A method and system for monitoring the performance of power cable insulation

Abstract

The present application relates to the technical field of cable insulation monitoring, and particularly relates to a power cable insulation performance monitoring method and system. The method comprises: obtaining a dielectric loss tangent signal of a power cable, and performing blind source separation on the dielectric loss tangent signal; for each independent component of the blind source separation, two composite discrimination indexes are constructed: a component fluctuation spectrum index, which is used to quantify the stationarity of the signal from the frequency characteristic; and an environmental coupling coefficient, which is used to judge the signal source from the correlation with temperature and load and the change trend of itself. An aging discrimination factor is calculated by fusing the two indexes, a real aging trend signal is identified from multiple independent components, so as to realize the monitoring of the power cable insulation performance. The present application significantly improves the automation level and anti-interference ability of cable insulation monitoring, and effectively avoids misjudgment caused by environmental interference.

Description

Technical Field

[0001] This invention relates to the field of cable insulation monitoring technology, and in particular to a method and system for monitoring the insulation performance of power cables. Background Technology

[0002] In modern power grid operation systems, power cables, as the core carriers of electrical energy transmission, directly determine the reliability and operational safety of the power grid's power supply through their insulation performance. Cable insulation aging is a significant cause of power grid faults; therefore, real-time monitoring of insulation performance has become a crucial aspect of power grid operation and maintenance. Among these factors, the dielectric loss tangent... It is a core quantitative indicator characterizing the degree of insulation aging.

[0003] However, in real-world operating environments, the acquired dielectric loss tangent signal is often overwhelmed by strong interference such as low-frequency drift caused by temperature and load variations, and high-frequency noise from complex electromagnetic environments, resulting in an extremely low signal-to-noise ratio. Traditional frequency domain filtering methods struggle to handle this complex non-stationary interference, making it impossible to accurately reproduce the true aging trend.

[0004] Existing technologies have incorporated Independent Component Analysis (ICA) algorithms. As an advanced blind source separation technique, ICA can separate multiple statistically independent source signals from mixed signals, theoretically distinguishing real aging signals from various interference signals. However, the ICA algorithm has inherent blindness when applied to this scenario. The algorithm only performs mathematical separation; the physical meaning, amplitude, and order of the separation results are uncertain. This means that after obtaining multiple separated independent components, the system cannot automatically and objectively identify which component represents a slowly changing, unidirectional insulation aging signal, which is drift interference highly correlated with environmental factors, and which is random high-frequency noise. This reliance on mathematical separation without the ability to analyze and judge the physical characteristics of each component makes automated, high-precision monitoring difficult to achieve, and is highly susceptible to erroneous diagnostic results due to human error or algorithmic confusion. Summary of the Invention

[0005] To address the technical problem that the aforementioned ICA algorithm suffers from blindness in signal separation, failing to automatically identify the physical meaning of each component and thus leading to erroneous monitoring results, this invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for monitoring the insulation performance of power cables, the method comprising the steps of:

[0007] The process involves acquiring the dielectric loss tangent signal, temperature data, and load current data of a power cable; performing blind source separation on the dielectric loss tangent signal to obtain multiple independent components; distinguishing the high-frequency and low-frequency ranges of each independent component based on a preset frequency division threshold; calculating the component fluctuation spectrum index of each independent component based on the ratio of energy in the high-frequency range to energy in the low-frequency range; obtaining the environmental coupling coefficient of each independent component based on the time correlation between the independent component and the temperature and load current data, as well as the changing trend of the independent component; calculating the aging discrimination factor of each independent component based on the component fluctuation spectrum index and the environmental coupling coefficient; the aging discrimination factor being negatively correlated with the product of the component fluctuation spectrum index and the environmental coupling coefficient; and selecting a target signal from the multiple independent components based on the aging discrimination factor, thereby enabling the monitoring of the insulation performance of the power cable.

