Distributed power supply state monitoring method and system based on optical fiber communication sensing

Abstract

The invention relates to the field of power supply equipment monitoring, in particular to a distributed power supply state monitoring method and system based on optical fiber communication sensing. The method comprises the following steps: acquiring a power supply equipment distribution diagram; performing spatial layout distribution analysis on the power supply equipment distribution diagram to obtain power supply node layout distribution data; performing distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensing node; performing time window fine-grained division on the real-time monitoring data of the power supply equipment to obtain a plurality of time windows; performing multi-layer time-frequency local decomposition on the real-time monitoring data of the power supply equipment based on a plurality of time windows, and constructing a multi-period spectrum feature map; and extracting a power supply equipment time sequence voltage sequence based on the power supply equipment real-time monitoring data. According to the invention, efficient and accurate power supply equipment state monitoring is realized.

Description

Technical Field

[0001] The present invention relates to the field of power supply equipment monitoring, and in particular to a distributed power supply status monitoring method and system based on optical fiber communication sensing. Background Art

[0002] With the continuous development of industrial automation and intelligent manufacturing, distributed power supply systems play an increasingly important role in many industrial scenarios. These distributed power supply systems are usually composed of multiple independent power supply units to provide the required power support for production equipment, robots, transportation tools, etc. Long-term stable and reliable power supply is the key to ensure the smooth operation of these automation systems. However, the power supply equipment of the distributed power supply system is often distributed in a large factory workshop or outdoor venue, and it is difficult to carry out centralized real-time monitoring and fault warning. Traditional power supply status monitoring methods often rely on manual inspections and single-point measurements, and often have low power supply equipment monitoring efficiency and cannot detect power supply anomalies in time. Therefore, there is an urgent need for a new distributed power supply status monitoring method based on advanced sensing technology, which can realize comprehensive dynamic monitoring of the operating status of power supply equipment. Summary of the invention

[0003] The present invention proposes a distributed power supply status monitoring method and system based on optical fiber communication sensing to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a distributed power supply status monitoring method based on optical fiber communication sensing, comprising the following steps: Step S1: obtaining a power supply equipment distribution map; performing spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; performing distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; Step S2: acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; performing fine-grained time window division on the real-time monitoring data of the power supply equipment to obtain multiple time windows; performing multi-layer time-frequency local decomposition on the real-time monitoring data of the power supply equipment based on the multiple time windows to construct a multi-time period spectrum feature diagram; Step S3: extracting a time-series voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; performing a spectrum distribution morphology change analysis on a multi-period spectrum feature graph based on the time-series voltage sequence of the power supply equipment to generate multi-period spectrum morphology change data; Step S4: performing spectrum amplitude trend evolution on the spectrum morphology change data of multiple time periods to generate spectrum change amplitude trend data; performing abnormal trend analysis on the spectrum change amplitude trend data to extract abnormal voltage spectrum bands; Step S5: dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and construct a dynamic rendering model of the abnormal area; and obtain voltage excitation response data of the abnormal area based on the dynamic rendering model of the abnormal area; Step S6: locate the abnormal state of the voltage excitation response data in the abnormal area to obtain the abnormal state node; based on the abnormal state node, adaptively adjust the operating parameters of the power supply node topology network to construct a distributed power supply node optimization strategy.

[0005] The present invention provides the location and layout information of power supply nodes through the spatial layout distribution analysis of the power supply equipment distribution map, and provides basic data for subsequent topology reconstruction. The distributed topology reconstruction reorganizes the connection mode of the power supply nodes to build a power supply node topology network that is more in line with the actual situation, thereby improving the reliability and stability of the power supply system. The optical fiber communication sensor node obtains the real-time monitoring data of the power supply equipment, realizes the real-time monitoring of the power supply equipment status, and provides a data basis for subsequent analysis and processing. The fine-grained division of the time window divides the real-time monitoring data according to the time period, making the analysis of the power supply equipment status more refined and accurate. The multi-layer time-frequency local decomposition converts the real-time monitoring data of the power supply equipment into frequency spectrum feature diagrams of multiple time periods, extracts the feature information of different frequency bands, and uses it for subsequent frequency spectrum analysis and anomaly detection. The time series voltage sequence of the power supply equipment is extracted to better analyze the voltage change trend of the power supply equipment, and provides a basis for the subsequent frequency spectrum morphology change analysis. The spectrum morphology change data reflects the changes in the spectrum characteristics of the power supply equipment in different time periods, which is used for anomaly detection and fault diagnosis. The spectrum amplitude trend evolution reveals the changing trend of the spectrum characteristics of the power supply equipment, which is helpful to discover abnormal conditions and fault warnings. The abnormal trend analysis extracts the abnormal voltage spectrum band and determines the spectrum range with abnormalities, which provides important information for the subsequent abnormal state positioning. The dynamic rendering reconstruction adjusts the power supply node topology network based on the abnormal voltage spectrum band, so that the abnormal area can be more accurately located and described. The abnormal area dynamic rendering model provides voltage excitation response data for the abnormal area, which provides a basis for abnormal state positioning and analysis. The abnormal state positioning determines the power supply node with abnormalities, and provides positioning information for subsequent fault handling and optimization strategies. The adaptive operation parameter fine-tuning adjusts the operation parameters of the power supply node topology network according to the situation of the abnormal state node to optimize the performance and stability of the power supply system.

[0006] Preferably, step S1 comprises the following steps: Step S11: Obtain a power supply equipment distribution map; Step S12: performing device identification on the power supply device distribution map to mark the power supply device nodes; Step S13: performing spatial layout distribution analysis on power supply equipment nodes to obtain power supply node layout distribution data; Step S14: performing line topology connection analysis on the power supply equipment distribution diagram to obtain a node topology line structure diagram; Step S15: Perform distributed topology reconstruction on the node topology line structure diagram based on the power supply node layout distribution data to construct a power supply node topology network.

[0007] The present invention obtains the position and distribution of each device in the power supply system by acquiring the power supply equipment distribution map, provides basic data for subsequent analysis and processing, performs equipment identification on the power supply equipment distribution map, accurately marks the power supply equipment nodes, distinguishes them from other non-power supply equipment, and facilitates subsequent analysis and processing. The spatial layout distribution analysis analyzes the power supply equipment nodes, including information such as the distance and relative position between the nodes, and provides a basis for subsequent topological reconstruction and power supply status monitoring. The power supply node layout distribution data reflects the spatial distribution characteristics of the power supply equipment nodes, which helps to understand the overall structure and layout of the power supply system. The line topology connection analysis analyzes the connection relationship and topological structure between the power supply equipment, including information such as the connection mode and topological path of the line, which provides a basis for subsequent topological reconstruction and power supply status monitoring. The node topology line structure diagram reflects the connection relationship between the power supply equipment nodes, which helps to understand the topological structure and power transmission path of the power supply system. The distributed topology reconstruction reconstructs the node topology line structure diagram based on the power supply node layout distribution data, optimizes the topological structure of the power supply system, improves the reliability, stability and economy of the system, constructs a power supply node topology network to establish the connection relationship between the nodes in the power supply system, and forms a distributed power supply network, which provides a basis for power supply status monitoring and abnormality detection.

