Maintenance method and system for land wind turbine generator

Abstract

The invention relates to the technical field of wind turbine generator overhauling, in particular to an overhauling method and system for a land wind turbine generator. Comprising the steps of setting a plurality of equipment modules based on a wind turbine generator, and establishing a fault interference model according to all the equipment modules; collecting a vibration signal of each equipment module according to a preset feedback time node, and generating a feedback data packet according to a preprocessing result; generating the operation state of each equipment module according to the feedback data packet and the fault interference model; generating a maintenance plan according to a preset decision model and the operation state of each equipment module; different devices in the wind turbine generator system are distinguished, corresponding device modules are established, the wind turbine generator system is monitored in different areas, the operation state of the wind turbine generator system is judged by periodically collecting monitoring characteristic signals of the device modules, and therefore the accurate position and severity of potential fault risk points of the wind turbine generator system are recognized. And a corresponding maintenance plan is made in time.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine maintenance, and in particular to a maintenance method and system for onshore wind turbines. Background Art

[0002] Wind turbines are one of the components of wind power generation. Wind turbines include wind rotors and generators. The wind rotors contain blades, hubs, reinforcements, etc. The blades rotate under wind power to generate electricity and the generator head rotates. The wind power source consists of a wind turbine, a tower supporting the turbine, a battery charge controller, an inverter, an unloader, a grid-connected controller, a battery pack, etc., and wind turbines need to be regularly inspected and maintained during operation.

[0003] During the maintenance of traditional wind turbines, workers are required to inspect and check different parts of the wind turbines one by one. Only when a clear fault is found can the corresponding maintenance work be carried out. This results in the inability to achieve the effect of preventive maintenance during the inspection process, which is very inconvenient to implement. During the maintenance of most wind turbines, multiple people are often required to analyze and process the inspection results, which takes a long time during the implementation process, and is time-consuming, labor-intensive and troublesome to operate. Summary of the invention

[0004] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a maintenance method and system for onshore wind turbines, aiming to improve the maintenance efficiency of wind turbines, reduce the probability of failure during the operation of wind turbines, and improve the stability of wind turbine operation.

[0005] In some embodiments of the present application, different equipment in a wind turbine is distinguished and corresponding equipment modules are established, so that the wind turbine is monitored in different areas. By periodically collecting monitoring characteristic signals of each equipment module, its operating status is judged, thereby identifying the exact location and severity of potential fault risk points of the wind turbine, and timely warning of various potential fault risks.

[0006] In some embodiments of the present application, by establishing a fault interference model, the collected monitoring characteristic signals are corrected based on the fault transmission relationship within the wind turbine generator set, thereby improving the accuracy of judging potential fault risk points and eliminating the disturbance of internal operating factors to the monitoring accuracy.

[0007] In some embodiments of the present application, optimization processing is performed based on a preset decision model and the real-time potential fault status of each equipment module, so as to select the optimal maintenance strategy for each equipment module, reduce the overall maintenance cost, improve the maintenance efficiency, reduce the failure probability during the operation of the wind turbine, and ensure the stability of the operation of the wind turbine.

[0008] In some embodiments of the present application, a maintenance method for an onshore wind turbine is provided, comprising: Set multiple equipment modules based on wind turbines, and establish fault interference models based on all equipment modules; Collect vibration signals of each equipment module according to the preset feedback time node, and generate feedback data packets according to the preprocessing results; Generate the operating status of each device module based on the feedback data packet and fault interference model; Generate maintenance plans based on preset decision models and the operating status of each equipment module; When setting multiple device modules, it includes: Establish an equipment module sequence A, A=(a1, a2…an), ai is the i-th equipment module, and n is the number of equipment modules.

[0009] In some embodiments of the present application, when establishing a fault interference model, the following steps are included: According to the equipment module sequence A, the i-th equipment module is selected as the target equipment module; Obtain historical fault parameters of wind turbines; Determine whether there is a signal interference path between the target device module and each device module in the device module array A according to the historical fault parameters; If there is a signal interference path between the i-th device module and the target device module, the i-th device module is set as a first-level interference module of the target device module; Establish a signal interference mapping table of the target device module according to all the first-level interference modules; Generate a signal interference mapping table for each device module in turn; A fault interference model is established based on all signal interference mapping tables.

[0010] In some embodiments of the present application, when the operating status of each device module is generated, it includes: Extract the monitoring characteristic signal of the target device module according to the feedback data packet, and establish the monitoring characteristic signal sequence B, B = (b1, b2…bm), where bi is the real-time value of the i-th monitoring characteristic signal of the target device module, and m is the number of monitoring characteristic signals; Generate a primary failure risk value f of the target device module according to the monitoring characteristic signal sequence B; f= αi*Qi*(bi-b'i) 2 ; Among them, αi is the influencing factor of the i-th monitoring characteristic signal, b'i is the standard value of the i-th monitoring characteristic signal of the target equipment module, and Qi is the fixed coefficient of the i-th monitoring characteristic signal; Generate the fault risk value of each equipment module in turn, and establish the fault risk value sequence F, F = (f1, f2…fm), where fi is the primary fault risk value of the i-th equipment module; Preset the first fault risk value threshold F1; If fi>F1, set the i-th equipment module as a first-level equipment module; Correction parameters are set according to the fault interference model, and the operating status of each equipment module is set according to the correction result.

