An ice melting system health diagnosis method, device, equipment and storage medium

Abstract

The method, device, equipment and storage medium provided by the exemplary embodiments of the present disclosure provide an ice melting system health diagnosis method, device, equipment and storage medium, the method comprising: performing wideband impedance scanning on a target heating circuit to obtain impedance spectrum data; obtaining working condition data of the target heating circuit, calibrating the impedance spectrum data based on the working condition data to obtain standard impedance spectrum data, extracting features from the standard impedance spectrum data to obtain a standard feature vector; matching the standard feature vector with a health feature vector set and a fault feature vector set respectively to determine the health status, fault type and fault section of the target heating circuit, and outputting a health diagnosis result; effectively realizing health status diagnosis of a fan blade electric heating ice melting system.

Description

Technical Field

[0001] This disclosure relates to the field of wind turbine blade anti-icing technology, and in particular to a method, apparatus, equipment and storage medium for health diagnosis of an ice melting system. Background Technology

[0002] Wind turbine blades are prone to icing when operating in cold and humid environments, significantly reducing aerodynamic efficiency and power generation. They are also susceptible to structural damage due to severe vibrations caused by mass imbalances. While the widely used resistance-type electrothermal de-icing system is effective, its reliability faces serious challenges. The heating elements and lightning protection conductors embedded inside the blades are subjected to extreme temperature differences, strong vibrations, and lightning surges over long periods, making them prone to hidden faults such as loose connections, localized ablation, or even breakage. Traditional maintenance methods rely heavily on periodic shutdowns for inspection and manual patrols, which are not only inefficient and costly but also make it difficult to detect early microscopic damage. Intervention is often only possible after the fault has worsened and caused a serious accident, lacking effective monitoring and early warning methods. Most existing detection methods for this type of problem have significant limitations; technologies such as infrared thermal imaging can only assess the surface temperature field distribution but cannot see the internal structural state; vibration analysis methods can sense overall modal changes but are not sensitive enough to local electrical connection deterioration; DC resistance measurement can only reflect the overall circuit continuity but cannot identify early local defects; it is difficult to achieve accurate diagnosis and quantitative assessment of the health status of key components of the de-icing system, and cannot meet the urgent need for intelligent operation and maintenance of wind farms to have a knowable and controllable equipment status. Impedance spectroscopy (ISS) technology obtains system state information by scanning electrical responses at different frequencies. It is currently mainly used in fields such as aging monitoring of electrolytic capacitors, health status assessment of batteries, and coating corrosion detection. It has extremely high sensitivity to changes in resistance and capacitance parameters caused by changes in the microstructure of materials. However, existing technologies are mostly focused on offline analysis in laboratory environments, while wind turbine blade de-icing systems are usually under complex operating conditions. Summary of the Invention

[0003] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a method, apparatus, equipment and storage medium for health diagnosis of ice melting system.

[0004] An exemplary embodiment of this disclosure provides a method for health diagnosis of an ice-melting system, the method comprising: A broadband impedance scan was performed on the target heating circuit to obtain impedance spectrum data; The operating condition data of the target heating circuit is obtained, and the impedance spectrum data is calibrated based on the operating condition data to obtain standard impedance spectrum data. Feature extraction is performed on the standard impedance spectrum data to obtain a standard feature vector. Based on the standard feature vector, the health feature vector set and the fault feature vector set are matched respectively to determine the health status, fault type and fault location of the target heating circuit, and output the health diagnosis result.

[0005] In some exemplary embodiments, performing a broadband impedance scan on the target heating circuit to obtain impedance spectrum data includes: When the ice melting system is not in operation, a broadband sweep excitation signal with a preset amplitude is injected into the target heating circuit to obtain the voltage response data and current response data of the target heating circuit. The voltage response data and the current response data are converted to the frequency domain to obtain voltage frequency domain phasors and current frequency domain phasors, respectively. Impedance spectrum data are obtained based on the ratio of the voltage frequency domain phasor to the current frequency domain phasor.

[0006] In some exemplary embodiments, the calibration includes at least a condition normalization process; The operating condition data and the impedance spectrum data are synchronized and matched using the same timestamp. The process involves acquiring the operating condition data of the target heating circuit, calibrating the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extracting features from the standard impedance spectrum data to obtain a standard feature vector, including: Based on a pre-built health status benchmark database, obtain the temperature correction coefficient corresponding to the ambient temperature in the operating condition data, and the blade pitch angle correction coefficient corresponding to the blade pitch angle in the operating condition data. The standard impedance spectrum data is obtained by dividing the impedance spectrum data by the product of the temperature correction factor and the pitch angle correction factor. Impedance spectrum feature parameters are extracted based on the standard impedance spectrum data. The impedance spectrum feature parameters include at least the change in the real part of the impedance in the preset low-frequency band, the change in the imaginary part of the impedance and the phase angle in the preset mid-frequency band, the offset of the resonant frequency point in the preset high-frequency band, and the change in the semicircle radius and curvature of the Nyquist curve. Based on a preset combination order, the impedance spectrum characteristic parameters are combined to obtain a standard feature vector.