[0008] This invention first decomposes a mixed signal into multiple independent components through blind source separation. Then, it proposes two composite indices: the component fluctuation spectrum index and the environmental coupling coefficient. The former judges the signal's stability based on its inherent frequency characteristics, while the latter determines its source based on the signal's correlation with the external environment and its own changing trends. Finally, by fusing information from these two dimensions, an aging discrimination factor is calculated, thereby fundamentally distinguishing the slow, stable true aging trend from drastic, random environmental interference, such as temperature, load current changes, and noise. This significantly improves the accuracy and reliability of insulation performance monitoring, effectively avoids false alarms caused by environmental factors, and solves the long-standing technical problems of poor anti-interference capability and susceptibility to misjudgment in existing technologies.

[0009] Preferably, the component fluctuation spectrum index of the independent component satisfies the following relationship:

[0010] ;

[0011] in, It is the first The component fluctuation spectrum index of each independent component; It is the frequency division threshold between the low-frequency range and the high-frequency range; It is the first The highest frequency of an independent component; It is the first The frequency of each independent component; It is the first The power spectral density function of the nth independent component, by applying the nth... The independent components are obtained by performing Fourier transform.

[0012] This invention defines the component fluctuation spectrum index by the ratio of high-frequency and low-frequency power spectra. This approach makes the quantification of signal fluctuations more objective, accurate, and reproducible, providing a solid mathematical foundation for the accurate calculation of subsequent discriminant factors.

[0013] Preferably, obtaining the environmental coupling coefficient of the independent component includes: constructing a time series corresponding to the independent component, denoted as the independent component series; and also constructing a temperature series corresponding to the temperature data and a load current series corresponding to the load current data; the environmental coupling coefficient of the independent component satisfies the following relationship:

[0014] ;

[0015] in, It is the first The environmental coupling coefficient of an independent component; , They are the first The correlation coefficients between the sequences corresponding to each independent component and the temperature and load current sequences during the same period; It is the first The number of groups in the sequence corresponding to each independent component whose difference between adjacent data points is positive; It is the first The number of groups in the sequence corresponding to each independent component whose difference between adjacent data points is not positive; It is the number of data points in the sequence corresponding to the independent component; It is a preset micro value; It is a standard normalized function; It is the absolute value symbol.

[0016] This invention integrates the correlation between independent components and the two main sources of interference, temperature and load current, as well as the two key characteristics of whether the signal itself has a monotonically increasing trend, into a single formula. This comprehensive consideration of multiple dimensions and factors makes the judgment on whether an independent component is due to environmental interference or actual aging more comprehensive and robust, significantly improving the ability to distinguish between them.

[0017] Preferably, the difference between adjacent data points is the difference between the previous data point and the next data point.

[0018] Preferably, the aging discrimination factor of each independent component is calculated by a negative exponential function of the product of the component fluctuation spectrum index and the environmental coupling coefficient of the independent component.

[0019] This invention clarifies that the aging discrimination factor is calculated as a negative exponential function of the product of the component fluctuation spectrum index and the environmental coupling coefficient. This nonlinear mapping effectively amplifies the differences in discrimination factors between the target signal and the interference signal, resulting in higher discriminative power and clearer decision boundaries in the screening results, thereby improving the accuracy of the final screening.

[0020] Preferably, the step of selecting the target signal from the plurality of independent components based on the aging discriminant factor includes: determining the independent component with the largest aging discriminant factor as the target signal.

[0021] Preferably, the monitoring of the insulation performance of the power cable based on the target signal includes: obtaining the scaling factor corresponding to the target signal by using the reverse process of the blind source separation; recovering the amplitude of the target signal using the scaling factor, and superimposing the mean value of the dielectric loss tangent signal to obtain a pure dielectric loss tangent value variation curve; and using the local outlier factor algorithm to detect anomalies in the pure dielectric loss tangent value variation curve.

[0022] After successfully identifying the target signal, this invention further utilizes the inverse process of blind source separation to reconstruct a pure aging curve free of all interference, and introduces a local outlier factor algorithm for anomaly detection. This not only provides implementers with a clearer and more intuitive aging trend, but also enables automatic early warning of potential sudden failures.

