Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; θ1 is the number of monitoring characteristic indexes; β i is the influence factor of the i-th monitoring characteristic index; j iis the real-time reference value of the i-th monitoring feature index generated based on the feature data packet; j' i is the standard reference value of the i-th monitoring feature index; r i The compensation coefficient of the i-th monitoring feature index.

[0010] In some embodiments of the present application, the second processing module is further configured to: Preset a first abnormal evaluation value threshold F1 and a second abnormal evaluation value threshold F2, and F1 < F2; If f < F1, no maintenance instruction is generated at the current feedback time node; If F1 < f < F2, a first-level inspection instruction is generated at the current feedback time node; If f > F2, a first-level maintenance instruction is generated at the current feedback time node.

[0011] In some embodiments of the present application, the third processing module is further configured to: Establish multiple inspection cycles; Determine whether there is a first-level maintenance instruction within the current inspection cycle; If there is, generate a first-level inspection strategy according to the generation time node of the first-level maintenance instruction; Obtain a first-level inspection package according to the first-level inspection strategy; If not, generate a second-level inspection strategy according to the end time node of the current inspection cycle; Obtain a second-level inspection package according to the second-level inspection strategy.

[0012] In some embodiments of the present application, the third processing module is further configured to: Construct a first-level analysis model and a second-level analysis model; Obtain a real-time inspection data packet and determine the category of the real-time inspection data packet; If the real-time inspection data packet is a first-level inspection package, generate a first-level risk value c1 according to the first-level analysis model and the first-level inspection package; If the real-time inspection data packet is a second-level inspection package, generate a second-level risk value c2 according to the second-level analysis model and the second-level inspection package.

[0013] In some embodiments of the present application, when generating the first-level risk value c1, it includes: c1 = e3 * Q3 * η i * k 1i + e4 * Q4 * Δf; Wherein, e3 is a preset third weight coefficient; e4 is a preset fourth weight coefficient; Q3 is a preset third fixed coefficient; Q4 is a predicted fourth fixed coefficient; Δf is the inspection abnormal evaluation value; θ2 is the number of risk evaluation indicators; η i is the influence factor of the i-th risk evaluation indicator; k1i is the real-time reference value of the i-th risk evaluation index generated based on the first-level inspection package; Preset the first-level risk value threshold C'1; If the first-level risk value c1 > C'1, generate a first-level maintenance instruction.

[0014] In some embodiments of the present application, when generating the second-level risk value c2, it includes: Set the inspection cycle corresponding to the second-level inspection package as the target inspection cycle; Set multiple time intervals within the target inspection cycle according to the feedback time axis: Generate the abnormal evaluation value of each time interval; Establish an abnormal evaluation value sequence F', F'=(f'1, f'2…f' i …f' m ), where f' i is the abnormal evaluation value of the i-th time interval within the target inspection cycle; m is the number of time intervals within the target inspection cycle; Generate the second-level risk value c2 according to the abnormal evaluation value sequence F' and the second-level inspection package.

[0015] In some embodiments of the present application, when generating the second-level risk value c2, it further includes: c2 = e5 * Q5 * η i *k 2i +e6 * Q6 * g i *d i +e7 * Q7 * U; Wherein, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; e7 is the preset seventh weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; Q7 is the preset seventh fixed coefficient; θ2 is the number of risk evaluation indexes; η i is the influence factor of the i-th risk evaluation index; k 2i is the real-time reference value of the i-th risk evaluation index generated based on the second-level inspection package; θ3 is the number of auxiliary evaluation indexes; g i is the influence factor of the i-th auxiliary evaluation index; d i is the reference value of the i-th auxiliary evaluation index generated based on the abnormal evaluation value sequence F'; U is the historical evaluation value generated based on the historical second-level inspection package; Preset the second-level risk value threshold C'2; If the second-level risk value c2 > C'2, generate a first-level maintenance instruction.