[0007] In some exemplary embodiments, determining the health status of the target heating circuit by matching the standard feature vector with a set of health feature vectors includes: Based on the Mahalanobis distance algorithm, the degree of deviation between the standard feature vector and the health feature vector of the corresponding working condition and the corresponding loop in the health feature vector set is obtained; Based on the degree of deviation, the health quantification index of the target heating circuit is obtained by calculation using an exponential decay function. Based on the preset health threshold and the health quantification index, the health status of the target heating circuit is determined. The health status includes healthy state, slight deterioration warning state, moderate deterioration concern state, and severe fault state.

[0008] In some exemplary embodiments, determining the fault type of the target heating circuit by matching the standard feature vector with the fault feature vector set includes: Based on the weighted cosine similarity algorithm, the matching degree between the standard feature vector and the fault feature vector in the fault feature vector set is calculated, and the fault type corresponding to the maximum matching degree is selected as the fault type of the target heating circuit.

[0009] In some exemplary embodiments, determining the faulty section of the target heating circuit by matching the standard feature vector with the fault feature vector set includes: Based on the impedance response attenuation difference of the standard feature vector under different feature frequency bands, it is compared with the standard attenuation characteristics corresponding to the blade root segment, blade middle segment and blade tip segment of the target heating circuit to obtain the matching degree of each segment, and the segment with the largest matching degree is selected as the segment where the fault is located.

[0010] In some exemplary embodiments, it also includes: Match a preset operation and maintenance strategy based on the health status; If the health status is healthy, then the monitoring period will be maintained; If the health status is in a state of slight deterioration warning, the monitoring period will be shortened and a warning notification will be sent. If the health status is classified as moderately deteriorated and of concern, it will be included in the planned maintenance list. If the health status is a serious fault, a shutdown warning signal will be triggered and maintenance instructions will be sent.

[0011] An exemplary embodiment of this disclosure also provides a health diagnostic device for an ice-melting system, the device comprising: The first module is used to perform a broadband impedance scan on the target heating circuit to obtain impedance spectrum data. The second obtaining module is used to acquire the operating condition data of the target heating circuit, calibrate the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extract features from the standard impedance spectrum data to obtain a standard feature vector. The output module is used to match the standard feature vector with the health feature vector set and the fault feature vector set respectively, to determine the health status, fault type and fault location of the target heating circuit, and output the health diagnosis result.

[0012] The apparatus provided in the exemplary embodiments of this disclosure includes a first obtaining module, specifically used for: When the ice melting system is not in operation, a broadband sweep excitation signal with a preset amplitude is injected into the target heating circuit to obtain the voltage response data and current response data of the target heating circuit. The voltage response data and the current response data are converted to the frequency domain to obtain voltage frequency domain phasors and current frequency domain phasors, respectively. Impedance spectrum data are obtained based on the ratio of the voltage frequency domain phasor to the current frequency domain phasor.

[0013] The apparatus provided in the exemplary embodiments of this disclosure includes at least a condition normalization process for calibration. The operating condition data and the impedance spectrum data are synchronized and matched using the same timestamp. The second obtaining module is specifically used for: Based on a pre-built health status benchmark database, obtain the temperature correction coefficient corresponding to the ambient temperature in the operating condition data, and the blade pitch angle correction coefficient corresponding to the blade pitch angle in the operating condition data. The standard impedance spectrum data is obtained by dividing the impedance spectrum data by the product of the temperature correction factor and the pitch angle correction factor. Impedance spectrum feature parameters are extracted based on the standard impedance spectrum data. The impedance spectrum feature parameters include at least the change in the real part of the impedance in the preset low-frequency band, the change in the imaginary part of the impedance and the phase angle in the preset mid-frequency band, the offset of the resonant frequency point in the preset high-frequency band, and the change in the semicircle radius and curvature of the Nyquist curve. Based on a preset combination order, the impedance spectrum characteristic parameters are combined to obtain a standard feature vector.

[0014] The apparatus provided in this exemplary embodiment, wherein the output module is specifically used for: Based on the Mahalanobis distance algorithm, the degree of deviation between the standard feature vector and the health feature vector of the corresponding working condition and the corresponding loop in the health feature vector set is obtained; Based on the degree of deviation, the health quantification index of the target heating circuit is obtained by calculation using an exponential decay function. Based on the preset health threshold and the health quantification index, the health status of the target heating circuit is determined. The health status includes healthy state, slight deterioration warning state, moderate deterioration concern state, and severe fault state.

[0015] The apparatus provided in this exemplary embodiment, wherein the output module is specifically used for: Based on the weighted cosine similarity algorithm, the matching degree between the standard feature vector and the fault feature vector in the fault feature vector set is calculated, and the fault type corresponding to the maximum matching degree is selected as the fault type of the target heating circuit.