[0023] Preferably, acquiring the dielectric loss tangent signal of the power cable specifically includes: synchronously acquiring the voltage reference signal and the total current signal of the power cable; calculating the phase difference between the voltage reference signal and the total current signal; determining the loss angle based on the phase difference, and calculating the dielectric loss tangent signal.

[0024] Preferably, the blind source separation is achieved using an independent component analysis algorithm.

[0025] In a second aspect, the present invention provides a power cable insulation performance monitoring system, which includes a memory and a processor. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the power cable insulation performance monitoring method of the first aspect of the present invention is implemented.

[0026] By adopting the above technical solution, a computer program for monitoring the insulation performance of power cables according to the first aspect of the present invention is generated and stored in a memory so that it can be loaded and executed by a processor. A terminal device can then be made based on the memory and the processor for convenient use.

[0027] The beneficial effects of this invention are as follows: Addressing the challenge of existing technologies failing to accurately distinguish between genuine aging and environmental interference, this invention proposes a discrimination mechanism based on blind source separation and multi-dimensional feature fusion. It constructs two composite indices—the component fluctuation spectrum index and the environmental coupling coefficient—to accurately profile each independent signal component after separation, considering both the signal's intrinsic stability and extrinsic correlation. Finally, it calculates the aging discrimination factor, thereby intelligently identifying the genuine aging signal. This method effectively filters out strong interferences such as temperature and load, significantly improving monitoring accuracy. Furthermore, this invention introduces a local outlier factor algorithm for anomaly detection. This not only provides implementers with a clearer and more intuitive understanding of aging trends but also enables automatic early warning of potential sudden faults. Attached Figure Description

[0028] Figure 1 A flowchart illustrating a method for monitoring the insulation performance of power cables, provided as an embodiment of the present invention;

[0029] Figure 2 A graph of the original source signal provided in an embodiment of the present invention;

[0030] Figure 3 This is a curve of the dielectric loss tangent value provided in an embodiment of the present invention;

[0031] Figure 4 A graph of multiple independent components output by the ICA algorithm provided in this embodiment of the invention;

[0032] Figure 5 This is a curve showing the variation of the loss tangent of the pure dielectric provided in an embodiment of the present invention.

[0033] Figure 6 This is a structural block diagram of a power cable insulation performance monitoring system provided in an embodiment of the present invention. Detailed Implementation

[0034] The first aspect of this invention provides a method for monitoring the insulation performance of power cables, such as... Figure 1 As shown, the method includes steps S100-S600:

[0035] Step S100: Obtain the dielectric loss tangent signal, temperature data, and load current data of the power cable.

[0036] It should be noted that this step aims to obtain necessary basic data for subsequent insulation condition analysis and evaluation. Among these, the dielectric loss tangent value (… Energy loss (EW) is an internationally recognized core physical quantity that can sensitively reflect the internal energy loss of dielectrics and the degree of aging of insulating materials. However, in online monitoring environments, The measured values ​​are highly susceptible to fluctuations in cable operating temperature and load current, resulting in drift and disturbances unrelated to actual aging. Therefore, synchronously acquiring these three sets of key data signals is the data foundation for constructing subsequent interference elimination and accurate aging trend identification models.

[0037] Specifically, a non-intrusive high-frequency current transformer is installed on the cable grounding wire to measure the total current signal flowing through the cable insulation layer in real time. This signal includes capacitive current and a weak resistive current related to insulation loss. Simultaneously, the system uses a capacitive voltage divider to synchronously acquire the voltage reference signal from the power grid.

[0038] In one feasible implementation, the acquisition device samples the aforementioned current and voltage signals at a frequency of 50Hz. Subsequently, in the data processing unit, a Fast Fourier Transform (FFT) algorithm is used to calculate the phase difference between the voltage and the total current signal. This phase difference is compared with... The complementary angle is the loss angle. And then calculate The value is the dielectric loss tangent signal. It is calculated from the values ​​at each sampling time. The values ​​are arranged in chronological order, thus constructing a time series of the dielectric loss tangent signal, which serves as the core input for subsequent analysis. Regarding the sampling time, data from 1000 time points is considered; implementers can choose according to their needs.

