Wind power generation system and wind turbine main bearing early warning method and storage medium

Abstract

The present invention discloses a wind power generation system and a method for early warning of a main bearing of a wind turbine thereof, and a storage medium. The method comprises: when a lubrication anomaly of a main bearing of a wind turbine in the wind power generation system is detected based on a preset detection model, obtaining the temperature value of the main shaft corresponding to the anomaly during the abnormal period, and generating a temperature residual distribution and a thermal comparison diagram of the main shaft based on the temperature value; obtaining the power generation value of the generator corresponding to the anomaly, and the wind speed value collected by the anemometer of the wind turbine where the generator is located, and generating the wind speed value and the power generation value into a wind power curve comparison diagram; determining a risk value and reference maintenance measures based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram; and generating the obtained historical early warning information, risk value, and reference maintenance measures corresponding to the main bearing lubrication anomaly as early warning information for early warning. In this way, early warning of the main bearing lubrication anomaly is achieved through the early warning information, making maintenance more convenient and improving maintenance efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a wind power generation system and an early warning method for a main bearing of a wind turbine thereof, and a storage medium. Background Art

[0002] Wind power generation is gaining increasing attention due to its clean, environmentally friendly, and renewable nature. Its basic operating principle is that wind turbines convert wind energy into mechanical energy, which is then converted into electrical energy by generators and output to the power grid. A wind power generation system primarily consists of multiple wind turbines, including a rotor, main shaft, gearbox, generator, and supporting tower. The rotors are equipped with blades, which, when rotated by the wind, convert wind energy into mechanical energy.

[0003] Wind turbine power generation is closely tied to the proper functioning of its various internal components, such as the generator and main shaft. However, certain anomalies are inevitable, such as excessive generator temperature rise and main bearing lubrication failures. Currently, there's no early warning mechanism for main bearing anomalies. Maintenance personnel only initiate repairs when a main bearing anomaly causes the wind turbine to malfunction, failing to provide early warning of the anomaly. Furthermore, maintenance personnel cannot directly determine the cause of the anomaly, requiring them to test each component individually. This makes maintenance difficult and inefficient. Summary of the Invention

[0004] The main purpose of the present invention is to provide an early warning method, equipment and storage medium for the main bearings of wind turbines in a wind power generation system, aiming to solve the technical problems in the prior art that the main bearings of wind turbines in wind power generation systems cannot achieve early warning of abnormalities due to the lack of an early warning mechanism, resulting in difficult maintenance and low maintenance efficiency.

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

[0006] When a main bearing lubrication anomaly is detected in any wind turbine in the wind power generation system based on a preset detection model, a temperature value of the main shaft corresponding to the main bearing lubrication anomaly during the abnormal period is obtained, and a temperature residual distribution of the main shaft and a thermal comparison diagram of the main shaft are generated based on the temperature value;

[0007] Obtaining a power generation value of the generator corresponding to the main bearing lubrication abnormality and a wind speed value collected by an anemometer of a wind turbine where the generator is located, and generating a wind power curve comparison diagram of the wind speed value and the power generation value;

[0008] Determining the risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram;

[0009] Historical warning information corresponding to the main bearing lubrication abnormality is obtained, and the historical warning information, the risk value and the reference maintenance measures are generated into warning information, and a warning of the main bearing lubrication abnormality is performed based on the warning information.

[0010] Optionally, the temperature value of the spindle includes a front-end temperature value and a rear-end temperature value, and the temperature residual distribution of the spindle includes a front-end temperature residual distribution and a rear-end temperature residual distribution;

[0011] The step of generating the temperature residual distribution of the main shaft according to the temperature value includes:

[0012] Obtaining a front-end sample residual curve generated based on the front-end historical sample data, and a back-end sample residual curve generated based on the back-end historical sample data;

[0013] Obtaining a front-end temperature estimate value and a rear-end temperature estimate value, and generating the front-end temperature value and the front-end temperature estimate value into a front-end residual curve, and generating the rear-end temperature value and the rear-end temperature estimate value into a rear-end residual curve;

[0014] The front-end temperature residual distribution is generated according to the front-end sample residual curve and the front-end residual curve, and the rear-end temperature residual distribution is generated according to the rear-end sample residual curve and the rear-end residual curve.

[0015] Optionally, the step of determining the risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram includes:

[0016] Verifying the authenticity of the main bearing lubrication anomaly based on the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram;

[0017] If the authenticity of the main bearing lubrication abnormality is verified, a first risk value, a second risk value, and a third risk value are generated respectively according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram, and a first maintenance measure, a second maintenance measure, and a third maintenance measure are generated respectively;

[0018] The risk value and the reference maintenance measure are determined according to 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.

[0019] Optionally, the step of verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram includes:

[0020] Obtaining a baseline value and a residual expected value in the temperature residual distribution, generating a deviation value from the baseline value and the residual expected value, and determining whether the deviation value is abnormal;

[0021] Determine whether, in an area of ​​the thermal comparison diagram with the same rotational speed value, the temperature value of the spindle is abnormal relative to the reference temperature value of the thermal comparison diagram;

[0022] Determining whether a wind speed power curve generated by the wind speed value and the generated power value in the wind power curve comparison diagram is abnormal relative to a reference wind speed power curve in the wind power curve comparison diagram;

[0023] If the deviation value is abnormal, and / or the temperature value of the main shaft is abnormal relative to the reference temperature value, and / or the wind speed power curve is abnormal relative to the reference wind speed power curve, then the authenticity of the main bearing lubrication abnormality is determined to be verified.

[0024] Optionally, the step of determining the risk value and the reference maintenance measure according to 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:

[0025] comparing the first risk value, the second risk value, and the third risk value, and determining a maximum value as the risk value;

[0026] Perform a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and obtain a union operation result as the reference maintenance measure.

[0027] Optionally, the step of generating a first risk value, a second risk value, and a third risk value respectively according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram includes:

[0028] Comparing the deviation value with each first preset numerical interval to determine a first target numerical interval in which the deviation value is located, and determining the first risk value based on a first preset risk value corresponding to the first target numerical interval;

[0029] determining an average difference between the temperature value of the spindle and the reference temperature value, comparing the average difference with each second preset numerical interval, determining a second target numerical interval within which the average difference lies, and determining a second risk value based on a second preset risk value corresponding to the second target numerical interval;

[0030] Determine the average deviation of the wind speed power curve relative to the reference wind speed power curve, compare the average deviation with each third preset numerical interval, determine the third target numerical interval in which the average deviation lies, and determine the third risk value based on the third preset risk value corresponding to the third target numerical interval.