[0016] The apparatus provided in this exemplary embodiment, wherein the output module is specifically used for: Based on the impedance response attenuation difference of the standard feature vector under different feature frequency bands, it is compared with the standard attenuation characteristics corresponding to the blade root segment, blade middle segment and blade tip segment of the target heating circuit to obtain the matching degree of each segment, and the segment with the largest matching degree is selected as the segment where the fault is located.

[0017] The apparatus provided in the exemplary embodiments of this disclosure further includes: Match a preset operation and maintenance strategy based on the health status; If the health status is healthy, then the monitoring period will be maintained; If the health status is in a state of slight deterioration warning, the monitoring period will be shortened and a warning notification will be sent. If the health status is classified as moderately deteriorated and of concern, it will be included in the planned maintenance list. If the health status is a serious fault, a shutdown warning signal will be triggered and maintenance instructions will be sent.

[0018] An exemplary embodiment of this disclosure also provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement a health diagnosis method for an ice melting system as provided in an exemplary embodiment of this disclosure.

[0019] This disclosure also provides a computer-readable storage medium storing a computer program for performing a health diagnosis method for an ice-melting system as provided in this disclosure.

[0020] The technical solution provided by the exemplary embodiments of this disclosure has the following advantages compared with the prior art: This exemplary embodiment provides a health diagnosis method for an ice-melting system. The method involves performing a broadband impedance scan on a target heating circuit to obtain impedance spectrum data; acquiring operating condition data of the target heating circuit; calibrating the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data; extracting features from the standard impedance spectrum data to obtain standard feature vectors; matching the standard feature vectors with a health feature vector set and a fault feature vector set respectively to determine the health status, fault type, and fault location of the target heating circuit; and outputting a health diagnosis result. This method effectively diagnoses the health status of an electrothermal ice-melting system for wind turbine blades. Attached Figure Description

[0021] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A schematic flowchart of a health diagnosis method for an ice-melting system provided as an exemplary embodiment of this disclosure; Figure 2 A schematic diagram of a health diagnostic device for an ice-melting system provided as an exemplary embodiment of this disclosure; Figure 3 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present disclosure. Detailed Implementation

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0025] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0026] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0027] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0028] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0029] To address the aforementioned issues, this exemplary embodiment provides a method for health diagnosis of an ice-melting system, which will be described below with reference to specific embodiments.

[0030] Figure 1 This is a flowchart illustrating a method for health diagnosis of an ice-melting system, provided as an exemplary embodiment of the present disclosure. The method can be executed by an ice-melting system health diagnosis device, which can be implemented in software and / or hardware and is generally integrated into an electronic device.

[0031] This exemplary embodiment takes a 1.5MW horizontal axis lift wind turbine in a domestic wind farm as the implementation object. The turbine is equipped with three fiberglass wind turbine blades, each blade with a built-in resistance electrothermal de-icing system. The de-icing system of a single blade is set with three independent heating circuits, corresponding to the three heating sections of the blade root, blade middle section and blade tip section respectively. The rated power supply voltage of a single heating circuit is AC220V and the rated heating power is 5kW. The heating element adopts a metal heating film embedded in the composite material layer of the blade. The power supply line is connected to the power supply system in the nacelle through the slip ring at the blade root.

[0032] This exemplary embodiment of the present disclosure is based on the above-described wind turbine blade electrothermal de-icing system, and implements a de-icing system health diagnosis method provided by this exemplary embodiment of the present disclosure, including: Step S101: Perform a broadband impedance scan on the target heating circuit to obtain impedance spectrum data.

[0033] In some exemplary embodiments, a broadband impedance scan is performed on the target heating circuit to obtain impedance spectrum data, including: When the ice melting system is not in operation, a broadband sweep excitation signal with a preset amplitude is injected into the target heating circuit to obtain the voltage response data and current response data of the target heating circuit. The voltage response data and the current response data are converted to the frequency domain to obtain voltage frequency domain phasors and current frequency domain phasors, respectively. Impedance spectrum data are obtained based on the ratio of the voltage frequency domain phasor to the current frequency domain phasor.

[0034] In some exemplary embodiments, the terms "electric heating de-icing system" and "de-icing system" both refer to the same system, namely, the wind turbine blade electric heating de-icing system.

[0035] In some exemplary embodiments, during normal operation of the wind turbine, a broadband impedance measurement unit integrated in parallel with the power supply terminal of the heating circuit of the electrothermal de-icing system injects a broadband sweep excitation signal of preset amplitude into the target heating circuit when the de-icing system is not in operation, thereby acquiring the response data of the target heating circuit.

[0036] In some exemplary embodiments, the acquired voltage response data and current response data are converted into frequency domain phasor data through a fast Fourier transform, and then impedance spectrum data is calculated using the complex impedance calculation formula. ; in, Represents angular frequency Impedance spectrum data of the corresponding target heating circuit; Represents angular frequency Frequency domain phasors of the voltage response data of the target heating circuit; Represents angular frequency Frequency domain phasors of the current response data of the target heating circuit; This represents the real part of the complex impedance, i.e., the resistive component of the target heating circuit; This represents the imaginary part of the complex impedance, i.e., the reactance component of the target heating circuit; It represents the imaginary unit.