[0039] At the same time, temperature and load current data of the cable are acquired using temperature and current sensors deployed on the surface of the cable at the same 50Hz acquisition frequency.

[0040] At this point, three sets of key data have been obtained for subsequent analysis.

[0041] Step S200: Perform blind source separation on the dielectric loss tangent signal to obtain multiple independent components.

[0042] It should be noted that the original acquired dielectric loss tangent signal is a complex hybrid signal, typically containing at least three types of signal sources linearly superimposed: a signal representing the true aging trend of irreversible insulation degradation, a reversible drift signal caused by temperature and load changes, and a high-frequency noise signal generated by electromagnetic interference or measurement errors. For example... Figure 2 The graph shown is a curve of the original source signal. In this graph, the horizontal axis represents the sampling points, and the vertical axis represents the amplitude of the original signal. The graph contains three curves: the blue curve is the aging trend signal curve, the green curve is the high-frequency noise signal curve, and the orange curve is the environmental drift signal curve. The original source signal is existing technology and is the fundamental reason for the existence of ICA, so it will not be elaborated on here.

[0043] like Figure 3The figure shows the dielectric loss tangent signal curve. In this figure, the horizontal axis represents the sampling point, and the vertical axis represents the amplitude of the mixed dielectric loss tangent signal. The figure also contains three curves: the blue curve is the curve after mixing the aging trend signal, the green curve is the curve after mixing the high-frequency noise signal, and the orange curve is the curve after mixing the environmental drift signal.

[0044] Blind source separation (BSS) technology can recover the original, statistically independent source signals to a maximum extent when both the source signals and the mixing matrix are unknown. The purpose of this step is to utilize this technology to recover the mixed signals... The signal is decomposed into a series of purer signal components with independent physical meaning.

[0045] Specifically, Independent Component Analysis (ICA) is the preferred technique for achieving blind source separation. ICA is a blind source separation tool whose core idea is to find an unmixing matrix that maximizes the non-Gaussianity of the output signal components, thereby achieving the highest statistical independence among the components.

[0046] The dielectric loss tangent signal obtained in step S100 is used as input. The ICA algorithm is executed to output multiple independent signal components, i.e., independent components. The physical meaning of these independent components is unknown at the beginning of the separation process; they may correspond to real insulation aging signals, high-frequency noise signals, or temperature- and load-related environmental drift signals. For example... Figure 4 The graph shown represents the output of multiple independent signal components after executing the ICA algorithm. The horizontal axis represents the sampling points, and the vertical axis represents the amplitude of each independent component. The graph also contains three curves: the blue curve corresponding to IC-1 is the aging trend signal curve separated by ICA; the green curve corresponding to IC-3 is the high-frequency noise signal curve separated by ICA; and the orange curve corresponding to IC-2 is the environmental drift signal curve separated by ICA. The ICA algorithm is existing technology and will not be elaborated upon further here.

[0047] Thus, multiple independent components obtained from the decomposition of the dielectric loss tangent signal were acquired.

[0048] Step S300: Distinguish the high-frequency and low-frequency ranges of each independent component according to a preset frequency division threshold, and calculate the component fluctuation spectrum index of each independent component based on the ratio of the energy of the high-frequency range to the energy of the low-frequency range.

[0049] It should be noted that each independent component typically exhibits significantly different characteristics in the frequency domain, while insulation aging is an extremely slow physicochemical process. Its corresponding signal components will inevitably exhibit slowly varying signal characteristics in the frequency domain, with energy highly concentrated in the extremely low frequency band. In contrast, various noises and periodic interferences are mainly distributed in the high frequency band. Therefore, by quantifying the energy distribution characteristics of each independent component in the frequency domain, this invention can preliminarily distinguish potential aging signals from high-frequency interference.

[0050] Specifically, the first one separated from ICA Performing a Fourier transform on each independent component yields its power spectral density function. .

