Remote monitoring and routing inspection side station system for wind generating set

Abstract

The invention discloses a remote monitoring and routing inspection side station system for a wind generating set, and relates to the technical field of wind power generation monitoring system equipment. The remote monitoring and routing inspection side station system for the wind generating set comprises a data acquisition unit, a state analysis unit, a health analysis unit, a fatigue analysis unit and a processing unit, analyzes the running state of the wind generating set step by step, and realizes abnormal recognition, health assessment, fatigue judgment and power-off control; the multi-layer nested operation evaluation system with the power response index, the vibration temperature response index, the fusion health state index and the gearbox composite fatigue index as the core is constructed, so that the problems that in a traditional system, the state judgment granularity is coarse, the reaction mechanism is single, and fault logic is not closed are effectively solved, fault recognition is more sensitive, and the system reliability is improved. The response is more hierarchical and controllable, and the intelligent diagnosis capability and the safety control level of the remote monitoring system of the wind turbine generator are remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation monitoring system equipment, and in particular to a wind power generator set remote monitoring and inspection station system. Background Art

[0002] With the rapid development of wind power generation technology, large wind turbines have been widely deployed in coastal, mountainous and offshore areas with abundant wind resources. Wind turbines have complex structures and changeable operating environments. Their core components such as blades, main shafts, gearboxes, generators, bearings, etc. are under high load, high fatigue, severe vibration and complex climatic conditions for a long time, and are prone to abnormal operation such as wear, aging, looseness, cracks, etc. In order to ensure the operating safety and power generation efficiency of wind turbines, remote monitoring systems have emerged to achieve real-time collection, remote viewing, alarm response and preliminary diagnosis of wind turbine operating status.

[0003] In recent years, patrol station systems, as an extension of remote monitoring, have gradually been applied to unmanned wind farms to achieve auxiliary diagnosis and intelligent decision-making support for the operating status of key components. Existing monitoring systems mostly rely on SCADA platforms to collect basic signals such as voltage, current, wind speed, and power. Some systems deploy multi-modal sensors such as images, infrared, and sound to achieve visual perception of the external status of the unit. However, with the increase in the size and intelligence of the units, traditional parameter monitoring and abnormal alarms alone can no longer meet the actual operation and maintenance needs of fatigue evolution trends, health status changes, and core risk positioning of key components under complex working conditions. Therefore, how to realize intelligent patrol, health assessment, and accurate early warning of wind turbines based on multi-source operation data has become an important technical issue to be solved in the field of wind power operation and maintenance.

[0004] Prior art, such as the invention patent application with announcement number: CN115693926A, discloses a remote monitoring and inspection station system for wind turbines, including a host control platform, a monitoring display terminal and a data acquisition module. The host control platform stores critical values ​​of operating parameter data. The host control platform can compare the received operating data with the critical value. The critical value is input and stored inside the host control platform when in use. The critical value is the data value of the equipment when it is working normally, which is obtained based on the original detection data. When the detected data exceeds the critical value, the equipment fails. The data acquisition module includes an external tower warning module, an infrared detection module, a sound detection module and a tower safety detection module. The characteristics of the intelligent patrol system are used to increase the patrol depth, expand the patrol range, strengthen background management, and unify the background; considering the analysis capabilities of the intelligent patrol system, etc., strengthen data analysis and management, strengthen system intelligent analysis and background analysis, and the system can realize global camera patrol scheduling.

[0005] Based on the above solution, it is found that the limitations of the existing technology include at least the following problems: the current remote monitoring system of wind turbines generally focuses on the intuitive monitoring of external images, sounds or surface operating data. Although an alarm signal can be issued when an obvious abnormality occurs, it lacks the overall ability to conduct multi-level step-by-step analysis based on core operating parameters such as power response and bearing temperature rise. Especially when facing early potential failures or progressive fatigue processes, there is a lack of clear response paths and judgment logic, and technical shortcomings of abnormal signals are prone to occur, resulting in false alarms, missed judgments or delayed responses, which is not conducive to the accurate perception and dynamic closed-loop control of the wind turbine operating status. Summary of the invention

[0006] In view of the deficiencies of the prior art, the present invention provides a remote monitoring and inspection station system for a wind turbine generator set, which solves the problem in the prior art of lacking an intelligent step-by-step analysis and risk judgment mechanism for the internal state of a wind turbine generator set.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a remote monitoring and inspection station system for wind turbines, comprising: a data acquisition unit, used to acquire power status data and bearing status data of the wind turbine, and analyze the power response index and vibration-temperature response index of the wind turbine; a status analysis unit, used to judge and analyze the power response index and vibration-temperature response index of the wind turbine with the preset power response evaluation interval and vibration-temperature response evaluation interval respectively; a health analysis unit, used to analyze the fused health status index of the wind turbine when the power response index and vibration-temperature response index of the wind turbine are abnormal, and compare them with the preset health evaluation interval A judgment analysis is performed. If the fusion health status index of the wind turbine is within the preset health assessment interval, no measures are taken. A fatigue analysis unit is used to analyze the composite fatigue index of the gearbox of the wind turbine when the fusion health status index of the wind turbine is outside the preset health assessment interval, and to perform a judgment analysis with the preset fatigue assessment interval. If the composite fatigue index of the gearbox of the wind turbine is within the preset fatigue assessment interval, a health abnormality warning is sent. A processing unit is used to execute power-off measures on the wind turbine and send a gearbox abnormality alarm when the composite fatigue index of the gearbox of the wind turbine is outside the preset fatigue assessment interval.

