CN-122017449-A - Wind farm collector line drop-out safety fault diagnosis method and system

CN122017449ACN 122017449 ACN122017449 ACN 122017449ACN-122017449-A

Abstract

The invention discloses a wind power plant current collecting circuit drop-out fault diagnosis method and system, wherein the wind power plant current collecting circuit drop-out fault diagnosis method comprises the steps of deploying a multi-source sensor network on target drop-out equipment, collecting operation and environment data including fusion tube surface temperature, conductive loop contact resistance, fuse action times, environment temperature, humidity, wind speed and pollution degree in real time, filtering, denoising and normalizing the collected original data, and constructing a multidimensional characteristic parameter set X= { X1, X2, X n; by continuous monitoring and trend analysis of the dynamic health score H (t), the system is able to issue early warning at an early stage of measurable degradation of device performance. The method enables operation and maintenance personnel to plan maintenance windows in advance, remarkably reduces unplanned downtime, remarkably improves the availability of power generation equipment, and can discover potential problems of the equipment earlier compared with the traditional mode of relying on manual inspection or single parameter threshold value alarm.

Inventors

LIN MENG
ZHANG DAIWEI

Assignees

湖北省天顺零碳技术有限公司

Dates

Publication Date: 20260512
Application Date: 20251230

Claims (10)