[0011] In some embodiments of the present application, when setting correction parameters according to the fault interference model, it includes: Establish the first-level equipment module sequence A1, A1=(a 11 , a 12 …a 1n1 ), where a1i is the i-th primary equipment module, n1 is the number of primary equipment modules, and n>n1; Sequentially set the i-th first-level equipment module as the target first-level equipment module; Obtain all first-level interference modules of the target first-level equipment module according to the signal interference mapping table of the target first-level equipment module; A correction model of a target first-level equipment module is established according to the first-level fault risk value of each first-level interference module; Generate a secondary failure risk value d of the target primary equipment module according to the modified model; d= αi*Qi*(βi*ci-c'i) 2 ; Wherein, ci is the real-time value of the i-th monitoring characteristic signal of the target first-level equipment module, c'i is the standard value of the i-th characteristic monitoring signal of the target first-level equipment module, and βi is the correction coefficient of the i-th monitoring characteristic signal set based on the correction module; If d>F1; Set the target first-level equipment module to the second-level equipment module; Correcting the monitoring characteristic signal of the target first-level equipment module according to the correction model, and generating a comparison data packet of the target first-level equipment module according to the correction result; Get all secondary equipment modules and establish secondary equipment module array A2, A2=(a 21 , a 22 …a 2n2), where a2i is the i-th secondary equipment module, n2 is the number of secondary equipment modules, and n1>n2.

[0012] In some embodiments of the present application, when the operating state of each device module is set according to the correction result, it includes: According to the equipment module sequence A, the operating status of each equipment module is set in sequence; If ai is not a secondary equipment module, set the operating state of ai to a non-fault state; Select the target secondary equipment modules in sequence according to the secondary equipment module sequence A2; According to the historical operating parameters, a potential fault state sequence H of the target secondary equipment module is established, H=(h1, h2…hr), where r is the number of potential fault states of the target secondary equipment module, and hi is the i-th potential fault state of the target secondary equipment module; Generate similarities with each potential fault state based on the comparison data packet of the target secondary device module and the preset similarity model; The real-time potential fault status of the target secondary equipment module is set according to all similarities.

[0013] In some embodiments of the present application, when generating a maintenance plan, the process includes: Set multiple maintenance strategies for target secondary equipment modules; Generate expected costs for each maintenance strategy; g η =X η + Yi*P η (hi); Among them, g η is the expected cost when adopting the ηth maintenance strategy, X η is the cost of the i-th maintenance strategy, Yi is the risk loss when the next state of the target secondary equipment module is hi, P η (hi) is the probability that the next state of the target secondary equipment module is converted to hi after adopting the nth maintenance strategy; Establish the expected cost series G, G=(g1,g2…g r1 ), where r1 is the number of maintenance strategies, g i is the expected cost of the ith maintenance strategy; Select the minimum value g in the expected cost sequence G min The corresponding maintenance strategy is the primary maintenance strategy of the target secondary equipment module; Obtain the primary maintenance strategy for each secondary equipment module and generate a maintenance plan.

[0014] In some embodiments of the present application, a maintenance system for an onshore wind turbine generator system is provided, comprising: The central control unit is used to set multiple equipment modules based on the wind turbine and establish a fault interference model based on all equipment modules; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are used to collect vibration signals of various equipment modules according to preset feedback time nodes, and generate feedback data packets according to preprocessing results; The central control unit comprises: A fault diagnosis module is used to generate the operating status of each device module according to the feedback data packet and the fault interference model; Maintenance decision module, used to generate maintenance plan according to preset decision model and operation status of each equipment module; The first processing module is used to establish an equipment module sequence A, A=(a1, a2...an), ai is the i-th equipment module, and n is the number of equipment modules.

[0015] In some embodiments of the present application, the central control unit further includes: The second processing module is used to select the i-th equipment module as the target equipment module in sequence according to the equipment module sequence A; Obtain historical fault parameters of wind turbines; Determine whether there is a signal interference path between the target device module and each device module in the device module array A according to the historical fault parameters; If there is a signal interference path between the i-th device module and the target device module, the i-th device module is set as a first-level interference module of the target device module; Establish a signal interference mapping table of the target device module according to all the first-level interference modules; Generate a signal interference mapping table for each device module in turn; A fault interference model is established based on all signal interference mapping tables.