[0008] Furthermore, the power status data includes actual output power and rated output power, and the bearing status data includes current bearing temperature value and set bearing temperature value.

[0009] Further, the specific steps to obtain the power response index of the wind turbine are as follows: Obtain the regional wind speed value within the set area of the wind turbine; comprehensively analyze the actual output power and rated output power of the wind turbine in combination with the regional wind speed value within the set area of the wind turbine to obtain the power response index of the wind turbine.

[0010] Further, the specific steps to obtain the vibration-temperature response index of the wind turbine are as follows: Obtain the maximum allowable temperature rise of the bearing and the vibration acceleration index of the wind turbine; comprehensively analyze the current temperature value of the bearing and the rated temperature value of the bearing of the wind turbine in combination with the maximum allowable temperature rise of the bearing and the vibration acceleration index of the wind turbine to obtain the vibration-temperature response index of the wind turbine.

[0011] Further, the specific steps to obtain the vibration acceleration index of the wind turbine are as follows: Obtain the current vibration acceleration values of several vibrating components of the wind turbine; comprehensively analyze the current vibration acceleration values of several vibrating components of the wind turbine to obtain the vibration acceleration index of the wind turbine.

[0012] Further, the specific steps to analyze the integrated health status index of the wind turbine are as follows: Obtain the rated wind speed value of the wind turbine; respectively input the actual output power, rated output power, vibration acceleration index, rated wind speed value, and regional wind speed value within the set area of the wind turbine into a preset health analysis model for health analysis to obtain the integrated health status index of the wind turbine.

[0013] Further, the specific health analysis model is as follows: Among them, FjK is the integrated health status index of the wind turbine, SsC is the actual output power of the wind turbine, δ 1 is the power influence coefficient stored in the database, QfS is the regional wind speed value within the set area of the wind turbine, EdF is the rated wind speed value of the wind turbine, δ 2 is the wind speed influence coefficient stored in the database, ZdJ is the vibration acceleration index of the wind turbine, α 1 is the vibration response coefficient stored in the database, EsC is the rated output power of the wind turbine, α 2 is the vibration amplification coefficient stored in the database.

[0014] Further, the specific steps for analyzing the composite fatigue index of the gearbox of a wind turbine are as follows: Obtain the oil temperature value inside the gearbox of the wind turbine, the oil temperature reference set, the rotational speed comprehensive index, and the rotational speed reference index. The oil temperature reference set includes a first oil temperature threshold and a second oil temperature threshold; input the actual output power, rated output power, oil temperature value inside the gearbox, oil temperature reference set, rotational speed comprehensive index, and rotational speed reference index of the wind turbine into a preset fatigue analysis model for fatigue analysis to obtain the composite fatigue index of the gearbox of the wind turbine.

[0015] Further, the specific steps for obtaining the rotational speed comprehensive index of the wind turbine are as follows: Obtain the main shaft rotational speed value and the generator rotational speed value of the wind turbine; perform a comprehensive analysis on the main shaft rotational speed value and the generator rotational speed value of the wind turbine to obtain the rotational speed comprehensive index of the wind turbine.

[0016] Further, the fatigue analysis model is specifically as follows: Where CpL is the composite fatigue index of the gearbox of the wind turbine, YwZ is the oil temperature value inside the gearbox of the wind turbine, λ 1 is the low-temperature secondary thermal wear coefficient stored in the database, λ 2 is the low-temperature linear thermal wear coefficient stored in the database, χ is the low-temperature basic offset coefficient stored in the database, ZzH is the rotational speed comprehensive index of the wind turbine, ZcD is the rotational speed reference index of the wind turbine, ε is the rotational speed coupling coefficient stored in the database, YyW is the first oil temperature threshold of the wind turbine, ξ 1 is the medium-temperature tertiary thermal wear coefficient stored in the database, ξ 2 is the medium-temperature secondary thermal wear coefficient stored in the database, EyW is the second oil temperature threshold of the wind turbine, θ 1 is the high-temperature burst benchmark coefficient stored in the database, e is the natural constant, θ 2 is the high-temperature exponential growth coefficient stored in the database, SsC is the actual output power of the wind turbine, EsC is the rated output power of the wind turbine, θ 3 is the high-temperature load amplification coefficient stored in the database.