[0031] Optionally, after the step of verifying the authenticity of the main bearing lubrication anomaly based on the temperature residual distribution, the thermal comparison diagram and the wind power curve comparison diagram, the following steps are performed:

[0032] If the authenticity verification of the main bearing lubrication anomaly fails, a prompt message for optimizing the preset detection model is output.

[0033] Optionally, the reference maintenance measures include at least detecting the operating status of the temperature sensor corresponding to the main shaft, detecting whether the lubricating grease of the fan where the main bearing is located is sufficient, and detecting whether there is any fault in the cooling system of the fan where the main bearing is located.

[0034] Furthermore, to achieve the above-mentioned object, the present invention also provides a wind power generation system, which further includes: a memory, a processor, a communication bus, and a control program stored in the memory:

[0035] The communication bus is used to realize the connection and communication between the processor and the memory;

[0036] The processor is used to execute the control program to implement the steps of the early warning method for the main bearing of a wind turbine in a wind power generation system as described above.

[0037] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a storage medium having a control program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for early warning of a main bearing of a wind turbine in a wind power generation system.

[0038] The wind power generation system and its wind turbine main bearing early warning method and storage medium of the present invention are provided with a preset detection model. When the preset detection model detects lubrication anomalies in the main bearing of any wind turbine in the wind power generation system, the temperature of the main shaft within the wind turbine where the main bearing experiencing the lubrication anomaly is located during the abnormal period is acquired. Based on the acquired temperature values, a temperature residual distribution and a thermal comparison diagram of the main shaft are generated. Simultaneously, the generated power value of the generator within the wind turbine and the wind speed value collected by the anemometer within the wind turbine are acquired, and the wind speed and generated power values ​​are generated into a wind power curve comparison diagram. Furthermore, based on the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram, a risk value and reference maintenance measures for the main bearing experiencing the lubrication anomaly are determined. The risk value reflects the degree of anomaly in the main bearing, and the reference maintenance measures reflect possible maintenance measures for the abnormal main bearing. Subsequently, historical early warning information for the main bearing experiencing the lubrication anomaly is acquired, and this historical warning information, the risk value, and the reference maintenance measures are collectively generated and output as early warning information for providing an early warning of the main bearing experiencing the lubrication anomaly. This allows early warning of possible main bearing anomalies, preventing the turbine from noticing them until after the anomaly has caused the turbine to stop generating power. Maintenance personnel can then identify the cause of the anomaly and the corresponding repair measures by viewing the reference repair measures in the warning information. This helps quickly eliminate the cause, making maintenance more convenient and significantly improving efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 1. A schematic flow chart of a first embodiment of an early warning method for a main bearing of a wind turbine in a wind power generation system according to the present invention;

[0040] Figure 2 A front-end thermal comparison diagram generated by an embodiment of an early warning method for a main bearing of a wind turbine in a wind power generation system according to the present invention;

[0041] Figure 3 A rear-end thermal comparison diagram generated by an embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system according to the present invention;

[0042] Figure 4 A wind power curve comparison diagram generated by an embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention;

[0043] Figure 5 1. It is a flow chart of a second embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system according to the present invention;

[0044] Figure 6 The front-end temperature residual distribution generated by an embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention;

[0045] Figure 7 The rear-end temperature residual distribution generated by an embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention;

[0046] Figure 8 1. It is a flow chart of a third embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system according to the present invention;

[0047] Figure 9 It is a structural diagram of the hardware operating environment involved in an embodiment of the wind power generation system of the present invention.

[0048] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] The present invention provides an early warning method for the main bearing of a wind turbine in a wind power generation system. Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of a method for early warning of a main bearing of a wind turbine in a wind power generation system according to the present invention.

[0051] The present invention provides an embodiment of a method for early warning of a main bearing of a wind turbine in a wind power generation system. It should be noted that although the flowchart shows a logical order, in some cases, the steps shown or described may be performed in a different order. Specifically, the method for early warning of a main bearing of a wind turbine in a wind power generation system in this embodiment includes:

[0052] Step S10: When a main bearing lubrication anomaly is detected in any wind turbine in the wind power generation system based on a preset detection model, a temperature value of the main shaft corresponding to the main bearing lubrication anomaly during the abnormal period is obtained, and a temperature residual distribution of the main shaft and a thermal comparison diagram of the main shaft are generated based on the temperature value;

[0053] The wind power generation system of this embodiment includes multiple wind turbines, each of which comprises at least a rotor, a main shaft, a gearbox, a generator, and a supporting tower. The main shaft is equipped with a main bearing, while the rotor comprises at least blades, a hub, bearings, and a rotor. The blades, in response to wind, generate torque that rotates the shaft, converting the rotor into mechanical energy. This mechanical energy is then transmitted to the generator via a transmission device, including a gearbox, coupling, and bearings, which converts it into alternating current (AC) through electromagnetic induction.

[0054] This main bearing early warning method can be applied to the entire wind power generation system, and can also be applied to each wind turbine in the wind power generation system. The wind power generation system must be provided with a control device for controlling the orderly operation of each component to achieve wind power generation. The control device can be a centralized overall control or a distributed overall plus local control. For the former, the early warning method of the generator is applied to the overall control device, that is, the control device of the system. For the latter, the early warning method of the generator can be applied to both the overall control device and the local control device, that is, the control device of each wind turbine. This embodiment is preferably described by taking the control device of the system as an example.

[0055] Furthermore, to monitor the operating conditions of various components in the wind turbine, multiple detection models are pre-set. For example, detection models for main bearing lubrication, generator temperature rise, and power curves can be set. Different types of detection models can also be set for anemometers, gearboxes, etc. In this embodiment, various detection models can be unified into a pre-set detection model. Of course, each detection model can also be separated and multiple detection models can be set.

[0056] Furthermore, the preset detection model is pre-trained to generate reference data that reflects the normal operation of the main bearing lubrication. This type of reference data can be used to monitor in real time whether the main bearing lubrication is operating normally. When a lubrication anomaly is detected in the main bearing of a wind turbine in a wind power generation system, indicating that there may be a problem with the main bearing lubrication, in order to ensure the accuracy of the detection, a verification mechanism is also provided that combines the temperature residual of the main shaft, the thermal map, and the wind speed and power curve of the generator. Specifically, the temperature value of the main shaft in the wind turbine where the main bearing with the lubrication anomaly is located is first obtained during the abnormal period, and the temperature residual distribution and thermal comparison map of the main shaft are generated based on the obtained temperature value.