[0051] Based on the above logic, the first Component fluctuation spectrum index of each independent component Satisfying the relation:

[0052] ;

[0053] in, It is the frequency division threshold between the low-frequency range and the high-frequency range; It is the first The highest frequency of an independent component; It is the first The frequency of each independent component; It is the first The power spectral density function of the nth independent component, by applying the nth... The independent components are obtained by performing Fourier transform.

[0054] In this relation, the numerator represents the first... The signal of each independent component in The total energy in the high-frequency range, the denominator represents the first... The signal of each independent component in The total energy in the low-frequency range. Therefore, when the component fluctuation spectrum index... A larger value indicates that the energy of this independent component is more concentrated in the high-frequency part, and it is more likely to correspond to high-frequency noise or periodic interference. Conversely, when... The smaller the value, the more concentrated the energy of the component is in the low-frequency part, and the greater the possibility that it belongs to a slowly varying signal.

[0055] It should be added that, This is a frequency threshold used to define the low-frequency and high-frequency ranges, and its setting is crucial for effective separation. The selection of this threshold is based on the characteristic frequency that distinguishes between the true aging trend and periodic environmental interference. The true insulation aging of power cables is an extremely low-frequency process measured in months or years, while the most significant low-frequency interference originates from the daily variation cycle caused by factors such as temperature and load, with a characteristic frequency of approximately [missing information]. Hz. In one feasible implementation, frequency division thresholds can be used. Set as Hz. This setting ensures that the energy of major disturbances such as daily variation cycles is included in the high-frequency part of the numerator of the equation, while the energy of the actual aging trend is attributed to the low-frequency part of the denominator. Calculated component fluctuation spectrum index. This allows for highly effective characterization of the physical properties of signal components, laying the foundation for subsequent accurate identification. Those skilled in the art will understand that, under other specific operating conditions, such as when weekly variations are the primary interference, the value of the frequency division threshold can be adaptively adjusted.

[0056] It should also be noted that the highest frequency Typically, half of the sampling frequency is taken, and the highest frequency analyzed is... Setting the sampling frequency to half is not an arbitrary choice, but strictly follows a fundamental principle in digital signal processing, namely the Nyquist-Shannon sampling theorem, to ensure the effectiveness and accuracy of spectral analysis. The Nyquist-Shannon sampling theorem is existing technology and will not be discussed further here.

[0057] Thus, the component fluctuation spectrum index, which can characterize the frequency distribution features of each independent component, has been obtained.

[0058] Step S400: For each independent component, based on the time correlation between the independent component and temperature data and load current data, as well as the changing trend of the independent component, obtain the environmental coupling coefficient of the independent component.

[0059] It should be noted that, based on the component fluctuation spectral index of each independent component, we can distinguish between low-frequency and high-frequency signal components. Low-frequency signal components may include both genuine insulation aging signals and drift interference signals caused by changes in environmental factors such as temperature and load, which also exhibit low-frequency characteristics. These two types of signals have similar morphology in the time domain, which is the main reason for misjudgments by traditional methods.

[0060] True insulation aging is essentially a permanent degradation of the inherent properties of the cable insulation material itself. This degradation trend is unidirectional and irreversible, with a weak direct correlation to short-term fluctuations in external environmental factors such as temperature and load. Environmental drift interference, on the other hand, is highly correlated with changes in temperature and load, and is usually a reversible fluctuation. This step aims to construct a comprehensive index that can simultaneously quantify environmental relevance and trend reversibility.

[0061] Specifically, in order to conduct subsequent quantitative analysis, it is first necessary to construct a structured time series from the original data signal and the isolated independent components.

[0062] For the construction of the independent component sequence: This sequence is the direct output of the ICA algorithm, when the input dielectric loss tangent signal time series contains When there are 10 data points, the algorithm will output multiple independent data points that also contain 10 data points. The signal components of each data point. Each output signal component has a data point that corresponds one-to-one with the timestamp of the original signal, thus forming an independent component sequence.