[0017] The present invention has the following beneficial effects:

[0018] (1) The remote monitoring and inspection on-site system for wind turbines constructs a multi-layer nested operation evaluation system with the power response index, vibration-temperature response index, integrated health status index, and gearbox composite fatigue index as the core. The system first calculates the power response index based on the wind speed and power deviation, and combines the bearing temperature rise and vibration coupling to calculate the vibration-temperature response index. In case of any abnormality, it further integrates multi-source indicators to construct the health status index, forming a medium-level risk judgment. Then, when the health status is abnormal, it leads to the fatigue modeling level, deduces the gearbox composite fatigue index, and triggers corresponding handling. There is a logical dependence and data input inheritance among these indexes, preventing false alarms, missed alarms, and unnecessary shutdowns. This structure effectively solves the problems of coarse state judgment granularity, single reaction mechanism, and non-closed fault logic in traditional systems, making the fault identification more sensitive, the response more hierarchical and controllable, and significantly improving the intelligent diagnosis ability and safety control level of the wind turbine remote monitoring system.

[0019] (2) The remote monitoring and inspection on-site system for wind turbines accurately constructs the power response index and vibration-temperature response index to identify potential risks of wind turbines under complex operating conditions. The power response index establishes an exponential decay relationship through the actual output power, rated output power, and regional wind speed, and introduces the wind speed response coefficient and wind speed adjustment coefficient obtained from training in the database, thus effectively reflecting the dynamic changes in wind energy utilization efficiency. The vibration-temperature response index depicts the non-linear composite relationship between the bearing thermal load and mechanical shock through the current bearing temperature, reference temperature, and allowable temperature rise, combined with the current vibration acceleration index. These two indexes no longer rely on a single threshold judgment, but are classified based on the modeling results and the set evaluation interval, with trendiness, adjustability, and strong interpretability. They can identify micro-abnormalities that are difficult to detect by traditional systems, such as high wind speed and low power or light vibration but fast temperature rise, much earlier, greatly improving the sensitivity of fault precursor identification and serving as an important reinforcement for existing monitoring systems.

[0020] (3) The remote monitoring and inspection on-site system for wind turbine generators realizes refined analysis and automatic power-off protection for core transmission components in high-risk states by establishing a compound fatigue index model for the gearbox. The model takes the oil temperature as the main spindle variable and is divided into three sections: low temperature, medium temperature, and high temperature. The quadratic polynomial, cubic polynomial, and exponential model are respectively used to simulate the fatigue relationship of the oil temperature. At the same time, the rotational speed comprehensive index, power normalization value, and rotational speed amplification coefficient are introduced to describe the exacerbating effect of long-term high-speed operation and high load on fatigue. The coefficients of each section are fitted through historical data and stored in the database, improving the adaptability and accuracy of the model. The system judges the current index level according to the set fatigue evaluation interval. If it enters the high-risk area, the power-off mechanism is immediately triggered through the processing unit, and a gearbox fault alarm is pushed, so as to implement effective isolation before the fatigue reaches the critical damage, avoiding risks such as transmission chain breakage, motor reverse torque, and major shutdown accidents. This structure fills the gap in the traditional system's abnormal detection but without risk evolution reasoning, realizing the full-process linkage control from risk identification to safety disposal.

[0021] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a block diagram of a remote monitoring and inspection on-site system for a wind turbine generator according to the present invention.

[0023] Figure 2 It is a specific step flow chart for obtaining the vibration and temperature response index of a wind turbine generator in a remote monitoring and inspection on-site system for a wind turbine generator according to the present invention.

[0024] Figure 3 It is a current vibration acceleration broken line graph of five vibrating components in a remote monitoring and inspection on-site system for a wind turbine generator according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0025] Please refer to Figure 1, an embodiment of the present invention provides a technical solution: a remote monitoring and inspection on-site system for a wind turbine generator set, including: a data acquisition unit, configured to acquire the power status data and bearing status data of the wind turbine generator set, and analyze the power response index and vibration-temperature response index of the wind turbine generator set; a status analysis unit, configured to respectively perform judgment and analysis on the power response index and vibration-temperature response index of the wind turbine generator set with a preset power response evaluation interval and vibration-temperature response evaluation interval; a health analysis unit, configured to analyze the integrated health status index of the wind turbine generator set when the power response index and vibration-temperature response index of the wind turbine generator set are abnormal (that is, when any one of the power response index and vibration-temperature response index is outside the corresponding evaluation interval), and perform judgment and analysis with a preset health evaluation interval. If the integrated health status index of the wind turbine generator set is within the preset health evaluation interval, no measures are taken; a fatigue analysis unit, configured to analyze the gearbox composite fatigue index of the wind turbine generator set when the integrated health status index of the wind turbine generator set is outside the preset health evaluation interval, and perform judgment and analysis with a preset fatigue evaluation interval. If the gearbox composite fatigue index of the wind turbine generator set is within the preset fatigue evaluation interval, a health abnormality warning is sent to the relevant staff; a processing unit, configured to perform a power-off measure on the wind turbine generator set when the gearbox composite fatigue index of the wind turbine generator set is outside the preset fatigue evaluation interval, and send a gearbox abnormality alarm to the relevant staff.

