Method and device for determining equipment fault result and electronic equipment

Abstract

The invention discloses an equipment fault result determination method and device and electronic equipment. The method comprises the steps that a discrete waveform sequence of target equipment is acquired, the discrete waveform sequence comprises multiple pieces of sampling point data, and the multiple pieces of sampling point data comprise corresponding current instantaneous values at corresponding sampling moments; determining a plurality of differential waveform sequences according to the discrete waveform sequence; determining probability distributions respectively corresponding to the plurality of differential waveform sequences; determining a difference index between any two probability distributions in the plurality of probability distributions to obtain a plurality of difference indexes; and according to the plurality of difference indexes, determining a fault result of whether the target equipment has a fault. According to the method and the device, the technical problem that whether the equipment has a fault or not is difficult to accurately judge under the condition that the fault signal representing the fault is relatively weak in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method, device, and electronic device for determining the result of equipment failure. Background Art

[0002] Power equipment, such as power cables, as the core equipment for transmitting and distributing electric energy, is widely used in all links of power generation, power transmission, and power distribution. Its safe and stable operation is directly related to the reliability of power supply in the power system and the stability of the urban power grid. Compared with traditional overhead lines, power cables have the advantages of small occupied space, strong anti-interference ability, adaptability to complex urban environments, and low failure rate, and play an irreplaceable role in the construction and upgrading of modern urban power grids. However, since power cables are laid underground for a long time, their operating environment is complex and changeable, and they are easily affected by various factors, including production process defects, accumulation of operating time, mechanical stress, humidity, and corrosion and other external environmental factors. These factors may cause partial discharge, aging, or defects in the cable insulation material, thereby inducing early failures. Although early failures have little impact on the short-term operation of the cable, with the repeated occurrence of failures, it will accelerate the degradation of insulation, and ultimately may lead to permanent failure of the cable, bringing serious potential hazards to the stable operation of the power grid. Before the failure develops into a permanent failure, by effectively detecting and identifying means to timely detect the early cable failure and take targeted maintenance measures, the insulation degradation process can be significantly delayed, and a larger range of power system losses can be avoided.

[0003] Traditional detection methods have problems with insufficient sensitivity to weak signals in the detection of early equipment failures. Especially in a complex operating environment, partial discharge signals are often masked or interfered by background noise, making it difficult to effectively extract and identify signal features. This lack of sensitivity not only increases the risk of missed detection but also leads to a lag in the monitoring and early warning of potential failures.

[0004] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, and electronic device for determining the result of equipment failure, so as to at least solve the technical problem in the related art that it is difficult to accurately judge the failure result of whether the equipment fails when the failure signal representing the failure is relatively weak.

[0006] According to one aspect of the embodiments of the present invention, a method for determining the result of equipment failure is provided, including: obtaining a discrete waveform sequence of a target device, where the discrete waveform sequence includes a plurality of sampling point data, and the plurality of sampling point data includes corresponding current instantaneous values at corresponding sampling moments; determining a plurality of differential waveform sequences based on the discrete waveform sequence; determining probability distributions respectively corresponding to the plurality of differential waveform sequences; determining difference indices between any two probability distributions among the plurality of probability distributions to obtain a plurality of difference indices; and determining a failure result of whether the target device fails based on the plurality of difference indices.

[0007] Optionally, the determining probability distributions respectively corresponding to the plurality of differential waveform sequences includes: determining multiple sets of random variable values based on the plurality of sampling point data respectively included in the plurality of differential waveform sequences, where the multiple sets of random variable values correspond one-to-one to the plurality of differential waveform sequences; determining multiple sets of probability distribution data based on the multiple sets of random variable values, where the multiple sets of random variable values correspond one-to-one to the multiple sets of probability distribution data; and determining probability distributions respectively corresponding to the plurality of differential waveform sequences based on the multiple sets of probability distribution data.

[0008] Optionally, the determining probability distributions respectively corresponding to the plurality of differential waveform sequences based on the multiple sets of probability distribution data includes: when the probability distributions respectively corresponding to the plurality of differential waveform sequences include a first probability distribution and a second probability distribution, determining multi-segment data corresponding to target probability distribution data and determining weight data corresponding to the target probability distribution data, where the target probability distribution data is any set of data among the multiple sets of probability distribution data; determining a first probability distribution corresponding to the target probability distribution data based on the multi-segment data, and obtaining a second probability distribution corresponding to the target probability distribution data based on the weight data corresponding to the target probability distribution data.

[0009] Optionally, the determining a plurality of differential waveform sequences based on the discrete waveform sequence includes: determining a plurality of adjacent cycle sequences based on the discrete waveform sequence; performing alignment processing on the plurality of adjacent cycle sequences to obtain a plurality of aligned cycle sequences, where the reference point data respectively corresponding in the plurality of aligned cycle sequences are aligned in time, and the plurality of adjacent cycle sequences correspond one-to-one to the plurality of aligned cycle sequences; and determining the plurality of differential waveform sequences based on the plurality of aligned cycle sequences.

[0010] Optionally, the obtaining of the discrete waveform sequence of the target device includes: collecting an initial discrete waveform sequence of the target device; determining filtering parameters for the target device, where the filtering parameters include filtering frequency band parameters; determining impulse response parameters according to the filtering parameters; and filtering frequency components included in corresponding current values in the initial discrete waveform sequence according to the impulse response parameters to obtain the discrete waveform sequence.

[0011] Optionally, determining a fault result of whether the target device is faulty according to the multiple difference indices includes: obtaining environmental parameters; determining a predetermined threshold according to the environmental parameters; and determining a fault result of whether the target device is faulty according to the multiple difference indices and the predetermined threshold.