[0008] Preferably, the specific steps of step S14 are: Calculate the node position of the power supply equipment distribution map based on the power supply equipment node, so as to obtain the power supply node position coordinates; Perform redundant position difference positioning analysis based on the power supply node position coordinates to obtain the inter-node positioning correlation data; Based on the inter-node positioning association data, the line topology connection analysis of the power supply equipment nodes is performed to generate the node topology line; Calculate the minimum hopping frequency between nodes of the power supply equipment to obtain the minimum hopping frequency value; Calculate the topological adjacency distance of the node topological lines to obtain the topological distance data between nodes; Based on the minimum frequency hopping value and the topological distance data between nodes, the topological logic path of the power supply equipment distribution diagram is optimized to generate a node topology line structure diagram.

[0009] The present invention determines the accurate position coordinates of the power supply node by performing node position calculation on the power supply equipment distribution map based on the power supply equipment node, providing basic data for subsequent analysis and processing; the redundant position difference positioning analysis is based on the power supply node position coordinates, and the redundant position difference between the nodes is calculated, so as to obtain the positioning association data between the nodes, providing a basis for the subsequent topological connection analysis; the spatial layout distribution analysis of the power supply equipment nodes is performed to obtain the layout distribution data of the power supply nodes, including the distance and relative position between the nodes and other information, providing a basis for the subsequent topological connection analysis and path optimization; the line topological connection analysis is based on the positioning association data between the nodes, determines the connection relationship and topological structure between the power supply equipment nodes, generates the node topology line, and provides basic data for the subsequent topological logic path optimization According to the minimum hopping frequency calculation between nodes, the minimum hopping frequency value between power supply equipment nodes is calculated, which indicates the shortest number of jumps between nodes and is used for subsequent topological logical path optimization. The topological adjacent distance calculation determines the topological distance between power supply equipment nodes, which indicates the closeness of the topological relationship between nodes and provides a basis for subsequent topological logical path optimization. Based on the minimum hopping frequency value and the topological distance data between nodes, the topological logical path optimization of the power supply equipment distribution map is performed to optimize the path layout of the power supply system, making the communication path between nodes more reasonable and efficient, providing a good data transmission foundation for distributed power supply status monitoring, generating a node topological line structure diagram to form a connection relationship diagram between nodes in the power supply system, and providing a visual representation of the topological structure of the power supply node, which is convenient for system management and monitoring.

[0010] Preferably, the specific steps of step S2 are: Step S21: acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; Step S22: performing segmented low-pass filtering on the real-time monitoring data of the power supply equipment to obtain noise-reduced power supply monitoring data; Step S23: performing fine-grained division of the time window for the real-time monitoring data of the power supply equipment to obtain multiple time windows; Step S24: performing multi-layer time-frequency local decomposition on the noise reduction power supply monitoring data based on multiple time windows to obtain a multi-time-frequency frequency domain; Step S25: performing multi-scale frequency domain distribution analysis on the multi-time-frequency frequency domain to obtain multi-scale time-frequency frequency domain distribution data; Step S26: integrating the main frequency components of each scale on the multi-scale time-frequency frequency domain distribution data to construct a multi-time period frequency spectrum feature diagram.

[0011] The present invention obtains the monitoring data of the power supply equipment in real time based on the optical fiber communication sensor node, including parameters such as voltage, current, and power, to provide a real-time data source for subsequent analysis and processing. The real-time monitoring data of the power supply equipment is subjected to noise reduction processing by segmented low-pass filtering to remove high-frequency noise components and extract relatively smooth monitoring data, so that the subsequent frequency domain analysis is more accurate and reliable. The real-time monitoring data of the power supply equipment is divided into multiple time windows by fine-grained time window division, and the monitoring data is locally analyzed to capture the characteristics and change trends of different time periods. The multi-layer time-frequency local decomposition is based on multiple time windows to perform time-frequency decomposition on the noise-reduced power supply monitoring data. , convert the time domain signal into the frequency domain, and obtain the distribution of the power supply equipment monitoring data at different frequencies, which helps to capture the fault characteristics and abnormal changes at different frequencies. Multi-scale frequency domain distribution analysis analyzes the multi-time-frequency frequency domain to obtain the distribution of the power supply equipment monitoring data at different scales and frequency domains, revealing the time-frequency characteristics of the power supply equipment, which is helpful for fault diagnosis and status assessment. The integration processing of the main frequency components of each scale processes the multi-scale time-frequency frequency domain distribution data, extracts the main frequency components at each scale, and constructs a multi-time period spectrum feature diagram to better represent the frequency domain characteristics of the power supply equipment in different time periods, providing an effective feature description and identification basis for distributed power supply status monitoring.

[0012] Preferably, the specific steps of step S3 are: Step S31: extracting the time-series voltage from the real-time monitoring data of the power supply equipment to obtain the time-series voltage sequence of the power supply equipment; Step S32: identifying the voltage fluctuation trend of the power supply equipment time series voltage sequence and generating voltage fluctuation trend data; Step S33: identifying low-frequency bandwidth fluctuations on the multi-period spectrum characteristic graph based on the voltage fluctuation trend data, thereby obtaining multi-period spectrum bandwidth fluctuation data; Step S34: Analyze the spectrum distribution morphology changes of the spectrum bandwidth fluctuation data in multiple time periods to generate spectrum morphology change data in multiple time periods.

[0013] The present invention processes the real-time monitoring data of the power supply equipment through time-series voltage extraction, extracts the time-series voltage sequence of the power supply equipment, converts the monitoring data into time sequence data, and provides basic data for subsequent fluctuation trend analysis and spectrum feature extraction. The voltage fluctuation trend identification is based on the time-series voltage sequence of the power supply equipment, analyzes and identifies the voltage fluctuation changes, generates voltage fluctuation trend data, judges the voltage stability and fluctuation of the power supply equipment, and provides important information for fault diagnosis and status evaluation. The low-frequency bandwidth fluctuation identification in the multi-period spectrum feature graph is based on the voltage fluctuation trend data, identifies the low-frequency bandwidth in the multi-period spectrum feature graph, captures the fluctuation of the power supply equipment in the low frequency band, and detects abnormal changes related to the low-frequency bandwidth in the power supply system. The spectrum distribution morphology change analysis analyzes the multi-period spectrum bandwidth fluctuation data, identifies the morphological changes of the spectrum distribution of the power supply equipment in different time periods, reveals the spectrum feature change trend of the power supply equipment, and provides useful information for fault diagnosis and status evaluation. These data are used to detect spectrum anomalies, spectrum distortion and other problems in the power supply system, which helps to monitor the status of the power supply equipment and perform corresponding maintenance and repair.

[0014] Preferably, the specific steps of step S4 are: Step S41: performing time series change trajectory analysis on the spectrum morphology change data of multiple time periods to obtain the spectrum morphology change trajectory; Step S42: performing spectrum amplitude trend evolution on the spectrum morphology change trajectory to generate spectrum change amplitude trend data; Step S43: performing abnormal trend analysis on the spectrum variation amplitude trend data to obtain voltage spectrum abnormal trend data; Step S44: Based on the voltage spectrum abnormal trend data, abnormal frequency bands are identified on the multi-period spectrum characteristic diagram to extract abnormal voltage spectrum bands.