[0016] Compared with the prior art, the beneficial effect of the blade online monitoring system of a wind turbine generator set in the embodiments of the present application is as follows: By establishing multiple monitoring points to collect multi-dimensional data of the wind turbine blade, early warnings can be given for abnormal states such as internal damage and defects of the wind power blade. By combining the unmanned aerial vehicle (UAV) inspection technology to obtain the infrared data and image data of the wind turbine blade, potential fault risks of the wind turbine blade can be warned and repaired in a timely manner, avoiding the expansion of faults, reducing maintenance costs, and ensuring the safe operation of the wind turbine. Description of the Drawings

[0017] Figure 1 It is a schematic structural diagram of an on-line monitoring system for a wind turbine blade according to an embodiment of the present application. Detailed Embodiments

[0018] The following will further describe in detail the specific embodiments of the present application in conjunction with the drawings and embodiments. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0019] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0020] The terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0021] In the description of the present application, it should be noted that unless otherwise clearly defined and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0022] As Figure 1 shown, an on-line monitoring system for a wind turbine blade according to a preferred embodiment of an embodiment of the present application includes: A central control unit for setting multiple monitoring points according to blade parameters; The monitoring unit includes multiple monitoring sub - modules, and the monitoring sub - modules are set at each monitoring point; The inspection unit is used to collect infrared data and image data of the wind turbine blades; The central control unit includes: The first processing module is used to establish a sequence of monitoring points A, A=(a1, a2…a i …a n ), where a i is the i - th monitoring point; n is the number of monitoring points; The second processing module is used to obtain the monitoring data packets of each monitoring point, and generate an anomaly evaluation value according to the preset state evaluation model and all monitoring data packets.

[0023] Specifically, according to the equipment parameters and historical fault parameters of the wind turbine blades, the blade surface is divided into multiple regions, monitoring points are set in each region, and at the same time, the position points prone to failure and loss (such as the blade root or key parts) are set as monitoring points.

[0024] Specifically, the central control unit further includes: The third processing module is used to set the inspection strategy of the inspection unit; The third processing module is also used to obtain the inspection data packet according to the inspection strategy, and generate a risk evaluation value according to the inspection data packet; The third processing module is also used to judge whether to generate a maintenance instruction according to the risk evaluation value.

[0025] Specifically, the inspection unit is preferably a drone device, equipped with a high - definition camera and a thermal imager. It can collect infrared and image data of the wind turbine blades for identifying cracks, coating peeling, structural deformation, internal water accumulation, delamination or lightning strike damage, etc.

[0026] It can be understood that in the above - mentioned embodiments, by establishing multiple monitoring points to collect multi - dimensional data of the wind turbine blades, early warning of abnormal states such as internal damage and defects of the wind power blades is carried out. By combining the drone inspection technology to obtain infrared data and image data of the wind turbine blades, early warning and maintenance of potential fault risks of the wind turbine blades are carried out in a timely manner, avoiding the expansion of faults, reducing the maintenance cost, and ensuring the safe operation of the wind turbine.

[0027] In the preferred embodiment of the present application, the second processing module is further used for: Setting multiple monitoring characteristic indexes and simulation sub - models according to the historical operation parameters of the wind turbine blades; Constructing a state evaluation model according to all monitoring characteristic indexes; Setting a feedback time axis, and the feedback time axis includes multiple feedback time nodes; Obtain the monitoring data packets of all monitoring points at the current feedback time node, and generate an operation data packet and a feature data packet based on all the monitoring data packets; Establish a compensation coefficient sequence R according to the simulation sub-model and the operation data packet; R = (r1, r2…r i …r θ1 ), where r i is the compensation coefficient of the i-th monitoring feature index at the current feedback time node; θ1 is the number of monitoring feature indices; Generate an abnormal evaluation value f at the current feedback time node according to the feature data packet and the status evaluation model.

[0028] Specifically, the monitoring feature indices include, but are not limited to, parameters such as the high-frequency acoustic wave signal, vibration frequency, ultrasonic echo signal, and strain distribution data of the blade.