[0012] Optionally, after determining a fault result of whether the target device is faulty according to the multiple difference indices, it includes: when the fault result is that the target device is faulty, determining fault parameters according to the multiple difference indices, where the fault parameters include a fault type and a fault level corresponding to the fault type; determining a fault handling strategy corresponding to the fault parameters, and sending the fault parameters to a predetermined terminal.

[0013] According to one aspect of an embodiment of the present invention, there is provided a device for determining a device fault result, including: an obtaining module configured to obtain a discrete waveform sequence of a target device, where the discrete waveform sequence includes a plurality of sampling point data, and the plurality of sampling point data include corresponding current instantaneous values at corresponding sampling times; a first determining module configured to determine a plurality of differential waveform sequences according to the discrete waveform sequence; a second determining module configured to determine probability distributions respectively corresponding to the plurality of differential waveform sequences; a third determining module configured to determine difference indices between any two of the plurality of probability distributions to obtain a plurality of difference indices; and a fourth determining module configured to determine a fault result of whether the target device is faulty according to the plurality of difference indices.

[0014] According to one aspect of an embodiment of the present invention, there is provided an electronic device, including: a processor; and a memory for storing instructions executable by the processor; where the processor is configured to execute the instructions to implement the method for determining a device fault result according to any one of the above.

[0015] According to one aspect of an embodiment of the present invention, there is provided a computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the method for determining a device fault result according to any one of the above.

[0016] In an embodiment of the present invention, a discrete waveform sequence of a target device is obtained, where the discrete waveform sequence includes a plurality of sampling point data, and the plurality of sampling point data includes corresponding instantaneous current values at corresponding sampling times. According to the discrete waveform sequence, a plurality of differential waveform sequences are determined. Probability distributions corresponding to the plurality of differential waveform sequences are determined. The difference index between any two probability distributions among the plurality of probability distributions is determined to obtain a plurality of difference indexes. According to the plurality of difference indexes, a fault result indicating whether the target device is faulty is determined. It can be seen that the distribution changes between multiple differential waveform sequences are considered. Since the fault signals are relatively weak, these signals will not be exactly the same in adjacent cycles, thus leaving traces of faults in the differential waveforms. Then, through their corresponding probability distributions, the fault or non-fault results they represent can be further amplified. Therefore, it is possible to accurately determine whether the device is faulty through multiple differential waveform sequences, thereby solving the technical problem in the related art that it is difficult to accurately determine the fault result of whether the device is faulty when the fault signals indicating faults are relatively weak. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0018] Figure 1 is a flowchart of a method for determining a device fault result according to an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of a method for detecting weak signals of early cable faults based on the distribution difference of waveform feature points provided by an alternative embodiment of the present invention;

[0020] Figure 3 is a structural block diagram of a device for determining a device fault result according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] Embodiment 1

[0024] According to an embodiment of the present invention, an embodiment of a method for determining the result of equipment failure is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0025] Figure 1 is a flowchart of a method for determining the result of equipment failure according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0026] Step S102, obtain the discrete waveform sequence of the target device, where the discrete waveform sequence includes a plurality of sampling point data, and the plurality of sampling point data includes the corresponding current instantaneous value at the corresponding sampling moment;

[0027] In step S102 provided in this application, the discrete waveform sequence of the target device is obtained.

[0028] Among them, it involves the discrete waveform sequence of the target device, which is a sequence composed of a series of discrete data points obtained by sampling the current signal of the target device (such as a cable). In the power system, the operating state of the device can be reflected by its current or voltage waveform, and the discrete waveform sequence is to convert this continuous waveform signal into a series of instantaneous values discretely distributed in time, which is convenient for storage and digital signal processing.

[0029] Among them, it involves a plurality of sampling point data, which means that within a certain time interval, the signal sampler will regularly collect the instantaneous values of the signal at multiple time points. The sampling frequency can be adaptively set according to the actual application and scenario. For example, setting a higher sampling frequency can capture more details. The high-frequency components can include the high-frequency components of partial discharge, which can better reflect the characteristic signals of faults.

[0030] Among them, it involves the instantaneous current value at the corresponding sampling moment, that is, the signal intensity measured by the sampler at each sampling moment. In the power system, the instantaneous current value is a direct reflection of the operating state of the equipment. By detecting the changes in the current waveform, the differences between the normal operating state and the abnormal state of the equipment can be identified.

[0031] Step S104: Determine a plurality of differential waveform sequences according to the discrete waveform sequence.

[0032] In step S104 provided in this application, a plurality of differential waveform sequences are determined.

[0033] Among them, it involves the differential waveform sequence. The differential waveform sequence is a new signal sequence obtained by calculating the difference between the instantaneous values of the corresponding sampling points in two adjacent discrete waveform sequences. The purpose of calculating the differential waveform sequence is usually to highlight the dynamic characteristics of the signal change, eliminate or suppress the influence of the trend background signal, so as to more easily identify the abnormal or fault characteristics in the signal. In the early fault detection of power cables, the differential waveform sequence can enhance the weak fault signals and make these signals more prominent in the complex background noise.

[0034] By calculating the differential waveform sequence, the change amount of the signal can be highlighted, which helps to identify the weak changes that may be masked by the background noise or trend signal in the original waveform sequence, and improves the sensitivity of signal detection. And the differential waveform sequence can suppress the static or trend noise in the signal, because these noises change little between adjacent cycles, while the signal changes related to the fault will be amplified in the differential sequence, so as to realize the separation of the signal and the noise. For the weak signals of the early faults of power cables, the differential waveform sequence can capture their dynamic characteristics and can identify them even if the signals are very weak, which greatly improves the accuracy and timeliness of early fault detection.