1. The method for diagnosing the drop-out safety faults of the collecting line of the wind power plant is characterized by comprising the following steps of: Disposing a multi-source sensor network on target drop safety equipment, collecting operation and environment data including fusion tube surface temperature, conductive loop contact resistance, fuse action times, environment temperature, humidity, wind speed and pollution degree in real time, filtering, denoising and normalizing the collected original data, and constructing a multi-dimensional characteristic parameter set X= { X1, X2, & gt, xn }; Based on historical fault data, identifying a key failure mode set F= { F1, F2,..once, fm } which causes drop insurance faults by adopting a failure mode and influence analysis FMEA and fault tree analysis FTA method, and calculating weight vectors W= { W1, W2,..once, wm } of the failure modes by utilizing an analytic hierarchy process AHP, wherein Σwi=1; based on the multidimensional characteristic parameter set X and the weight vector W of the failure mode, establishing a dynamic health degree evaluation model of the equipment, and calculating a comprehensive health degree score H (t) of the equipment; Setting a health degree scoring threshold H_th and an abnormal threshold of each characteristic parameter, triggering early warning when H (t) calculated in real time is lower than H_th or any key characteristic parameter exceeds the abnormal threshold, and matching with a failure mode library according to a characteristic parameter deviation mode to locate the most probable failure cause; a diagnostic report is generated that includes the device number, the health score, the fault pre-warning level, the suspected fault cause, and the maintenance recommendation.
2. The method for diagnosing the drop-out safety fault of the collecting line of the wind power plant according to claim 1, wherein the surface temperature of the fusion tube is collected by an infrared temperature measuring sensor or a wireless temperature measuring label, the contact resistance of the conductive loop is obtained through indirect calculation of the voltage drop of the measuring loop, and the environmental pollution degree is estimated through a leakage current monitoring or image recognition device.
3. The method for diagnosing a drop-out fault of a collector line of a wind farm according to claim 1, wherein the critical failure mode set F at least comprises mechanical damage caused by poor contact, melt aging, pollution flashover of insulating parts, mechanical mechanism jamming, abnormal installation stress and external short-circuit current impact.
4. The wind farm collector line drop-out fault diagnosis method of claim 1, wherein the integrated health score H (t) is defined by: H(t)=100*exp(-λ*t)*∏_{i=1}^{k}[1-α_i*(S_i(t)/S_{i,max})^β_i] wherein: h (t) represents the comprehensive health degree score of the equipment at the time t, the range is 0-100, and the higher the score is, the healthier the equipment is; exp (- λ×t) is a reference aging factor based on the device run time, λ is an aging coefficient related to the device's intrinsic lifetime; k is the number of key characteristic parameters participating in evaluation; s_i (t) is the severity value of the ith key characteristic parameter deviating from a normal reference after normalization at time t; s_ { i, max } is the maximum deviation severity threshold allowed by the ith key feature parameter; Alpha_i is the sensitivity coefficient of the ith characteristic parameter, 0< alpha_i is less than or equal to 1, and the value of the alpha_i is related to the weight of the failure mode associated with the parameter in the failure mode analysis step; Beta_i is the morphological coefficient of the ith characteristic parameter, and beta_i is more than or equal to 1 and is used for adjusting the nonlinearity degree of the influence of the parameter on the health degree.
5. The wind farm collector line drop-out fault diagnosis method according to claim 4, wherein the key characteristic parameters at least comprise a fusion tube temperature rise rate, a contact resistance increase rate, a ratio of an action frequency accumulated value to a design life frequency, three-phase current unbalance and an insulator surface leakage current effective value.
6. The method for diagnosing the drop-out safety fault of the collecting line of the wind power plant according to claim 4, wherein the initial value of the aging coefficient lambda is set according to the Mean Time Between Failure (MTBF) provided by equipment manufacturers, and the initial value is dynamically corrected by adopting a Bayesian updating method according to group historical data of similar equipment in the running process of the equipment.
7. The method for diagnosing a drop-out fault of a collector line of a wind farm according to claim 4, wherein the severity value S_i (t) is calculated by S_i (t) =max (0, (P_i (t) -P_i, base)/(P_i, limit } -P_i, base) }), wherein P_i (t) is a current value of a characteristic parameter, P_i, base is a normal reference value, and P_i, limit is a safe operation limit.
8. The wind farm collecting line drop insurance fault diagnosis method according to claim 1 is characterized in that the fault diagnosis adopts a mixed diagnosis mechanism based on case reasoning CBR and rule reasoning RBR, wherein the method comprises the steps of firstly matching a real-time characteristic mode with a historical fault case library in a similarity mode, outputting a corresponding fault reason if the matching is successful, and triggering a predefined expert rule to conduct reasoning judgment if the matching is failed.
9. The method for diagnosing a drop-out fault of a collector line of a wind farm according to claim 1, further comprising predicting a time point T_m at which the health score H (T) falls to a preset maintenance threshold H_ maint and a time point T_f at which the health score H (T) falls to a failure threshold H_fail by a trend extrapolation method according to a history change curve, thereby generating a predictive maintenance plan.
10. The utility model provides a wind-powered electricity generation field collection circuit fall insurance fault diagnosis system which characterized in that includes: The data acquisition processing module is used for deploying a multi-source sensor network on the target drop safety equipment, acquiring running and environment data including the surface temperature of a fusion tube, the contact resistance of a conductive loop, the action times of a fuse, the environment temperature, the humidity, the wind speed and the pollution degree in real time, and carrying out filtering, denoising and normalization preprocessing on the acquired original data to construct a multi-dimensional characteristic parameter set X= { X1, X2, the first place and the second place; The failure mode analysis module is used for analyzing the FTA method by adopting failure modes and influences to analyze FMEA and a fault tree based on historical fault data, identifying a key failure mode set F= { F1, F2, & gt, fm } which causes the drop insurance fault, and calculating weight vectors W= { W1, W2, & gt, wm } of each failure mode by utilizing an analytic hierarchy process AHP, wherein Σwi=1; The health degree evaluation module is used for establishing a dynamic health degree evaluation model of the equipment based on the multidimensional characteristic parameter set X and the weight vector W of the failure mode, and calculating the comprehensive health degree score H (t) of the equipment; The fault diagnosis module is used for setting a health degree scoring threshold H_th and an abnormal threshold of each characteristic parameter, triggering early warning when the H (t) calculated in real time is lower than the H_th or any key characteristic parameter exceeds the abnormal threshold, and matching the characteristic parameter deviation mode with the failure mode library to locate the most probable fault cause; And the result output module is used for generating a diagnosis report containing the equipment number, the health degree score, the fault early warning level, the suspected fault reason and the maintenance suggestion.