[0037] In some exemplary embodiments, the wind turbine does not need to be shut down during the process of performing a broadband impedance scan on the target heating circuit to obtain impedance spectrum data, and the normal operating logic and standby status of the de-icing system are not affected or changed.

[0038] As an example, a wideband impedance measurement unit is connected in parallel to the power supply input terminals of the three heating circuits of the de-icing system of each blade. The signal output terminal of the measurement unit is connected to the edge computing gateway in the wind turbine nacelle. The edge computing gateway communicates with the original SCADA system of the turbine. During the normal grid-connected operation of the wind turbine, the edge computing gateway sends a sweep frequency acquisition command to the wideband impedance measurement unit during the interval when the de-icing system is not heating. The wideband impedance measurement unit injects a sweep frequency excitation signal with an amplitude of 2V and a frequency band of 10Hz~1MHz (full band) into the corresponding target heating circuit and collects the voltage response data and current response data of the target heating circuit.

[0039] Step S102: Obtain the operating condition data of the target heating circuit, calibrate the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extract features from the standard impedance spectrum data to obtain a standard feature vector.

[0040] In some exemplary embodiments, the calibration includes at least a condition normalization process.

[0041] In some exemplary embodiments, the operating condition data and the impedance spectrum data are synchronized and matched using the same timestamp.

[0042] In some exemplary embodiments, the steps of acquiring the operating condition data of the target heating circuit, calibrating the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extracting features from the standard impedance spectrum data to obtain a standard feature vector include: Based on a pre-built health status benchmark database, obtain the temperature correction coefficient corresponding to the ambient temperature in the operating condition data, and the blade pitch angle correction coefficient corresponding to the blade pitch angle in the operating condition data. The standard impedance spectrum data is obtained by dividing the impedance spectrum data by the product of the temperature correction factor and the pitch angle correction factor. Impedance spectrum feature parameters are extracted based on the standard impedance spectrum data. The impedance spectrum feature parameters include at least the change in the real part of the impedance in the preset low-frequency band, the change in the imaginary part of the impedance and the phase angle in the preset mid-frequency band, the offset of the resonant frequency point in the preset high-frequency band, and the change in the semicircle radius and curvature of the Nyquist curve. Based on a preset combination order, the impedance spectrum characteristic parameters are combined to obtain a standard feature vector.

[0043] In some exemplary embodiments, the edge computing gateway first uses a wavelet transform filtering algorithm to remove noise signals caused by on-site electromagnetic interference and unit vibration from the acquired impedance spectrum data. Then, based on the synchronously (at the same moment) acquired operating condition data and the operating condition correction coefficients in the pre-built health status benchmark database, the impedance spectrum data is subjected to baseline correction and operating condition normalization processing through the operating condition normalization formula to eliminate impedance baseline drift caused by changes in ambient temperature and blade attitude.

[0044] In some exemplary embodiments, the operating condition correction factor includes at least a temperature correction factor and a pitch angle correction factor, wherein the temperature correction factor is obtained in advance through a temperature calibration experiment under a reference operating condition, and the pitch angle correction factor is obtained in advance through a pitch angle calibration experiment under a reference operating condition.

[0045] In some exemplary embodiments, after the wind turbine blades are installed and the de-icing system is wired and debugged, and the de-icing system is confirmed to be in good condition by factory inspection and on-site no-load test, a wideband impedance scan test is performed on the three independent heating circuits of a single blade under the reference operating conditions to obtain the real part, imaginary part, impedance magnitude, and phase angle reference data of each heating circuit in the entire frequency band; at the same time, the above frequency scan test is repeated at typical operating points within the preset ambient temperature range and the preset blade pitch angle range to obtain the impedance spectrum correction coefficients under different operating conditions, and a health status reference database is pre-constructed.

[0046] In some exemplary embodiments, the operating condition normalization formula is as follows: ; in, This represents the standard impedance spectrum data after normalization of the operating conditions. Represents impedance spectrum data; This represents the temperature correction factor; This represents the pitch angle correction factor.

[0047] As an example, the SCADA system synchronously acquires the ambient temperature, blade pitch angle, and loop on / off status data corresponding to the moment of data acquisition and response, and matches a unique timestamp for each set of impedance spectrum data to achieve synchronous alignment between the operating condition data and the impedance spectrum data.

[0048] As an example, an ambient temperature of 25°C, standard atmospheric pressure, and blade pitch angle of 0° are selected as the baseline operating conditions.

[0049] As an example, after the wind turbine blades are installed and the de-icing system is wired and commissioned, and the de-icing system is confirmed to be in good condition by factory inspection and on-site no-load testing, wideband impedance scanning tests are performed on the three independent heating circuits of a single blade under the baseline conditions of ambient temperature 25℃, standard atmospheric pressure, and blade pitch angle 0°. The sweep frequency range is set to 10Hz~1MHz, the sweep frequency interval is 100 frequency points / decade, and the excitation signal amplitude is set to 2V. The real part, imaginary part, impedance magnitude, and phase angle baseline data of each heating circuit in the entire frequency band are obtained. At the same time, in the ambient temperature range of -30℃~40℃ and the blade pitch angle range of 0°~90°, the above sweep frequency test is repeated at typical operating points to obtain the impedance spectrum correction coefficients under different operating conditions, forming a complete health status baseline database.