[0029] Specifically, set the monitoring feature index data to be collected according to the position parameters of each monitoring point, and at the same time set the device type of its corresponding monitoring sub-module. For example, set an acceleration sensor at the blade root or key parts to collect vibration signals, and detect the state of structural looseness or internal damage by analyzing the change of dynamic frequency. Set resistance strain gauges on the blade to collect the strain distribution data of each part and monitor fatigue damage. Set ultrasonic devices at some monitoring points to actively emit ultrasonic waves and collect echo signals to analyze whether there are internal defects.

[0030] Specifically, by performing fusion processing on the monitoring data packets collected from each monitoring point, the corresponding operation data packet and feature data packet are generated. The real-time values of each monitoring feature index are included in the feature data packet, and the operation parameters of the fan blade during the time interval between the previous feedback time node and the current feedback time node are included in the operation data packet. Analyze the operating state of the fan blade through the simulation sub-model and the operation data packet, so as to generate the compensation coefficients for each monitoring feature index.

[0031] Specifically, the greater the deviation value between the real-time operating state of the fan blade and the standard operating state, the greater the corresponding compensation coefficient. The standard operating state refers to the state of the fan blade when there are no potential faults. The value range of the compensation coefficient is from zero to one.

[0032] Specifically, when generating the abnormal evaluation value f, it includes: f = e1 * Q1 * β i * (j i - j' i ) 2 + e2 * Q2 * β i * (ri *j i -j' i ) 2 ; Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; θ1 is the number of monitored characteristic indicators; β i is the influence factor of the i-th monitored characteristic indicator; j i is the real-time reference value of the i-th monitored characteristic indicator generated based on the feature data packet; j' i is the standard reference value of the i-th monitored characteristic indicator; r i is the compensation coefficient of the i-th monitored characteristic indicator.

[0033] Specifically, the larger the abnormal evaluation value is, the greater the possibility that there is a potential fault risk in the fan blade at the current feedback time node.

[0034] Specifically, by setting the compensation coefficients of each monitored characteristic indicator, the significance of the potential fault risk is improved, thereby improving the monitoring efficiency of the fan blade.

[0035] Specifically, by presetting the first fixed coefficient and the second fixed coefficient, all parameters in the model are normalized, so that each parameter of the model is within the same value range.

[0036] Specifically, the second processing module is further configured to: Preset a first abnormal evaluation value threshold F1 and a second abnormal evaluation value threshold F2, and F1 < F2; If f < F1, no maintenance instruction is generated at the current feedback time node; If F1 < f < F2, a first-level inspection instruction is generated at the current feedback time node; If f > F2, a first-level maintenance instruction is generated at the current feedback time node.

[0037] In a preferred embodiment of the present application, the third processing module is further configured to: Establish multiple inspection cycles; Judge whether there is a first-level maintenance instruction within the current inspection cycle; If it exists, generate a first-level inspection strategy according to the generation time node of the first-level maintenance instruction; Obtain a first-level inspection package according to the first-level inspection strategy; If it does not exist, generate a second-level inspection strategy according to the end time node of the current inspection cycle; Obtain a second-level inspection package according to the second-level inspection strategy.

[0038] Specifically, the first-level abnormal evaluation value threshold and the second-level abnormal evaluation value threshold can be set according to historical parameters.

[0039] Specifically, the first-level inspection instruction means that based on the analysis results of various monitoring characteristic indicators collected by the monitoring unit at the current time node, it is judged that there is a potential fault risk in the current wind turbine blade, and it is necessary to conduct real-time inspection on the wind turbine blade, collect the infrared data and image data of the wind turbine blade, and timely detect damages (such as cracks, corrosion, lightning damage, etc.).

[0040] Specifically, the second-level inspection strategy means that within a single inspection cycle, the overall operating state of the wind turbine blade is good, and it is necessary to inspect the wind turbine blade at the end time node of a single inspection cycle, collect its infrared data and image data, so as to judge whether there is a potential fault risk in the wind turbine blade.

[0041] Specifically, the first-level maintenance instruction means that there are fault damages in the current wind turbine blade, and it is necessary to stop the machine for maintenance in time to avoid the expansion of the fault, reduce the maintenance cost, and ensure the safe operation of the wind turbine.

