Bearing health intelligent management system

Abstract

The invention discloses a bearing health intelligent management system which comprises an intelligent control system and further comprises an oiling unit, a grease suction unit and a monitoring system which are controlled by the intelligent control system in real time, and the monitoring system detects grease components in real time and monitors health indexes of a wind turbine generator set in real time by arranging corresponding sensors at monitoring points; the grease suction unit is further connected with a waste oil collection unit, the intelligent management system further comprises a cloud server, and the cloud server comprises an AI calculation module, an AI cross analysis module and an AI risk analysis module; the system performs iterative operation and self-learning according to monitoring data, establishes a regression function, performs predictive analysis, decides fat liquoring and fat suction, alarms and the like, forms a personalized control strategy more suitable for the wind turbine generator, performs health monitoring on the operation condition of the bearing under the unattended condition, makes an implementation decision and ensures the healthy operation of the bearing.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and particularly relates to an intelligent management system for bearing health based on data learning. Background Art

[0002] In the field of wind power generation, bearings are important components used to support the rotor and shaft of a generator, and at the same time bear the inertia and wind load generated by the rotation of the blades to ensure the normal operation of the generator set. During the operation of the bearing, sufficient lubrication is required. The grease can ensure the surface finish of the bearing raceway during the operation of the bearing, reduce the friction coefficient and wear, improve the working stability, and effectively extend the service life.

[0003] The component state of a wind power bearing during its service life has an important impact on the wind turbine generator set at both the system level and the whole machine level. Moreover, since the bearing is hidden inside, due to its unclear fault phenomenon and long troubleshooting period for the cause of the fault, it has a high dependence on expert experience, resulting in a long mechanical fault operation and maintenance cycle for the wind power bearing, affecting the normal operation of the wind turbine generator set and directly affecting the economic benefits of the wind farm.

[0004] To solve the above problems, the current traditional method is to monitor relevant data of the bearing through sensors, such as data of wind wheel speed, nacelle vibration, oil pressure, oil temperature, etc., and then perform corresponding maintenance after the data is abnormal.

[0005] It has the following problems: 1. The fault factors of the bearing are greatly affected by the lubricating oil, such as impurities and deterioration. There is currently no solution to monitor the quality of the lubricating oil during use and then manage the bearing health; 2. After the data is abnormal, even if maintenance is carried out, due to the fact that many wind turbines are assembled in remote mountainous areas, the time interval is long, affecting the power generation efficiency; 3. The bearing lacks dynamic health lubrication management, lacks effective cooperation between grease addition and grease suction, and it is difficult to automatically lubricate the bearings of different wind turbines; 4. The bearing state cannot be grasped in real time. Summary of the Invention

[0006] The present invention provides an intelligent management system for bearing health based on data learning, which iteratively calculates and self-learns according to the monitored data, establishes a regression function, conducts predictive analysis, makes decisions on grease addition, grease suction, alarm, etc., forms a personalized control strategy more suitable for the wind turbine generator set, monitors the operation status of the bearing and makes implementation decisions under unattended conditions to ensure the healthy operation of the bearing, so as to solve the problems raised in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution: A bearing health intelligent management system based on data learning, including an intelligent control system, further including a grease adding unit and a grease sucking unit controlled by the intelligent control system. The intelligent control system performs grease adding, grease sucking, and alarm actions according to the operating health condition of the bearing to ensure the healthy operation of the bearing;

[0008] The grease adding unit fills grease into the bearing cavity under the control of the intelligent control system, and the intelligent control system controls the adding amount of the grease adding unit according to the system feedback data;

[0009] The grease sucking unit sucks waste grease out of the bearing lubrication cavity under the control of the intelligent control system.

[0010] Preferably, the grease sucking unit is further connected to a waste oil collection unit for collecting waste grease; the intelligent control system further includes a monitoring system, and the monitoring system includes a grease component detection system connected to the waste grease.

[0011] Preferably, the monitoring system further includes a temperature monitoring system and a vibration monitoring system distributed on the bearing.

[0012] Preferably, the grease adding unit is further connected to a cleaning oil, and under the control of the intelligent control system, the grease cavity is cleaned. When cleaning, the intelligent control system controls the grease sucking unit to gradually discharge waste oil.

[0013] Preferably, the grease adding unit is a high-pressure plunger lubrication pump.