[0026] The power status data includes the actual output power and the rated output power, and the bearing status data includes the current bearing temperature value and the rated bearing temperature value.

[0027] Among them, the actual output power can be calculated in real time from the current and voltage of the generator.

[0028] The rated output power can be extracted from the technical specification table or equipment nameplate of the wind turbine generator set.

[0029] The current bearing temperature value can be measured and obtained through a temperature sensor.

[0030] The rated bearing temperature value can be extracted from the technical specification table or equipment nameplate of the wind turbine generator set.

[0031] Specifically, the specific steps to obtain the power response index of the wind turbine generator set are as follows: obtain the regional wind speed value within the set area of the wind turbine generator set; comprehensively analyze the actual output power and rated output power of the wind turbine generator set in combination with the regional wind speed value within the set area of the wind turbine generator set to obtain the power response index of the wind turbine generator set.

[0032] Among them, the regional wind speed value can be measured and obtained through a wind speed sensor.

[0033] Among them, the specific formula for calculating the power response index of a wind turbine is as follows: Among them, GxY is the power response index of the wind turbine, SsC is the actual output power of the wind turbine, EsC is the rated output power of the wind turbine, QfS is the regional wind speed value within the set area of the wind turbine, ω 1 is the wind speed response coefficient stored in the database, ω 2 is the wind speed adjustment coefficient stored in the database.

[0034] It should be explained that the wind speed adjustment coefficient ω 1 and the wind speed influence coefficient ω 2 are obtained through the following specific steps: First, based on the actual wind speed values and output power values recorded during the long-term operation of the wind turbine, a historical data comparison model of the relationship between wind speed and power response is established. Then, a non-linear fitting method (such as the least squares method for fitting the tanh curve) is used to train multiple groups of wind speed-power samples, and the response curvature and sensitivity parameters that can best reflect the influence of wind speed changes on power deviation are extracted. Among them, the response amplitude of the fitting curve is ω 2 , and the normalization coefficient of the adjusted wind speed for the calculation index weight is ω 1 . Finally, the results are stored in the database as standard model parameters for subsequent calculation and dynamic evaluation of the real-time power response index.

[0035] In this implementation plan, by introducing the power response index and its calculation method, the quantitative evaluation of the wind energy utilization efficiency of the wind turbine is realized, significantly improving the sensitivity and response accuracy of the system to the operating state of the unit. Compared with the traditional extensive mode that only judges whether it is abnormal based on a single power threshold, the present invention comprehensively considers the relationship among the actual output power, the rated power, and the regional wind speed, constructs a non-linear evaluation model in the form of an index, and can more accurately reflect whether the power output is reasonable under wind speed changes. By introducing the wind speed response coefficient and the wind speed adjustment coefficient, and performing tanh curve fitting training based on historical operation data, the adaptive modeling of the influence of wind speed on the power change trend is realized, making the index not only universal but also have the adjustment ability to match the actual operating conditions of specific units. The finally formed power response index can not only provide accurate judgment when the wind speed changes violently and the operation boundary is blurred, but also serve as an important input variable for integrating the health state index, providing high-quality data support for the subsequent state evaluation and early warning decision-making of the system, and effectively enhancing the intelligent analysis ability of the system in early power anomaly identification and wind energy utilization efficiency fluctuation monitoring.

[0036] Specifically, such as Figure 2As shown in the figure, the specific steps to obtain the vibration-temperature response index of the wind turbine are as follows: Obtain the maximum allowable temperature rise of the bearings of the wind turbine and the vibration acceleration index; comprehensively analyze the current temperature value of the bearings of the wind turbine, the rated temperature value of the bearings, the maximum allowable temperature rise of the bearings of the wind turbine, and the vibration acceleration index to obtain the vibration-temperature response index of the wind turbine.

[0037] Among them, the maximum allowable temperature rise of the bearings can be extracted from the technical specification table or the equipment nameplate of the wind turbine.

[0038] The specific steps to obtain the vibration acceleration index of the wind turbine are as follows: Obtain the current vibration acceleration values of several vibrating components (such as bearings, gearboxes, etc.) of the wind turbine; comprehensively analyze (i.e., average analysis) the current vibration acceleration values of several vibrating components (such as bearings, gearboxes, etc.) of the wind turbine to obtain the vibration acceleration index of the wind turbine.

[0039] Among them, the specific implementation example of obtaining the vibration acceleration index of the wind turbine is as follows. There are the following parameters, including the current vibration acceleration values (m / s 2 ) of five vibrating components (front bearing of the main shaft, rear bearing of the main shaft, input shaft section of the gearbox, output shaft section of the gearbox, fixed support at the generator end). The specific data are shown in Table 1 and Figure 3 as follows:

[0040] Table 1 Example of current vibration acceleration value data of five vibrating components

[0041]

[0042]

[0043] Perform average analysis on the data in Table 1 to obtain that the vibration acceleration index of the wind turbine is approximately:

[0044] 3.814 m / s 2 .