[0015] The present invention performs time series analysis on the spectrum morphology change data of multiple time periods through time series change trajectory analysis, revealing the change trend of the spectrum morphology of the power supply equipment, so as to understand the evolution process and change law of the power supply equipment status. The spectrum amplitude trend evolution analysis performs amplitude trend analysis on the spectrum morphology change trajectory, extracts the spectrum amplitude change trend data, and helps to determine whether there is an abnormality or abnormal change in the spectrum amplitude of the power supply equipment. The abnormal trend analysis is based on the spectrum change amplitude trend data, analyzes the abnormal trend of the voltage spectrum, identifies the existing abnormal conditions, and provides a basis for fault diagnosis and early warning. The abnormal frequency band identification is based on the voltage spectrum abnormal trend data, extracts the abnormal frequency band in the multi-time spectrum feature diagram, that is, the frequency range where the abnormality occurs in the voltage spectrum, which helps to locate and identify the fault or abnormal condition of the power supply equipment, and provides abnormal frequency band information for distributed power supply status monitoring.

[0016] Preferably, the specific steps of step S5 are: Step S51: locating the abnormal area of ​​the power supply node topology network based on the abnormal voltage spectrum band to obtain the abnormal area topology network; Step S52: dynamically rendering and reconstructing the abnormal area topology network using the voltage fluctuation trend data to construct a dynamic rendering model for the abnormal area; Step S53: performing multi-frequency voltage excitation simulation on the abnormal area dynamic rendering model to obtain abnormal area voltage excitation response data.

[0017] The present invention locates abnormal areas of the power supply node topology network based on the abnormal voltage spectrum band and determines the abnormal areas in the power supply system by analyzing the abnormal voltage spectrum. It helps to quickly locate potential faults or abnormal areas and improve the efficiency of fault diagnosis. The voltage fluctuation trend data is used to dynamically render and reconstruct the topological network of the abnormal area to visualize the voltage fluctuation trend in the abnormal area and reconstruct the topological network model of the abnormal area. It helps to intuitively understand and analyze the voltage changes in the abnormal area, and provide more accurate information for subsequent fault location and processing. Multi-frequency voltage excitation simulation is performed on the dynamic rendering model of the abnormal area to simulate the response of voltage excitations at different frequencies to the abnormal area. By simulating voltage excitations at different frequencies, the response characteristics of the abnormal area can be more comprehensively understood, including frequency response, amplitude response, etc. It helps to deeply analyze the characteristics and behaviors of the abnormal area and provide a basis for further fault diagnosis and processing.

[0018] Preferably, the specific steps of step S6 are: Step S61: performing abnormal response analysis on the abnormal region voltage excitation response data to obtain abnormal voltage response data; Step S62: locating the abnormal state of the abnormal region dynamic rendering model based on the abnormal voltage response data to obtain an abnormal state node; Step S63: Perform fault attribution analysis on the abnormal state node to obtain the fault factor of the abnormal state node; Step S64: Adaptively fine-tune the operating parameters of the power supply node topology network based on the abnormal state node failure factors, and construct a distributed power supply node optimization strategy.

[0019] The present invention analyzes the voltage excitation response data of the abnormal area, identifies and extracts the abnormal voltage response pattern, which helps to determine the abnormal conditions existing in the power supply system, such as voltage fluctuation, harmonic distortion, etc., and provides a basis for subsequent abnormal state positioning and fault attribution analysis. By analyzing the abnormal area dynamic rendering model based on the abnormal voltage response data, the abnormal state node is accurately located, which helps to determine that there is an abnormality in a specific node in the power supply system, and provides more specific fault location information. Fault attribution analysis is performed on the abnormal state node to determine the specific fault factor that causes the node abnormality, which helps to understand the root cause of the fault and provide guidance for subsequent fault repair and preventive maintenance. According to the fault factors of the abnormal state node, the power supply node topology network is adaptively adjusted in terms of operating parameters. By adjusting the operating parameters, such as the voltage setting value, the transmission line impedance, etc., the performance and stability of the power supply node are optimized and the fault risk is reduced.

[0020] In this specification, a distributed power supply status monitoring system based on optical fiber communication sensing is provided, which is used to execute the distributed power supply status monitoring method based on optical fiber communication sensing as described above, including: A topology network module is used to obtain a power supply equipment distribution map; perform spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; perform distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; The time-frequency local module is used to obtain the real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; the real-time monitoring data of the power supply equipment is finely divided into time windows to obtain multiple time windows; the real-time monitoring data of the power supply equipment is decomposed into multiple layers of time and frequency based on multiple time windows to construct a multi-time spectrum feature diagram; The spectrum morphology module is used to extract the time-series voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; analyze the spectrum distribution morphology changes of the multi-period spectrum characteristic diagram based on the time-series voltage sequence of the power supply equipment, and generate multi-period spectrum morphology change data; The abnormal trend module is used to perform spectrum amplitude trend evolution on spectrum morphology change data in multiple time periods to generate spectrum change amplitude trend data; perform abnormal trend analysis on spectrum change amplitude trend data to extract abnormal voltage spectrum bands; The voltage excitation response module is used to dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and build a dynamic rendering model for the abnormal area; based on the dynamic rendering model for the abnormal area, the voltage excitation response data of the abnormal area is obtained; The adaptive fine-tuning module is used to locate the abnormal state of the voltage excitation response data in the abnormal area and obtain the abnormal state nodes; based on the abnormal state nodes, the power supply node topology network is adaptively fine-tuned to construct a distributed power supply node optimization strategy.

[0021] The present invention provides basic data for subsequent distributed power supply status monitoring by acquiring a power supply equipment distribution map. The power supply equipment distribution map reflects the topological connection relationship between various devices in the power supply system, including the layout of power supply nodes, the connection method of lines, etc. The real-time monitoring data of the power supply equipment is acquired by using optical fiber communication sensor nodes, and the real-time monitoring data is divided into time windows and multi-layer time-frequency local decomposition is performed to obtain the spectrum characteristic maps of the power supply equipment in different time periods. These characteristic maps reflect the spectrum distribution of the power supply equipment in different frequency bands, which is helpful for subsequent spectrum morphology analysis and abnormal trend analysis. The time series voltage sequence is extracted based on the real-time monitoring data of the power supply equipment, and the spectrum distribution morphology change analysis is performed on the multi-time period spectrum characteristic map, so that the spectrum morphology change data of the power supply equipment in different time periods is obtained, revealing the time-varying nature of the spectrum characteristics of the power supply equipment. Through the spectrum amplitude trend evolution and abnormal trend analysis, the abnormal voltage spectrum of the power supply equipment is extracted. Frequency bands are used to further locate abnormal states, and spectrum amplitude trend evolution analysis is performed on spectrum morphology change data in multiple time periods to obtain spectrum change amplitude trend data of power supply equipment. Through abnormal trend analysis, abnormal voltage spectrum bands are extracted to identify frequency bands where power supply equipment has abnormalities. Abnormal voltage spectrum bands are used to dynamically render and reconstruct the power supply node topology network, and a dynamic rendering model of abnormal areas is constructed. This model reflects the location and range of abnormal areas in the power supply node topology network, and provides voltage excitation response data of abnormal areas for subsequent abnormal state positioning and optimization strategy construction. The abnormal state node positioning results are used to adaptively fine-tune the operating parameters of the power supply node topology network. According to the location and characteristics of the abnormal state nodes, the layout and operating parameters of the power supply nodes are adjusted to optimize the performance of the power supply system. By fine-tuning the location and parameters of the power supply nodes, the power supply quality of the power supply system is improved, energy consumption is reduced, and the reliability and efficiency of the power grid are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of the steps of a distributed power supply status monitoring method based on optical fiber communication sensing according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0024] The present application example provides a distributed power supply status monitoring method and system based on optical fiber communication sensing. The execution subject of the distributed power supply status monitoring method and system based on optical fiber communication sensing includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0025] See also Figures 1 to 4 The present invention provides a distributed power supply status monitoring method based on optical fiber communication sensing, comprising the following steps: Step S1: obtaining a power supply equipment distribution map; performing spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; performing distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; Step S2: acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; performing fine-grained time window division on the real-time monitoring data of the power supply equipment to obtain multiple time windows; performing multi-layer time-frequency local decomposition on the real-time monitoring data of the power supply equipment based on the multiple time windows to construct a multi-time period spectrum feature diagram; Step S3: extracting a time-series voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; performing a spectrum distribution morphology change analysis on a multi-period spectrum feature graph based on the time-series voltage sequence of the power supply equipment to generate multi-period spectrum morphology change data; Step S4: performing spectrum amplitude trend evolution on the spectrum morphology change data of multiple time periods to generate spectrum change amplitude trend data; performing abnormal trend analysis on the spectrum change amplitude trend data to extract abnormal voltage spectrum bands; Step S5: dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and construct a dynamic rendering model of the abnormal area; and obtain voltage excitation response data of the abnormal area based on the dynamic rendering model of the abnormal area; Step S6: locate the abnormal state of the voltage excitation response data in the abnormal area to obtain the abnormal state node; based on the abnormal state node, adaptively adjust the operating parameters of the power supply node topology network to construct a distributed power supply node optimization strategy.

