Electric appliance power supply network health state detection method and system

Abstract

The invention discloses an electric appliance power supply network health state detection method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting the three-phase current data of a CT power supply network; calculating a three-phase current unbalance degree based on the three-phase current data, and generating an unbalance degree time sequence based on the three-phase current unbalance degree; constructing a dynamic track based on the dynamic unbalance degree sequence; extracting a characteristic quantity from the dynamic track; and inputting the characteristic quantity into a pre-trained health assessment model, and outputting the health state level of the CT power supply network, thereby facilitating solving the problem that the health state of the CT power supply network cannot be accurately detected in the prior art.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method and system for detecting the health status of electrical power supply networks. Background Technology

[0002] The CT power supply network is a core support for the safe and stable operation of the power system, and its health status directly affects the reliability and security of power transmission. Currently, CT power supply network monitoring mainly focuses on static indicators such as output voltage and circuit continuity, and maintenance methods are mainly based on periodic inspections or reactive repairs after a fault, lacking the ability to predict potential faults such as cable aging and loose connections in advance.

[0003] While some technologies detect grid anomalies by monitoring three-phase current imbalance, most rely solely on whether the instantaneous absolute value of the imbalance exceeds a fixed threshold. This static threshold method has significant drawbacks: insufficient sensitivity, making it difficult to identify early, slowly changing faults; high false alarm rate, failing to effectively distinguish between normal load fluctuations and actual equipment degradation trends; and static indicators cannot reflect the dynamic process of fault development, making fault location and type identification difficult, thus hindering the implementation of predictive maintenance.

[0004] Therefore, there is an urgent need for a method to accurately detect the health status of the CT power supply network. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for detecting the health status of electrical power supply networks, which can accurately detect the health status of CT power supply networks.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A method for detecting the health status of an electrical appliance power supply network, comprising: Collect three-phase current data of the CT power supply network; The three-phase current imbalance is calculated based on the three-phase current data, and an imbalance time series is generated based on the three-phase current imbalance. A dynamic trajectory is constructed based on the aforementioned imbalance dynamic sequence; Extract feature quantities from the dynamic trajectory; The feature values ​​are input into a pre-trained health assessment model, which outputs the health status level of the CT power supply network.

[0007] Based on the above technical solution, the present invention can be further improved as follows: Optionally, the calculation of the three-phase current imbalance based on the three-phase current data includes: The three-phase current imbalance is calculated using formula (1); Unbalance = [(maximum current - minimum current) / three-phase average current] × 100% Formula (1); The maximum current is the maximum value among the three-phase current data, and the minimum current is the minimum value among the three-phase current data.

[0008] Optionally, constructing the dynamic trajectory based on the imbalance dynamic sequence includes: Using the load current of the CT power supply network as the X-axis and the unbalance degree as the Y-axis, a two-dimensional dynamic trajectory of load-unbalance degree is constructed. Perform a short-time Fourier transform or wavelet transform on the imbalance time series to obtain the frequency domain / time-frequency domain dynamic trajectory; A dynamic trajectory is constructed based on the two-dimensional dynamic trajectory of the load-imbalance degree and the dynamic trajectory of the frequency domain / time frequency domain.

[0009] Optionally, extracting feature quantities from the dynamic trajectory includes: The slope of the dynamic trajectory is fitted by linear regression, and trend features are extracted from the dynamic trajectory based on the slope. Calculate the standard deviation, variance, or range of the dynamic trajectory within a preset time window, and extract fluctuation features from the dynamic trajectory based on the standard deviation, variance, or range; Identify whether a specific pattern exists in the dynamic trajectory, and extract morphological features from the dynamic trajectory based on the specific pattern. The specific pattern includes step, periodic oscillation, spike or spur.

[0010] Optionally, before inputting the feature values ​​into the pre-trained health assessment model, the method further includes: Historical three-phase current data of the CT power supply network under different health conditions were collected. The historical three-phase current imbalance is calculated based on the historical three-phase current data, and a historical imbalance time series is generated based on the historical three-phase current imbalance. Construct historical dynamic trajectories based on the aforementioned historical imbalance dynamic sequence; Extract historical feature quantities from the historical dynamic trajectory; The historical features are used as training data and input into the initial health assessment model for training to obtain the pre-trained health assessment model.