[0045] Among them, the current vibration acceleration value can be measured and obtained through an acceleration sensor.

[0046] Among them, the specific formula for calculating the vibration-temperature response index of the wind turbine is as follows: Among them, ZwY is the vibration-temperature response index of the wind turbine, ZwD is the current temperature value of the bearings of the wind turbine, ZwC is the rated temperature value of the bearings of the wind turbine, ZwR is the maximum allowable temperature rise of the bearings of the wind turbine, ZdJ is the vibration acceleration index of the wind turbine, and β is the vibration adjustment coefficient stored in the database.

[0047] It should be explained that the specific steps for obtaining the vibration amplification coefficient β stored in the database are as follows: Based on the coupling relationship between the bearing temperature and vibration acceleration in the historical operation data of the wind turbine, first select multiple groups of vibration acceleration values and the corresponding bearing temperature rise amplitudes under typical stable working conditions as samples, calculate the influence trend of the vibration intensity on the temperature rise change, then use the exponential or quadratic curve fitting method to model the amplification effect between the vibration index and the temperature response deviation, extract the amplification factor that best reflects the temperature rise amplification trend under high vibration conditions as β, and finally store the β coefficient with the optimal stability in the fitting result into the database for use as the standard parameter in the subsequent calculation of the real-time vibration-temperature response index.

[0048] Among them, the specific implementation example of calculating the vibration-temperature response index of the wind turbine is as follows. The following parameters are available, including:

[0049] The current temperature value of the bearing of the wind turbine is approximately: 68.742 °C.

[0050] The rated temperature value of the bearing of the wind turbine is approximately: 55.230 °C.

[0051] The maximum allowable temperature rise of the bearing of the wind turbine is approximately: 25.000 °C.

[0052] The vibration acceleration index of the wind turbine is approximately: 3.814 m / s 2 。

[0053] The vibration adjustment coefficient stored in the database is approximately: 0.276.

[0054] Substitute the above data into the specific formula for calculating the vibration-temperature response index of the wind turbine respectively, and we get:

[0055] The vibration-temperature response index of the wind turbine = ((68.742 - 55.230) / 25.000) × (1 + 0.276 × ((3.814^2) / (1 + 3.814))) ≈ 0.991.

[0056] In this implementation, by constructing a vibration-temperature response index, the abnormal characteristics of the bearings of wind turbines under the combined action of heat and vibration are accurately captured, effectively solving the problem of insufficient recognition ability of traditional monitoring systems for latent faults such as light vibration and high temperature or rapid temperature rise faster than expected. The vibration-temperature response index takes the current bearing temperature value, reference temperature value, and maximum allowable temperature rise as basic thermal parameters, and at the same time integrates the vibration acceleration index calculated from the average vibration acceleration of multiple key components to reflect the indirect impact of mechanical shock on temperature rise. Compared with monitoring temperature or vibration alone, this index shows an improved sensitivity to the operating state of the system, can dynamically identify combined abnormalities caused by factors such as lubrication deterioration, bearing fatigue, or transient excitation. At the same time, the vibration amplification coefficient obtained by training with historical operating condition data quantifies and maps the non-linear effect of vibration amplitude on the temperature rise trend, realizing the adaptive adjustment ability of the index under different operating intensities. Finally, this index can not only be used as a means for pre-identifying local abnormalities, but also provide key inputs for the health state assessment model, helping the system play an important role in early risk judgment, improving the accuracy of early warning, and reducing the cost of fault expansion.

[0057] Specifically, the specific steps for analyzing the integrated health state index of a wind turbine are as follows: Obtain the rated wind speed value of the wind turbine; input the actual output power, rated output power, vibration acceleration index, rated wind speed value, and regional wind speed value within the set area of the wind turbine into a preset health analysis model for health analysis to obtain the integrated health state index of the wind turbine.

[0058] Among them, the rated wind speed refers to the wind speed required for the wind turbine to just be able to output the rated power.

[0059] The health analysis model is specifically as follows: Among them, FjK is the integrated health state index of the wind turbine, SsC is the actual output power of the wind turbine, δ 1 is the power influence coefficient stored in the database, QfS is the regional wind speed value within the set area of the wind turbine, EdF is the rated wind speed value of the wind turbine, δ 2 is the wind speed influence coefficient stored in the database, ZdJ is the vibration acceleration index of the wind turbine, α 1 is the vibration response coefficient stored in the database, EsC is the rated output power of the wind turbine, α 2 is the vibration amplification coefficient stored in the database.