[0026] The present invention provides the location and layout information of power supply nodes through the spatial layout distribution analysis of the power supply equipment distribution map, and provides basic data for subsequent topology reconstruction. The distributed topology reconstruction reorganizes the connection mode of the power supply nodes to build a power supply node topology network that is more in line with the actual situation, thereby improving the reliability and stability of the power supply system. The optical fiber communication sensor node obtains the real-time monitoring data of the power supply equipment, realizes the real-time monitoring of the power supply equipment status, and provides a data basis for subsequent analysis and processing. The fine-grained division of the time window divides the real-time monitoring data according to the time period, making the analysis of the power supply equipment status more refined and accurate. The multi-layer time-frequency local decomposition converts the real-time monitoring data of the power supply equipment into frequency spectrum feature diagrams of multiple time periods, extracts the feature information of different frequency bands, and uses it for subsequent frequency spectrum analysis and anomaly detection. The time series voltage sequence of the power supply equipment is extracted to better analyze the voltage change trend of the power supply equipment, and provides a basis for the subsequent frequency spectrum morphology change analysis. The spectrum morphology change data reflects the changes in the spectrum characteristics of the power supply equipment in different time periods, which is used for anomaly detection and fault diagnosis. The spectrum amplitude trend evolution reveals the changing trend of the spectrum characteristics of the power supply equipment, which is helpful to discover abnormal conditions and fault warnings. The abnormal trend analysis extracts the abnormal voltage spectrum band and determines the spectrum range with abnormalities, which provides important information for the subsequent abnormal state positioning. The dynamic rendering reconstruction adjusts the power supply node topology network based on the abnormal voltage spectrum band, so that the abnormal area can be more accurately located and described. The abnormal area dynamic rendering model provides voltage excitation response data for the abnormal area, which provides a basis for abnormal state positioning and analysis. The abnormal state positioning determines the power supply node with abnormalities, and provides positioning information for subsequent fault handling and optimization strategies. The adaptive operation parameter fine-tuning adjusts the operation parameters of the power supply node topology network according to the situation of the abnormal state node to optimize the performance and stability of the power supply system.

[0027] In the embodiment of the present invention, refer to Figure 1 , is a schematic diagram of the steps of a distributed power supply status monitoring method based on optical fiber communication sensing of the present invention. In this example, the steps of the distributed power supply status monitoring method based on optical fiber communication sensing include: Step S1: obtaining a power supply equipment distribution map; performing spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; performing distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; In this embodiment, after obtaining authorization, a spatial layout distribution map of the power supply equipment is obtained through field survey. The distribution map should include the specific location coordinate information of the power supply equipment and the connection status between the equipment. Based on the obtained power supply equipment distribution map, the spatial distribution of the power supply equipment is analyzed, the area through which the power supply line passes is determined, and the location distribution of each power supply node is statistically analyzed. Through clustering, principal component analysis and other methods, the spatial layout distribution characteristics of the power supply nodes are obtained, and the analysis results are organized into spatial location distribution data of the power supply nodes. The power supply nodes are regarded as nodes in the network, and the power supply lines between the nodes are regarded as network connection edges. According to the node location information and connection relationship, a distributed topological network diagram of the power supply system is established. The topological network diagram can more accurately reflect the actual operation structure of the power supply system, and the constructed distributed topological network is further optimized and calibrated. The parameter information such as the rated capacity and line impedance of the power supply equipment is introduced to improve the physical characteristics of the network model. By comparing and verifying with the actual power supply system operation data, the accuracy of the topological network model is further improved.

[0028] Step S2: acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; performing fine-grained time window division on the real-time monitoring data of the power supply equipment to obtain multiple time windows; performing multi-layer time-frequency local decomposition on the real-time monitoring data of the power supply equipment based on the multiple time windows to construct a multi-time period spectrum feature diagram; In this embodiment, optical fiber communication sensor nodes are deployed around the power supply equipment to collect various operating parameters of the equipment in real time, such as voltage, current, power, etc., and these real-time monitoring data are transmitted back to the central control system using optical fiber communication technology. A real-time monitoring data acquisition network for power supply equipment is established to ensure that data is acquired in a timely and accurate manner. The acquired real-time monitoring data sequence of the power supply equipment is divided into multiple time windows. The length of the time window can be flexibly set according to actual needs, such as 1 hour, 6 hours, 12 hours, etc., to ensure that there is a certain overlap between the time windows to ensure the continuity of data analysis. The power supply equipment monitoring data in each time window is analyzed in the time and frequency domain, such as short-time Fourier transform, wavelet transform, etc., to obtain the spectrum characteristics of the operating status of the power supply equipment in different time windows, and these spectrum characteristics are combined along the time axis to construct a multi-time period spectrum characteristic diagram of the power supply equipment. The constructed multi-time period spectrum characteristic diagram is analyzed to identify abnormal modes of the operating status of the power supply equipment. Machine learning, pattern recognition and other methods are used to automatically detect abnormal conditions of the equipment to provide a basis for fault warning. Targeted power supply equipment operation and maintenance strategies are formulated based on the spectrum characteristics of different time periods.

[0029] Step S3: extracting a time-series voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; performing a spectrum distribution morphology change analysis on a multi-period spectrum feature graph based on the time-series voltage sequence of the power supply equipment to generate multi-period spectrum morphology change data; In this embodiment, a time series voltage data sequence of each power supply device is extracted. The voltage data sequence reflects the voltage change of the power supply device in each time window. These time series voltage data provide a basis for the subsequent spectrum distribution morphology analysis. The extracted time series voltage data sequence of the power supply device is analyzed by a time-frequency domain analysis method (such as short-time Fourier transform, wavelet transform, etc.) to obtain the spectrum feature distribution of the voltage signal of the power supply device in each time window. The spectrum distribution morphology in adjacent time windows is compared, and its change trend and difference characteristics are analyzed. The spectrum morphology change of the power supply equipment in each time window is sorted into a time series data set. These data reflect the dynamic change process of the spectrum characteristics of the power supply equipment in different time periods. These data are visualized in the form of time series charts, heat maps, etc., and the generated spectrum morphology change data is deeply analyzed to identify the abnormal mode of the operating status of the power supply equipment. By using machine learning and other methods, a correlation model between spectrum morphology changes and equipment failures is established. Based on the model, early warning and diagnosis of power supply equipment failures are achieved, and at the same time, an important basis is provided for status monitoring and operation and maintenance decision-making of power supply equipment.