[0042] Specifically, the third processing module is further configured to: Construct a first-level analysis model and a second-level analysis model; Obtain a real-time inspection data packet and judge the category of the real-time inspection data packet; If the real-time inspection data packet is a first-level inspection packet, generate a first-level risk value c1 according to the first-level analysis model and the first-level inspection packet; If the real-time inspection data packet is a second-level inspection packet, generate a second-level risk value c2 according to the second-level analysis model and the second-level inspection packet.

[0043] Specifically, when generating the first-level risk value c1, it includes: c1 = e3 * Q3 * η i * k 1i + e4 * Q4 * Δf; Wherein, e3 is a preset third weight coefficient; e4 is a preset fourth weight coefficient; Q3 is a preset third fixed coefficient; Q4 is a predicted fourth fixed coefficient; Δf is an inspection anomaly evaluation value; θ2 is the number of risk evaluation indicators; η i is the influence factor of the i-th risk evaluation indicator; k 1i is the real-time reference value of the i-th risk evaluation indicator generated based on the first-level inspection packet; Preset a first-level risk value threshold C'1; If the first-level risk value c1 > C'1, generate a first-level maintenance instruction.

[0044] Specifically, the first-level risk value threshold can be set according to historical parameters.

[0045] Specifically, the risk assessment indicators include, but are not limited to, the number and area of external damage points on the wind turbine blade, the abnormal temperature points and areas of the wind turbine blade, and other characteristic indicators related to the faults of the wind turbine blade. By quantifying each risk assessment indicator, accurate diagnosis of the potential fault risk of the wind turbine blade is achieved. The larger the value of the risk characteristic indicator, the greater the deviation of the corresponding parameter from the value in the standard operating state, and the greater the possibility that the wind turbine blade has a fault risk.

[0046] Specifically, the inspection anomaly value Δf is the real-time anomaly evaluation value at the time node corresponding to obtaining the first-level inspection package.

[0047] Specifically, the influence factors of each risk assessment indicator are set according to their correlation with the faults of the risk blades. The greater the correlation, the greater the corresponding influence factor.

[0048] Specifically, the greater the first-level risk value, the greater the possibility that the current wind turbine blade has a fault damage.

[0049] Specifically, by presetting the third fixed coefficient and the fourth fixed coefficient, all parameters in the model are normalized, so that each parameter in the model is within the same value range.

[0050] It can be understood that in the above embodiments, by combining the drone inspection technology to obtain the infrared data and image data of the wind turbine blade, the potential fault risk of the wind turbine blade is timely warned and repaired, the fault expansion is avoided, the maintenance cost is reduced, and the safe operation of the wind turbine is guaranteed.

[0051] In the preferred embodiment of the present application, when generating the secondary risk value c2, it includes: Setting the inspection cycle corresponding to the secondary inspection package as the target inspection cycle; Setting multiple time intervals within the target inspection cycle according to the feedback time axis: Generating the anomaly evaluation value of each time interval; Establishing an anomaly evaluation value sequence F', F'=(f'1, f'2…f' i …f' m ), where f' i is the anomaly evaluation value of the i-th time interval within the target inspection cycle; m is the number of time intervals within the target inspection cycle; Generating the secondary risk value c2 according to the anomaly evaluation value sequence F' and the secondary inspection package.

[0052] Specifically, when generating the secondary risk value c2, it further includes: c2 = e5 * Q5 * η i * k 2i + e6 * Q6 * g i *d i +e7*Q7*U; wherein, e5 is a preset fifth weight coefficient; e6 is a preset sixth weight coefficient; e7 is a preset seventh weight coefficient; Q5 is a preset fifth fixed coefficient; Q6 is a preset sixth fixed coefficient; Q7 is a preset seventh fixed coefficient; θ2 is the number of risk evaluation indicators; η i is the influence factor of the i-th risk evaluation indicator; k 2i is the real-time reference value of the i-th risk evaluation indicator generated based on the secondary inspection package; θ3 is the number of auxiliary evaluation indicators; g i is the influence factor of the i-th auxiliary evaluation indicator; d i is the reference value of the i-th auxiliary evaluation indicator generated based on the abnormal evaluation value sequence F'; U is the historical evaluation value generated based on the historical secondary inspection package; Specifically, the auxiliary evaluation indicators include, but are not limited to, multiple parameters such as the average value, variance, and change trend of all data in the abnormal evaluation value sequence F'. By setting multiple auxiliary evaluation indicators, a comprehensive analysis of the actual operating state of the wind turbine blade within the target inspection cycle is carried out. The influence factor of each auxiliary evaluation indicator can be set according to its correlation with the potential fault risk. The greater the correlation, the greater the corresponding influence factor.