[0060] It should be explained that the power influence coefficient δ 1 stored in the database, the wind speed influence coefficient δ 2 , the vibration response coefficient α 1 , and the vibration amplification coefficient α 2The specific acquisition steps are as follows: conduct multivariate analysis based on the response trends of various variables in the long-term operation data of the wind turbine to the change of the health status. First, construct a correlation regression model between historical power, wind speed, vibration data and health assessment results (such as failure frequency, health level), and use methods such as machine learning regression, principal component analysis or least squares fitting to extract the sensitivity and amplification parameters of each variable to the health status deviation. The slope corresponding to the power change term in the regression model is δ 1 The weight corresponding to the normalized wind speed item is δ 2 The influence factor obtained by fitting the vibration index and the health deviation item is α 1 The non-linear amplification coefficient of the influence of the vibration square term on the overall index mutation in the health critical area is α 2 Finally, the above four items are solidified in the database as standard parameters for adjusting the weights of the real-time health fusion index.

[0061] In this implementation plan, by constructing a fusion health status index, the comprehensive analysis and unified health assessment of the multi-source operation parameters of the wind turbine are realized, significantly improving the system's recognition accuracy of potential risks and intelligent decision-making ability under complex operating conditions. This index integrates multiple key variables such as the actual output power, rated power, regional wind speed, rated wind speed, and vibration acceleration index of the wind turbine, and introduces the power influence coefficient, wind speed influence coefficient, vibration response coefficient, and vibration amplification coefficient obtained by fitting based on historical operation data as weight adjustment factors, effectively reflecting the true contribution degree of each variable to the health status deviation. Through the set health analysis model, it can not only evaluate the health fluctuations caused by the abnormality of a single index, but also achieve early perception when multiple factors are slightly abnormal at the same time but the trends are superimposed. It is especially suitable for identifying complex hidden dangers such as sufficient wind speed but power decline or normal vibration but health mutation. Compared with the traditional health judgment method that relies on fixed thresholds or single variable judgment, this fusion index has stronger correlation analysis ability and trend insight ability, and can provide a scientific decision-making basis for whether to conduct fatigue analysis and whether intervention is needed in the future. It is the key support index for realizing the intelligent and adaptive state assessment of the wind turbine.

[0062] Specifically, the specific steps for analyzing the composite fatigue index of the gearbox of the wind turbine are as follows: obtain the oil temperature value inside the gearbox of the wind turbine, the oil temperature reference set, the rotational speed comprehensive index, and the rotational speed reference index. The oil temperature reference set includes the first oil temperature threshold and the second oil temperature threshold; input the actual output power, rated output power, oil temperature value inside the gearbox, oil temperature reference set, rotational speed comprehensive index, and rotational speed reference index of the wind turbine into a preset fatigue analysis model for fatigue analysis to obtain the composite fatigue index of the gearbox of the wind turbine.

[0063] Among them, the oil temperature value inside the gearbox can be measured and obtained through thermocouples (K type, J type), PT100, and NTC temperature sensors.

[0064] The rotational speed reference index is obtained by performing an average analysis on the reference value of the main shaft rotational speed and the reference value of the generator rotational speed of the wind turbine generator set.

[0065] The specific steps to obtain the comprehensive rotational speed index of the wind turbine generator set are as follows: Obtain the main shaft rotational speed value and the generator rotational speed value of the wind turbine generator set; perform a comprehensive analysis (i.e., average analysis) on the main shaft rotational speed value and the generator rotational speed value of the wind turbine generator set to obtain the comprehensive rotational speed index of the wind turbine generator set.

[0066] Among them, the main shaft rotational speed value can be measured and obtained through Hall elements and magnetoelectric speed measuring devices.

[0067] The generator rotational speed value can be measured and obtained through high-speed encoders, magnetoelectric speed measuring devices, and Hall effect rotational speed probes.

[0068] The fatigue analysis model is specifically as follows: Among them, CpL is the composite fatigue index of the gearbox of the wind turbine generator set, YwZ is the oil temperature value inside the gearbox of the wind turbine generator set, λ 1 is the low-temperature secondary thermal wear coefficient stored in the database, λ 2 is the low-temperature linear thermal wear coefficient stored in the database, χ is the low-temperature base offset coefficient stored in the database, ZzH is the comprehensive rotational speed index of the wind turbine generator set, ZcD is the rotational speed reference index of the wind turbine generator set, ε is the rotational speed coupling coefficient stored in the database, YyW is the first oil temperature threshold of the wind turbine generator set, ξ 1 is the medium-temperature tertiary thermal wear coefficient stored in the database, ξ 2 is the medium-temperature secondary thermal wear coefficient stored in the database, EyW is the second oil temperature threshold of the wind turbine generator set, θ 1 is the high-temperature burst benchmark coefficient stored in the database, e is the natural constant, and its value is 2.71 in this embodiment, θ 2 is the high-temperature exponential growth coefficient stored in the database, SsC is the actual output power of the wind turbine generator set, EsC is the rated output power of the wind turbine generator set, θ 3 is the high-temperature load amplification coefficient stored in the database.