[0016] In some embodiments of the present application, the fault diagnosis module is also used to: Extract the monitoring characteristic signal of the target device module according to the feedback data packet, and establish the monitoring characteristic signal sequence B, B = (b1, b2…bm), where bi is the real-time value of the i-th monitoring characteristic signal of the target device module, and m is the number of monitoring characteristic signals; Generate a primary failure risk value f of the target device module according to the monitoring characteristic signal sequence B; f= αi*Qi*(bi-b'i) 2 ; Among them, αi is the influencing factor of the i-th monitoring characteristic signal, b'i is the standard value of the i-th monitoring characteristic signal of the target equipment module, and Qi is the fixed coefficient of the i-th monitoring characteristic signal; Generate the fault risk value of each equipment module in turn, and establish the fault risk value sequence F, F = (f1, f2…fm), where fi is the primary fault risk value of the i-th equipment module; Preset the first fault risk value threshold F1; If fi>F1, set the i-th equipment module as a first-level equipment module; Establish the first-level equipment module sequence A1, A1=(a 11 , a 12 …a 1n1 ), where a1i is the i-th primary equipment module, n1 is the number of primary equipment modules, and n>n1; Sequentially set the i-th first-level equipment module as the target first-level equipment module; Obtain all first-level interference modules of the target first-level equipment module according to the signal interference mapping table of the target first-level equipment module; A correction model of a target first-level equipment module is established according to the first-level fault risk value of each first-level interference module; Generate a secondary failure risk value d of the target primary equipment module according to the modified model; d= αi*Qi*(βi*ci-c'i) 2 ; Wherein, ci is the real-time value of the i-th monitoring characteristic signal of the target first-level equipment module, c'i is the standard value of the i-th characteristic monitoring signal of the target first-level equipment module, and βi is the correction coefficient of the i-th monitoring characteristic signal set based on the correction module; If d>F1; Set the target first-level equipment module to the second-level equipment module; Correcting the monitoring characteristic signal of the target first-level equipment module according to the correction model, and generating a comparison data packet of the target first-level equipment module according to the correction result; Get all secondary equipment modules and establish secondary equipment module array A2, A2=(a 21 , a 22 …a 2n2 ), where a2i is the i-th secondary equipment module, n2 is the number of secondary equipment modules, and n1>n2; According to the equipment module sequence A, the operating status of each equipment module is set in sequence; If ai is not a secondary equipment module, set the operating state of ai to a non-fault state; Select the target secondary equipment modules in sequence according to the secondary equipment module sequence A2; According to the historical operating parameters, a potential fault state sequence H of the target secondary equipment module is established, H=(h1, h2…hr), where r is the number of potential fault states of the target secondary equipment module, and hi is the i-th potential fault state of the target secondary equipment module; Generate similarities with each potential fault state based on the comparison data packet of the target secondary device module and the preset similarity model; The real-time potential fault status of the target secondary equipment module is set according to all similarities.

[0017] In some embodiments of the present application, the maintenance decision module is also used to: Set multiple maintenance strategies for target secondary equipment modules; Generate expected costs for each maintenance strategy; g η =X η + Yi*P η (hi); Among them, g η is the expected cost when adopting the ηth maintenance strategy, X η is the cost of the i-th maintenance strategy, Yi is the risk loss when the next state of the target secondary equipment module is hi, P η (hi) is the probability that the next state of the target secondary equipment module is converted to hi after adopting the nth maintenance strategy; Establish the expected cost series G, G=(g1,g2…g r1 ), where r1 is the number of maintenance strategies; g i is the expected cost of the ith maintenance strategy; Select the minimum value g in the expected cost sequence G min The corresponding maintenance strategy is the primary maintenance strategy of the target secondary equipment module; Obtain the primary maintenance strategy for each secondary equipment module and generate a maintenance plan.

[0018] Compared with the prior art, the maintenance method and system for an onshore wind turbine generator set in the embodiment of the present application has the following beneficial effects: Different equipment in the wind turbine is distinguished and corresponding equipment modules are established to monitor the wind turbine in different areas. By periodically collecting the monitoring characteristic signals of each equipment module, its operating status is judged to identify the exact location and severity of the potential fault risk points of the wind turbine, and timely warn of various potential fault risks.

[0019] By establishing a fault interference model and based on the fault transmission relationship within the wind turbine, the collected monitoring characteristic signals are corrected to improve the accuracy of judging potential fault risk points and eliminate the disturbance of internal operating factors to the monitoring accuracy.

[0020] According to the preset decision model and the real-time potential fault status of each equipment module, optimization processing is performed to select the optimal maintenance strategy for each equipment module, reduce the overall maintenance cost, improve maintenance efficiency, reduce the failure probability during the operation of the wind turbine, and ensure the stability of the wind turbine operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a maintenance method for an onshore wind turbine generator set in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0022] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0023] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0025] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0026] like Figure 1As shown, a maintenance method for an onshore wind turbine generator system according to a preferred embodiment of the present application includes: S101: setting a plurality of equipment modules based on the wind turbine generator set, and establishing a fault interference model according to all the equipment modules; S102: collecting vibration signals of various equipment modules according to preset feedback time nodes, and generating feedback data packets according to preprocessing results; S103: Generate the operating status of each device module according to the feedback data packet and the fault interference model; S104: Generate a maintenance plan according to a preset decision model and the operating status of each equipment module; When setting multiple device modules, it includes: Establish an equipment module sequence A, A=(a1, a2…an), where ai is the i-th equipment module and n is the number of equipment modules.