[0035] Step S106: Determine the probability distributions respectively corresponding to the plurality of differential waveform sequences.

[0036] In step S106 provided in this application, the probability distributions respectively corresponding to the plurality of differential waveform sequences are determined.

[0037] Among them, probability distributions are involved. A probability distribution is a set of functions or charts that describe the possible values of a random variable and their probabilities. In signal processing, a probability distribution can reflect the statistical characteristics of the signal value range, such as the frequency, mean, variance, etc. of the signal values. Constructing the probability distributions of multiple differential waveform sequences means performing statistical analysis on the differences of each sampling point in these sequences to determine the probabilities of these differences occurring within the entire value range. In the detection process of power cables, each differential waveform sequence corresponds to a probability distribution, and these distributions reflect the statistical characteristics of the cable current waveforms at different time points. These probability distributions may vary due to equipment status, operating conditions, or potential faults.

[0038] The construction of probability distributions allows the use of different statistical methods for fault detection, such as histogram analysis, kernel density estimation, relative entropy KL divergence calculation, etc., increasing the diversity and flexibility of fault detection strategies.

[0039] Step S108: Determine the difference index between any two probability distributions among multiple probability distributions to obtain multiple difference indices.

[0040] In step S108 provided in this application, the difference index between any two probability distributions among multiple probability distributions is determined until the difference index between every two probability distributions among multiple probability distributions is determined to obtain multiple difference indices.

[0041] Among them, the difference index is involved. The difference index is a quantitative index used to measure the statistical difference between two probability distributions. In signal processing and data analysis, the difference index can be the KL divergence (Kullback-Leibler divergence), Jensen-Shannon divergence, Bhattacharyya distance, or Wasserstein distance, etc. These difference indices can help evaluate the similarity or distance between the current signal state and the known normal state.

[0042] For the probability distributions constructed from multiple differential waveform sequences, the difference index between any two distributions will be calculated to obtain a series of difference index values. This step is essentially evaluating the changes in the signal distributions at different time points or different operating states of the cable, especially finding the time points with significant differences from the distribution in the normal operating state to identify signs of potential early faults.

[0043] Step S110: Determine the fault result of whether the target device is faulty based on multiple difference indices.

[0044] In step S110 provided in this application, the final fault result is determined.

[0045] Among them, a fault result is involved. The fault result refers to the difference index obtained through analysis and calculation, which is the result of determining whether an early fault or abnormal state has occurred in a device, such as a cable.

[0046] Through multiple difference indexes, minor abnormalities in power cables can be detected early, even if these abnormalities are very weak in the early stage, which helps to take corrective measures before the fault develops into a more serious problem.

[0047] Through the above steps S102 - S110, a discrete waveform sequence of the target device is obtained. Among them, the discrete waveform sequence includes multiple sampling point data, and the multiple sampling point data includes the corresponding instantaneous current values at the corresponding sampling moments. Based on the discrete waveform sequence, multiple differential waveform sequences are determined. The probability distributions corresponding to the multiple differential waveform sequences are determined. The difference indexes between any two probability distributions among the multiple probability distributions are determined to obtain multiple difference indexes. Based on the multiple difference indexes, the fault result of whether the target device is faulty is determined. It can be seen that it considers the distribution changes among multiple differential waveform sequences. Because the fault signals are relatively weak, these signals will not be exactly the same in adjacent cycles, thus leaving traces of faults in the differential waveforms. Then, through their corresponding probability distributions, the fault or non - fault results they represent can be further amplified. Therefore, it can accurately judge whether the device is faulty through multiple differential waveform sequences, and thus solves the technical problem in the related art that it is difficult to accurately judge the fault result of whether the device is faulty when the fault signals indicating faults are relatively weak.

[0048] As an optional embodiment, determining the probability distributions corresponding to the multiple differential waveform sequences includes: based on the multiple sampling point data respectively included in the multiple differential waveform sequences, determining multiple sets of random variable values, where the multiple sets of random variable values correspond one - to - one with the multiple differential waveform sequences; based on the multiple sets of random variable values, determining multiple sets of probability distribution data, where the multiple sets of random variable values correspond one - to - one with the multiple sets of probability distribution data; based on the multiple sets of probability distribution data, determining the probability distributions corresponding to the multiple differential waveform sequences.

[0049] In this embodiment, the process of constructing a probability distribution from the differential waveform sequences collected from a power cable is described.

[0050] Among them, multiple sets of random variable values are involved. In statistics, a random variable is a mathematical model used to describe uncertain events. Multiple sets of random variable values refer to regarding the sampling point data in each differential waveform sequence as the values of a random variable. Due to the uncertainty of current changes during cable operation, these difference values can be regarded as random variables, and their statistical characteristics (such as mean and variance) reflect the fluctuations of the cable state.

[0051] Among them, multiple sets of probability distribution data are involved. Probability distribution data is information that describes the possible values within the range of a random variable and their occurrence frequencies. In the detection of power cables, this usually means converting each differential waveform sequence into the probability distribution of its value range, which helps to identify abnormal signal patterns.

[0052] Among them, probability distributions corresponding to multiple differential waveform sequences are involved. This refers to constructing a probability distribution for each differential waveform sequence, which describes the statistical characteristics of the sampled point values in the sequence. By comparing these probability distributions with the probability distributions in the known normal state, the degree of change of the differential waveform sequence can be quantified.