[0011] Optionally, the electrical appliance is a medical device.

[0012] Optionally, the medical device is a CT scanner.

[0013] An electrical appliance power supply network health status detection system, comprising: The data acquisition module is used to acquire three-phase current data of the CT power supply network; The calculation module is used to calculate the three-phase current imbalance based on the three-phase current data and generate an imbalance time series based on the three-phase current imbalance. A trajectory construction module is used to construct a dynamic trajectory based on the dynamic sequence of imbalance. The feature extraction module is used to extract feature quantities from the dynamic trajectory; The health assessment module is used to input the feature quantities into a pre-trained health assessment model and output the health status level of the CT power supply network.

[0014] An electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method described herein.

[0015] A non-transitory computer-readable storage medium having a computer program stored thereon, the computer program implementing the steps of the method when executed by a processor.

[0016] The present invention has the following advantages: The present invention discloses a method for detecting the health status of an electrical power supply network. This method calculates the three-phase current imbalance based on three-phase current data, generates an imbalance time series based on the three-phase current imbalance, constructs a dynamic trajectory based on the dynamic imbalance sequence, extracts feature quantities from the dynamic trajectory, inputs these feature quantities into a pre-trained health assessment model, and outputs the health status level of the CT power supply network. This method accurately captures the dynamic process of fault development, enabling early identification of early, slowly changing faults and solving the problem of delayed early warning in existing technologies. Attached Figure Description

[0017] For illustrative and not limiting purposes, the present invention will now be described in conjunction with embodiments and accompanying drawings, wherein: Figure 1 This is a flowchart illustrating the electrical power supply network health status detection method according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the main components of the electrical power supply network health status detection system in an embodiment of the present invention; Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be noted that, where there is no conflict, the embodiments and features of the present invention can be combined with each other. The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0021] Figure 1 This is a flowchart illustrating the electrical power supply network health status detection method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the electrical power supply network health status detection method provided in this embodiment of the invention includes the following steps S101 to S105.

[0022] S101 collects three-phase current data of the CT power supply network.

[0023] At the outlet of the distribution transformer or at key nodes, current transformers are used to collect the three-phase current data Ia, Ib, and Ic of the CT power supply network in real time.

[0024] S102 calculates the three-phase current imbalance based on the three-phase current data and generates an imbalance time series based on the three-phase current imbalance.

[0025] The three-phase current imbalance is calculated using formula (1); Unbalance = [(maximum current - minimum current) / three-phase average current] × 100% Formula (1); The maximum current is the maximum value among the three-phase current data, and the minimum current is the minimum value among the three-phase current data.

[0026] The three-phase current imbalance was calculated, and the original imbalance time series ε(t) was obtained. Assume the three-phase currents a, b, and c are Ia = 100A, Ib = 110A, and Ic = 120A, respectively. Imax=120A; Imin=100A; Iavg = (100 + 110 + 120) / 3 = 110A; Three-phase current imbalance ε = (120 − 100) / 110 × 100% ≈ 18.2%; S103, constructing dynamic trajectories based on imbalance dynamic sequences.

[0027] Using the load current of the CT power supply network as the X-axis and the unbalance degree as the Y-axis, a two-dimensional dynamic trajectory of load-unbalance degree is constructed. For a healthy power supply network, this trajectory is a relatively compact "band" that fluctuates around a low unbalance degree level.

[0028] Perform a short-time Fourier transform or wavelet transform on the unbalance time series to obtain the frequency domain / time-frequency domain dynamic trajectory; observe the trajectory of the amplitude of a specific harmonic component (such as the 3rd harmonic) in the unbalance as a function of time / load. Aging cables may cause the growth of specific harmonics.

[0029] A dynamic trajectory is constructed based on the two-dimensional dynamic trajectory of the load-imbalance degree and the dynamic trajectory of the frequency domain / time frequency domain.

[0030] Cable insulation aging leads to a decrease in insulation resistance, especially an imbalance in the insulation resistance to ground across different phases. This causes changes in the distributed capacitance to ground, with inconsistent changes across the three phases. These changes directly exacerbate the imbalance in leakage current to ground across the three-phase load.