[0053] Specifically, the historical evaluation value can be set according to the change trend of the secondary risk value generated by previous secondary inspection packages. The greater the increase in the probability of the fault risk, the greater the corresponding historical evaluation value.

[0054] Preset secondary risk value threshold C'2; If the secondary risk value c2 > C'2, a primary maintenance instruction is generated.

[0055] Specifically, all parameters in the model are normalized by presetting the fifth fixed coefficient, the sixth fixed coefficient, and the seventh fixed coefficient, so that each parameter in the model is within the same value range.

[0056] Specifically, the secondary risk value threshold can be set according to historical parameters.

[0057] According to the first concept of the present application, by establishing multiple monitoring points to collect multi-dimensional data of the wind turbine blade, early warnings for abnormal states such as internal damage and defects of the wind power blade are carried out. By combining the drone inspection technology to obtain infrared data and image data of the wind turbine blade, early warnings and maintenance of the potential fault risk of the wind turbine blade are carried out in a timely manner, avoiding the expansion of faults, reducing maintenance costs, and ensuring the safe operation of the wind turbine.

[0058] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present application, several improvements and substitutions can be made, and these improvements and substitutions should also be regarded as the protection scope of the present application.

Claims

1. An on-line monitoring system for wind turbine blades, characterized in that, Comprising: A central control unit, configured to set a plurality of monitoring points according to blade parameters; A monitoring unit, including a plurality of monitoring sub-modules, and the monitoring sub-modules are arranged at each monitoring point; An inspection unit, configured to collect infrared data and image data of the wind turbine blade; The central control unit includes: The first processing module is used to establish a sequence of monitoring points A, A = (a1, a2... a i … a n ), where a i is the i-th monitoring point; n is the number of monitoring points; A second processing module, configured to obtain monitoring data packets of each monitoring point, and generate an anomaly evaluation value according to a preset status evaluation model and all the monitoring data packets.

2. The on-line monitoring system for the blades of a wind turbine generator set according to claim 1, characterized in that, The central control unit further includes: A third processing module, configured to set an inspection strategy for the inspection unit; The third processing module is further configured to obtain an inspection data packet according to the inspection strategy, and generate a risk evaluation value according to the inspection data packet; The third processing module is further configured to determine whether to generate a maintenance instruction according to the risk evaluation value.

3. The on-line monitoring system for a wind turbine blade according to claim 2, wherein, The second processing module is further configured to: Set a plurality of monitoring characteristic indexes and simulation sub-models according to the historical operation parameters of the wind turbine blade; Construct a status evaluation model according to all the monitoring characteristic indexes; Set a feedback time axis, and a plurality of feedback time nodes are included on the feedback time axis; Obtain the monitoring data packets of all the monitoring points at the current feedback time node, and generate an operation data packet and a characteristic data packet according to all the monitoring data packets; Establish a compensation coefficient sequence R according to the simulation sub-model and the operation data packet; R = (r1, r2…r i …r θ1 ), where r i is the compensation coefficient of the i-th monitoring feature index at the current feedback time node; θ1 is the number of monitoring feature indices; Generate an anomaly evaluation value f of the current feedback time node according to the characteristic data packet and the status evaluation model.

4. The on-line monitoring system for wind turbine blades according to claim 3, characterized in that, When generating the anomaly evaluation value f, it includes: f = e1 * Q1 * β i * (j i - j' i ) 2 + e2 * Q2 * β i * (r i * j i - j' i ) 2 ; Among them, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; θ1 is the number of monitored characteristic indicators; β i is the influence factor of the i-th monitored characteristic indicator; j i is the real-time reference value of the i-th monitored characteristic indicator generated based on the feature data packet; j' i is the standard reference value of the i-th monitored characteristic indicator; r i The compensation coefficient of the i-th monitored characteristic indicator.