[0053] In this step, the sampled point data in a series of differential waveform sequences are regarded as random variables, and then the probability distribution data of these random variables are constructed, and finally the probability distribution corresponding to each sequence is obtained. This process converts the time-domain signal into a statistical-domain representation, which helps to identify weak abnormal signals in the noise background.

[0054] Probability distribution can highlight the statistical characteristics of signals, such as mean, variance, etc., which is crucial for extracting weak changes in early fault signals. And it can improve the sensitivity of fault detection. Through the change of probability distribution, even when the signal amplitude is very small, potential faults can be identified, improving the sensitivity of fault detection. In addition, the construction of probability distribution is usually accompanied by a noise suppression process, which makes the detection method have strong robustness to background noise and can more accurately identify real signal changes.

[0055] As an alternative embodiment, determining the probability distributions corresponding to multiple differential waveform sequences based on multiple sets of probability distribution data includes: when the probability distributions corresponding to multiple differential waveform sequences include a first probability distribution and a second probability distribution, determining the multi-segment data corresponding to the target probability distribution data and determining the weight data corresponding to the target probability distribution data, where the target probability distribution data is any set of data among the multiple sets of probability distribution data; determining the first probability distribution corresponding to the target probability distribution data based on the multi-segment data, and obtaining the second probability distribution corresponding to the target probability distribution data based on the weight data corresponding to the target probability distribution data.

[0056] In this embodiment, it describes how to determine multiple probability distributions corresponding to a specific differential waveform sequence from multiple probability distribution data.

[0057] Among them, the first probability distribution and the second probability distribution are involved.

[0058] The first probability distribution can be a distribution calculated in a discrete form. The discrete form calculation is to divide the value range of the data into multiple intervals (bins), and count the frequency of data occurrences in each interval to construct a discrete probability distribution. Each interval represents a range of data values, and the frequency represents the number of data occurrences within that range. After normalizing the frequency, the probability of data occurrences in each interval is obtained. In the discrete form calculation, although we are dealing with all sampled point data, we count the probability in units of intervals rather than individual sampled points. The advantage of this approach is that it simplifies the calculation and facilitates processing and comparison, but the disadvantage is that some details about the specific distribution shape of the data may be lost.

[0059] The second probability distribution can be a distribution calculated in the form of kernel density estimation. Kernel density estimation (KDE) is a non-parametric method for estimating the probability density function (PDF). It attempts to smoothly estimate a continuous PDF from the data. In kernel density estimation, each sampled point is actually assigned a weight, which is calculated through a kernel function (such as a Gaussian kernel), and the magnitude of the weight depends on the distance between the sampled point and the observation point as well as the bandwidth parameter of the kernel function. KDE obtains the PDF estimated value at the observation point by summing up the weights of all sampled points and normalizing. In this way, KDE takes into account all sampled point data, but different from the discrete form calculation, it can provide a continuous and smooth probability density function estimation, retaining more details of the data distribution, especially being more flexible and accurate when estimating complex distribution shapes.

[0060] Among them, target probability distribution data and weight data are involved. The target probability distribution data is any one of multiple groups of probability distribution data, usually corresponding to the probability distribution of the recently collected differential waveform sequence. The weight data refers to the relative importance given to different data points or distributions when fusing or adjusting the probability distribution, and it can be dynamically adjusted according to the actual situation (such as signal strength, noise level, device status, etc.).

[0061] By this method, that is, considering both the first probability distribution and the second probability distribution, and comprehensively determining the fault result from both aspects, the accuracy of fault result determination is enhanced.

[0062] As an optional embodiment, based on the discrete waveform sequence, multiple differential waveform sequences are determined, including: based on the discrete waveform sequence, multiple adjacent cycle sequences are determined; alignment processing is performed on the multiple adjacent cycle sequences to obtain multiple aligned cycle sequences, where the reference point data corresponding to each other in the multiple aligned cycle sequences are aligned in time, and the multiple adjacent cycle sequences and the multiple aligned cycle sequences are in one-to-one correspondence; based on the multiple aligned cycle sequences, multiple differential waveform sequences are determined.

[0063] In this embodiment, a detailed process of generating multiple differential waveform sequences from the originally collected discrete waveform sequence in the early fault detection of power cables is described.

[0064] Among them, adjacent cycle sequences are involved. Adjacent cycle sequences refer to the discrete waveform sequence data within two consecutive power frequency cycles. Since the signals of power cables usually have periodicity, especially power frequency current signals, by comparing the signal changes within these cycles, weak fault signals or changes in equipment status can be captured.

[0065] Among them, alignment processing is involved. Alignment processing refers to performing time calibration between adjacent cycle sequences to ensure that the signals within multiple cycles are synchronized, thereby avoiding the influence of phase difference on the accuracy of subsequent differential waveform sequences. In power signal processing, it is usually achieved by detecting zero-crossing points, peaks or other synchronization markers.

[0066] Among them, multiple aligned cycle sequences and multiple differential waveform sequences are involved. After completing the alignment processing, by performing point-by-point differential operations on the sampled values of each aligned cycle sequence and the next aligned cycle sequence, multiple differential waveform sequences can be obtained. These sequences highlight the changes in the signal between cycles and are particularly effective for detecting small fluctuations in early faults.

[0067] From the originally collected discrete waveform sequence, multiple adjacent cycle sequences containing consecutive power frequency cycles are first selected. To ensure that these cycle sequences strictly correspond in time, alignment processing is performed on them to obtain multiple aligned cycle sequences. By performing differential operations on the aligned sequences, multiple differential waveform sequences are finally generated. These sequences can highlight the change characteristics of the cable signal between cycles and are sensitive indicators for detecting early faults.