[0063] For the construction of the temperature and load current sequences: the discrete data points synchronously acquired in step S100 are sorted chronologically according to their respective timestamps to form the temperature and load current sequences. The temperature sequence can be represented as follows: ,in For the first Temperature data at the sampling time. The load current sequence can be represented as... ,in For the first Load current data at the sampling time. Since temperature data, load current data, and dielectric loss tangent signals are acquired at the same frequency, their corresponding sampling times are the same. This means that the number of data points in the time series of these two environmental factors is the same as the number of data points for the independent components, and they also contain... Data points at each sampling time.

[0064] After constructing the aforementioned time series, this step allows for the calculation of the environmental coupling coefficient. The time correlation between the independent component and environmental factors (temperature and load current) is used as the numerator, and the unidirectional increasing trend of the independent component is used as the denominator. An independent component highly correlated with the environment and exhibiting reversible trend fluctuations will yield a relatively large environmental coupling coefficient.

[0065] Based on the above logic, the first Environmental coupling coefficient of each independent component Satisfying the relation:

[0066] ;

[0067] in, , They are the first The correlation coefficients between the sequences corresponding to each independent component and the temperature and load current sequences during the same period; It is the first The number of groups in the sequence corresponding to each independent component whose difference between adjacent data points is positive; It is the first The number of groups in the sequence corresponding to each independent component whose difference between adjacent data points is not positive; It is the number of data points in the independent component sequence, and also the total number of data points in the time series of the dielectric loss tangent signal. For example, 1000 consecutive data points can be taken for analysis. This is a preset microvalue used to prevent the denominator from being 0. It can be set to 0.001 or as needed. It is the standard normalization function, which normalizes the values ​​in the denominator. Mapped to interval; It is the absolute value symbol.

[0068] In this relationship, the numerator part Quantified the first The stronger the linear correlation between an independent component and external environmental factors such as temperature and load current, the stronger the correlation. The more likely an independent component is to be caused by environmental changes, the more likely the core term in the denominator is to be affected. Used to measure the The strength of the unidirectional increasing property of the sequence corresponding to each independent component varies. For a purely monotonically increasing sequence, this value approaches 1; for a fluctuating sequence, the value approaches 0. Therefore, when an independent component is an environmental drift, its numerator is large and its denominator is small, ultimately leading to... The value increases significantly. Conversely, for true aging signals, the numerator is smaller and the denominator is larger. The value will be very small.

[0069] It should be added that in this relation... , The preferred correlation coefficient is Pearson correlation coefficient, used to quantify the first... The strength of the linear correlation between each independent component and temperature and load current. In this relationship... and The difference between adjacent data points is calculated by subtracting the data of the previous data point from the data of the next data point.

[0070] To visually illustrate the role of the core term in the denominator, in order to include Taking a sequence of data points as an example, the number of sets of differences between corresponding adjacent data points is: , The number of groups with positive differences. If the number of groups has non-positive differences, then:

[0071] ;

[0072] Therefore, the first The core term in the denominator of the relationship for the environmental coupling coefficients of each independent component satisfies the following relationship:

[0073] ;

[0074] When the sequence is purely monotonically increasing At this point, the core term in the denominator is 1; when the sequence fluctuates up and down, The core term in the denominator approaches 0, thus quantifying the unidirectional increasing property.

[0075] Thus, an environmental coupling coefficient was obtained that can quantify the degree of coupling between each independent component and environmental factors.

[0076] Step S500: Calculate the aging discrimination factor for each independent component based on the component fluctuation spectrum index and the environmental coupling coefficient.

[0077] It should be noted that, considering the physical nature of power cable insulation aging and the characteristics of actual monitoring scenarios, a signal component that can accurately characterize true insulation aging must simultaneously meet two core attributes: First, from a frequency domain perspective, the degradation cycle of insulation aging lasts from several months to several years, belonging to an extremely low-frequency physical process. Therefore, its signal energy is highly focused in the extremely low-frequency band, without high-frequency fluctuations or periodic oscillations. Second, from a time domain perspective, the aging trend is unidirectional and irreversible, with extremely weak correlation to external environmental factors such as temperature and load. This step aims to integrate the component fluctuation spectrum index and the environmental coupling coefficient to construct an aging discrimination factor. This aging discrimination factor can identify signal components that conform to the characteristics of true insulation aging, providing a basis for subsequent selection of target aging signals from multiple independent components.