[0050] As an example, after completing the normalization process, impedance spectrum characteristic parameters are extracted from the standard impedance spectrum data. These parameters include at least the real part change of impedance in the low-frequency band (10Hz~1kHz), the imaginary part and phase angle change of impedance in the mid-frequency band (1kHz~100kHz), the resonant frequency shift in the high-frequency band (100kHz~1MHz), and the semicircular radius and curvature change of the Nyquist curve. These parameters are combined in a fixed order, such as the real part change of impedance in the low-frequency band, the imaginary part and phase angle change of impedance in the mid-frequency band, the resonant frequency shift in the high-frequency band, and the semicircular radius and curvature change of the Nyquist curve, to form an n-dimensional standardized feature vector X, thus completing the standardized extraction of the characteristic parameters required for diagnosis.

[0051] Step S103: Based on the standard feature vector, match it with the health feature vector set and the fault feature vector set respectively to determine the health status, fault type and fault location of the target heating circuit, and output the health diagnosis result.

[0052] In some exemplary embodiments, determining the health status of the target heating circuit by matching the standard feature vector with a set of health feature vectors includes: Based on the Mahalanobis distance algorithm, the degree of deviation between the standard feature vector and the health feature vector of the corresponding working condition and the corresponding loop in the health feature vector set is obtained; Based on the degree of deviation, the health quantification index of the target heating circuit is obtained by calculation using an exponential decay function. Based on the preset health threshold and the health quantification index, the health status of the target heating circuit is determined. The health status includes healthy state, slight deterioration warning state, moderate deterioration concern state, and severe fault state.

[0053] In some exemplary embodiments, determining the fault type of the target heating circuit by matching the standard feature vector with the fault feature vector set includes: Based on the weighted cosine similarity algorithm, the matching degree between the standard feature vector and the fault feature vector in the fault feature vector set is calculated, and the fault type corresponding to the maximum matching degree is selected as the fault type of the target heating circuit.

[0054] In some exemplary embodiments, determining the faulty section of the target heating circuit by matching the standard feature vector with the fault feature vector set includes: Based on the impedance response attenuation difference of the standard feature vector under different feature frequency bands, it is compared with the standard attenuation characteristics corresponding to the blade root segment, blade middle segment and blade tip segment of the target heating circuit to obtain the matching degree of each segment, and the segment with the largest matching degree is selected as the segment where the fault is located.

[0055] In some exemplary embodiments, the edge computing gateway matches the standard feature vector with the benchmark feature vectors of the corresponding operating conditions and circuits in a pre-built health benchmark database, and calculates the degree of deviation between the standard feature vector and the benchmark feature vector based on the Mahalanobis distance algorithm: ; in, This indicates the degree of deviation between the standard eigenvector and the baseline eigenvector; express 3D standard eigenvectors; The mean vector representing the baseline eigenvectors; The covariance matrix represents the baseline eigenvectors; superscript Indicates matrix transpose operation; superscript This represents the matrix inversion operation.

[0056] In some exemplary embodiments, a health metric for the target heating circuit is calculated using an exponential decay function based on the degree of deviation. ; in, A quantitative indicator representing the health of the target heating circuit; This represents the proportionality coefficient, determined through calibration experiments, used to match the linear correspondence between the degree of deviation and the degree of health. It represents the base of the natural logarithm.

[0057] In some exemplary embodiments, for a target heating circuit determined to be in a deterioration warning state, a concern state, or a fault state, the edge computing gateway performs multi-dimensional matching of its standard feature vector X with the fault feature vectors of various types of faults in a typical fault feature database, and calculates the matching degree using a weighted cosine similarity algorithm: ; in, Represents the standard eigenvector With the Matching degree of fault feature vectors, value range ; Represents the standard eigenvector; Indicates the first Fault feature vector; This represents the L2 norm operation of vectors.

[0058] In some exemplary embodiments, impedance spectrum characteristic data under different fault types and different degrees of degradation are obtained by artificially simulating four typical faults: loose circuit connection points, local ablation of heating film, wire breakage, and insulation layer damage. The specific characteristic frequency bands and parameter change patterns corresponding to each type of fault are extracted, and a typical fault characteristic database is pre-constructed.

[0059] In some exemplary embodiments, the heating circuits of different sections have different attenuation characteristics for high-frequency signals due to different transmission distances. The greater the distance, the greater the attenuation of high-frequency signals. Therefore, under the factory-safe state of the system, by disconnecting other sections and keeping only the target section, the impedance spectrum of each section is measured in the full frequency band, and the impedance modulus attenuation characteristics of the high-frequency band are extracted as the standard attenuation characteristics of each section. In addition, depending on the system characteristics, the mid-frequency band or low-frequency band, which are sensitive to distance, can be selected to locate the fault in the section.