[0027] Specifically, multiple equipment modules can be established according to different equipment categories such as front and rear propeller systems, drive systems, hubs, blades and cooling systems in wind turbines, and each equipment module can be monitored separately, so as to achieve accurate maintenance of wind turbines and reduce downtime costs during maintenance.

[0028] Specifically, the collected vibration signals of each equipment module are preprocessed, and each monitoring characteristic signal is separated from the interference signal through feature recognition and wavelet reconstruction, so as to accurately judge the potential fault status of each equipment module based on the monitoring characteristic signal.

[0029] Specifically, when establishing a fault interference model, it includes: According to the equipment module sequence A, the i-th equipment module is selected as the target equipment module; Obtain historical fault parameters of wind turbines; Determine whether there is a signal interference path between the target device module and each device module in the device module array A according to the historical fault parameters; If there is a signal interference path between the i-th device module and the target device module, the i-th device module is set as a first-level interference module of the target device module; Establish a signal interference mapping table of the target device module according to all the first-level interference modules; Generate a signal interference mapping table for each device module in turn; A fault interference model is established based on all signal interference mapping tables.

[0030] Specifically, the signal interference path refers to the disturbance of the collected monitoring characteristic signal of the target device module when the first-level interference module operates abnormally, thereby affecting the judgment result of the operating status of the target device module.

[0031] It can be understood that in the above embodiment, different equipment in the wind turbine group is distinguished and corresponding equipment modules are established, so as to monitor the wind turbine group in different areas, and by periodically collecting the monitoring characteristic signals of each equipment module, its operating status is judged, thereby identifying the exact location and severity of the potential fault risk points of the wind turbine group, and timely warning of various potential fault risks.

[0032] In a preferred embodiment of the present application, when generating the operating status of each device module, it includes: Extract the monitoring characteristic signal of the target device module according to the feedback data packet, and establish the monitoring characteristic signal sequence B, B = (b1, b2…bm), where bi is the real-time value of the i-th monitoring characteristic signal of the target device module, and m is the number of monitoring characteristic signals; Generate a primary failure risk value f of the target device module according to the monitoring characteristic signal sequence B; f= αi*Qi*(bi-b'i) 2 ; Among them, αi is the influencing factor of the i-th monitoring characteristic signal, b'i is the standard value of the i-th monitoring characteristic signal of the target equipment module, and Qi is the fixed coefficient of the i-th monitoring characteristic signal; Generate the fault risk value of each equipment module in turn, and establish the fault risk value sequence F, F = (f1, f2…fm), where fi is the primary fault risk value of the i-th equipment module; Preset the first fault risk value threshold F1; If fi>F1, set the i-th equipment module as a first-level equipment module; Correction parameters are set according to the fault interference model, and the operating status of each equipment module is set according to the correction result.

[0033] Specifically, corresponding influence factors are set according to the influence of each monitoring characteristic signal in different equipment modules, and fixed coefficients are set so that the fluctuation amounts of each monitoring characteristic signal are within the same evaluation interval.

[0034] Specifically, the standard value of each monitoring characteristic signal is different in different equipment modules and needs to be dynamically corrected according to the equipment module.

[0035] Specifically, when setting correction parameters according to the fault interference model, it includes: Establish the first-level equipment module sequence A1, A1=(a 11 , a 12 …a 1n1 ), where a1i is the i-th primary equipment module, n1 is the number of primary equipment modules, and n>n1; Sequentially set the i-th first-level equipment module as the target first-level equipment module; Obtain all first-level interference modules of the target first-level equipment module according to the signal interference mapping table of the target first-level equipment module; A correction model of a target first-level equipment module is established according to the first-level fault risk value of each first-level interference module; Generate a secondary failure risk value d of the target primary equipment module according to the modified model; d= αi*Qi*(βi*ci-c'i) 2 ; Wherein, ci is the real-time value of the i-th monitoring characteristic signal of the target first-level equipment module, c'i is the standard value of the i-th characteristic monitoring signal of the target first-level equipment module, and βi is the correction coefficient of the i-th monitoring characteristic signal set based on the correction module; If d>F1; Set the target first-level equipment module to the second-level equipment module; Correcting the monitoring characteristic signal of the target first-level equipment module according to the correction model, and generating a comparison data packet of the target first-level equipment module according to the correction result; Get all secondary equipment modules and establish secondary equipment module array A2, A2=(a 21 , a 22 …a 2n2 ), where a2i is the i-th secondary equipment module, n2 is the number of secondary equipment modules, and n1>n2.

[0036] Specifically, the interference intensity corresponding to the target first-level equipment module is judged according to the first-level fault risk value of all the first-level interference modules of the target first-level equipment module, so as to construct the corresponding correction model, and correct the various monitoring characteristic signals of the target first-level equipment module, so as to eliminate some equipment modules that are disturbed and behave abnormally, improve the accuracy of judging the operating status of the equipment modules, and improve the efficiency of formulating subsequent maintenance plans.