[0057] Among them, because the main bearing is installed on the main shaft, the main shaft in the fan where the main bearing is located is the main shaft and main bearing that are used together with each other in an installation relationship. The temperature residual is the difference between the actual temperature value and the estimated temperature value. According to the difference calculation between the obtained temperature value and the estimated value, the corresponding temperature residual distribution can be generated. The thermal comparison diagram is a temperature comparison of different main shafts at the same speed. The speed of the main shaft corresponding to the abnormal main bearing and the speed and temperature values ​​of the main shaft corresponding to other main bearings without abnormalities are obtained, and the temperature values ​​are arranged according to the speed, reflecting the temperature value of each main shaft at the same speed or speed range, and reflecting the abnormality through the difference between the temperature values. In addition, the thermal comparison diagram can also include the front-end thermal comparison diagram and the rear-end thermal comparison diagram of the main shaft. For the front-end thermal comparison diagram, please refer to Figure 2As shown, the main bearings of fans 69, 56, 50, and 47 did not have any abnormal lubrication. The front-end reference temperatures of their respective main shafts at speeds of 0-10, 10-12, 12-14, and 14-16 were arranged accordingly. The main bearing of fan 48 had abnormal lubrication. The front-end temperatures of its main shaft at speeds of 0-10, 10-12, 12-14, and 14-16 were arranged accordingly to generate a front-end thermal comparison diagram. For the rear-end thermal comparison diagram, please refer to Figure 3 As shown, the rear-end reference temperatures of the main shafts of fans No. 69, No. 56, No. 50 and No. 47 when the speeds are 0-10, 10-12, 12-14 and 14-16 are arranged accordingly, and the rear-end temperatures of the main shaft of fan No. 48 when the speeds are 0-10, 10-12, 12-14 and 14-16 are arranged accordingly to generate a rear-end thermal comparison diagram.

[0058] Step S20, obtaining a power generation value of the generator corresponding to the main bearing lubrication abnormality and a wind speed value collected by an anemometer of a wind turbine where the generator is located, and generating a wind power curve comparison diagram of the wind speed value and the power generation value;

[0059] Furthermore, the generator power value of the generator corresponding to the main bearing with bearing lubrication abnormality is obtained. The generator corresponding to the main bearing is the generator in the same wind turbine as the main bearing. Its power generation value can be directly the power value during the abnormal period, or it can be the power value during a longer period, and then the power value within the abnormal period is screened out. At the same time, the wind speed value collected by the anemometer in the wind turbine is also obtained. The wind speed value can also be directly the wind speed value during the abnormal period, or it can be the wind speed value during a longer period, and then the wind speed value within the abnormal period needs to be screened out. Thereafter, the wind speed value and the power generation value are generated into a wind speed power curve. At the same time, the wind speed value and the power generation value of the wind turbine where the main bearings that do not have abnormalities are located are obtained to form a normal wind speed power curve, and each normal wind speed power curve is fitted into a reference wind speed power curve. The wind speed power curve and the reference wind speed power curve are then generated into a wind power curve comparison diagram. The abnormality of the abnormal main bearing is reflected by the difference between the wind speed power curve and the reference wind speed power curve in the wind power curve comparison diagram. For details, please refer to Figure 4 As shown, curve ① is the reference wind speed power curve, and curve ② is the wind speed power curve, and the two are used to generate a wind power curve comparison diagram.

[0060] Step S30, determining a risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram;

[0061] It is understandable that different degrees of severity of main bearing lubrication anomalies have different impacts on wind turbine power generation. Some anomalies may have a more serious impact on the wind turbine, such as directly causing the wind turbine to shut down, while other anomalies have a lesser impact on the wind turbine. Therefore, in order to determine the severity of the main bearing lubrication anomaly, after determining that the main bearing with lubrication anomaly monitored by the preset detection model does have an anomaly through the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram, it is necessary to determine the risk value of the main bearing with lubrication anomaly based on the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram to reflect the severity of the risk. In addition, the warning level can also be determined based on the risk value. The correspondence between the risk value range and the warning level can be pre-set, such as setting the risk value range to 0-1, where 0-0.3 corresponds to a low warning level, 0.31-0.7 corresponds to a medium warning level, and 0.71-1 corresponds to a high warning level. After determining the risk value, the corresponding warning level can be determined based on the range in which the risk value lies.

[0062] Furthermore, corresponding maintenance measures can be set in advance for various fault anomalies, and possible anomalies can be determined through temperature residual distribution, thermal comparison diagram and wind power curve comparison diagram, and then the corresponding maintenance measures can be found as reference maintenance measures, so that maintenance personnel can quickly and accurately repair the main bearing with lubrication abnormalities based on the reference maintenance measures. Among them, the reference maintenance measures determined by the preset maintenance measures at least include detecting the operating status of the temperature sensor corresponding to the main shaft to determine whether there is a temperature sensor fault; detecting whether the lubricating grease of the fan where the main bearing is located is sufficient, such as determining whether the oil volume in the oil storage tank in the fan is sufficient, whether the oil pipeline is damaged, etc.; and detecting whether there is a fault in the cooling system of the fan where the main bearing is located, such as checking whether the air cooling pipe of the fan is blocked or damaged, whether the blades are damaged, etc.

[0063] Step S40, obtaining historical warning information corresponding to the main bearing lubrication abnormality, generating warning information from the historical warning information, the risk value and reference maintenance measures, and performing a warning of the main bearing lubrication abnormality based on the warning information.

[0064] Furthermore, the main bearings in the same wind turbine may have lubrication anomalies multiple times, and an early warning will be issued before each lubrication anomaly. For a new early warning, a mechanism is provided to combine all previous early warnings into early warning information, so as to comprehensively reflect the abnormality of the lubrication of the main bearings in the wind turbine. Specifically, the historical early warning information of the main bearing that currently has lubrication anomalies is obtained. The historical early warning information may include the number of previous early warnings and the warning level. For example, the warning level includes high, medium and low levels. The number of previous early warnings for the main bearing of the wind turbine is 8 times, including 3 high-level warnings, 3 medium-level warnings and 2 low-level warnings. At the same time, the historical early warning information can also include the specific description of the previous warnings and the time of the warning, as well as the warning curve. The warning curve is a curve generated by the number of historical warnings, the warning level and the warning time, which is convenient for maintenance personnel to view the overall warning situation of the main bearing.