5. The on-line monitoring system for the wind turbine blade according to claim 4, wherein The second processing module is further configured to: Preset a first anomaly evaluation value threshold F1 and a second anomaly evaluation value threshold F2, and F1 < F2; If f < F1, no maintenance instruction is generated at the current feedback time node; If F1 < f < F2, a first-level inspection instruction is generated at the current feedback time node; If f > F2, a first-level maintenance instruction is generated at the current feedback time node.

6. The on-line monitoring system for wind turbine blades according to claim 5, wherein, The third processing module is further configured to: Establish a plurality of inspection cycles; Judge whether there is a first-level maintenance instruction within the current inspection cycle; If so, generate a first-level inspection strategy according to the generation time node of the first-level maintenance instruction; Obtain a first-level inspection package according to the first-level inspection strategy; If not, generate a second-level inspection strategy according to the end time node of the current inspection cycle; Obtain a second-level inspection package according to the second-level inspection strategy.

7. The online monitoring system for a wind turbine blade according to claim 6, wherein The third processing module is further configured to: Construct a first-level analysis model and a second-level analysis model; Obtain a real-time inspection data packet, and judge the category of the real-time inspection data packet; If the real-time inspection data packet is a first-level inspection package, generate a first-level risk value c1 according to the first-level analysis model and the first-level inspection package; If the real-time inspection data packet is a second-level inspection package, generate a second-level risk value c2 according to the second-level analysis model and the second-level inspection package.

8. The on-line monitoring system for wind turbine blades according to claim 7, wherein, When generating the first-level risk value c1, it includes: c1 = e3 * Q3 * η i * k 1i + e4 * Q4 * Δf; Among them, e3 is a preset third weight coefficient; e4 is a preset fourth weight coefficient; Q3 is a preset third fixed coefficient; Q4 is a preset fourth fixed coefficient; Δf is the inspection anomaly evaluation value; θ2 is the number of risk evaluation indicators; η i is the influence factor of the i-th risk evaluation indicator; k 1i is the real-time reference value of the i-th risk evaluation indicator generated based on the first-level inspection package; Preset a first-level risk value threshold C'1; If the first-level risk value c1 > C'1, generate a first-level maintenance instruction.

9. The on-line monitoring system for wind turbine blades according to claim 8, wherein When generating the second-level risk value c2, it includes: Set the inspection cycle corresponding to the second-level inspection package as the target inspection cycle; Set a plurality of time intervals within the target inspection cycle according to the feedback time axis: Generate anomaly evaluation values of each time interval; Establish an abnormal evaluation value sequence F', F'=(f'1, f'2…f' i …f' m ), where f' i is the abnormal evaluation value of the i-th time interval within the target inspection cycle; m is the number of time intervals within the target inspection cycle; Generate a second-level risk value c2 according to the anomaly evaluation value sequence F' and the second-level inspection package.

10. The online monitoring system for wind turbine blades according to claim 9, characterized in that, When generating the second-level risk value c2, it further includes: c2 = e5 * Q5 * η i *k 2i +e6 * Q6 * g i *d i +e7 * Q7 * U; Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; e7 is the preset seventh weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; Q7 is the preset seventh fixed coefficient; θ2 is the number of risk evaluation indicators; η i is the influence factor of the i-th risk evaluation indicator; k 2i is the real-time reference value of the i-th risk evaluation indicator generated based on the secondary inspection package; θ3 is the number of auxiliary evaluation indicators; g i is the influence factor of the i-th auxiliary evaluation indicator; d i is the reference value of the i-th auxiliary evaluation indicator generated based on the abnormal evaluation value sequence F'; U is the historical evaluation value generated based on the historical secondary inspection package; Preset a second-level risk value threshold C'2; If the secondary risk value c2 > C'2, a primary maintenance instruction is generated.

Images