[0037] It can be understood that in the above embodiment, by establishing a fault interference model, the collected monitoring characteristic signals are corrected based on the fault transmission relationship within the wind turbine, and multiple judgments are made on each equipment module, thereby improving the accuracy of judging potential fault risk points and eliminating the disturbance of internal operating factors to the monitoring accuracy.

[0038] In a preferred embodiment of the present application, when setting the operating state of each device module according to the correction result, it includes: According to the equipment module sequence A, the operating status of each equipment module is set in sequence; If ai is not a secondary equipment module, set the operating state of ai to a non-fault state; Select the target secondary equipment modules in sequence according to the secondary equipment module sequence A2; According to the historical operating parameters, a potential fault state sequence H of the target secondary equipment module is established, H=(h1, h2…hr), where r is the number of potential fault states of the target secondary equipment module, and hi is the i-th potential fault state of the target secondary equipment module; Generate similarities with each potential fault state based on the comparison data packet of the target secondary device module and the preset similarity model; The real-time potential fault status of the target secondary equipment module is set according to all similarities.

[0039] Specifically, the corresponding potential fault state is established according to the historical operating parameters of the target secondary equipment module, and the potential fault state includes but is not limited to the abnormal operation of each component, the abnormal operation of the equipment module as a whole, etc. The collected comparison data packets are compared one by one with the operating characteristic signals of each potential fault state, and the potential fault state with the highest similarity is selected as the real-time potential fault state of the target secondary equipment module.

[0040] Specifically, when generating a maintenance plan, include: Set multiple maintenance strategies for target secondary equipment modules; Generate expected costs for each maintenance strategy; g η =X η + Yi*P η (hi); Among them, g η is the expected cost when adopting the ηth maintenance strategy, X η is the cost of the i-th maintenance strategy, Yi is the risk loss when the next state of the target secondary equipment module is hi, P η (hi) is the probability that the next state of the target secondary equipment module is converted to hi after adopting the nth maintenance strategy; Establish the expected cost series G, G=(g1,g2…g r1 ), where r1 is the number of maintenance strategies; g i is the expected cost of the ith maintenance strategy; Select the minimum value g in the expected cost sequence G min The corresponding maintenance strategy is the primary maintenance strategy of the target secondary equipment module; Obtain the primary maintenance strategy for each secondary equipment module and generate a maintenance plan.

[0041] Specifically, according to the historical maintenance parameters of the target secondary equipment module, a corresponding maintenance strategy is set, and the maintenance strategy includes but is not limited to replacing parts, no maintenance, partial maintenance, and overall replacement of the equipment module.

[0042] Specifically, by generating the expected cost of each maintenance strategy, an optimization process is performed to select the best maintenance strategy for the current target secondary equipment module.

[0043] Specifically, based on the historical operating parameters, a Markov chain state transfer matrix of each potential fault state in the target secondary equipment module is established to generate the corresponding probability value.

[0044] Specifically, the cost of the maintenance strategy can be set comprehensively based on environmental parameters. When the downtime costs are different during periods of abundant wind and scarce wind, the corresponding maintenance strategy costs are also different.

[0045] Specifically, in the above embodiment, optimization processing is performed based on the preset decision model and the real-time potential fault status of each equipment module, so as to select the optimal maintenance strategy for each equipment module, reduce the overall maintenance cost, improve the maintenance efficiency, reduce the failure probability during the operation of the wind turbine, and ensure the stability of the operation of the wind turbine.

[0046] Based on another preferred embodiment of a maintenance method for an onshore wind turbine generator set in any of the above preferred embodiments, this preferred embodiment provides a maintenance system for an onshore wind turbine generator set, including: The central control unit is used to set multiple equipment modules based on the wind turbine and establish a fault interference model based on all equipment modules; A monitoring unit, including a plurality of monitoring submodules, wherein the monitoring submodules are used to collect vibration signals of various equipment modules according to preset feedback time nodes, and generate feedback data packets according to preprocessing results; The central control unit includes: A fault diagnosis module is used to generate the operating status of each device module according to the feedback data packet and the fault interference model; Maintenance decision module, used to generate maintenance plan according to preset decision model and operation status of each equipment module; The first processing module is used to establish an equipment module sequence A, A=(a1, a2...an), ai is the i-th equipment module, and n is the number of equipment modules.

[0047] Specifically, the central control unit also includes: The second processing module is used to select the i-th equipment module as the target equipment module in sequence according to the equipment module sequence A; Obtain historical fault parameters of wind turbines; Determine whether there is a signal interference path between the target device module and each device module in the device module array A according to the historical fault parameters; If there is a signal interference path between the i-th device module and the target device module, the i-th device module is set as a first-level interference module of the target device module; Establish a signal interference mapping table of the target device module according to all the first-level interference modules; Generate a signal interference mapping table for each device module in turn; A fault interference model is established based on all signal interference mapping tables.