[0030] Step S4: performing spectrum amplitude trend evolution on the spectrum morphology change data of multiple time periods to generate spectrum change amplitude trend data; performing abnormal trend analysis on the spectrum change amplitude trend data to extract abnormal voltage spectrum bands; In this embodiment, voltage spectrum data within multiple time periods, such as daily spectrum data, are collected, and time series analysis is performed on the spectrum data to observe the amplitude change trend of each frequency band. Smoothing filtering, Fourier transform and other methods are used to analyze the change trend of the spectrum amplitude, and the trend data of the amplitude change of each frequency band over time are extracted to generate spectrum change amplitude trend data. The generated spectrum change amplitude trend data is analyzed to identify the frequency bands with abnormal changes. Statistical analysis methods are used, such as frequency bands that deviate from the average value or the standard deviation exceeds a certain threshold. Machine learning anomaly detection algorithms are also used to automatically discover abnormal patterns of spectrum change trends. In this way, frequency bands with abnormal changes in the voltage spectrum are extracted. Based on the aforementioned abnormal analysis results, frequency bands with abnormal changes in the voltage spectrum are extracted. These abnormal frequency bands are further analyzed and explained to determine the causes of the abnormal changes. In combination with equipment operation status data, environmental factors and other information, the abnormal frequency bands are deeply analyzed to ultimately form a diagnostic analysis report on abnormal changes in the voltage spectrum.

[0031] Step S5: dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and construct a dynamic rendering model of the abnormal area; and obtain voltage excitation response data of the abnormal area based on the dynamic rendering model of the abnormal area; In this embodiment, the power supply node topology network model is dynamically rendered and reconstructed. In the topology network model, the power supply nodes and lines corresponding to the abnormal frequency band are identified. Through visualization technology, such as 3D modeling, dynamic charts, etc., the local area of ​​the power supply system corresponding to the abnormal frequency band is presented. This dynamic rendering reconstruction can more intuitively display the power supply nodes and their connections corresponding to the abnormal frequency band. Based on the results of dynamic rendering reconstruction, a dynamic rendering model of the abnormal area is further constructed. The model not only contains the topological structure of the power supply node, but also should incorporate physical characteristics such as equipment parameters and line parameters. By establishing a dynamic rendering model of the abnormal area, the state of the power supply system corresponding to the abnormal frequency band is more comprehensively reflected. Using the constructed dynamic rendering model of the abnormal area, the voltage excitation response simulation analysis of the area is performed. The simulated voltage excitation is a sudden change, a periodic change, etc., to simulate the voltage change corresponding to the abnormal frequency band. The voltage response data of the power supply node during the simulation process is recorded, including amplitude, phase, etc. Analyze these voltage response data to further diagnose the operating state of the power supply system corresponding to the abnormal frequency band.

[0032] Step S6: locate the abnormal state of the voltage excitation response data in the abnormal area to obtain the abnormal state node; based on the abnormal state node, adaptively adjust the operating parameters of the power supply node topology network to construct a distributed power supply node optimization strategy.

[0033] In this embodiment, a power supply node topology network model is used, some key nodes are selected in the network as excitation points, voltage excitation signals are applied to these excitation points, response data of nodes in the entire network are measured, the response data are analyzed, nodes with abnormal responses, i.e., abnormal state nodes, are identified, and nodes where abnormal states occur are located by analyzing the amplitude, phase and other characteristics of the response data. Based on the located abnormal state node information, the information is fed back to the power supply node topology network model. For the area where the abnormal state node is located, the operating parameters in the network model are adaptively adjusted, and the supply capacity, line impedance and other parameters of the node are adjusted to optimize the operating state of the network in this area. Through iterative optimization, a distributed power supply node optimization strategy that adapts to abnormal states is constructed, and the constructed distributed power supply node optimization strategy is applied to the actual power supply system, the system operation status is monitored, the effect of the optimization strategy is observed, and the optimization strategy is continuously improved according to the feedback information. For the abnormal state that still exists, the positioning and targeted optimization are continued until the entire power supply system is stable, and a dynamic adaptive power supply node optimization control mechanism is established to improve the stability of the power supply system.

[0034] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Obtain a power supply equipment distribution map; Step S12: performing device identification on the power supply device distribution map to mark the power supply device nodes; Step S13: performing spatial layout distribution analysis on power supply equipment nodes to obtain power supply node layout distribution data; Step S14: performing line topology connection analysis on the power supply equipment distribution diagram to obtain a node topology line structure diagram; Step S15: Perform distributed topology reconstruction on the node topology line structure diagram based on the power supply node layout distribution data to construct a power supply node topology network.

[0035] In this embodiment, the geographical location distribution information of the power supply equipment in the study area is obtained, and the spatial coordinate data of the power supply equipment is obtained by using GPS positioning, remote sensing imaging and other technologies. The obtained spatial distribution data of the power supply equipment is organized into an electronic power supply equipment distribution map, and the equipment in the power supply equipment distribution map is automatically identified. Different types of power supply equipment such as substations, line towers, switches, etc. are identified and marked on the distribution map, and a corresponding relationship between the type and number of power supply equipment is established to form the marking information of the equipment node. The spatial coordinate data on the power supply equipment distribution map is used to analyze the spatial layout distribution characteristics of each power supply equipment node, calculate the distance, direction and other indicators between the nodes, analyze the degree of aggregation and dispersion of the nodes, and obtain The spatial layout distribution data of the power supply nodes provides a basis for the subsequent topology reconstruction. Combined with the power supply equipment distribution map and equipment identification information, the line connection relationship between the power supply equipment nodes is analyzed, the topological connection between key nodes such as substations and line towers is determined, and a node topology line structure diagram is formed. A line connection relationship database between power supply equipment nodes is established. The power supply node layout distribution data and node topology line structure diagram obtained above are used to reconstruct the distributed topology network. Considering the node spatial position, connection relationship and other characteristics, the node topology structure is optimized and adjusted, and a power supply node topology network model is constructed. This model takes into account the actual spatial layout of the power supply equipment and can better reflect the topological characteristics of the power supply system.

[0036] In this embodiment, the specific steps of step S14 are: Calculate the node position of the power supply equipment distribution map based on the power supply equipment node, so as to obtain the power supply node position coordinates; Perform redundant position difference positioning analysis based on the power supply node position coordinates to obtain the inter-node positioning correlation data; Based on the inter-node positioning association data, the line topology connection analysis of the power supply equipment nodes is performed to generate the node topology line; Calculate the minimum hopping frequency between nodes of the power supply equipment to obtain the minimum hopping frequency value; Calculate the topological adjacency distance of the node topological lines to obtain the topological distance data between nodes; Based on the minimum frequency hopping value and the topological distance data between nodes, the topological logic path of the power supply equipment distribution diagram is optimized to generate a node topology line structure diagram.