[0060] In some exemplary embodiments, the edge computing gateway synchronously transmits the diagnosed health status, health value, fault type, and fault location results to the wind turbine main control system and the operation and maintenance management platform of the wind farm central control center via a fiber optic ring network.

[0061] As an example, the system classifies the health status based on a preset health threshold. A health score of HI ≥ 90 indicates a healthy state, 80 ≤ HI < 90 indicates a slight deterioration warning state, 60 ≤ HI < 80 indicates a moderate deterioration concern state, and HI < 60 indicates a serious fault state, thus achieving quantitative assessment and classification of the health status of the ice melting system.

[0062] As an example, a significant increase in the real part of the impedance in the low-frequency band of 10Hz~1kHz (more than 20%) corresponds to a loose connection point in the circuit; a sudden change in the imaginary part of the impedance and the phase angle in the mid-frequency band of 1kHz~100kHz (a phase angle change of more than 15°) corresponds to a local ablation fault of the heating element; an impedance magnitude approaching infinity across the entire frequency band (an impedance magnitude greater than 10 megohms across the entire frequency band) corresponds to a conductor breakage fault in the circuit; and a large shift in the resonant frequency point in the high-frequency band of 100kHz~1MHz (a shift of more than 5kHz) corresponds to a deterioration fault of the insulation layer.

[0063] As an example, the target heating circuit is pre-defined into three sections: the blade root section (closest to the power input terminal, with a line length of approximately 5 meters), the blade middle section (with a line length of approximately 10 meters), and the blade tip section (farthest from the power input terminal, with a line length of approximately 15 meters).

[0064] As an example, the standard attenuation characteristic of the blade root segment in the high-frequency band is approximately 0.1 dB / m, that of the mid-section is approximately 0.3 dB / m, and that of the tip is approximately 0.5 dB / m. If the measured impedance modulus attenuation of the standard eigenvector in the high-frequency band is 0.48 dB / m, comparing this attenuation with the standard attenuation characteristics of each of the above segments, it is found that it is closest to the standard attenuation characteristic of the tip segment (0.5 dB / m), thus the fault is located in the tip segment. If the measured high-frequency attenuation is 0.26 dB / m, it is closest to the standard attenuation characteristic of the mid-section (0.3 dB / m), thus the fault is located in the mid-section. If the measured high-frequency attenuation is 0.13 dB / m, then the fault is located in the root segment.

[0065] In some exemplary embodiments, the method further includes: Match a preset operation and maintenance strategy based on the health status; If the health status is healthy, then the monitoring period will be maintained; If the health status is in a state of slight deterioration warning, the monitoring period will be shortened and a warning notification will be sent. If the health status is classified as moderately deteriorated and of concern, it will be included in the planned maintenance list. If the health status is a serious fault, a shutdown warning signal will be triggered and maintenance instructions will be sent.

[0066] As an example, for heating circuits in a healthy state, a regular monitoring cycle of 24 hours / time is maintained; for circuits in a state of slight deterioration warning, the monitoring cycle is shortened to 2 hours / time, continuously tracking the deterioration trend and pushing warning prompts to maintenance personnel; for circuits in a state of moderate deterioration concern, they are included in the monthly planned maintenance list, and the corresponding blades and heating sections are marked; for circuits in a state of severe failure, a shutdown warning signal is triggered to the main control system, and at the same time, precise maintenance guidance including the fault location and fault type is pushed to maintenance personnel.

[0067] In some exemplary embodiments, after the target heating circuit has been inspected and maintained, and the system has been confirmed to be in good health through on-site testing, the broadband impedance scan test is re-executed, and the newly acquired healthy impedance spectrum data is updated to the healthy reference database, replacing the original failed reference data.

[0068] As an example, every 6 months, based on impedance spectrum data collected in the past 6 months that has been consistently determined to be in a healthy state, the mean of the eigenvectors, covariance matrix, operating condition correction coefficient and health degree proportional coefficient in the health status benchmark database are adaptively corrected to adapt to the slow drift of parameters caused by normal aging of heating circuit and blade composite materials, reduce the probability of false alarms and false alarms during long-term operation, and improve the long-term stability and environmental adaptability of health diagnosis.

[0069] An exemplary embodiment of this disclosure provides a method for health diagnosis of an ice-melting system. By integrating an ice-melting system health diagnosis device inside a wind turbine, the method can collect characteristic parameters of the electrothermal ice-melting system without shutting down the wind turbine, and diagnose the health status of the electrothermal ice-melting system, effectively reducing power outage losses of the wind turbine and the safety risks of manual inspection.

[0070] To achieve the above embodiments, this disclosure also proposes a health diagnostic device for an ice-melting system.