[0014] Preferably, the grease sucking unit is an electric grease sucker, which cooperates with the grease adding unit, and the grease adding and grease sucking actions cooperate to complete the control of the grease stock balance in the lubrication cavity.

[0015] Preferably, the intelligent management system further includes a cloud server, and the cloud server includes an AI calculation module, which connects to the monitoring system to establish a regression function of the wind turbine bearing and lubricating oil according to the feedback bearing and lubricating oil data; predicts and analyzes the states of the wind turbine bearing and lubricating oil according to the data feedback, monitors the operating condition of the bearing, and makes implementation decisions.

[0016] Preferably, when the cloud server establishes a regression function, it further includes an AI cross-analysis module for performing cross-regression analysis. The AI cross-analysis module establishes the correlation analysis between multiple variables. When predicting different data, according to the correlation function, based on other correlated data, this data is predicted. Based on the comparison and analysis between the predicted data and the actual data, corresponding weighting factors are established according to the error situation, and weighted fusion regression prediction of multiple groups of data is performed. When the AI cross-analysis module establishes a regression function, it further includes a regression function of the wind turbine bearing state regarding the lubricating oil state, performs fusion prediction, realizes knowing the bearing state, predicts the bearing state after adding finished grease at the same time, corrects the actual data and the predicted data, and corrects the regression function.

[0017] Preferably, when the cloud server calculates and performs data iterative operations and self-learning, it further includes an AI risk analysis module. By the AI risk analysis module, corresponding risk thresholds for grease addition, oil suction, and grease metal impurities are established. When performing prediction analysis through the bearing and lubricating oil state prediction regression function, based on the risk thresholds, the health state of the wind turbine is known.

[0018] Preferably, the cloud server is also connected to a terminal for interconnection and interoperability to achieve real-time monitoring of the state of the wind turbine.

[0019] Compared with the prior art, the beneficial effects of the present invention are:

[0020] 1. The intelligent control system real-time controls the grease adding unit and the oil suction unit, makes decisions and implements interventions in a timely manner according to the running health condition of the bearing, such as grease adding, oil suction, alarming, etc., to ensure the healthy operation of the bearing.

[0021] 2. While monitoring the bearing state, it also real-time monitors the density of grease metal impurities and the color of the grease in the bearing, and feeds back the state of the grease in the bearing.

[0022] 3. The grease adding unit and the oil suction unit perform synchronous operations, suck the grease while balancing the grease inventory, and maintain the dynamic management of the grease in the lubrication cavity, which can avoid accelerated wear caused by the lack of lubricating oil in the lubrication cavity when discharging the grease.

[0023] 4. According to the data feedback, perform prediction analysis on the bearing and lubricating oil states of the wind turbine, make decisions on grease adding, oil suction, alarming, etc., form a personalized control strategy more suitable for the wind turbine, and under the condition of unattended operation, perform health monitoring on the running condition of the bearing and make implementation decisions to ensure the healthy operation of the bearing.

[0024] 5. When predicting different data, establish a correlation function, establish corresponding weighting factors according to the error situation, and perform weighted fusion regression prediction of multiple groups of data.

[0025] 6. Establish a regression function of the wind turbine bearing status with respect to the lubricating oil status, so as to predict the bearing status after adding finished grease while knowing the bearing status.

[0026] 7. Through health management and health prediction, it is convenient to accurately know the health status of the wind turbine, provide subsequent replacement and maintenance instructions, and facilitate early operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic structural diagram of the system of the present invention;

[0028] Figure 2 It is a schematic structural diagram of the grease adding unit of the present invention;

[0029] Figure 3 It is a schematic structural diagram of the oil suction unit of the present invention;

[0030] Figure 4 It is a schematic structural diagram of the cloud server of the present invention;

[0031] Figure 5 It is a schematic structural diagram of the cloud server and terminal of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] Please refer to Figure 1 , the present invention provides an intelligent bearing health management system based on data learning, including an intelligent control system, and also including a grease adding unit and an oil suction unit controlled by the intelligent control system. The intelligent control system makes decisions and implements interventions in a timely manner according to the running health condition of the bearing, such as adding grease, sucking oil, alarming, etc., to ensure the healthy operation of the bearing;

[0034] The grease adding unit fills grease into the bearing cavity under the control of the intelligent control system, and the intelligent control system controls the adding amount of the grease adding unit according to the system feedback data;

[0035] The oil suction unit sucks the waste oil out of the bearing lubrication cavity under the control of the intelligent control system. The grease adding port and the oil suction port of the bearing lubrication cavity are opposite in position, so as to realize synchronous oil change when the grease adding unit and the oil suction unit work synchronously.