[0037] In this embodiment, the obtained power supply equipment distribution map is used to identify the location coordinate information of each power supply equipment node, and the measurement, GIS and other methods are used to determine the specific position of each power supply equipment node in the plane coordinate system. The spatial position coordinate data of each node is used to calculate the relative position difference between any two nodes, and the position difference data between these nodes are analyzed to identify the node combination with positioning association, and obtain the positioning association data between the nodes, which reflects the topological connection relationship between the nodes. The obtained positioning association data between the nodes is applied to the power supply equipment distribution map, and the line connection between the power supply equipment nodes is determined according to the positioning association relationship, and the topological line connection relationship between the power supply equipment nodes is constructed to form a node topology line. Based on the constructed node Topological line, calculate the shortest connection path between any two nodes, count the number of nodes passed by each shortest path, as the minimum hopping frequency value between nodes, get the minimum hopping frequency data between each node, reflecting the topological distance between nodes, use the node position coordinate data to calculate the actual spatial distance between any two adjacent nodes on the node topological line, get the topological adjacency distance data between each adjacent node pair, describe the actual distance relationship between nodes, comprehensively consider the minimum hopping frequency value and actual topological distance between nodes, optimize and reconstruct the node topology on the power supply equipment distribution map, find the optimal logical connection path that meets the minimum hopping frequency and minimum topological distance, and generate a node topological line structure diagram, which better reflects the actual topological connection relationship between power supply equipment nodes.

[0038] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; Step S22: performing segmented low-pass filtering on the real-time monitoring data of the power supply equipment to obtain noise-reduced power supply monitoring data; Step S23: performing fine-grained division of the time window for the real-time monitoring data of the power supply equipment to obtain multiple time windows; Step S24: performing multi-layer time-frequency local decomposition on the noise reduction power supply monitoring data based on multiple time windows to obtain a multi-time-frequency frequency domain; Step S25: performing multi-scale frequency domain distribution analysis on the multi-time-frequency frequency domain to obtain multi-scale time-frequency frequency domain distribution data; Step S26: integrating the main frequency components of each scale on the multi-scale time-frequency frequency domain distribution data to construct a multi-time period frequency spectrum feature diagram.

[0039] In this embodiment, optical fiber communication sensor nodes are deployed at key positions of the power supply equipment to collect operating parameter data of the power supply equipment in real time. The real-time monitoring data of the power supply equipment collected by each sensor node is aggregated to the central control system through the optical fiber communication network to obtain a real-time monitoring data sequence of key operating indicators such as voltage, current, and power factor of the power supply equipment. The acquired real-time monitoring data sequence of the power supply equipment is divided into multiple short time periods. The monitoring data sequence in each time period is filtered by a low-pass filter. The high-frequency noise components in the monitoring data are effectively removed by segmented low-pass filtering to obtain smoother noise-reduced power supply monitoring data. The entire monitoring data time series is divided into multiple overlapping time windows, and the length of each time window is 10 seconds, 1 minute, or other suitable granularity. In this way, the operating status data fragments of the power supply equipment in multiple time windows are obtained, and the noise-reduced power supply monitoring data in each time window are obtained. The data sequence is measured, and time-frequency domain analysis is performed using methods such as wavelet transform or short-time Fourier transform. Through multi-level time-frequency local decomposition, the characteristic information of the operating status of the power supply equipment in different time scales and frequency ranges is obtained, and the time-frequency characteristics of multiple time windows are integrated to construct a multi-time-frequency frequency domain representation of the power supply equipment operation. For the constructed multi-time-frequency frequency domain data, the energy distribution characteristics of different frequency ranges in each time window are further analyzed. From macro to micro, multiple time-frequency scales are used to analyze and quantify the frequency domain distribution, and the time-frequency frequency domain distribution data describing the frequency domain characteristics of multiple time periods and multiple frequency bands of the power supply equipment operation are obtained. According to the obtained multi-scale time-frequency frequency domain distribution data, the main frequency component is extracted and integrated for each time window, and a visual map reflecting the main spectrum characteristics of the operating status of the power supply equipment in different time periods is constructed. The spectrum characteristic map can be used to analyze the changing law of the frequency domain characteristics of the power supply equipment under different working conditions.

[0040] In this embodiment, reference Figure 4 The above is a schematic flow chart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: extracting the time-series voltage from the real-time monitoring data of the power supply equipment to obtain the time-series voltage sequence of the power supply equipment; Step S32: identifying the voltage fluctuation trend of the power supply equipment time series voltage sequence and generating voltage fluctuation trend data; Step S33: identifying low-frequency bandwidth fluctuations on the multi-period spectrum characteristic graph based on the voltage fluctuation trend data, thereby obtaining multi-period spectrum bandwidth fluctuation data; Step S34: Analyze the spectrum distribution morphology changes of the spectrum bandwidth fluctuation data in multiple time periods to generate spectrum morphology change data in multiple time periods.

[0041] In this embodiment, time series data of voltage indicators are extracted from the real-time monitoring data of the power supply equipment. This time series voltage sequence reflects the voltage change of the power supply equipment during the monitoring time, which lays the foundation for the subsequent voltage fluctuation analysis. The extracted time series voltage data is subjected to sliding average, polynomial fitting and other methods to identify the overall fluctuation trend of the voltage, and generate a voltage fluctuation trend data sequence describing the voltage fluctuation characteristics (such as rising, falling, stable, etc.). This voltage fluctuation trend data provides a reference for the subsequent spectrum bandwidth fluctuation analysis, analyzes the low-frequency bandwidth changes of the spectrum characteristics in different time periods, identifies the changes of the spectrum bandwidth with voltage fluctuations, generates a data sequence describing the changes of the spectrum bandwidth in multiple time periods with voltage fluctuations, observes the morphological changes of the spectrum distribution in different time periods, including the number, amplitude, frequency position, etc. of the spectrum peaks, and combines these spectrum morphological change characteristics to generate a data sequence describing the spectrum change law of the power supply equipment. These spectrum morphological change data provide an important basis for power supply equipment status monitoring and fault diagnosis.

[0042] In this embodiment, step S4 includes the following steps: Step S41: performing time series change trajectory analysis on the spectrum morphology change data of multiple time periods to obtain the spectrum morphology change trajectory; Step S42: performing spectrum amplitude trend evolution on the spectrum morphology change trajectory to generate spectrum change amplitude trend data; Step S43: performing abnormal trend analysis on the spectrum variation amplitude trend data to obtain voltage spectrum abnormal trend data; Step S44: Based on the voltage spectrum abnormal trend data, abnormal frequency bands are identified on the multi-period spectrum characteristic diagram to extract abnormal voltage spectrum bands.

[0043] In this embodiment, based on the spectrum morphology change data of multiple time periods, they are integrated and analyzed in time series, the changing trend of the spectrum morphology is observed, and the changing trajectory of the spectrum morphology in the time domain is extracted. This spectrum morphology change trajectory reflects the evolution law of the spectrum characteristics of the power supply equipment over time. On the basis of the spectrum morphology change trajectory, the changing trend of the spectrum amplitude over time is further analyzed, including indicators such as the change of the spectrum peak amplitude and the change of the total power amplitude, to generate a trend data sequence describing the evolution law of the spectrum amplitude. Based on the spectrum change amplitude trend data, a comparative analysis is performed with the spectrum change law during normal operation to identify the abnormal trend of the spectrum amplitude change and extract it into an abnormal trend data sequence. This abnormal trend data reflects the abnormal changes in the spectrum characteristics of the power supply equipment. For the voltage spectrum abnormal trend data, the frequency bands with abnormal changes in the spectrum characteristics are identified, and these abnormal spectrum bands are extracted to provide a basis for subsequent equipment status diagnosis and fault analysis.