[0065] Furthermore, the acquired historical warning information is combined with risk values ​​and reference maintenance measures to generate a warning message. A pre-set template for generating warning messages is used to add various pieces of information, risk values, and reference maintenance measures from the historical warning information to the corresponding positions in the template to generate a warning message. This warning message is then output to the wind turbine system's monitoring center or to a maintenance personnel's smart terminal connected to the wind turbine system for early warning. This allows maintenance personnel to review the warning information and promptly repair the main bearings experiencing lubrication anomalies based on the warning information.

[0066] Understandably, after maintenance personnel inspect and repair the main bearing experiencing a lubrication anomaly based on the warning information, the main bearing can resume normal operation. The anomaly previously warned of has been resolved and becomes a historical warning, requiring an update of the historical warning information. Specifically, a preset detection model analyzes the data of the main bearing currently experiencing a lubrication anomaly, inspected by the maintenance personnel, to determine whether the main bearing still experiences the anomaly. If it does not, the detected anomaly has been resolved, and a warning elimination prompt is output. Simultaneously, the historical warning information is updated based on the latest warning information to facilitate maintenance and repair of the main bearing experiencing the lubrication anomaly the next time.

[0067] The present invention provides an early warning method for wind turbine main bearings in a wind power generation system. When the pre-set detection model detects lubrication anomalies in the main bearings of any wind turbine in the wind power generation system, the method obtains the temperature of the main shaft within the wind turbine where the main bearing experiencing the lubrication anomaly is located during the anomaly period. Based on the obtained temperature values, a temperature residual distribution and a thermal comparison diagram of the main shaft are generated. Simultaneously, the method obtains the power generated by the generator within the wind turbine and the wind speed value collected by the anemometer within the wind turbine. The wind speed and power values ​​are then combined to form a wind power curve comparison diagram. Furthermore, based on the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram, a risk value and reference maintenance measures are determined for the main bearing experiencing the lubrication anomaly. The risk value reflects the degree of anomaly, while the reference maintenance measures reflect potential maintenance measures for the anomaly. Subsequently, historical early warning information for the main bearing experiencing the lubrication anomaly is obtained. This historical warning information, the risk value, and the reference maintenance measures are combined to generate a warning output for the main bearing experiencing the lubrication anomaly. This allows early warning of possible main bearing anomalies, preventing the turbine from noticing them until after the anomaly has caused the turbine to stop generating power. Maintenance personnel can then identify the cause of the anomaly and the corresponding repair measures by viewing the reference repair measures in the warning information. This helps quickly eliminate the cause, making maintenance more convenient and significantly improving efficiency.

[0068] For further information, please refer to Figure 5 Based on the first embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention, a second embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention is proposed.

[0069] The second embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system differs from the first embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system in that the temperature value of the main shaft includes a front temperature value and a rear temperature value, and the temperature residual distribution of the main shaft includes a front temperature residual distribution and a rear temperature residual distribution;

[0070] The step of generating the temperature residual distribution of the main shaft according to the temperature value includes:

[0071] Step S11, obtaining a front-end sample residual curve generated based on the front-end historical sample data, and a back-end sample residual curve generated based on the back-end historical sample data;

[0072] Step S12, obtaining a front-end temperature estimate value and a rear-end temperature estimate value, and generating the front-end temperature value and the front-end temperature estimate value into a front-end residual curve, and generating the rear-end temperature value and the rear-end temperature estimate value into a rear-end residual curve;

[0073] Step S13 , generating the front-end temperature residual distribution according to the front-end sample residual curve and the front-end residual curve, and generating the rear-end temperature residual distribution according to the rear-end sample residual curve and the rear-end residual curve.

[0074] Furthermore, in the wind turbine of the wind power generation system, the main shaft includes a front end and a rear end, the front end flange is connected to the hub of the wind turbine, and the rear end is connected to the gearbox to transmit the rotation of the wind wheel to the gearbox. The temperature value of the main shaft includes the temperature of the front end and the temperature of the rear end, and in order to monitor the abnormality of the temperature, an estimated value representing normality is usually provided, and then the difference between the actual value detected and the estimated value is generated as a residual, and the residual reflects the abnormality. For the normal front end temperature and rear end temperature detected in the past, they are used as the front end historical sample data and the rear end historical sample data, and then the front end historical sample data and the front end estimated value are generated as a front end sample residual curve, and the rear end historical sample data and the rear end estimated value are generated as a rear end sample residual curve.

[0075] At the same time, for the currently acquired front-end temperature value and rear-end temperature value of the main shaft, the corresponding front-end temperature estimate value and rear-end temperature estimate value are obtained, and the front-end temperature estimate value and the front-end temperature value are generated as the front-end residual curve, and the rear-end temperature estimate value and the rear-end temperature value are generated as the rear-end residual curve. Thereafter, the front-end sample residual curve and the front-end residual curve are added to the preset residual distribution template diagram to generate the front-end temperature residual distribution, and the rear-end sample residual curve and the rear-end residual curve are added to the preset residual distribution template diagram to generate the rear-end temperature residual distribution. For the front-end temperature residual distribution, please refer to Figure 6 , where curve ④ is the front-end residual curve generated abnormally in April 2020, and curves ①, ②, and ③ are the normal front-end sample residual curves in August, September, and November 2019, respectively. These curves are combined to form the front-end temperature residual distribution. For the back-end temperature residual distribution, see Figure 7 Among them, curve No. 4 is the abnormally generated back-end residual curve in April 2020, and curves No. 1, 2, and 3 are the normal back-end sample residual curves in August 2019, September 2019, and November 2019, respectively. These curves are jointly generated to form the front-end temperature residual distribution.

[0076] This embodiment distinguishes between the front-end temperature and the rear-end temperature of the spindle, and generates a front-end sample residual curve and a rear-end sample residual curve based on previously detected normal front-end temperature and rear-end temperature, which serve as a reference for the front-end residual curve and rear-end residual curve generated by the current front-end temperature and rear-end temperature, thereby making the judgment of whether there is an abnormality in the front-end temperature and rear-end temperature of the spindle more accurate.

[0077] For further information, please refer to Figure 8 Based on the first or second embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention, a third embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention is proposed.