[0036] Please refer to Figure 1, the fat suction unit is also connected with a waste oil collection unit for collecting waste grease; the intelligent control system also includes a monitoring system, and the monitoring system also includes a grease component detection system connected to the waste grease, and may also include a color recognition system, which can monitor the density of metal impurities and the color of the grease in the bearing in real time by arranging corresponding sensors at the monitoring points, and feed back the grease state in the bearing.

[0037] Please refer to Figure 1 , the monitoring system includes conventional monitoring systems such as a temperature monitoring system and a vibration monitoring system distributed in the bearing lubrication cavity. By arranging corresponding sensors at the monitoring points, important indicators of the wind turbine, such as vibration and bearing temperature, can be monitored in real time, and the state of the wind turbine bearing can be fed back.

[0038] Please refer to Figure 2 , the grease adding unit is a high-pressure plunger lubrication pump, such as an integrated distributor lubrication pump, which integrates the lubrication pump and the distributor. The lubrication pump selects a pressure plate type lubrication pump, such as a multi-pump barrel lubrication pump disclosed in the patent with publication number CN219414370U. The integrated distributor lubrication pump also includes oil pipes and cables for adding finished grease to each lubrication point and can be controlled separately to maintain continuous lubrication of the lubrication cavity of the lubrication point.

[0039] Please refer to Figure 1 , the grease adding unit is also connected with cleaning oil. According to the actual situation, the corresponding brand and model of cleaning oil are selected. Under the control of the intelligent control system, the intelligent control system judges the adding amount of the cleaning oil, cleans the grease cavity, and at the same time, the bearing continues to work during the whole cleaning process, that is, the cleaning oil is added gradually, and at the same time, the intelligent control system controls the fat suction unit to gradually discharge waste oil to realize synchronous oil change.

[0040] Please refer to Figure 3 , the fat suction unit is an electric fat suction device, such as an electric fat suction device for sucking bearing grease disclosed in the patent with publication number CN222066974U. It can cooperate with the pressure plate type lubrication pump, and both are driven by an electric motor to drive an eccentric wheel to complete the coordination of grease adding and fat suction actions, realize oil change without stopping the machine, and minimize the interference to the bearing operation; and many wind turbines are assembled in remote mountainous areas, and the driving mode of the electric motor driving the eccentric wheel can meet the stable operation of long-term grease adding and fat suction.

[0041] The grease adding unit and the fat suction unit perform synchronous operations. During the operation, a pressure sensor is used to control the balance of the grease storage in the lubrication cavity, suck the grease under the balanced pressure, and maintain the dynamic management of the grease in the lubrication cavity, so as to avoid large pressure changes in the lubrication cavity when discharging the grease and accelerated wear caused by lack of lubricating oil.

[0042] Please refer to Figure 4, the intelligent management system further includes a cloud server. The cloud server includes an AI computing module that detects and stores data and uploads it to the cloud server via a 5G network. Its connection monitoring system iteratively calculates and self-learns based on the feedback bearing and lubricant data to establish regression functions for the wind turbine bearings and lubricants. Specifically, it is a regression function of the wind turbine bearing status regarding data such as vibration and bearing temperature, and a regression function of the lubricant status regarding the density of grease metal impurities and the color of the grease; it predicts and analyzes the status of the wind turbine bearings and lubricants based on the data feedback, makes decisions on greasing, degreasing, alarming, etc., forms a personalized control strategy more suitable for the wind turbine, monitors the health of the bearing operation and makes implementation decisions in the case of unattended operation to ensure the healthy operation of the bearing.

[0043] Please refer to Figure 4 , when the cloud server establishes a regression function, it also includes an AI cross-analysis module for cross-regression analysis to establish the correlation analysis between multiple variables, including the correlation function between bearing temperature data and the density of grease metal impurities in the bearing, etc. When predicting different data, based on the correlation function, this data is predicted based on other correlated data, and a comparative analysis is performed between the predicted data and the actual data. According to the error situation, corresponding weighting factors are established for weighted fusion regression prediction of multiple groups of data; when the AI cross-analysis module establishes a regression function, it also includes a regression function of the wind turbine bearing status regarding the lubricant status for fusion prediction, so as to predict the bearing status after adding finished grease while knowing the bearing status, and correct the actual data and the predicted data, and correct the regression function.