[0031] Early aging: Under the same load level, the minimum unbalance is slowly increasing. For example, in the past, with a load of 100A, the unbalance was between 0.5% and 1.5%; now, with the same load of 100A, it has become 1.0% to 2.5%. The "baseline" of the trajectory has shifted upwards overall.

[0032] Mid-term aging: The width of the trajectory band begins to diverge. This means that the range of imbalance fluctuations increases, as the instability of aging exacerbates the system's sensitivity to load changes.

[0033] Health status: When the load increases, the imbalance may increase slightly, but the trajectory is smooth.

[0034] Aging condition: During certain phases of load changes (such as when the load increases rapidly), abnormal "spiking" or "bumps" may appear. This is because the nonlinear conductivity of aged insulation becomes more pronounced when subjected to higher electric field strengths.

[0035] Aging alters the impedance characteristics of a circuit. This may trigger resonances that were not originally present at a specific load or harmonic frequency, which will manifest as a sudden "peak" in the "frequency domain trajectory".

[0036] S104, extracting feature quantities from dynamic trajectories.

[0037] By fitting the slope of the dynamic trajectory using linear regression, it is determined whether the imbalance is increasing, decreasing, or stable, and trend features are extracted from the dynamic trajectory based on the slope. Calculate the standard deviation, variance, or range of the dynamic trajectory within a preset time window to reflect the severity of the imbalance fluctuations, and extract fluctuation features from the dynamic trajectory based on the standard deviation, variance, or range. Identify whether a specific pattern exists in the dynamic trajectory, and extract morphological features from the dynamic trajectory based on the specific pattern. The specific pattern includes step, periodic oscillation, spike or spur.

[0038] S105 inputs the feature values ​​into the pre-trained health assessment model and outputs the health status level of the CT power supply network.

[0039] Health status levels can include: normal, attention, abnormal, and dangerous.

[0040] Before the step of inputting the feature quantities into the pre-trained health assessment model, the following steps are included: Historical three-phase current data of the CT power supply network under different health conditions were collected. The historical three-phase current imbalance is calculated based on the historical three-phase current data, and a historical imbalance time series is generated based on the historical three-phase current imbalance. Construct historical dynamic trajectories based on the aforementioned historical imbalance dynamic sequence; Extract historical feature quantities from the historical dynamic trajectory; The historical features are used as training data and input into the initial health assessment model for training to obtain the pre-trained health assessment model.

[0041] The step of inputting the feature quantities into a pre-trained health assessment model and outputting the health status level of the CT power supply network includes: Determine the thresholds K1, K2, and emergency threshold for the feature deviation judgment of the health assessment model; When the feature value deviates from the threshold K1 but does not exceed the threshold K2, the health status level of the CT power supply network is determined to be the attention level; When the feature quantity exceeds the threshold K2, the health status level of the CT power supply network is determined to be abnormal. When the characteristic value exceeds the emergency threshold and shows a continuous and rapid growth trend, the health status level of the CT power supply network is determined to be dangerous. When the characteristic quantity does not show any deviation and there are no abnormal morphological characteristics, the health status level of the CT power supply network is determined to be normal.

[0042] By analyzing the abnormal patterns of the trajectories at different monitoring points, it is possible to help locate the most severely aged section of the line.

[0043] When the health status level of the CT power supply network changes to "Attention Level", a yellow indicator will be displayed on the monitoring system; when the health status level of the CT power supply network changes to "Abnormal Level", an audible and visual alarm will be issued and a maintenance work order will be pushed.

[0044] Following the steps for determining the health status level of the output CT power supply network, the following is also included: Based on the health status level, a corresponding early warning signal is triggered, and the health status level and the early warning signal are output to the monitoring center.

[0045] Figure 2 This is a schematic diagram of the main components of the electrical power supply network health status detection system according to an embodiment of the present invention. Figure 2 As shown, the electrical power supply network health status detection system 1 provided in this embodiment of the invention includes a data acquisition module 10, a calculation module 20, a trajectory construction module 30, a feature extraction module 40, and a health assessment module 50.

[0046] Data acquisition module 10 is used to acquire three-phase current data of the CT power supply network; Calculation module 20 is used to calculate the three-phase current imbalance based on the three-phase current data and generate an imbalance time series based on the three-phase current imbalance. Trajectory construction module 30 is used to construct a dynamic trajectory based on the imbalance dynamic sequence; Feature extraction module 40 is used to extract feature quantities from the dynamic trajectory; The health assessment module 50 is used to input the feature quantities into the pre-trained health assessment model and output the health status level of the CT power supply network.