[0048] In a preferred embodiment of the present application, the fault diagnosis module is also used to: Extract the monitoring characteristic signal of the target device module according to the feedback data packet, and establish the monitoring characteristic signal sequence B, B = (b1, b2…bm), where bi is the real-time value of the i-th monitoring characteristic signal of the target device module, and m is the number of monitoring characteristic signals; Generate a primary failure risk value f of the target device module according to the monitoring characteristic signal sequence B; f= αi*Qi*(bi-b'i) 2 ; Among them, αi is the influencing factor of the i-th monitoring characteristic signal, b'i is the standard value of the i-th monitoring characteristic signal of the target equipment module, and Qi is the fixed coefficient of the i-th monitoring characteristic signal; Generate the fault risk value of each equipment module in turn, and establish the fault risk value sequence F, F = (f1, f2…fm), where fi is the primary fault risk value of the i-th equipment module; Preset the first fault risk value threshold F1; If fi>F1, set the i-th equipment module as a first-level equipment module; Establish the first-level equipment module sequence A1, A1=(a 11 , a 12 …a 1n1 ), where a1i is the i-th primary equipment module, n1 is the number of primary equipment modules, and n>n1; Sequentially set the i-th first-level equipment module as the target first-level equipment module; Obtain all first-level interference modules of the target first-level equipment module according to the signal interference mapping table of the target first-level equipment module; A correction model of a target first-level equipment module is established according to the first-level fault risk value of each first-level interference module; Generate a secondary failure risk value d of the target primary equipment module according to the modified model; d= αi*Qi*(βi*ci-c'i) 2 ; Wherein, ci is the real-time value of the i-th monitoring characteristic signal of the target first-level equipment module, c'i is the standard value of the i-th characteristic monitoring signal of the target first-level equipment module, and βi is the correction coefficient of the i-th monitoring characteristic signal set based on the correction module; If d>F1; Set the target first-level equipment module to the second-level equipment module; Correcting the monitoring characteristic signal of the target first-level equipment module according to the correction model, and generating a comparison data packet of the target first-level equipment module according to the correction result; Get all secondary equipment modules and establish secondary equipment module array A2, A2=(a 21 , a 22 …a 2n2 ), where a2i is the i-th secondary equipment module, n2 is the number of secondary equipment modules, and n1>n2; According to the equipment module sequence A, the operating status of each equipment module is set in sequence; If ai is not a secondary equipment module, set the operating state of ai to a non-fault state; Select the target secondary equipment modules in sequence according to the secondary equipment module sequence A2; According to the historical operating parameters, a potential fault state sequence H of the target secondary equipment module is established, H=(h1, h2…hr), where r is the number of potential fault states of the target secondary equipment module, and hi is the i-th potential fault state of the target secondary equipment module; Generate similarities with each potential fault state based on the comparison data packet of the target secondary device module and the preset similarity model; The real-time potential fault status of the target secondary equipment module is set according to all similarities.

[0049] In a preferred embodiment of the present application, the maintenance decision module is also used to: Set multiple maintenance strategies for target secondary equipment modules; Generate expected costs for each maintenance strategy; g η =X η + Yi*P η (hi); Among them, g η is the expected cost when adopting the ηth maintenance strategy, X η is the cost of the i-th maintenance strategy, Yi is the risk loss when the next state of the target secondary equipment module is hi, P η(hi) is the probability that the next state of the target secondary equipment module is converted to hi after adopting the nth maintenance strategy; Establish the expected cost series G, G=(g1,g2…g r1 ), where r1 is the number of maintenance strategies; g i is the expected cost of the ith maintenance strategy; Select the minimum value g in the expected cost sequence G min The corresponding maintenance strategy is the primary maintenance strategy of the target secondary equipment module; Obtain the primary maintenance strategy for each secondary equipment module and generate a maintenance plan.

[0050] According to the first concept of the present application, different equipment in the wind turbine is distinguished and corresponding equipment modules are established, so that the wind turbine is monitored in different areas, and the operating status is judged by periodically collecting the monitoring characteristic signals of each equipment module, so as to identify the exact location and severity of the potential fault risk points of the wind turbine, and timely warn of various potential fault risks.

[0051] According to the second concept of the present application, by establishing a fault interference model, the collected monitoring characteristic signals are corrected based on the fault transmission relationship within the wind turbine, thereby improving the accuracy of judging potential fault risk points and eliminating the disturbance of internal operating factors to the monitoring accuracy.

[0052] According to the third concept of the present application, optimization processing is performed based on the preset decision model and the real-time potential fault status of each equipment module, so as to select the optimal maintenance strategy for each equipment module, reduce the overall maintenance cost, improve the maintenance efficiency, reduce the probability of failure during the operation of the wind turbine, and ensure the stability of the operation of the wind turbine.

[0053] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A maintenance method for an onshore wind turbine generator system, characterized in that: include: Set multiple equipment modules based on wind turbines, and establish fault interference models based on all equipment modules; Collect vibration signals of each equipment module according to the preset feedback time node, and generate feedback data packets according to the preprocessing results; Generate the operating status of each device module based on the feedback data packet and fault interference model; Generate maintenance plans based on preset decision models and the operating status of each equipment module; When setting multiple device modules, it includes: Establish an equipment module sequence A, A=(a1, a2…an), where ai is the i-th equipment module and n is the number of equipment modules.