[0044] Please refer to Figure 4 , when the cloud server calculates and iteratively operates on data and self-learns, it also includes an AI risk analysis module. The AI risk analysis module establishes corresponding risk thresholds for grease addition, degreasing, and grease metal impurities. When performing predictive analysis through the bearing and lubricant status prediction regression function, since many wind turbines are assembled in remote mountainous areas, through health management and health prediction, based on the risk thresholds, it is convenient to accurately know the health status of the wind turbines, provide subsequent replacement and repair instructions, and facilitate early operation and maintenance.

[0045] Please refer to Figure 5 , the cloud server is also connected to terminals, including terminals such as computers, mobile phones, and tablets, for interconnection and interoperability to achieve real-time monitoring of the status of the wind turbines.

[0046] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent management system for bearing health, including an intelligent control system, characterized in that, It also includes a grease adding unit and a grease sucking unit controlled by an intelligent control system. The intelligent control system performs grease adding, grease sucking, and alarm actions according to the operating health condition of the bearing to ensure the healthy operation of the bearing; The grease adding unit, controlled by the intelligent control system, fills grease into the bearing cavity, and the intelligent control system controls the adding amount of the grease adding unit according to the system feedback data; The grease sucking unit, controlled by the intelligent control system, sucks waste grease out of the bearing lubrication cavity.

2. The intelligent bearing health management system according to claim 1, wherein The grease sucking unit is also connected with a waste oil collection unit for collecting waste grease; the intelligent control system also includes a monitoring system, and the monitoring system includes a grease component detection system connected to the waste grease.

3. The intelligent bearing health management system according to claim 2, characterized in that, The monitoring system also includes a temperature monitoring system and a vibration monitoring system distributed on the bearing.

4. The intelligent management system for bearing health according to claim 1, characterized in that, The grease adding unit is also connected with cleaning oil. Controlled by the intelligent control system, the grease cavity is cleaned, and when cleaning, the intelligent control system controls the grease sucking unit to gradually discharge waste oil.

5. The intelligent management system for bearing health according to claim 4, characterized in that, The grease adding unit is a high-pressure plunger lubrication pump.

6. An intelligent bearing health management system according to claim 1, characterized in that The grease sucking unit is an electric grease sucker, which cooperates with the grease adding unit. The grease adding and grease sucking actions cooperate to complete the control of the grease stock balance in the lubrication cavity.

7. The intelligent management system for bearing health according to claim 1, characterized in that The intelligent management system also includes a cloud server. The cloud server includes an AI computing module, which is connected to the monitoring system. According to the feedback data of the bearing and lubricating oil, a regression function of the wind turbine bearing and lubricating oil is established; according to the data feedback, the state of the wind turbine bearing and lubricating oil is predicted and analyzed, the operating condition of the bearing is health monitored, and implementation decisions are made.

8. An intelligent bearing health management system according to claim 7, characterized in that, When the cloud server establishes a regression function, it also includes an AI cross-analysis module for cross-regression analysis. The AI cross-analysis module establishes the correlation analysis between multiple variables. When predicting different data, according to the correlation function, based on other correlated data, this data is predicted. Based on the comparison analysis of the predicted data and the actual data, corresponding weighting factors are established according to the error situation, and weighted fusion regression prediction of multiple groups of data is carried out; when the AI cross-analysis module establishes a regression function, it also includes a regression function of the wind turbine bearing state with respect to the lubricating oil state for fusion prediction, so as to know the bearing state while predicting the bearing state after adding finished grease, and correct the actual data and the predicted data, and correct the regression function.

9. The intelligent bearing health management system according to claim 8, wherein, When the cloud server calculates and performs data iterative operation and self-learning, it also includes an AI risk analysis module. By establishing the corresponding risk thresholds for grease addition, grease sucking, and grease metal impurities through the AI risk analysis module, when predicting and analyzing through the bearing and lubricating oil state prediction regression function, based on the risk thresholds, the health state of the wind turbine is known.

10. The intelligent bearing health management system according to claim 6, characterized in that, The system is also connected with a terminal for interconnection and intercommunication to achieve real-time mastery of the state of the wind turbine.

Images