[0047] Figure 3 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3As shown, the electronic device 60 includes: a processor 601, a memory 602, and a bus 603; The processor 601 and the memory 602 communicate with each other via the bus 603. The processor 601 is used to call program instructions in the memory 602 to execute the methods provided in the above-described method embodiments, and to execute the methods provided in the embodiments of the present invention.

[0048] This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions, which cause a computer to execute the method provided in this embodiment of the invention.

[0049] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various storage media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0050] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting the health status of an electrical power supply network, characterized in that, include: Collect three-phase current data of the CT power supply network; The three-phase current imbalance is calculated based on the three-phase current data, and an imbalance time series is generated based on the three-phase current imbalance. A dynamic trajectory is constructed based on the aforementioned imbalance dynamic sequence; Extract feature quantities from the dynamic trajectory; The feature values ​​are input into a pre-trained health assessment model, which outputs the health status level of the CT power supply network.

2. The method for detecting the health status of an electrical power supply network according to claim 1, characterized in that, The calculation of the three-phase current imbalance based on the three-phase current data includes: The three-phase current imbalance is calculated using formula (1); Unbalance = [(maximum current - minimum current) / three-phase average current] × 100% Formula (1); The maximum current is the maximum value among the three-phase current data, and the minimum current is the minimum value among the three-phase current data.

3. The method for detecting the health status of an electrical power supply network according to claim 1, characterized in that, The construction of the dynamic trajectory based on the imbalance dynamic sequence includes: Using the load current of the CT power supply network as the X-axis and the unbalance degree as the Y-axis, a two-dimensional dynamic trajectory of load-unbalance degree is constructed. Perform a short-time Fourier transform or wavelet transform on the imbalance time series to obtain the frequency domain / time-frequency domain dynamic trajectory; A dynamic trajectory is constructed based on the two-dimensional dynamic trajectory of the load-imbalance degree and the dynamic trajectory of the frequency domain / time frequency domain.

4. The method for detecting the health status of an electrical power supply network according to claim 1, characterized in that, Extracting feature quantities from the dynamic trajectory includes: The slope of the dynamic trajectory is fitted by linear regression, and trend features are extracted from the dynamic trajectory based on the slope. Calculate the standard deviation, variance, or range of the dynamic trajectory within a preset time window, and extract fluctuation features from the dynamic trajectory based on the standard deviation, variance, or range; Identify whether a specific pattern exists in the dynamic trajectory, and extract morphological features from the dynamic trajectory based on the specific pattern. The specific pattern includes step, periodic oscillation, spike or spur.

5. The method for detecting the health status of an electrical power supply network according to claim 1, characterized in that, Before inputting the feature values ​​into the pre-trained health assessment model, the method further includes: Historical three-phase current data of the CT power supply network under different health conditions were collected. The historical three-phase current imbalance is calculated based on the historical three-phase current data, and a historical imbalance time series is generated based on the historical three-phase current imbalance. Construct historical dynamic trajectories based on the aforementioned historical imbalance dynamic sequence; Extract historical feature quantities from the historical dynamic trajectory; The historical features are used as training data and input into the initial health assessment model for training to obtain the pre-trained health assessment model.

6. The method for detecting the health status of an electrical power supply network according to any one of claims 1-5, characterized in that, The electrical appliance is a medical device.

7. The method for detecting the health status of an electrical power supply network according to claim 6, characterized in that, The medical equipment mentioned is a CT scanner.

8. A system for detecting the health status of an electrical power supply network, characterized in that, include: The data acquisition module is used to acquire three-phase current data of the CT power supply network; The calculation module is used to calculate the three-phase current imbalance based on the three-phase current data and generate an imbalance time series based on the three-phase current imbalance. A trajectory construction module is used to construct a dynamic trajectory based on the dynamic sequence of imbalance. The feature extraction module is used to extract feature quantities from the dynamic trajectory; The health assessment module is used to input the feature quantities into a pre-trained health assessment model and output the health status level of the CT power supply network.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images