2. The maintenance method for an onshore wind turbine generator set according to claim 1, characterized in that: When establishing a fault interference model, include: According to the equipment module sequence A, the i-th equipment module is selected as the target equipment module; Obtain historical fault parameters of wind turbines; Determine whether there is a signal interference path between the target device module and each device module in the device module array A according to the historical fault parameters; If there is a signal interference path between the i-th device module and the target device module, the i-th device module is set as a first-level interference module of the target device module; Establish a signal interference mapping table of the target device module according to all the first-level interference modules; Generate a signal interference mapping table for each device module in turn; A fault interference model is established based on all signal interference mapping tables.

3. The maintenance method for an onshore wind turbine generator set according to claim 2, characterized in that: When generating the operating status of each equipment module, it includes: Extract the monitoring characteristic signal of the target device module according to the feedback data packet, and establish the monitoring characteristic signal sequence B, B = (b1, b2…bm), where bi is the real-time value of the i-th monitoring characteristic signal of the target device module, and m is the number of monitoring characteristic signals; Generate a primary failure risk value f of the target device module according to the monitoring characteristic signal sequence B; f= αi*Qi*(bi-b'i) 2 ; Among them, αi is the influencing factor of the i-th monitoring characteristic signal, b'i is the standard value of the i-th monitoring characteristic signal of the target equipment module, and Qi is the fixed coefficient of the i-th monitoring characteristic signal; Generate the fault risk value of each equipment module in turn, and establish the fault risk value sequence F, F = (f1, f2…fm), where fi is the primary fault risk value of the i-th equipment module; Preset the first fault risk value threshold F1; If fi>F1, set the i-th equipment module as a first-level equipment module; Correction parameters are set according to the fault interference model, and the operating status of each equipment module is set according to the correction result.

4. The maintenance method for an onshore wind turbine generator set according to claim 3, characterized in that: When setting correction parameters according to the fault interference model, it includes: Establish the first-level equipment module sequence A1, A1=(a 11 , a 12 …a 1n1 ), where a1i is the i-th primary equipment module, n1 is the number of primary equipment modules, and n>n1; Sequentially set the i-th first-level equipment module as the target first-level equipment module; Obtain all first-level interference modules of the target first-level equipment module according to the signal interference mapping table of the target first-level equipment module; A correction model of a target first-level equipment module is established according to the first-level fault risk value of each first-level interference module; Generate a secondary failure risk value d of the target primary equipment module according to the modified model; d= αi*Qi*(βi*ci-c'i) 2 ; Wherein, ci is the real-time value of the i-th monitoring characteristic signal of the target first-level equipment module, c'i is the standard value of the i-th characteristic monitoring signal of the target first-level equipment module, and βi is the correction coefficient of the i-th monitoring characteristic signal set based on the correction module; If d>F1; Set the target first-level equipment module to the second-level equipment module; Correcting the monitoring characteristic signal of the target first-level equipment module according to the correction model, and generating a comparison data packet of the target first-level equipment module according to the correction result; Get all secondary equipment modules and establish secondary equipment module array A2, A2=(a 21 , a 22 …a 2n2 ), where a2i is the i-th secondary equipment module, n2 is the number of secondary equipment modules, and n1>n2.

5. The maintenance method for an onshore wind turbine generator set according to claim 4, characterized in that: When setting the operating status of each equipment module according to the correction result, it includes: According to the equipment module sequence A, the operating status of each equipment module is set in sequence; If ai is not a secondary equipment module, set the operating state of ai to a non-fault state; Select the target secondary equipment modules in sequence according to the secondary equipment module sequence A2; According to the historical operating parameters, a potential fault state sequence H of the target secondary equipment module is established, H=(h1, h2…hr), where r is the number of potential fault states of the target secondary equipment module, and hi is the i-th potential fault state of the target secondary equipment module; Generate similarities with each potential fault state based on the comparison data packet of the target secondary device module and the preset similarity model; The real-time potential fault status of the target secondary equipment module is set according to all similarities.

6. The maintenance method for an onshore wind turbine generator set according to claim 5, characterized in that: When generating a maintenance plan, include: Set multiple maintenance strategies for target secondary equipment modules; Generate expected costs for each maintenance strategy; g η =X η + Yi*P η (hi); Among them, g η is the expected cost when adopting the ηth maintenance strategy, X η is the cost of the i-th maintenance strategy, Yi is the risk loss when the next state of the target secondary equipment module is hi, P η (hi) is the probability that the next state of the target secondary equipment module is converted to hi after adopting the nth maintenance strategy; Establish the expected cost series G, G=(g1,g2…g r1 ), where r1 is the number of maintenance strategies, g i is the expected cost of the ith maintenance strategy; Select the minimum value g in the expected cost sequence G min The corresponding maintenance strategy is the primary maintenance strategy of the target secondary equipment module; Obtain the primary maintenance strategy for each secondary equipment module and generate a maintenance plan.