[0044] In this embodiment, step S5 includes the following steps: Step S51: locating the abnormal area of ​​the power supply node topology network based on the abnormal voltage spectrum band to obtain the abnormal area topology network; Step S52: dynamically rendering and reconstructing the abnormal area topology network using the voltage fluctuation trend data to construct a dynamic rendering model for the abnormal area; Step S53: performing a multi-frequency voltage excitation simulation on the abnormal region dynamic rendering model to obtain abnormal region voltage excitation response data.

[0045] In this embodiment, based on the abnormal voltage spectrum band information combined with the topological network model of the power supply system, by analyzing the distribution of abnormal spectrum bands in the power supply network, the areas causing these abnormal spectra are located, and the topological network information of power supply nodes in these abnormal areas is extracted to form a topological network model of the abnormal area. In combination with the abnormal trend data of the voltage spectrum, the voltage fluctuation characteristics of the abnormal area are analyzed, and these voltage fluctuation trend information are mapped to the topological network model of the abnormal area to achieve dynamic rendering and visual display of the abnormal area network, and construct a dynamic rendering model of the abnormal area. Based on the abnormal area dynamic rendering model constructed in the steps, voltage excitation signals of multiple frequency bands are used, and through simulation, the response characteristics of the abnormal area under voltage excitation in different frequency bands are observed, and the voltage excitation response data of these abnormal areas are extracted to provide a basis for subsequent fault diagnosis.

[0046] In this embodiment, step S6 includes the following steps: Step S61: performing abnormal response analysis on the abnormal region voltage excitation response data to obtain abnormal voltage response data; Step S62: locating the abnormal state of the abnormal region dynamic rendering model based on the abnormal voltage response data to obtain an abnormal state node; Step S63: Perform fault attribution analysis on the abnormal state node to obtain the fault factor of the abnormal state node; Step S64: Adaptively fine-tune the operating parameters of the power supply node topology network based on the abnormal state node failure factors, and construct a distributed power supply node optimization strategy.

[0047] In this embodiment, based on the voltage excitation response data of the abnormal area, the response with abnormal characteristics is analyzed in detail. By comparing the voltage response characteristics of the normal area, the abnormal part of the voltage response in the abnormal area is identified, and the abnormal voltage response data are extracted to provide a basis for subsequent fault location. The response characteristics of each node in the dynamic rendering model are analyzed, the abnormal state nodes are identified, and the information of these abnormal state nodes is extracted to provide input for the subsequent fault attribution analysis. For the located abnormal state nodes, combined with the topological structure and operating characteristics of the power supply system, the root causes of the abnormal state of these nodes, such as equipment failure, load change, etc., are analyzed, and the fault attribution information of these abnormal state nodes is extracted as a basis for the subsequent optimization strategy formulation. The obtained abnormal state node fault factor information is fed back to the topological network model of the power supply system. For different fault factors, the operating parameters of the power supply nodes are optimized and adjusted in an adaptive manner, and a set of distributed power supply node optimization strategies are constructed to deal with abnormal conditions in the power supply system. This adaptive optimization strategy based on the root cause of the fault is helpful to improve the stability and reliability of the power supply system.

[0048] In this embodiment, a distributed power supply status monitoring system based on optical fiber communication sensing is provided, which is used to execute the distributed power supply status monitoring method based on optical fiber communication sensing as described above, including: A topology network module is used to obtain a power supply equipment distribution map; perform spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; perform distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; The time-frequency local module is used to obtain the real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; the real-time monitoring data of the power supply equipment is finely divided into time windows to obtain multiple time windows; the real-time monitoring data of the power supply equipment is decomposed into multiple layers of time and frequency based on multiple time windows to construct a multi-time spectrum feature diagram; The spectrum morphology module is used to extract the time-series voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; analyze the spectrum distribution morphology changes of the multi-period spectrum characteristic diagram based on the time-series voltage sequence of the power supply equipment, and generate multi-period spectrum morphology change data; The abnormal trend module is used to perform spectrum amplitude trend evolution on spectrum morphology change data in multiple time periods to generate spectrum change amplitude trend data; perform abnormal trend analysis on spectrum change amplitude trend data to extract abnormal voltage spectrum bands; The voltage excitation response module is used to dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and build a dynamic rendering model for the abnormal area; based on the dynamic rendering model for the abnormal area, the voltage excitation response data of the abnormal area is obtained; The adaptive fine-tuning module is used to locate the abnormal state of the voltage excitation response data in the abnormal area and obtain the abnormal state nodes; based on the abnormal state nodes, the power supply node topology network is adaptively fine-tuned to construct a distributed power supply node optimization strategy.

[0049] The present invention provides basic data for subsequent distributed power supply status monitoring by acquiring a power supply equipment distribution map. The power supply equipment distribution map reflects the topological connection relationship between various devices in the power supply system, including the layout of power supply nodes, the connection method of lines, etc. The real-time monitoring data of the power supply equipment is acquired by using optical fiber communication sensor nodes, and the real-time monitoring data is divided into time windows and multi-layer time-frequency local decomposition is performed to obtain the spectrum characteristic maps of the power supply equipment in different time periods. These characteristic maps reflect the spectrum distribution of the power supply equipment in different frequency bands, which is helpful for subsequent spectrum morphology analysis and abnormal trend analysis. The time series voltage sequence is extracted based on the real-time monitoring data of the power supply equipment, and the spectrum distribution morphology change analysis is performed on the multi-time period spectrum characteristic map, so that the spectrum morphology change data of the power supply equipment in different time periods is obtained, revealing the time-varying nature of the spectrum characteristics of the power supply equipment. Through the spectrum amplitude trend evolution and abnormal trend analysis, the abnormal voltage spectrum of the power supply equipment is extracted. Frequency bands are used to further locate abnormal states, and spectrum amplitude trend evolution analysis is performed on spectrum morphology change data in multiple time periods to obtain spectrum change amplitude trend data of power supply equipment. Through abnormal trend analysis, abnormal voltage spectrum bands are extracted to identify frequency bands where power supply equipment has abnormalities. Abnormal voltage spectrum bands are used to dynamically render and reconstruct the power supply node topology network, and a dynamic rendering model of abnormal areas is constructed. This model reflects the location and range of abnormal areas in the power supply node topology network, and provides voltage excitation response data of abnormal areas for subsequent abnormal state positioning and optimization strategy construction. The abnormal state node positioning results are used to adaptively fine-tune the operating parameters of the power supply node topology network. According to the location and characteristics of the abnormal state nodes, the layout and operating parameters of the power supply nodes are adjusted to optimize the performance of the power supply system. By fine-tuning the location and parameters of the power supply nodes, the power supply quality of the power supply system is improved, energy consumption is reduced, and the reliability and efficiency of the power grid are improved.