[0071] Figure 2 This is a schematic diagram of a health diagnostic device for an ice-melting system provided as an exemplary embodiment of the present disclosure. The device 200 can be implemented by software and / or hardware and is generally integrated into an electronic device. For example... Figure 2 As shown, the device 200 includes: a first obtaining module 201, a second obtaining module 202, and an output module 203, wherein, The first module 201 is used to perform a broadband impedance scan on the target heating circuit to obtain impedance spectrum data. The second module 202 is used to acquire the operating condition data of the target heating circuit, calibrate the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extract features from the standard impedance spectrum data to obtain a standard feature vector. The output module 203 is used to match the standard feature vector with the health feature vector set and the fault feature vector set respectively, to determine the health status, fault type and fault location of the target heating circuit, and output the health diagnosis result.

[0072] The apparatus provided in the exemplary embodiments of this disclosure includes a first obtaining module 201, specifically used for: When the ice melting system is not in operation, a broadband sweep excitation signal with a preset amplitude is injected into the target heating circuit to obtain the voltage response data and current response data of the target heating circuit. The voltage response data and the current response data are converted to the frequency domain to obtain voltage frequency domain phasors and current frequency domain phasors, respectively. Impedance spectrum data are obtained based on the ratio of the voltage frequency domain phasor to the current frequency domain phasor.

[0073] The apparatus provided in the exemplary embodiments of this disclosure includes at least a condition normalization process for calibration. The operating condition data and the impedance spectrum data are synchronized and matched using the same timestamp. The second obtaining module 202 is specifically used for: Based on a pre-built health status benchmark database, obtain the temperature correction coefficient corresponding to the ambient temperature in the operating condition data, and the blade pitch angle correction coefficient corresponding to the blade pitch angle in the operating condition data. The standard impedance spectrum data is obtained by dividing the impedance spectrum data by the product of the temperature correction factor and the pitch angle correction factor. Impedance spectrum feature parameters are extracted based on the standard impedance spectrum data. The impedance spectrum feature parameters include at least the change in the real part of the impedance in the preset low-frequency band, the change in the imaginary part of the impedance and the phase angle in the preset mid-frequency band, the offset of the resonant frequency point in the preset high-frequency band, and the change in the semicircle radius and curvature of the Nyquist curve. Based on a preset combination order, the impedance spectrum characteristic parameters are combined to obtain a standard feature vector.

[0074] The apparatus provided in the exemplary embodiments of this disclosure, wherein the output module 203 is specifically used for: Based on the Mahalanobis distance algorithm, the degree of deviation between the standard feature vector and the health feature vector of the corresponding working condition and the corresponding loop in the health feature vector set is obtained; Based on the degree of deviation, the health quantification index of the target heating circuit is obtained by calculation using an exponential decay function. Based on the preset health threshold and the health quantification index, the health status of the target heating circuit is determined. The health status includes healthy state, slight deterioration warning state, moderate deterioration concern state, and severe fault state.

[0075] The apparatus provided in the exemplary embodiments of this disclosure, wherein the output module 203 is specifically used for: Based on the weighted cosine similarity algorithm, the matching degree between the standard feature vector and the fault feature vector in the fault feature vector set is calculated, and the fault type corresponding to the maximum matching degree is selected as the fault type of the target heating circuit.

[0076] The apparatus provided in the exemplary embodiments of this disclosure, wherein the output module 203 is specifically used for: Based on the impedance response attenuation difference of the standard feature vector under different feature frequency bands, it is compared with the standard attenuation characteristics corresponding to the blade root segment, blade middle segment and blade tip segment of the target heating circuit to obtain the matching degree of each segment, and the segment with the largest matching degree is selected as the segment where the fault is located.

[0077] The apparatus provided in the exemplary embodiments of this disclosure, the apparatus 200 further includes: Match a preset operation and maintenance strategy based on the health status; If the health status is healthy, then the monitoring period will be maintained; If the health status is in a state of slight deterioration warning, the monitoring period will be shortened and a warning notification will be sent. If the health status is classified as moderately deteriorated and of concern, it will be included in the planned maintenance list. If the health status is a serious fault, a shutdown warning signal will be triggered and maintenance instructions will be sent.

[0078] The ice-melting system health diagnosis device provided by the exemplary embodiments of this disclosure can execute the ice-melting system health diagnosis method provided by any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0079] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program / instructions, which, when executed by a processor, implements a method for health diagnosis of an ice-melting system as described above.

[0080] Figure 3 A schematic diagram of the structure of an electronic device provided for an exemplary embodiment of this disclosure.

[0081] The following is a detailed reference. Figure 3 The diagram illustrates a structural schematic suitable for implementing the electronic device 300 in the exemplary embodiments of this disclosure. The electronic device 300 in the exemplary embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the exemplary embodiments disclosed herein.

[0082] like Figure 3As shown, the electronic device 300 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a memory 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processor 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0083] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0084] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a memory 308, or installed from a ROM 302. When the computer program is executed by the processor 301, it performs the functions defined in an exemplary embodiment of this disclosure of a method for health diagnosis of an ice-melting system.

[0085] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0086] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0087] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0088] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned method for diagnosing the health of an ice-melting system.