[0069] It should be noted that the low-temperature secondary thermal wear coefficient λ stored in the database 1 and the low-temperature linear thermal wear coefficient λ 2, the specific steps for obtaining the low-temperature base offset coefficient χ and the rotational speed coupling coefficient ε are as follows: perform regression modeling based on the historical operation data of the gearbox in the low oil temperature range (temperature lower than the first oil temperature threshold), select the sample data with the most relevant trend between the oil temperature and fatigue loss in this temperature segment, construct a quadratic polynomial function with the oil temperature as the independent variable and the fatigue index as the dependent variable, and extract the quadratic term, linear term, and constant term coefficients as λ 1 , λ 2 , χ respectively through the least squares fitting method. At the same time, construct the coupling ratio between the corresponding rotational speed and fatigue as a normalization factor, and obtain the amplification effect coefficient of the average rotational speed on fatigue growth as the rotational speed coupling coefficient stored in the database.

[0070] The medium-temperature cubic thermal grinding coefficient ξ 1 and the medium-temperature quadratic thermal grinding coefficient ξ 2 stored in the database are obtained as follows: based on the intermediate temperature rise range where the oil temperature of the gearbox is between the first oil temperature threshold and the second oil temperature threshold, extract the historical curve of the relationship between the fatigue index and the oil temperature rise in this temperature range, and use a non-linear cubic regression function for fitting. With the oil temperature as the variable and the fatigue increment as the response, the cubic term and quadratic term coefficients in the fitting curve are respectively used as ξ 1 and ξ 2 , thereby constructing a polynomial thermal fatigue enhancement model in the medium-temperature stage. These two parameters reflect the non-linear upward trend of the fatigue rate after the oil temperature enters the critical lubrication zone.

[0071] The high-temperature burst benchmark coefficient θ 1 , the high-temperature exponential growth coefficient θ 2 , and the high-temperature load amplification coefficient θ 3 stored in the database are obtained as follows: based on the historical operation samples where the oil temperature of the gearbox is higher than the second threshold range, extract the combined data of power output, oil temperature, and fatigue accumulation, establish a fatigue burst model driven by the oil temperature through an exponential fitting function, and obtain its growth starting base value (θ 1 ) and the high-temperature exponential growth coefficient θ 2 . Then, perform a quadratic regression on the normalized power and fatigue change in the same range to obtain the amplification coefficient of the power load on the fatigue enhancement effect, denoted as θ 3 . Finally, take the above three items as the response parameters of the fatigue mutation behavior under extreme high temperature and store them in the database for real-time calculation and early warning judgment.

[0072] In this implementation, by constructing a composite fatigue index for the gearbox, a dynamic fatigue modeling and risk prediction mechanism for the core transmission components of wind turbines is established, effectively filling the technical gap in the traditional system where anomalies can be perceived but fatigue is difficult to deduce. This index segments and models key parameters such as oil temperature, power, and rotational speed. According to the oil temperature in different temperature zones (low temperature, medium temperature, high temperature), different functional forms are used to fit the fatigue growth trend, and polynomial models and exponential models are established respectively to accurately reflect the non-linear evolution process of material fatigue accumulation on the gear meshing surface under different thermal states. At the same time, through the normalized speed difference term constructed by the rotational speed comprehensive index and the rotational speed reference value, combined with the rotational speed coupling coefficient, the shear stress effect brought by high-speed operation is introduced, making the model sensitive to the influence of long-term high-speed operation. The power normalization term and the high-temperature load amplification coefficient are introduced to exponentially amplify the load-fatigue relationship under extreme conditions, making it closer to the actual damage process. The coefficients of each segment are all derived from historical data training and fitting, enhancing the engineering adaptability and stability of the model. Finally, as a refined diagnosis tool after the health state is abnormal, this index can not only realize the real-time quantitative judgment of the fatigue degree of the gearbox, but also provide a direct basis for whether to cut off the power, significantly improving the initiative of the system to respond to faults and the level of safety control.

[0073] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A remote monitoring and inspection system for wind turbine generator sets, characterized in that: include: A data acquisition unit, used to acquire power status data and bearing status data of the wind turbine generator set, and analyze the power response index and vibration temperature response index of the wind turbine generator set; A state analysis unit, used to judge and analyze the power response index and the vibration-temperature response index of the wind turbine generator set with the preset power response evaluation interval and the vibration-temperature response evaluation interval respectively; The health analysis unit is used to analyze the fusion health status index of the wind turbine generator set when there are abnormalities in the power response index and the vibration temperature response index of the wind turbine generator set, and make a judgment analysis with the preset health assessment interval. If the fusion health status index of the wind turbine generator set is within the preset health assessment interval, no measures are taken; A fatigue analysis unit is used to analyze the composite fatigue index of the gearbox of the wind turbine generator set when the fusion health status index of the wind turbine generator set is outside the preset health assessment interval, and to make a judgment analysis with the preset fatigue assessment interval. If the composite fatigue index of the gearbox of the wind turbine generator set is within the preset fatigue assessment interval, a health abnormality warning is sent; The processing unit is used to execute power-off measures on the wind turbine generator set and send a gearbox abnormality alarm when the composite fatigue index of the gearbox of the wind turbine generator set is outside a preset fatigue assessment interval.