[0078] The third embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system differs from the first or second embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system in that the step of determining a risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram comprises:

[0079] Step S31, verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram;

[0080] In this embodiment, the abnormality of the temperature residual distribution, the abnormality of the thermal comparison diagram, and the abnormality of the wind power curve comparison diagram can all be used to reflect the severity of the main shaft lubrication abnormality, and can also seriously preset the accuracy of the detection model monitoring. Specifically, first, based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram, the authenticity of the main bearing lubrication abnormality is verified. If there is an abnormality in the temperature residual distribution, the thermal comparison diagram, or the wind power curve comparison diagram, it can be determined that the main bearing does have a lubrication abnormality. Among them, the step of verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram includes:

[0081] Step a1, obtaining a baseline value and an expected residual value in the temperature residual distribution, generating a deviation value from the baseline value and the expected residual value, and determining whether the deviation value is abnormal;

[0082] Step a2, determining whether there is an abnormality in the temperature value of the spindle relative to the reference temperature value of the thermal comparison diagram in the area with the same speed value in the thermal comparison diagram;

[0083] Step a3, determining whether there is any abnormality in the wind speed power curve generated by the wind speed value and the generated power value in the wind power curve comparison diagram relative to the reference wind speed power curve in the wind power curve comparison diagram;

[0084] Step a4: If the deviation value is abnormal, and / or the temperature value of the main shaft is abnormal relative to the reference temperature value, and / or the wind speed power curve is abnormal relative to the reference wind speed power curve, then the authenticity of the main bearing lubrication abnormality is determined to be verified.

[0085] Furthermore, the temperature residual distribution includes the front-end temperature residual distribution and the rear-end temperature residual distribution, so the verification of the temperature residual distribution can also be divided into the verification of the front-end temperature residual distribution and the rear-end temperature residual distribution. Specifically, the front-end sample residual curve and the rear-end sample residual curve in the front-end temperature residual distribution and the rear-end temperature residual distribution both include baseline values, and in order to distinguish the front end from the rear end, they can be used as the front-end baseline value and the rear-end baseline value, respectively. In addition, the front-end residual curve and the rear-end residual curve in the front-end temperature residual distribution and the rear-end temperature residual distribution both include residual expected values, and in order to distinguish the front end from the rear end, they can be used as the front-end residual expected value and the rear-end residual expected value, respectively.

[0086] Furthermore, the front-end baseline value, the front-end residual expected value, the back-end baseline value, and the back-end residual expected value are obtained from the front-end temperature residual distribution and the back-end temperature residual distribution respectively, and then the front-end baseline value and the front-end residual expected value are used as the difference to generate the front-end deviation value, and the back-end baseline value and the back-end residual expected value are used as the difference to generate the back-end deviation value, and it is judged whether the front-end deviation value and the back-end deviation value have abnormalities. The abnormality can be judged by the difference threshold. If the front-end deviation value is greater than the difference threshold, or the back-end deviation value is greater than the difference threshold, it is judged that the deviation value formed by the front-end deviation value and the back-end deviation value has abnormalities. On the contrary, if both the front-end deviation value and the back-end deviation value are not greater than the difference threshold, it is judged that the deviation value formed by the front-end deviation value and the back-end deviation value has no abnormalities. For example, the difference threshold is set to 1. Figure 6 The front-end temperature residual distribution and Figure 7 The rear-end temperature residual distribution shown has a front-end baseline value and a rear-end baseline value of 4, a front-end residual expected value and a rear-end residual expected value of 0, and a front-end deviation value and a rear-end deviation value of 4, so it can be determined that the deviation value is abnormal.

[0087] Furthermore, for the thermal comparison chart, the spindle temperature corresponding to the main bearing without lubrication anomalies is used as the reference temperature value in the thermal comparison chart. The spindle temperature value is then compared with the reference temperature at the same speed value or speed value range to determine whether the spindle temperature value is abnormal relative to the reference temperature value. For example, the thermal comparison chart is a bar chart, where each bar in the chart represents the spindle of a fan. The bar is divided into multiple intervals according to height, each interval representing a speed value or speed range. The intervals can represent temperature values. Then, by comparing the temperature values ​​between the bars in the same interval, it is determined whether the spindle temperature value is abnormal relative to the reference temperature value. In addition, to facilitate inspection personnel, the temperature of the interval can also be represented by color blocks, with different color blocks representing different temperatures. The temperature differences can be intuitively displayed by the color differences between the bars in the same interval. If the difference between the spindle temperature value and the reference temperature value is large, it can be determined that the spindle temperature value is abnormal relative to the reference temperature value; otherwise, no abnormality exists. The size of the difference can be indicated in advance by a preset threshold value, and a difference operation is performed between the temperature value and the reference temperature value. If the operation result is greater than the preset threshold value, it means that the difference is large, otherwise the difference is not large.

[0088] Furthermore, for the wind power curve comparison diagram, the wind speed power curve and the reference wind speed power curve are compared based on the same wind speed value to determine whether the difference between the two is large at the same wind speed value. In addition, in order to ensure the accuracy of the comparison, multiple wind speed values ​​can be selected for comparison. At the same time, a difference threshold is set, and the power value at the same wind speed and the reference power value are calculated to determine whether the calculation result is greater than the difference threshold. If it is greater, it means that the difference between the two is large, otherwise it means that the difference between the two is not large. The size of the difference is used to determine whether there is any abnormality in the wind speed power curve relative to the reference wind speed power curve.

[0089] Furthermore, if it is determined that the deviation value generated by the temperature residual distribution is abnormal, or the temperature value of the main shaft in the thermal comparison diagram is abnormal relative to the reference temperature value, or the wind speed power curve in the wind power curve comparison diagram is abnormal relative to the reference wind speed power curve, then it means that the lubrication of the main bearing is indeed abnormal, so the authenticity verification of the main bearing lubrication abnormality is judged to be passed. On the contrary, if it is determined that there is no abnormality in the deviation value, there is no abnormality in the temperature value of the main shaft relative to the reference temperature value, and there is no abnormality in the wind speed power curve relative to the reference wind speed power curve, then it means that there is no abnormality in the lubrication of the main bearing, so the authenticity verification of the main bearing lubrication abnormality is judged to be failed, which further indicates that the detection of the preset detection model that monitors the main bearing lubrication abnormality is inaccurate, and thus a prompt message for optimizing the preset detection model is output, and the accuracy of its detection is improved by optimizing the preset detection model.