[0078] Specifically, based on the above logic, the first Aging discriminant factors of individual components Satisfying the relation:

[0079] ;

[0080] in, It is the first The component fluctuation spectrum index of each independent component; It is the first Environmental coupling coefficient of each independent component ; It is a natural exponential function.

[0081] In this relation, if and only if and When all terms are relatively small, their product is minimized, and the exponent term... The value of is closest to its maximum value of 1. Therefore, the aging discriminant factor The larger the value, the more the corresponding independent component conforms to the characteristics of a real insulation aging signal that is low-frequency, slowly changing, and independent of the environment.

[0082] Step S600: Select the target signal from multiple independent components based on the aging discrimination factor, and monitor the insulation performance of the power cable based on the target signal.

[0083] It should be noted that this step is the final execution stage of the entire monitoring method. Through the preceding steps of screening and quantitative evaluation, a clear aging discrimination factor has been assigned to each independent component. The purpose of this step is to accurately identify and extract the target signal from the numerous isolated independent components based on this discrimination factor, and then perform amplitude recovery and anomaly detection on this basis, ultimately outputting the monitoring conclusions on the cable insulation performance.

[0084] Specifically, the execution process of this step is as follows:

[0085] First, the aging discrimination factors of all independent components calculated in step S500 are compared, and the independent component with the largest aging discrimination factor is determined as the target signal.

[0086] Then, to give the target signal its true physical meaning and amplitude, it needs to be restored. Using the inverse process of ICA, the scaling factor corresponding to the target signal in the original mixing matrix is ​​obtained. This scaling factor is used to restore the amplitude of the target signal, and then superimposed with the overall mean of the original dielectric loss tangent signal, resulting in a pure dielectric loss tangent change curve that reflects the true aging accumulation process, free from noise and environmental interference. The original... The overall mean of the signal is calculated because the signal is typically preprocessed with zero mean before ICA separation, resulting in a baseline of 0 for the independent components after separation. Superimposing the mean restores the true physical baseline of the target signal, ensuring that the final clean curve closely matches the actual baseline. The measured values ​​are of the same magnitude. This operation is existing technology and will not be elaborated on here.

[0087] Finally, the insulation performance was monitored based on the pure change curve.

[0088] As a preferred implementation, the Local Outlier Factor (LOF) algorithm can be used for real-time anomaly detection of the curve. LOF is a classic density-based unsupervised anomaly detection algorithm that can effectively identify anomalous abrupt changes in a data sequence. When the LOF algorithm detects an outlier on the curve, it indicates an abnormal acceleration in the accumulation rate of the dielectric loss tangent. Based on this, the system can determine that the cable insulation performance is abnormal and trigger an early warning. Figure 5 The graph shown is a curve of the change in the pure dielectric loss tangent. The horizontal axis represents time, and the vertical axis represents the recovered dielectric loss tangent. The blue curve is the curve of the change in the pure dielectric loss tangent, and the red dots are outliers detected by the LOF algorithm, corresponding to abnormal points where the cable insulation performance is abnormal.

[0089] In the LOF algorithm, the number of neighboring points is a key parameter, and empirically, it can be optimized to be 20. The optimal number of neighboring points (20) is based on power cables. The signal is monitored daily / weekly, typically covering 1000 data points. A period of 20 neighborhood points can balance the stability of local density calculation with the sensitivity of outlier identification. If the data sampling frequency is higher, such as N>5000, it can be appropriately adjusted to [missing information]. The LOF algorithm is a current technology and will not be discussed in detail here.