Description

Wind farm collector line drop-out safety fault diagnosis method and system Technical Field The invention relates to the technical field of power equipment state monitoring, in particular to a method and a system for diagnosing a drop-out safety fault of a collector line of a wind power plant. Background The drop-out fuse (drop-out fuse) is an overload and short-circuit protection device widely used in a wind power plant collector circuit, and reliable operation of the drop-out fuse is important for guaranteeing the stability of electric energy transmission in the wind power plant. Because wind power plants are mostly located in field areas with severe natural environments, drop insurance is exposed to complex environmental factors such as strong wind, high and low temperature, humidity, salt fog, sand dust, thunder and lightning for a long time, and load changes and even short-circuit current impact caused by wind condition fluctuation are required to be frequently born, so that the failure rate is relatively high. At present, operation and maintenance management of drop insurance mainly depends on periodic manual inspection and post-fault maintenance. The mode has obvious limitations that the inspection period is long, potential defects and performance degradation trends of equipment are difficult to discover in time, the equipment state is lack of objective and quantitative evaluation standards depending on experience and responsibility of maintenance personnel, the equipment is often treated after faults occur, unplanned shutdown is caused, the power generation benefit is influenced, and larger equipment damage and even safety accidents can be caused due to the expansion of the faults. Some existing equipment state monitoring solutions generally monitor and threshold alarm only for a single parameter (such as temperature). Although the method can find out partial dominant faults, the whole health state of the equipment under the multi-factor coupling effect cannot be comprehensively reflected, early warning and accurate positioning of the composite faults are difficult, the residual service life of the equipment cannot be quantitatively estimated, and the transition from periodic maintenance to predictive maintenance is difficult to support. Disclosure of Invention The invention aims to overcome the technical defects, provides a wind farm collector line drop-out safety fault diagnosis method and system, and solves the technical problems that in the prior art, the collector line drop-out safety monitoring dimension of a wind farm is single, the assessment lacks quantification, the fault diagnosis is difficult, and the maintenance cannot be predicted. In order to achieve the technical purpose, in a first aspect, the technical scheme of the invention provides a method for diagnosing a drop-out safety fault of a collector line of a wind farm, which comprises the following steps: Disposing a multi-source sensor network on target drop safety equipment, collecting operation and environment data including fusion tube surface temperature, conductive loop contact resistance, fuse action times, environment temperature, humidity, wind speed and pollution degree in real time, filtering, denoising and normalizing the collected original data, and constructing a multi-dimensional characteristic parameter set X= { X1, X2, & gt, xn }; Based on historical fault data, identifying a key failure mode set F= { F1, F2,..once, fm } which causes drop insurance faults by adopting a failure mode and influence analysis FMEA and fault tree analysis FTA method, and calculating weight vectors W= { W1, W2,..once, wm } of the failure modes by utilizing an analytic hierarchy process AHP, wherein Σwi=1; based on the multidimensional characteristic parameter set X and the weight vector W of the failure mode, establishing a dynamic health degree evaluation model of the equipment, and calculating a comprehensive health degree score H (t) of the equipment; Setting a health degree scoring threshold H_th and an abnormal threshold of each characteristic parameter, triggering early warning when H (t) calculated in real time is lower than H_th or any key characteristic parameter exceeds the abnormal threshold, and matching with a failure mode library according to a characteristic parameter deviation mode to locate the most probable failure cause; a diagnostic report is generated that includes the device number, the health score, the fault pre-warning level, the suspected fault cause, and the maintenance recommendation. Optionally, the surface temperature of the melting tube is acquired by an infrared temperature measuring sensor or a wireless temperature measuring tag, the contact resistance of the conductive loop is indirectly calculated by measuring the voltage drop of the loop, and the environmental pollution degree is estimated by a leakage current monitoring or image recognition device. Optionally, the critical failure mode set F at least comp