[0090] Step S32: If the authenticity of the main bearing lubrication anomaly is verified, generating a first risk value, a second risk value, and a third risk value, and generating a first maintenance measure, a second maintenance measure, and a third maintenance measure, respectively, based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram;

[0091] Step S33: determining the risk value and the reference maintenance measure according to 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.

[0092] Furthermore, for main bearings whose lubrication anomalies have been verified, a first risk value and a first maintenance measure are generated based on the temperature residual distribution. The risk value corresponding to the temperature residual distribution reflects the degree of the main bearing lubrication anomaly and possible maintenance measures. Simultaneously, a second risk value and a second maintenance measure are generated based on the thermal comparison diagram. The risk value corresponding to the thermal comparison diagram reflects the degree of the main bearing lubrication anomaly and possible maintenance measures. Furthermore, a third risk value and a third maintenance measure are generated based on the wind power curve comparison diagram. The risk value corresponding to the wind power curve comparison diagram reflects the degree of the main bearing lubrication anomaly and possible maintenance measures.

[0093] Furthermore, because the risks represented by the first risk value, the second risk value, and the third risk value are different, it is necessary to determine an overall risk value based on the three. At the same time, the maintenance methods represented by the first maintenance measure, the second maintenance measure, and the third maintenance measure are also different, and it is also necessary to determine an overall reference maintenance measure based on the 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 b1, comparing the first risk value, the second risk value, and the third risk value, and determining the maximum value as the risk value;

[0095] Step b2: performing a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and obtaining a union operation result as the reference maintenance measure.

[0096] Furthermore, the first, second, and third risk values ​​each represent different levels of risk, with larger values ​​indicating greater risk. Therefore, the first, second, and third risk values ​​can be compared to determine the largest overall risk value. The first, second, and third maintenance measures represent the repair methods for possible faults. To ensure comprehensiveness, the first, second, and third maintenance measures are combined to form a union, resulting in a comprehensive reference maintenance measure.

[0097] This embodiment establishes a verification mechanism for main bearing lubrication anomalies based on temperature residual distribution, thermal comparison diagrams, and wind power curve comparison diagrams, thereby enhancing the accuracy of the predictive detection model. Furthermore, for confirmed main bearing lubrication anomalies, an overall risk value is determined using these data to accurately reflect the risk of the main bearing experiencing lubrication anomalies. Comprehensive reference maintenance measures are then determined for maintenance personnel to quickly eliminate the anomaly and proceed with repairs.

[0098] Furthermore, based on the first, second or third embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention, a fourth embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system of the present invention is proposed.

[0099] The fourth embodiment of the early warning method for a main bearing of a wind turbine in a wind power generation system differs from the first, second, or third embodiments of the early warning method for a main bearing of a wind turbine in a wind power generation system in that the steps of respectively generating a first risk value, a second risk value, and a third risk value based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram include:

[0100] Step S321: Compare the deviation value with each first preset numerical interval to determine the first target numerical interval in which the deviation value is located, and determine the first risk value based on the first preset risk value corresponding to the first target numerical interval;

[0101] Step S322, determining an average difference between the temperature value of the spindle and the reference temperature value, comparing the average difference with each second preset numerical interval, determining a second target numerical interval within which the average difference falls, and determining a second risk value based on a second preset risk value corresponding to the second target numerical interval;

[0102] Step S323: determine the average deviation of the wind speed power curve relative to the reference wind speed power curve, and compare the average deviation with each third preset numerical interval to determine the third target numerical interval in which the average deviation is located, and determine the third risk value based on the third preset risk value corresponding to the third target numerical interval.

[0103] After verifying that the main bearing does have lubrication anomalies, this embodiment generates risk values ​​that reflect the degree of impact of the main bearing lubrication anomaly on the normal operation of the wind turbine based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram. Among them, for the temperature residual distribution, the greater the deviation between the baseline value and the residual expected value, the higher the degree of anomaly in the main bearing lubrication. For the thermal comparison diagram, the greater the difference between the main shaft temperature value and the reference temperature value, the higher the degree of anomaly in the main bearing lubrication. For the wind power curve comparison diagram, the greater the deviation of the wind speed power curve from the reference wind speed power curve, the higher the degree of anomaly in the main bearing lubrication.

[0104] Furthermore, for the temperature residual distribution, a plurality of first preset numerical intervals are pre-set, and different first preset numerical intervals correspond to different first preset risk values, reflecting different risk levels. The larger the boundary value of the first preset numerical interval, the larger the corresponding first preset risk value, and the higher the risk level represented. The deviation value between the baseline value and the residual expected value in the temperature residual distribution is compared with each first preset numerical interval, and the first preset numerical interval in which the deviation value falls is determined as the first target numerical interval. Then, based on the correspondence between each first preset numerical interval and each first preset risk value, the first preset risk value corresponding to the first target numerical interval is determined. The first preset risk value is the first risk value corresponding to the temperature residual distribution, indicating the risk level of the main bearing with lubrication abnormality reflected by the temperature residual distribution.

[0105] Furthermore, since the thermal comparison diagram contains multiple fan main shaft temperature values, i.e., multiple reference temperature values, it is possible that the difference between the main shaft temperature value and the reference temperature value may also be multiple. To accurately reflect the magnitude of these differences, the multiple differences are averaged, and this average is used as the average difference between the main shaft temperature value and the reference temperature value. Similarly, the thermal comparison diagram is pre-set with multiple second preset numerical intervals. Different second preset numerical intervals correspond to different second preset risk values, reflecting different levels of risk. Larger boundary values ​​in the second preset numerical intervals correspond to larger second preset risk values, indicating a higher level of risk. The average difference between the main shaft temperature value and the reference temperature value is compared with each second preset numerical interval, and the second preset numerical interval within which the average difference falls is determined as the second target numerical interval. Based on the correspondence between each second preset numerical interval and each second preset risk value, the second preset risk value corresponding to the second target numerical interval is determined. This second preset risk value is then the second risk value corresponding to the thermal comparison diagram, indicating the risk level of the main bearing experiencing lubrication abnormality as reflected by the thermal comparison diagram.