[0090] The second aspect of this embodiment provides a power cable insulation performance monitoring system, such as... Figure 6 As shown, the power cable insulation performance monitoring system includes a memory and a processor. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the power cable insulation performance monitoring method of the first aspect of the present invention is implemented.

[0091] The power cable insulation performance monitoring system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces. Their setup and functions are known in the art and will not be described in detail here.

[0092] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as resistive random access memory (DRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (DRAM), high-bandwidth memory, hybrid memory cube, etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device.

[0093] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method of monitoring the condition of the insulation of a power cable, characterized by The method comprises the steps of: obtaining a medium loss tangent signal, temperature data and load current data of a power cable; performing blind source separation on the medium loss tangent signal to obtain a plurality of independent components; distinguishing a high-frequency interval and a low-frequency interval of each independent component according to a preset frequency division threshold, and calculating a component fluctuation spectral index of each independent component based on a ratio of energy of the high-frequency interval to energy of the low-frequency interval; For each independent component, based on the time correlation of the independent component and the temperature data and the load current data, and the change trend of the independent component, an environment coupling coefficient of the independent component is obtained, and the formula is: ; wherein, is the environment coupling coefficient of the first independent component; , are respectively the correlation coefficients of the sequence corresponding to the first independent component and the temperature sequence and the load current sequence in the same period; is the number of groups of adjacent data points in the sequence corresponding to the first independent component, which are positive after subtraction; is the number of groups of adjacent data points in the sequence corresponding to the first independent component, which are not positive after subtraction; is the number of data points of the sequence corresponding to the independent component; is a preset infinitesimal value; is a standard normalization function; is an absolute value symbol; calculating an aging discriminant factor of each independent component based on the component fluctuation spectral index and an environmental coupling coefficient; the aging discriminant factor is negatively correlated with the product of the component fluctuation spectral index and the environmental coupling coefficient; selecting a target signal from the plurality of independent components according to the aging discriminant factor, and realizing monitoring of insulation performance of the power cable based on the target signal.

2. The method of claim 1, wherein The component fluctuation spectral index of the independent component satisfies a relationship: ； wherein, is the component fluctuation spectrum index of the th independent component; is the frequency division threshold between the low frequency interval and the high frequency interval; is the highest frequency of the th independent component; is the frequency of the th independent component; is the highest frequency of the th independent component; th independent component.

3. The power cable insulation performance monitoring method according to claim 1, characterized by, The difference between the adjacent data points is the latter data point minus the former data point.

4. The power cable insulation performance monitoring method according to claim 1, characterized by, The aging discriminant factor of each independent component is calculated by a negative exponential function of the product of the component fluctuation spectral index and the environmental coupling coefficient.

5. The power cable insulation performance monitoring method according to claim 1, characterized by, The selecting of the target signal from the plurality of independent components according to the aging discriminant factor comprises: determining the independent component with the largest aging discriminant factor as the target signal.

6. The power cable insulation performance monitoring method according to claim 1, characterized by, The monitoring of the insulation performance of the power cable based on the target signal comprises: obtaining a scaling coefficient corresponding to the target signal by using an inverse process of the blind source separation; restoring an amplitude of the target signal by using the scaling coefficient, and superimposing a mean value of the medium loss tangent signal to obtain a pure medium loss tangent change curve; performing abnormality detection on the pure medium loss tangent change curve by using a local outlier factor algorithm.

7. The power cable insulation performance monitoring method according to claim 1, characterized by, The obtaining of the medium loss tangent signal of the power cable specifically comprises: synchronously collecting a voltage reference signal and a total current signal of the power cable; calculating a phase difference between the voltage reference signal and the total current signal; determining a loss angle based on the phase difference, and calculating the medium loss tangent signal.

8. The power cable insulation performance monitoring method according to claim 1, characterized by, The blind source separation is implemented by using an independent component analysis algorithm.

9. A power cable insulation performance monitoring system, characterized by The insulation performance monitoring system of the power cable comprises a processor and a memory, and the memory stores computer program instructions which, when executed by the processor, realize the insulation performance monitoring method of the power cable according to any one of claims 1-8.

Images