[0068] Through the differential waveform sequences, weak signals can be enhanced, especially those related to early faults, because they may exhibit inconsistent patterns within adjacent cycles. And the alignment processing can eliminate the phase difference in periodic signals, thereby suppressing the influence of periodic noise and improving the recognition rate of fault signals. The differential waveform sequences can intuitively quantify the degree of change in the signal between cycles, which is very useful for analyzing the fluctuations in the operating state of the cable.

[0069] As an alternative embodiment, obtaining the discrete waveform sequence of the target device includes: collecting the initial discrete waveform sequence of the target device; determining the filtering parameters of the target device, where the filtering parameters include filtering frequency band parameters; determining the impulse response parameters according to the filtering parameters; and filtering the frequency components included in the corresponding current values in the initial discrete waveform sequence according to the impulse response parameters to obtain the discrete waveform sequence.

[0070] In this embodiment, it describes how to extract a clear waveform sequence from the collected original signals in the early fault detection of power cables for subsequent fault analysis.

[0071] Among them, filter parameters are involved. Filter parameters are a set of parameters used to set the characteristics of the filter, including filter band parameters (such as passband frequency, stopband frequency), etc. The filter band parameters define the frequency range allowed to pass through the filter. For power signal processing, this usually involves removing or suppressing unwanted frequency components, such as noise or interference signals.

[0072] Among them, impulse response parameters are involved. The impulse response is the response of the filter to a single impulse signal, which describes the characteristics of the filter. Impulse response parameters such as filter type (low-pass, high-pass, band-pass, etc.), cut-off frequency, filter order, etc.

[0073] Among them, filtering the initial discrete waveform sequence is involved. This refers to applying the filter to the original discrete waveform sequence to remove noise and unwanted frequency components and retain the signals related to the analysis target. In this application, the goal is to retain the signal components that can reflect the early faults of power cables, such as signals generated by partial discharges or weak changes in insulating materials.

[0074] The original discrete waveform sequence obtained from the target device may contain a large amount of noise and unwanted frequency components, which will mask the weak signals of early faults. Therefore, first determine the filter parameters, including the filter band parameters, to define the passband and stopband of the filter. Then, according to these filter parameters, determine the impulse response parameters of the filter and construct a filter model suitable for power cable signal processing. Finally, apply this filter to filter the original discrete waveform sequence, retain the signal components related to early faults, so as to obtain a clearer and more accurate discrete waveform sequence, providing a pure signal input for subsequent fault detection and analysis.

[0075] As an alternative embodiment, according to multiple difference indices, determine the fault result of whether the target device is faulty, including: obtaining environmental parameters; determining a predetermined threshold according to the environmental parameters; determining the fault result of whether the target device is faulty according to the multiple difference indices and the predetermined threshold.

[0076] In this embodiment, it describes the specific process of how to combine environmental parameters and difference indices to determine whether the target device (such as a power cable) has a fault in the early fault detection of power cables.

[0077] Among them, environmental parameters are involved. Environmental parameters refer to external factors that affect the operating state of power cables, including but not limited to temperature, humidity, cable load, electromagnetic interference level, etc. These parameters have a significant impact on the performance and signal characteristics of the cable and need to be considered in fault determination.

[0078] Among them, a predetermined threshold is involved. The predetermined threshold is preset in the fault detection algorithm and is used to determine the boundary value of whether the difference index reaches the fault warning standard. This threshold is usually determined based on historical data analysis, equipment characteristics, and the influence of environmental parameters, and it can help distinguish normal fluctuations and fault signals.

[0079] In the fault detection of power cables, first, multiple difference indexes are calculated. These indexes quantify the differences between the statistical distribution characteristics of the cable current waveform at different time points and the normal state. Then, the current environmental parameters are obtained because environmental factors such as temperature, humidity, and electromagnetic interference will affect the values of the difference indexes, thus possibly affecting the accuracy of fault judgment. Next, according to the influence of the environmental parameters, the predetermined threshold is dynamically determined to adapt to the current operating conditions. Finally, by comparing multiple difference indexes with the adjusted predetermined threshold, it is determined whether the target device has a fault. This process ensures the accuracy and reliability of fault detection and can adapt to changes in various operating environments and device states. By considering environmental parameters and dynamically adjusting the predetermined threshold, the fault detection system can adapt to various operating conditions and improve the sensitivity and accuracy of detection.

[0080] As an alternative embodiment, after determining the fault result of whether the target device is faulty based on multiple difference indexes, it includes: in the case where the fault result is that the target device is faulty, determining the fault parameters based on multiple difference indexes, where the fault parameters include the fault type and the fault level corresponding to the fault type; determining the fault handling strategy corresponding to the fault parameters, and sending the fault parameters to a predetermined terminal.

[0081] In this embodiment, it describes how to further analyze the fault characteristics and adopt targeted handling strategies in the early fault detection of power cables after confirming the device fault.

[0082] Among them, fault parameters are involved. Fault parameters are detailed information for classifying and grading the detected faults, including the fault type (such as insulation aging, partial discharge, conductor breakage, etc.) and the fault level corresponding to the fault type (such as minor, moderate, severe, etc.). These parameters help to more accurately identify the nature and severity of the faults.

[0083] Among them, fault handling strategies are involved. Fault handling strategies are specific countermeasures designed according to the fault parameters, including but not limited to monitoring upgrade, preventive maintenance, fault location, emergency shutdown, etc. These strategies should ensure the safety and stability of the power system while considering the economic cost of the fault and its impact on power grid operation.