[0106] Similarly, for the wind power curve comparison chart, there are power deviation values ​​between the wind speed power curve and the reference wind speed power curve, including multiple wind speed points, such as the power deviation value at a wind speed of 5 meters per second, the power deviation value at a wind speed of 10 meters per second, etc. In order to accurately reflect the size of the deviation, multiple wind speed points are selected, and the power deviation of each wind speed point is obtained. Then, a mean operation is performed between each power deviation, and the calculation result is obtained as the average deviation size of the wind speed power curve relative to the reference wind speed power curve. In addition, for the wind power curve comparison chart, multiple third preset numerical intervals are pre-set, and different third preset numerical intervals correspond to different third preset risk values, reflecting different risk levels. The larger the boundary value of the third preset numerical interval, the larger the corresponding third preset risk value, indicating a higher risk level. The average deviation size of the wind speed power curve relative to the reference wind speed power curve is compared with each third preset numerical interval, and the third preset numerical interval in which the average deviation size falls is determined as the third target numerical interval. Then, based on the correspondence between each third preset numerical interval and each third preset risk value, the third preset risk value corresponding to the third target numerical interval is determined. The third preset risk value is the third risk value corresponding to the wind power curve comparison chart, indicating the risk level of the main bearing with lubrication abnormality as reflected by the wind power curve comparison chart.

[0107] This embodiment determines respective risk values ​​for the temperature residual distribution, thermal comparison diagram and wind power curve comparison diagram, indicating the high and low risks of the main bearing with lubrication abnormality as reflected by the temperature residual distribution, thermal comparison diagram and wind power curve comparison diagram, respectively. This makes the risk value finally determined by the three more accurate, accurately reflects the level of risk, and thus improves the accuracy of the main bearing lubrication abnormality warning.

[0108] In addition, an embodiment of the present invention also provides a wind power generation system. Figure 9 , Figure 9 It is a structural diagram of the equipment hardware operating environment involved in the embodiment of the wind power generation system of the present invention.

[0109] like Figure 9As shown, 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. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0110] Those skilled in the art will understand that Figure 9 The hardware structure of the wind power generation system shown in the figure does not constitute a limitation on the wind power generation system, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0111] like Figure 9 As shown, the memory 1005, which is 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, and supports the operation of the network communication module, the user interface module, the control program, and other programs or software. The network communication module is used to manage and control the network interface 1004; and the user interface module is used to manage and control the user interface 1003.

[0112] exist Figure 9 In the hardware structure of the wind power generation system shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the control program stored in the memory 1005 and perform the following operations:

[0113] When a main bearing lubrication anomaly is detected in any wind turbine in the wind power generation system based on a preset detection model, a temperature value of the main shaft corresponding to the main bearing lubrication anomaly during the abnormal period is obtained, and a temperature residual distribution of the main shaft and a thermal comparison diagram of the main shaft are generated based on the temperature value;

[0114] Obtaining a power generation value of the generator corresponding to the main bearing lubrication abnormality and a wind speed value collected by an anemometer of a wind turbine where the generator is located, and generating a wind power curve comparison diagram of the wind speed value and the power generation value;

[0115] Determining the risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram;

[0116] Historical warning information corresponding to the main bearing lubrication abnormality is obtained, and the historical warning information, the risk value and the reference maintenance measures are generated into warning information, and a warning of the main bearing lubrication abnormality is performed based on the warning information.

[0117] Furthermore, the temperature value of the spindle includes a front-end temperature value and a rear-end temperature value, and the temperature residual distribution of the spindle includes a front-end temperature residual distribution and a rear-end temperature residual distribution;

[0118] The step of generating the temperature residual distribution of the main shaft according to the temperature value includes:

[0119] Obtaining a front-end sample residual curve generated based on the front-end historical sample data, and a back-end sample residual curve generated based on the back-end historical sample data;

[0120] Obtaining a front-end temperature estimate value and a rear-end temperature estimate value, and generating the front-end temperature value and the front-end temperature estimate value into a front-end residual curve, and generating the rear-end temperature value and the rear-end temperature estimate value into a rear-end residual curve;

[0121] The front-end temperature residual distribution is generated according to the front-end sample residual curve and the front-end residual curve, and the rear-end temperature residual distribution is generated according to the rear-end sample residual curve and the rear-end residual curve.

[0122] Furthermore, the step of determining the risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram includes:

[0123] Verifying the authenticity of the main bearing lubrication anomaly based on the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram;

[0124] If the authenticity of the main bearing lubrication abnormality is verified, a first risk value, a second risk value, and a third risk value are generated respectively according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram, and a first maintenance measure, a second maintenance measure, and a third maintenance measure are generated respectively;

[0125] The risk value and the reference maintenance measure are determined according to 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.

[0126] Furthermore, the step of verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram and the wind power curve comparison diagram includes:

[0127] Obtaining a baseline value and a residual expected value in the temperature residual distribution, generating a deviation value from the baseline value and the residual expected value, and determining whether the deviation value is abnormal;

[0128] Determine whether, in an area of ​​the thermal comparison diagram with the same rotational speed value, the temperature value of the spindle is abnormal relative to the reference temperature value of the thermal comparison diagram;

[0129] Determining whether a wind speed power curve generated by the wind speed value and the generated power value in the wind power curve comparison diagram is abnormal relative to a reference wind speed power curve in the wind power curve comparison diagram;

[0130] If the deviation value is abnormal, and / or the temperature value of the main shaft is abnormal relative to the reference temperature value, and / or the wind speed power curve is abnormal relative to the reference wind speed power curve, then the authenticity of the main bearing lubrication abnormality is determined to be verified.

[0131] Furthermore, 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:

[0132] comparing the first risk value, the second risk value, and the third risk value, and determining a maximum value as the risk value;

[0133] Perform a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and obtain a union operation result as the reference maintenance measure.

[0134] Furthermore, the step of generating a first risk value, a second risk value, and a third risk value respectively according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram includes:

[0135] Comparing the deviation value with each first preset numerical interval to determine a first target numerical interval in which the deviation value is located, and determining the first risk value based on a first preset risk value corresponding to the first target numerical interval;

[0136] determining an average difference between the temperature value of the spindle and the reference temperature value, comparing the average difference with each second preset numerical interval, determining a second target numerical interval within which the average difference lies, and determining a second risk value based on a second preset risk value corresponding to the second target numerical interval;

[0137] Determine the average deviation of the wind speed power curve relative to the reference wind speed power curve, compare the average deviation with each third preset numerical interval, determine the third target numerical interval in which the average deviation lies, and determine the third risk value based on the third preset risk value corresponding to the third target numerical interval.

[0138] Furthermore, after the step of verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram, the processor 1001 may call the control program stored in the memory 1005 and perform the following operations:

[0139] If the authenticity verification of the main bearing lubrication anomaly fails, a prompt message for optimizing the preset detection model is output.