[0050] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0051] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A distributed power supply status monitoring method based on optical fiber communication sensing, characterized in that: The following steps are involved: Step S1: Obtain a power supply equipment distribution map; perform spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; Distributed topology reconstruction is performed based on the power supply node layout distribution data to build a power supply node topology network; Step S2: Acquire real-time monitoring data of power supply equipment based on optical fiber communication sensor nodes; The real-time monitoring data of the power supply equipment is divided into time windows in fine granularity to obtain multiple time windows; based on multiple time windows, the real-time monitoring data of the power supply equipment is decomposed into multiple layers of time and frequency locally to construct a multi-period spectrum feature diagram; Step S3: extracting the timing voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; Based on the time-series voltage sequence of the power supply equipment, the spectrum distribution morphology change analysis is performed on the multi-period spectrum characteristic diagram to generate multi-period spectrum morphology change data; Step S4: performing spectrum amplitude trend evolution on the spectrum morphology change data of multiple time periods to generate spectrum change amplitude trend data; performing abnormal trend analysis on the spectrum change amplitude trend data to extract abnormal voltage spectrum bands; Step S5: dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and construct a dynamic rendering model of the abnormal area; and obtain voltage excitation response data of the abnormal area based on the dynamic rendering model of the abnormal area; Step S6: locating the abnormal state of the voltage excitation response data in the abnormal area to obtain the abnormal state node; Based on abnormal status nodes, the power supply node topology network is adaptively adjusted to adjust the operating parameters and build a distributed power supply node optimization strategy.

2. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: Obtain a power supply equipment distribution map; Step S12: performing device identification on the power supply device distribution map to mark the power supply device nodes; Step S13: performing spatial layout distribution analysis on power supply equipment nodes to obtain power supply node layout distribution data; Step S14: performing line topology connection analysis on the power supply equipment distribution diagram to obtain a node topology line structure diagram; Step S15: Perform distributed topology reconstruction on the node topology line structure diagram based on the power supply node layout distribution data to construct a power supply node topology network.

3. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 2 is characterized in that: The specific steps of step S14 are: Calculate the node position of the power supply equipment distribution map based on the power supply equipment node, so as to obtain the power supply node position coordinates; Perform redundant position difference positioning analysis based on the power supply node position coordinates to obtain the inter-node positioning correlation data; Based on the inter-node positioning association data, the line topology connection analysis of the power supply equipment nodes is performed to generate the node topology line; Calculate the minimum hopping frequency between nodes of the power supply equipment to obtain the minimum hopping frequency value; Calculate the topological adjacency distance of the node topological lines to obtain the topological distance data between nodes; Based on the minimum frequency hopping value and the topological distance data between nodes, the topological logic path of the power supply equipment distribution diagram is optimized to generate a node topology line structure diagram.

4. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: acquiring real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; Step S22: performing segmented low-pass filtering on the real-time monitoring data of the power supply equipment to obtain noise-reduced power supply monitoring data; Step S23: performing fine-grained division of the time window for the real-time monitoring data of the power supply equipment to obtain multiple time windows; Step S24: performing multi-layer time-frequency local decomposition on the noise reduction power supply monitoring data based on multiple time windows to obtain a multi-time-frequency frequency domain; Step S25: performing multi-scale frequency domain distribution analysis on the multi-time-frequency frequency domain to obtain multi-scale time-frequency frequency domain distribution data; Step S26: integrating the main frequency components of each scale on the multi-scale time-frequency frequency domain distribution data to construct a multi-time period frequency spectrum feature diagram.

5. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: extracting the time-series voltage from the real-time monitoring data of the power supply equipment to obtain the time-series voltage sequence of the power supply equipment; Step S32: identifying the voltage fluctuation trend of the power supply equipment time series voltage sequence and generating voltage fluctuation trend data; Step S33: identifying low-frequency bandwidth fluctuations on the multi-period spectrum characteristic graph based on the voltage fluctuation trend data, thereby obtaining multi-period spectrum bandwidth fluctuation data; Step S34: Analyze the spectrum distribution morphology changes of the spectrum bandwidth fluctuation data in multiple time periods to generate spectrum morphology change data in multiple time periods.

6. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: performing time series change trajectory analysis on the spectrum morphology change data of multiple time periods to obtain the spectrum morphology change trajectory; Step S42: performing spectrum amplitude trend evolution on the spectrum morphology change trajectory to generate spectrum change amplitude trend data; Step S43: performing abnormal trend analysis on the spectrum variation amplitude trend data to obtain voltage spectrum abnormal trend data; Step S44: Based on the voltage spectrum abnormal trend data, abnormal frequency bands are identified on the multi-period spectrum characteristic diagram to extract abnormal voltage spectrum bands.

7. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: locating the abnormal area of ​​the power supply node topology network based on the abnormal voltage spectrum band to obtain the abnormal area topology network; Step S52: dynamically rendering and reconstructing the abnormal area topology network using the voltage fluctuation trend data to construct a dynamic rendering model for the abnormal area; Step S53: performing a multi-frequency voltage excitation simulation on the abnormal region dynamic rendering model to obtain abnormal region voltage excitation response data.

8. The distributed power supply status monitoring method based on optical fiber communication sensing according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: performing abnormal response analysis on the abnormal region voltage excitation response data to obtain abnormal voltage response data; Step S62: locating the abnormal state of the abnormal region dynamic rendering model based on the abnormal voltage response data to obtain an abnormal state node; Step S63: Perform fault attribution analysis on the abnormal state node to obtain the fault factor of the abnormal state node; Step S64: Adaptively fine-tune the operating parameters of the power supply node topology network based on the abnormal state node failure factors, and construct a distributed power supply node optimization strategy.

9. A distributed power supply status monitoring system based on optical fiber communication sensing, characterized in that: The method for monitoring the state of distributed power supply based on optical fiber communication sensing as claimed in claim 1 comprises: A topology network module is used to obtain a power supply equipment distribution map; perform spatial layout distribution analysis on the power supply equipment distribution map to obtain power supply node layout distribution data; perform distributed topology reconstruction based on the power supply node layout distribution data to construct a power supply node topology network; The time-frequency local module is used to obtain the real-time monitoring data of the power supply equipment based on the optical fiber communication sensor node; the real-time monitoring data of the power supply equipment is finely divided into time windows to obtain multiple time windows; the real-time monitoring data of the power supply equipment is decomposed into multiple layers of time and frequency based on multiple time windows to construct a multi-time spectrum feature diagram; The spectrum morphology module is used to extract the time-series voltage sequence of the power supply equipment based on the real-time monitoring data of the power supply equipment; analyze the spectrum distribution morphology changes of the multi-period spectrum characteristic diagram based on the time-series voltage sequence of the power supply equipment, and generate multi-period spectrum morphology change data; The abnormal trend module is used to perform spectrum amplitude trend evolution on spectrum morphology change data in multiple time periods to generate spectrum change amplitude trend data; perform abnormal trend analysis on spectrum change amplitude trend data to extract abnormal voltage spectrum bands; The voltage excitation response module is used to dynamically render and reconstruct the power supply node topology network based on the abnormal voltage spectrum band, and build a dynamic rendering model for the abnormal area; based on the dynamic rendering model for the abnormal area, the voltage excitation response data of the abnormal area is obtained; The adaptive fine-tuning module is used to locate the abnormal state of the voltage excitation response data in the abnormal area and obtain the abnormal state nodes; based on the abnormal state nodes, the power supply node topology network is adaptively fine-tuned to construct a distributed power supply node optimization strategy.

Images