[0089] Electronic devices can be programmed with computer program code in one or more programming languages ​​or combinations thereof to perform the operations of this disclosure. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] The units described in the exemplary embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0092] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0093] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0094] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0095] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0096] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for health diagnosis of an ice-melting system, characterized in that, include: A broadband impedance scan was performed on the target heating circuit to obtain impedance spectrum data; The operating condition data of the target heating circuit is obtained, and the impedance spectrum data is calibrated based on the operating condition data to obtain standard impedance spectrum data. Feature extraction is performed on the standard impedance spectrum data to obtain a standard feature vector. Based on the standard feature vector, the health feature vector set and the fault feature vector set are matched respectively to determine the health status, fault type and fault location of the target heating circuit, and output the health diagnosis result.

2. The method according to claim 1, characterized in that, The broadband impedance scan of the target heating circuit to obtain impedance spectrum data includes: When the ice melting system is not in operation, a broadband sweep excitation signal with a preset amplitude is injected into the target heating circuit to obtain the voltage response data and current response data of the target heating circuit. The voltage response data and the current response data are converted to the frequency domain to obtain voltage frequency domain phasors and current frequency domain phasors, respectively. Impedance spectrum data are obtained based on the ratio of the voltage frequency domain phasor to the current frequency domain phasor.

3. The method according to claim 1, characterized in that, The calibration includes at least a condition normalization process; The operating condition data and the impedance spectrum data are synchronized and matched using the same timestamp. The process involves acquiring the operating condition data of the target heating circuit, calibrating the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extracting features from the standard impedance spectrum data to obtain a standard feature vector, including: Based on a pre-built health status benchmark database, obtain the temperature correction coefficient corresponding to the ambient temperature in the operating condition data, and the blade pitch angle correction coefficient corresponding to the blade pitch angle in the operating condition data. The standard impedance spectrum data is obtained by dividing the impedance spectrum data by the product of the temperature correction factor and the pitch angle correction factor. Impedance spectrum feature parameters are extracted based on the standard impedance spectrum data. The impedance spectrum feature parameters include at least the change in the real part of the impedance in the preset low-frequency band, the change in the imaginary part of the impedance and the phase angle in the preset mid-frequency band, the offset of the resonant frequency point in the preset high-frequency band, and the change in the semicircle radius and curvature of the Nyquist curve. Based on a preset combination order, the impedance spectrum characteristic parameters are combined to obtain a standard feature vector.

4. The method according to claim 1, characterized in that, The health status of the target heating circuit is determined by matching the standard feature vector with the health feature vector set, including: Based on the Mahalanobis distance algorithm, the degree of deviation between the standard feature vector and the health feature vector of the corresponding working condition and the corresponding loop in the health feature vector set is obtained; Based on the degree of deviation, the health quantification index of the target heating circuit is obtained by calculation using an exponential decay function. Based on the preset health threshold and the health quantification index, the health status of the target heating circuit is determined. The health status includes healthy state, slight deterioration warning state, moderate deterioration concern state, and severe fault state.

5. The method according to claim 1, characterized in that, Based on the matching of the standard feature vector with the fault feature vector set, the fault type of the target heating circuit is determined, including: Based on the weighted cosine similarity algorithm, the matching degree between the standard feature vector and the fault feature vector in the fault feature vector set is calculated, and the fault type corresponding to the maximum matching degree is selected as the fault type of the target heating circuit.

6. The method according to claim 1, characterized in that, Based on matching the standard feature vector with the fault feature vector set, the faulty section of the target heating circuit is determined, including: Based on the impedance response attenuation difference of the standard feature vector under different feature frequency bands, it is compared with the standard attenuation characteristics corresponding to the blade root segment, blade middle segment and blade tip segment of the target heating circuit to obtain the matching degree of each segment, and the segment with the largest matching degree is selected as the segment where the fault is located.

7. The method according to claim 1, characterized in that, Also includes: Match a preset operation and maintenance strategy based on the health status; If the health status is healthy, then the monitoring period will be maintained; If the health status is in a state of slight deterioration warning, the monitoring period will be shortened and a warning notification will be sent. If the health status is classified as moderately deteriorated and of concern, it will be included in the planned maintenance list. If the health status is a serious fault, a shutdown warning signal will be triggered and maintenance instructions will be sent.

8. A health diagnostic device for an ice-melting system, characterized in that, include: The first module is used to perform a broadband impedance scan on the target heating circuit to obtain impedance spectrum data. The second module is used to acquire the operating condition data of the target heating circuit, calibrate the impedance spectrum data based on the operating condition data to obtain standard impedance spectrum data, and extract features from the standard impedance spectrum data to obtain a standard feature vector. The output module is used to match the standard feature vector with the health feature vector set and the fault feature vector set respectively, to determine the health status, fault type and fault segment of the target heating circuit, and output the health diagnosis result.

9. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program / instruction thereon, which, when executed by a processor, implements the steps of the method described in any one of claims 1-7.

Images