[0140] Furthermore, the reference maintenance measures include at least detecting the operating status of the temperature sensor corresponding to the main shaft, detecting whether the lubricating grease of the fan where the main bearing is located is sufficient, and detecting whether there is any fault in the cooling system of the fan where the main bearing is located.

[0141] The specific implementation of the wind power generation system of the present invention is basically the same as the embodiments of the early warning method for the main bearing of the wind turbine in the above-mentioned wind power generation system, and will not be described in detail here.

[0142] An embodiment of the present invention further provides a storage medium having a control program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for early warning of a main bearing of a wind turbine in a wind power generation system.

[0143] The storage medium of the present invention may be a computer-readable storage medium, and its specific implementation is substantially the same as the embodiments of the above-mentioned early warning method for the main bearing of a wind turbine in a wind power generation system, and will not be described in detail here.

[0144] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the present invention, or directly or indirectly used in other related technical fields, all fall within the protection of the present invention.

Claims

1. A method for early warning of a main bearing of a wind turbine in a wind power generation system, characterized in that: The early warning method includes: When a main bearing lubrication anomaly is detected in any wind turbine in the wind power generation system based on a preset detection model, a temperature value of the main shaft corresponding to the main bearing lubrication anomaly during the abnormal period is obtained, and a temperature residual distribution of the main shaft and a thermal comparison diagram of the main shaft are generated based on the temperature value; Obtaining a power generation value of the generator corresponding to the main bearing lubrication abnormality and a wind speed value collected by an anemometer of a wind turbine where the generator is located, and generating a wind power curve comparison diagram of the wind speed value and the power generation value; Determining the risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram; Acquiring historical warning information corresponding to the main bearing lubrication abnormality, generating warning information from the historical warning information, the risk value, and reference maintenance measures, and issuing a warning of the main bearing lubrication abnormality based on the warning information; The temperature value of the spindle includes a front-end temperature value and a rear-end temperature value, and the temperature residual distribution of the spindle includes a front-end temperature residual distribution and a rear-end temperature residual distribution; The step of generating the temperature residual distribution of the main shaft according to the temperature value includes: Obtaining a front-end sample residual curve generated based on the front-end historical sample data, and a back-end sample residual curve generated based on the back-end historical sample data; Obtaining a front-end temperature estimate value and a rear-end temperature estimate value, and generating the front-end temperature value and the front-end temperature estimate value into a front-end residual curve, and generating the rear-end temperature value and the rear-end temperature estimate value into a rear-end residual curve; Generating the front-end temperature residual distribution according to the front-end sample residual curve and the front-end residual curve, and generating the rear-end temperature residual distribution according to the rear-end sample residual curve and the rear-end residual curve; and determining the risk value and reference maintenance measures corresponding to the main bearing lubrication abnormality according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram, comprising: Verifying the authenticity of the main bearing lubrication anomaly based on the temperature residual distribution, thermal comparison diagram, and wind power curve comparison diagram; If the authenticity of the main bearing lubrication abnormality is verified, a first risk value, a second risk value, and a third risk value are generated respectively according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram, and a first maintenance measure, a second maintenance measure, and a third maintenance measure are generated respectively; The risk value and the reference maintenance measure are determined according to 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.

2. The early warning method according to claim 1, characterized in that: The step of verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram and the wind power curve comparison diagram includes: Obtaining a baseline value and a residual expected value in the temperature residual distribution, generating a deviation value from the baseline value and the residual expected value, and determining whether the deviation value is abnormal; Determine whether, in an area of ​​the thermal comparison diagram with the same rotational speed value, the temperature value of the spindle is abnormal relative to the reference temperature value of the thermal comparison diagram; Determining whether a wind speed power curve generated by the wind speed value and the generated power value in the wind power curve comparison diagram is abnormal relative to a reference wind speed power curve in the wind power curve comparison diagram; If the deviation value is abnormal, and / or the temperature value of the main shaft is abnormal relative to the reference temperature value, and / or the wind speed power curve is abnormal relative to the reference wind speed power curve, then the authenticity of the main bearing lubrication abnormality is determined to be verified.

3. The early warning method according to claim 1, characterized in that: The step of determining the risk value and the reference maintenance measure according to 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, and determining a maximum value as the risk value; Perform a union operation on the first maintenance measure, the second maintenance measure, and the third maintenance measure, and obtain a union operation result as the reference maintenance measure.

4. The early warning method according to claim 2, characterized in that: The step of generating a first risk value, a second risk value, and a third risk value respectively according to the temperature residual distribution, the thermal comparison diagram, and the wind power curve comparison diagram comprises: Comparing the deviation value with each first preset numerical interval to determine a first target numerical interval in which the deviation value is located, and determining the first risk value based on a first preset risk value corresponding to the first target numerical interval; determining an average difference between the temperature value of the spindle and the reference temperature value, comparing the average difference with each second preset numerical interval, determining a second target numerical interval within which the average difference lies, and determining a second risk value based on a second preset risk value corresponding to the second target numerical interval; Determine the average deviation of the wind speed power curve relative to the reference wind speed power curve, compare the average deviation with each third preset numerical interval, determine the third target numerical interval in which the average deviation lies, and determine the third risk value based on the third preset risk value corresponding to the third target numerical interval.

5. The early warning method according to claim 1, characterized in that: After the step of verifying the authenticity of the main bearing lubrication abnormality based on the temperature residual distribution, the thermal comparison diagram and the wind power curve comparison diagram, the following steps are performed: If the authenticity verification of the main bearing lubrication anomaly fails, a prompt message for optimizing the preset detection model is output.

6. The early warning method according to any one of claims 1 to 5, characterized in that: The reference maintenance measures include at least detecting the operating status of the temperature sensor corresponding to the main shaft, detecting whether the lubricating grease of the fan where the main bearing is located is sufficient, and detecting whether there is any fault in the cooling system of the fan where the main bearing is located.

7. A wind power generation system, characterized in that: The wind power generation system further includes: a memory, a processor, a communication bus, and a control program stored in the memory: The communication bus is used to realize the connection and communication between the processor and the memory; The processor is configured to execute the control program to implement the steps of the early warning method for a main bearing of a wind turbine in a wind power generation system according to any one of claims 1 to 6.

8. A storage medium, characterized in that: The storage medium stores a control program, which, when executed by the processor, implements the steps of the early warning method for a main bearing of a wind turbine in a wind power generation system according to any one of claims 1 to 6.

Images