[0084] Among them, a predetermined terminal is involved. The predetermined terminal refers to the destination for receiving fault parameters and processing strategy information, which can be a computer system in a monitoring center, a mobile device of maintenance personnel, an automatic control device, etc. By sending the fault parameters to the predetermined terminal, rapid response and fault handling can be ensured.

[0085] Through the analysis of multiple difference indices, the type and location of faults can be identified more accurately, providing a basis for targeted fault handling. The setting of fault levels helps maintenance personnel prioritize handling according to the severity of faults, avoiding waste of resources and improving the efficiency of system maintenance at the same time. Sending the fault parameter information directly to the predetermined terminal can achieve real-time transmission of fault information, ensure rapid response and handling, and reduce the impact of faults on the power grid. The fault handling strategy is formulated based on specific fault parameters, which helps to reduce misoperations and enhance the operational safety of the power system.

[0086] Based on the above embodiments and optional embodiments, an optional implementation manner is provided, which is specifically described below.

[0087] An optional implementation manner of the present invention proposes a method for early fault detection of a power device, especially a cable, by using the deviation degree of the adjacent cycle differential waveform from the Gaussian distribution for the weak current disturbance signal that may occur in the early fault state. Through data acquisition of multi-cycle power frequency current waveforms, construction of differential waveforms, extraction of distribution characteristics, calculation of KL divergence, and combination with threshold determination, high-sensitivity detection and early warning of weak signals of cable early faults are realized. Figure 2 It is a schematic diagram of a method for detecting weak signals of early cable faults based on the distribution difference of waveform feature points provided by an optional implementation manner of the present invention. The following combines Figure 2 to introduce it:

[0088] The current waveform is more sensitive to the state of the cable device and is used for detecting weak signals of early faults. Taking the change amount of the instantaneous value of the current waveform as a feature, by taking the difference between adjacent cycle waveform signals, and taking the distribution law of the signal difference as a typical feature, the abnormality is detected by comparing the statistical distributions of waveforms with and without early fault disturbances. If the device is in normal operation, the differential waveform only contains noise information and conforms to the Gaussian statistical distribution law. If the device is in the early fault state, the differential waveform not only contains noise information but also contains fault signals. Therefore, the statistical distribution law of the differential waveform containing fault information will deviate from the Gaussian distribution. Therefore, the KL divergence (KLD) can be used to evaluate the KLD distance between the distribution of the differential waveform in the early fault state and the Gaussian distribution of the normal differential waveform. According to the set threshold, it is judged whether there is a fault. If the KLD is greater than the threshold, there is an early fault disturbance.

[0089] This method includes the following steps:

[0090] 1. Data acquisition and preprocessing

[0091] (1) Data acquisition

[0092] Under normal cable operation or test environment, a high-speed data acquisition device is used to collect the power frequency current waveform. Let the power frequency be (such as 50 Hz), and the sampling rate (such as 10 kHz, 50 kHz or higher) is selected to capture the high-frequency components that may be included in the early faults. If the number of sampling points collected in each power frequency cycle is

[0093]

[0094] Several consecutive cycles are collected at one time (denoted as cycles), then the total number of sampling points is approximately . In high-voltage or extra-high-voltage environments, optical current sensors or high-precision Hall current sensors can be selected to ensure high bandwidth and high resolution of signal measurement.

[0095] (2) Data preprocessing

[0096] To avoid masking of early fault signals by power frequency fundamental waves and environmental noise, the collected discrete waveform sequence is usually band-pass filtered. If the impulse response of the filter in the digital domain is and the length is , it can be expressed as

[0097]

[0098] The filtered signal is obtained. The filtering range should cover the potential fault frequency band (such as several hundred Hz to several tens of kHz), while suppressing extremely low-frequency and extremely high-frequency noises. h[n] represents the impulse response coefficient of the filter at time point n, and I[k - n] represents the value of the input signal I at time k - n.

[0099] 2. Construction of adjacent cycle differential waveforms

[0100] (1) Cycle registration

[0101] There may be a small phase shift between adjacent power frequency cycles of the current waveform. Through synchronous signals or zero-crossing alignment methods, it can be ensured that the starting point (or any point) of each cycle strictly corresponds in time. Assume that after alignment, the cycle contains sampling points

[0102]

[0103] Among them, M represents the number of groups or samples of the data set or signal sequence. Specifically, in this scenario, it represents the number of groups of differential waveforms.

[0104] (2)Differential operation

[0105] On the basis of completing the cycle registration, the adjacent cycles are subtracted point by point to obtain a differential waveform sequence. If the cycle and the cycle sampling values are respectively denoted as:

[0106]

[0107] Among them, k is an index used to represent the specific sample point position in the differential waveform sequence.

[0108] Then the differential waveform is defined as:

[0109]

[0110] When consecutive cycles are collected at one time, groups of differential waveforms can be obtained. Differential processing can suppress the power frequency fundamental wave and conventional noise, making the weak anomalies brought by early faults prominent.

[0111] 3. Extraction of differential waveform distribution characteristics

[0112] (1)Probability density estimation

[0113] Regarding all the sampling points in the differential waveform as the values of random variables.

[0114] To quantify its statistical law, a histogram can be constructed or the kernel density estimation (KDE) can be used to approximate the probability density function.

[0115] 1) Histogram method

[0116] Dividing the value range of the differential value into intervals equally, the probability of the th interval is defined as:

[0117]

[0118] Among them, represents the number of differential samples falling into the th interval, and is the total number of sampling points of this differential waveform.