2. The wind turbine generator remote monitoring and inspection station system according to claim 1 is characterized in that: The power status data includes actual output power and rated output power, and the bearing status data includes current bearing temperature value and set bearing temperature value.

3. The wind turbine generator remote monitoring and inspection station system according to claim 2 is characterized in that: The specific steps to obtain the power response index of a wind turbine are as follows: Obtain regional wind speed values ​​within a set area of ​​the wind turbine generator set; The actual output power and rated output power of the wind turbine generator set are comprehensively analyzed in combination with the regional wind speed value in the set area of ​​the wind turbine generator set to obtain the power response index of the wind turbine generator set.

4. The wind turbine generator remote monitoring and inspection station system according to claim 2 is characterized in that: The specific steps to obtain the vibration temperature response index of the wind turbine generator set are as follows: Obtain the maximum allowable temperature rise and vibration acceleration index of the bearings of the wind turbine generator set; The current bearing temperature value and the reference bearing temperature value of the wind turbine generator set are comprehensively analyzed in combination with the maximum allowable bearing temperature rise value and the vibration acceleration index of the wind turbine generator set to obtain the vibration-temperature response index of the wind turbine generator set.

5. The wind turbine generator remote monitoring and inspection station system according to claim 4 is characterized in that: The specific steps to obtain the vibration acceleration index of a wind turbine are as follows: Obtaining current vibration acceleration values ​​of several vibration components of the wind turbine generator set; The current vibration acceleration values ​​of several vibration components of the wind turbine generator set are comprehensively analyzed to obtain the vibration acceleration index of the wind turbine generator set.

6. The wind turbine generator remote monitoring and inspection station system according to claim 4 is characterized in that: The specific steps for analyzing the integrated health status index of a wind turbine are as follows: Get the rated wind speed value of the wind turbine generator set; The actual output power, rated output power, vibration acceleration index, rated wind speed value, and regional wind speed value in the set area of ​​the wind turbine are respectively input into the preset health analysis model for health analysis to obtain the fused health status index of the wind turbine.

7. The wind turbine generator remote monitoring and inspection station system according to claim 6 is characterized in that: The health analysis model is as follows: Among them, FjK is the integrated health status index of the wind turbine, SsC is the actual output power of the wind turbine, δ1 is the power influence coefficient stored in the database, QfS is the regional wind speed value in the set area of ​​the wind turbine, EdF is the rated wind speed value of the wind turbine, δ2 is the wind speed influence coefficient stored in the database, ZdJ is the vibration acceleration index of the wind turbine, α1 is the vibration response coefficient stored in the database, EsC is the rated output power of the wind turbine, and α2 is the vibration amplification factor stored in the database.

8. The wind turbine generator remote monitoring and inspection station system according to claim 2 is characterized in that: The specific steps for analyzing the composite fatigue index of the gearbox of a wind turbine are as follows: Acquire the oil temperature value, oil temperature parameter set, speed comprehensive index and speed parameter index in the gearbox of the wind turbine generator set, wherein the oil temperature parameter set includes a first oil temperature threshold and a second oil temperature threshold; The actual output power, rated output power, oil temperature value in the gearbox, oil temperature parameter set, speed comprehensive index, and speed parameter index of the wind turbine are respectively input into the preset fatigue analysis model for fatigue analysis to obtain the composite fatigue index of the gearbox of the wind turbine.

9. The wind turbine generator remote monitoring and inspection station system according to claim 8 is characterized in that: The specific steps for obtaining the comprehensive speed index of a wind turbine generator set are as follows: Obtain the main shaft speed value and generator speed value of the wind turbine generator set; A comprehensive analysis is performed on the main shaft speed value and the generator speed value of the wind turbine generator set to obtain the comprehensive speed index of the wind turbine generator set.

10. The wind turbine generator remote monitoring and inspection station system according to claim 8, characterized in that: The fatigue analysis model is as follows: Among them, CpL is the composite fatigue index of the gearbox of the wind turbine generator set, YwZ is the oil temperature value in the gearbox of the wind turbine generator set, λ1 is the low-temperature secondary thermal wear coefficient stored in the database, λ2 is the low-temperature linear thermal wear coefficient stored in the database, χ is the low-temperature basic offset coefficient stored in the database, ZzH is the comprehensive speed index of the wind turbine generator set, ZcD is the speed parameter index of the wind turbine generator set, ε is the speed coupling coefficient stored in the database, YyW is the first oil temperature threshold of the wind turbine generator set, ξ1 is the medium-temperature tertiary thermal wear coefficient stored in the database, ξ2 is the medium-temperature secondary thermal wear coefficient stored in the database, EyW is the second oil temperature threshold of the wind turbine generator set, θ1 is the high-temperature outbreak reference coefficient stored in the database, e is a natural constant, θ2 is the high-temperature exponential growth coefficient stored in the database, SsC is the actual output power of the wind turbine generator set, EsC is the rated output power of the wind turbine generator set, and θ3 is the high-temperature load amplification factor stored in the database.

Images