7. A maintenance system for an onshore wind turbine generator set, using the maintenance method for an onshore wind turbine generator set according to any one of claims 1 to 6, characterized in that: include: The central control unit is used to set multiple equipment modules based on the wind turbine and establish a fault interference model based on all equipment modules; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are used to collect vibration signals of various equipment modules according to preset feedback time nodes, and generate feedback data packets according to preprocessing results; The central control unit comprises: A fault diagnosis module is used to generate the operating status of each device module according to the feedback data packet and the fault interference model; Maintenance decision module, used to generate maintenance plan according to preset decision model and operation status of each equipment module; The first processing module is used to establish an equipment module sequence A, A=(a1, a2...an), ai is the i-th equipment module, and n is the number of equipment modules.

8. The maintenance system for an onshore wind turbine generator set according to claim 7, characterized in that: The central control unit also includes: The second processing module is used to select the i-th equipment module as the target equipment module in sequence according to the equipment module sequence A; Obtain historical fault parameters of wind turbines; Determine whether there is a signal interference path between the target device module and each device module in the device module array A according to the historical fault parameters; If there is a signal interference path between the i-th device module and the target device module, the i-th device module is set as a first-level interference module of the target device module; Establish a signal interference mapping table of the target device module according to all the first-level interference modules; Generate a signal interference mapping table for each device module in turn; A fault interference model is established based on all signal interference mapping tables.

9. The maintenance system for an onshore wind turbine generator set according to claim 8, characterized in that: The fault diagnosis module is also used for: Extract the monitoring characteristic signal of the target device module according to the feedback data packet, and establish the monitoring characteristic signal sequence B, B = (b1, b2…bm), where bi is the real-time value of the i-th monitoring characteristic signal of the target device module, and m is the number of monitoring characteristic signals; Generate a primary failure risk value f of the target device module according to the monitoring characteristic signal sequence B; f= αi*Qi*(bi-b'i) 2 ; Among them, αi is the influencing factor of the i-th monitoring characteristic signal, b'i is the standard value of the i-th monitoring characteristic signal of the target equipment module, and Qi is the fixed coefficient of the i-th monitoring characteristic signal; Generate the fault risk value of each equipment module in turn, and establish the fault risk value sequence F, F = (f1, f2…fm), where fi is the primary fault risk value of the i-th equipment module; Preset the first fault risk value threshold F1; If fi>F1, set the i-th equipment module as a first-level equipment module; Establish the first-level equipment module sequence A1, A1=(a 11 , a 12 …a 1n1 ), where a1i is the i-th primary equipment module, n1 is the number of primary equipment modules, and n>n1; Sequentially set the i-th first-level equipment module as the target first-level equipment module; Obtain all first-level interference modules of the target first-level equipment module according to the signal interference mapping table of the target first-level equipment module; A correction model of a target first-level equipment module is established according to the first-level fault risk value of each first-level interference module; Generate a secondary failure risk value d of the target primary equipment module according to the modified model; d= αi*Qi*(βi*ci-c'i) 2 ; Wherein, ci is the real-time value of the i-th monitoring characteristic signal of the target first-level equipment module, c'i is the standard value of the i-th characteristic monitoring signal of the target first-level equipment module, and βi is the correction coefficient of the i-th monitoring characteristic signal set based on the correction module; If d>F1; Set the target first-level equipment module to the second-level equipment module; Correcting the monitoring characteristic signal of the target first-level equipment module according to the correction model, and generating a comparison data packet of the target first-level equipment module according to the correction result; Get all secondary equipment modules and establish secondary equipment module array A2, A2=(a 21 , a 22 …a 2n2 ), where a2i is the i-th secondary equipment module, n2 is the number of secondary equipment modules, and n1>n2; According to the equipment module sequence A, the operating status of each equipment module is set in sequence; If ai is not a secondary equipment module, set the operating state of ai to a non-fault state; Select the target secondary equipment modules in sequence according to the secondary equipment module sequence A2; According to the historical operating parameters, a potential fault state sequence H of the target secondary equipment module is established, H=(h1, h2…hr), where r is the number of potential fault states of the target secondary equipment module, and hi is the i-th potential fault state of the target secondary equipment module; Generate similarities with each potential fault state based on the comparison data packet of the target secondary device module and the preset similarity model; The real-time potential fault status of the target secondary equipment module is set according to all similarities.

10. The maintenance system for an onshore wind turbine generator set according to claim 9, characterized in that: The maintenance decision module is also used for: Set multiple maintenance strategies for target secondary equipment modules; Generate expected costs for each maintenance strategy; g η =X η + Yi*P η (hi); Among them, g η is the expected cost when adopting the ηth maintenance strategy, X η is the cost of the i-th maintenance strategy, Yi is the risk loss when the next state of the target secondary equipment module is hi, P η (hi) is the probability that the next state of the target secondary equipment module is converted to hi after adopting the nth maintenance strategy; Establish the expected cost series G, G=(g1,g2…g r1 ), where r1 is the number of maintenance strategies; g i is the expected cost of the ith maintenance strategy; Select the minimum value g in the expected cost sequence G min The corresponding maintenance strategy is the primary maintenance strategy of the target secondary equipment module; Obtain the primary maintenance strategy for each secondary equipment module and generate a maintenance plan.

Images