[0119] 2) For the Gaussian kernel in Kernel Density Estimation (KDE), the estimated probability density function can be written as:

[0120]

[0121] where is the bandwidth parameter, is the sampled value of the differential waveform, x is the value of the continuous variable, representing the point at which the probability density is to be estimated. KDE can obtain a smoother distribution curve.

[0122] (2)Reference distribution establishment

[0123] Under the recognized normal state of the cable, multiple groups of differential waveforms are collected and their overall probability distribution is estimated, denoted as . If this distribution is close to a Gaussian distribution, is the standard deviation, is the mean, is the variance, that is:

[0124]

[0125] If there is a deviation from the Gaussian hypothesis, the measured distribution can be directly saved as a discrete form or a kernel density function for use as a subsequent comparison benchmark.

[0126] 4. KLD (KL divergence) calculation

[0127] (1)KLD concept

[0128] KLD is an important indicator for evaluating the difference between two probability distributions. Let the reference distribution be , and the real-time measured distribution be , then in the continuous form, there is:

[0129]

[0130] When is exactly the same as , then The greater the difference between the two, the larger the value.

[0131] (2)Discretization implementation

[0132] In practice, KLD is often calculated through the discrete probability of a histogram or kernel density estimation. If the differential waveform distribution is discretized into using the histogram method and the reference distribution is , then KLD is approximately:

[0133]

[0134] To avoid or In case of numerical divergence caused thereby, the distribution probability can be smoothed or a minimum value threshold (such as ) can be used to replace zero values.

[0135] 5. Threshold determination

[0136] (1) Threshold setting

[0137] Under the normal state where the cable is fault-free, by statistically analyzing the distribution of KLD values of a large number of differential waveforms, the KLD threshold can be determined in combination with a certain confidence interval (such as 95% or 99%) or the results of on-site test fault simulation. . When the noise level or load condition changes significantly, an adaptive threshold strategy can also be adopted to improve the reliability of detection.

[0138] (2) Fault judgment

[0139] Let the divergence value obtained by real-time calculation be:

[0140]

[0141] Then it is judged that the cable has shown early fault perturbation; otherwise, it is considered that the device is still in the normal state. For marginal cases, a threshold interval can be set to strengthen subsequent data collection and observation.

[0142] (3) Multiple confirmation mechanism

[0143] To reduce misjudgment caused by transient spikes or one-time interference, multiple groups of differential waveforms can be continuously obtained and calculated separately within a short period of time (such as 0.5 seconds or 1 second).

[0144] If there are at least several consecutive exceedances of the threshold, a fault alarm is issued. If there is only one or accidental exceedance of the threshold, it is temporarily recorded as a suspicious event and monitoring continues.

[0145] 6. Fault output and early warning

[0146] (1) Alarm and data recording

[0147] Once the fault state is determined, the system immediately triggers an alarm and stores the current differential waveform, sampling time, noise level, load information, and the numerical value into the database, and sends the alarm information to the dispatching center or maintenance personnel.

[0148] (2) Early warning classification and subsequent evaluation

[0149] According to and the threshold Based on the gap, the fault risk can be divided into different levels. If the alarms appear continuously and the trend becomes more and more obvious, other diagnostic methods (such as partial discharge measurement, harmonic energy analysis) can be combined to locate the fault area and arrange maintenance as soon as possible.

[0150] Through the above optional implementation manners, at least the following beneficial effects can be achieved:

[0151] (1) By using the KL divergence to quantitatively analyze the difference between the differential distribution of the current waveform and the normal Gaussian distribution, the present invention can accurately capture the subtle changes in the early fault signals. This method can not only effectively distinguish the noise in the normal state from the fault signals in the fault state, but also significantly improve the sensitivity and accuracy of detection. By taking the difference of the current waveforms in adjacent cycles, extracting statistical features, and comparing them with the Gaussian distribution, it is ensured that the abnormality can be detected in the initial stage of the fault, reducing the probability of missed detection and false detection.

[0152] (2) The method of the present invention is based on the KL divergence analysis of the waveform differential distribution and has strong anti-noise ability. In the actual power system, the current waveform is often interfered by various noises, such as electromagnetic interference, environmental noise, etc. The traditional time-domain and frequency-domain analysis methods are easily masked by noise in a high-noise environment, resulting in a decline in detection performance. However, the present invention can effectively suppress the influence of noise through the quantification of the statistical distribution difference, ensuring that the fault signals can still be accurately detected under a complex noise background.

[0153] (3) By analyzing the statistical characteristics of the differential distribution of the current waveform, the method of the present invention has the ability to adapt to various different types of faults, such as insulation aging, partial discharge, conductor fracture, etc. Since different fault types have different effects on the current waveform, this method does not rely on specific fault characteristics, but quantifies the overall distribution difference through the KL divergence, thereby realizing the unified detection of various faults. This versatility enables the method to still maintain good detection performance when facing diverse faults, improving the adaptability and flexibility of the system.

[0154] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0155] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0156] Embodiment 2

[0157] According to an embodiment of the present invention, there is also provided a device for implementing the method for determining the result of the above device failure. Figure 3 It is a structural block diagram of a device for determining the result of a device failure according to an embodiment of the present invention, as Figure 3 shown. The device includes: an acquisition module 302, a first determination module 304, a second determination module 306, a third determination module 308, and a fourth determination module 310. The device will be described in detail below.

[0158] The acquisition module 302 is used to acquire a discrete waveform sequence of a target device. Among them, the discrete waveform sequence includes a plurality of sampling point data, and the plurality of sampling point data includes corresponding current instantaneous values at corresponding sampling moments; the first determination module 304 is connected to the above acquisition module 302 and is used to determine a plurality of differential waveform sequences based on the discrete waveform sequence; the second determination module 306 is connected to the above first determination module 304 and is used to determine probability distributions respectively corresponding to the plurality of differential waveform sequences; the third determination module 308 is connected to the above second determination module 306 and is used to determine difference indices between any two probability distributions among the plurality of probability distributions to obtain a plurality of difference indices; the fourth determination module 310 is connected to the above third determination module 308 and is used to determine a failure result of whether the target device fails based on the plurality of difference indices.

[0159] It should be noted here that the above acquisition module 302, first determination module 304, second determination module 306, third determination module 308, and fourth determination module 310 correspond to steps S102 to step S110 in the method for determining the result of device failure. The instances and application scenarios implemented by the multiple modules and the corresponding steps are the same, but are not limited to the content disclosed in the above Embodiment 1.

[0160] Embodiment 3

[0161] According to another aspect of the embodiments of the present invention, an electronic device is further provided, including: a processor; a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the method for determining the device failure result in any one of the above.

[0162] Embodiment 4

[0163] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is further provided. When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the method for determining the device failure result in any one of the above.

[0164] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0165] In the above embodiments of the present invention, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0166] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0167] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0169] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0170] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for determining the result of a device failure, characterized in that, Including: Obtain a discrete waveform sequence of a target device, where the discrete waveform sequence includes a plurality of sampled point data, and the plurality of sampled point data includes corresponding instantaneous current values at corresponding sampling moments; Determine a plurality of differential waveform sequences according to the discrete waveform sequence; Determine probability distributions respectively corresponding to the plurality of differential waveform sequences; Determine difference indices between any two of the plurality of probability distributions among the plurality of probability distributions to obtain a plurality of difference indices; Determine a fault result indicating whether the target device is faulty according to the plurality of difference indices.

2. The method according to claim 1, characterized in that, The determining the probability distributions respectively corresponding to the plurality of differential waveform sequences includes: Determine multiple sets of random variable values according to the plurality of sampled point data respectively included in the plurality of differential waveform sequences, where the multiple sets of random variable values correspond one-to-one to the plurality of differential waveform sequences; Determine multiple sets of probability distribution data according to the multiple sets of random variable values, where the multiple sets of random variable values correspond one-to-one to the multiple sets of probability distribution data; Determine the probability distributions respectively corresponding to the plurality of differential waveform sequences according to the multiple sets of probability distribution data.

3. The method according to claim 2, wherein The determining the probability distributions respectively corresponding to the plurality of differential waveform sequences according to the multiple sets of probability distribution data includes: When the probability distributions respectively corresponding to the plurality of differential waveform sequences include a first probability distribution and a second probability distribution, determine multi-segment data corresponding to target probability distribution data and determine weight data corresponding to the target probability distribution data, where the target probability distribution data is any set of data among the multiple sets of probability distribution data; Determine a first probability distribution corresponding to the target probability distribution data according to the multi-segment data, and obtain a second probability distribution corresponding to the target probability distribution data according to the weight data corresponding to the target probability distribution data.

4. The method according to claim 1, wherein The determining the plurality of differential waveform sequences according to the discrete waveform sequence includes: Determine a plurality of adjacent cycle sequences according to the discrete waveform sequence; Perform alignment processing on the plurality of adjacent cycle sequences to obtain a plurality of aligned cycle sequences, where the reference point data respectively corresponding to the plurality of aligned cycle sequences are aligned in time, and the plurality of adjacent cycle sequences correspond one-to-one to the plurality of aligned cycle sequences; Determine the plurality of differential waveform sequences according to the plurality of aligned cycle sequences.

5. The method according to claim 1, wherein The obtaining the discrete waveform sequence of the target device includes: Collect an initial discrete waveform sequence of the target device; Determine filtering parameters of the target device, where the filtering parameters include filtering frequency band parameters; Determine impulse response parameters according to the filtering parameters; Filter frequency components included in the corresponding current values in the initial discrete waveform sequence according to the impulse response parameters to obtain the discrete waveform sequence.

6. The method according to claim 1, wherein The determining the fault result indicating whether the target device is faulty according to the plurality of difference indices includes: Obtain environmental parameters; Determine a predetermined threshold according to the environmental parameters; Determine the fault result indicating whether the target device is faulty according to the plurality of difference indices and the predetermined threshold.

7. The method according to any one of claims 1 to 6, characterized in that, After determining the fault result of whether the target device is faulty based on the multiple difference indices, it includes: In the case where the fault result is that the target device is faulty, determine the fault parameters based on the multiple difference indices, where the fault parameters include the fault type and the fault level corresponding to the fault type; Determine the fault handling strategy corresponding to the fault parameters and send the fault parameters to a predetermined terminal.

8. An apparatus for determining a device failure result, characterized in that, It includes: An acquisition module, configured to acquire the discrete waveform sequence of the target device, where the discrete waveform sequence includes a plurality of sampling point data, and the plurality of sampling point data includes the corresponding instantaneous current values at the corresponding sampling moments; A first determination module, configured to determine a plurality of differential waveform sequences based on the discrete waveform sequence; A second determination module, configured to determine the probability distributions respectively corresponding to the plurality of differential waveform sequences; A third determination module, configured to determine the difference indices between any two probability distributions among the plurality of probability distributions to obtain a plurality of difference indices; A fourth determination module, configured to determine the fault result of whether the target device is faulty based on the plurality of difference indices.

9. An electronic device, characterized in that, It includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the instructions to implement the method for determining the device fault result according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is enabled to execute the method for determining the device fault result according to any one of claims 1 to 7.

Images