A bus duct trend analysis early warning method, system and storage medium

Abstract

The present invention discloses a bus duct trend analysis and early warning method, system and storage medium, and relates to the field of data processing technology. The method includes: determining N key positions of the bus duct, respectively arranging sensor groups at the N key positions of the bus duct, and obtaining a sensor monitoring network; collecting and acquiring N temperature time series data and N current time series data; performing temperature difference calculation and current change rate calculation on the N temperature time series data, and obtaining the temperature change rate of N key positions and the current change rate of N key positions; performing integrated trend analysis to determine the abnormal operation trend results of the bus duct; constructing an alarm mechanism, triggering the alarm mechanism based on the abnormal operation trend results of the bus duct to perform classification matching, determine the operation early warning parameters, and perform operation early warning control on the target bus duct. The technical problems of inaccurate monitoring of the operation status of the bus duct and untimely early warning in the prior art are solved, and the technical effect of improving the accuracy and timeliness of bus duct operation monitoring is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a bus duct trend analysis and early warning method, system and storage medium. Background Art

[0002] In modern power systems, bus ducts, as important power distribution facilities, undertake the key function of transmitting electricity. However, with the continuous increase of power load and the complexity of the operating environment, bus ducts are prone to overload, excessive temperature rise, poor contact and other faults during long-term operation. These problems may affect the stability and safety of the power system. Therefore, real-time monitoring of the operating status of the bus duct, timely detection of abnormalities and early warning have become the key to ensuring the safety of the power system. However, existing bus duct monitoring technologies mostly rely on manual inspections or use a single sensor for data collection. The monitoring results often lack real-time and accuracy, and cannot fully reflect the operating status of the bus duct. Summary of the invention

[0003] The present application provides a bus duct trend analysis and early warning method, system and storage medium, which solve the technical problems of inaccurate bus duct operation status monitoring and untimely early warning in the prior art.

[0004] In view of the above problems, the present application provides a bus duct trend analysis and early warning method, system and storage medium.

[0005] A first aspect of the present application provides a bus duct trend analysis and early warning method, the method comprising:

[0006] A key position analysis is performed on the target bus duct to determine N key positions of the bus duct, and sensor groups are respectively arranged at the N key positions of the bus duct to obtain a sensor monitoring network; N temperature time series data and N current time series data are collected and acquired through the sensor monitoring network, and the N temperature time series data and the N current time series data are cached and indexed; a sliding window mechanism is used to perform temperature difference calculation and current change rate calculation on the N temperature time series data to obtain N key position temperature change rates and N key position current change rates; an integrated trend analysis is performed on the N key position temperature change rates and the N key position current change rates to determine the abnormal operation trend results of the bus duct; an alarm mechanism is constructed, and the alarm mechanism is triggered based on the abnormal operation trend results of the bus duct to perform classification matching, determine operation warning parameters, and perform operation warning control on the target bus duct through the operation warning parameters.

[0007] A second aspect of the present application provides a bus duct trend analysis and early warning system, the system comprising:

[0008] Position analysis module: perform key position analysis on the target bus duct, determine N key positions of the bus duct, and respectively arrange sensor groups at the N key positions of the bus duct to obtain a sensor monitoring network; data acquisition module: collect and obtain N temperature time series data and N current time series data through the sensor monitoring network, and cache index the N temperature time series data and N current time series data; calculation module: use a sliding window mechanism to perform temperature difference calculation and current change rate calculation on the N temperature time series data to obtain N key position temperature change rates and N key position current change rates; integrated trend analysis module: perform integrated trend analysis on the N key position temperature change rates and N key position current change rates to determine the abnormal operation trend results of the bus duct; early warning control module: construct an alarm mechanism, trigger the alarm mechanism based on the abnormal operation trend results of the bus duct to perform classification matching, determine the operation early warning parameters, and perform operation early warning control on the target bus duct through the operation early warning parameters.

[0009] The third aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a bus duct trend analysis and early warning method provided in the present application.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] First, the key positions of the target bus duct are analyzed to determine N key positions of the bus duct, and sensor groups are arranged at the key positions of the N bus ducts to obtain a sensor monitoring network. Then, N temperature time series data and N current time series data are collected and acquired through the sensor monitoring network, and the N temperature time series data and N current time series data are cached and indexed. Then, the sliding window mechanism is used to calculate the temperature difference and current change rate of the N temperature time series data to obtain the temperature change rate of N key positions and the current change rate of N key positions. Further, the temperature change rate of N key positions and the current change rate of N key positions are integrated trend analysis to determine the abnormal operation trend results of the bus duct. Finally, an alarm mechanism is constructed, and the alarm mechanism is triggered based on the abnormal operation trend results of the bus duct for classification matching, and the operation warning parameters are determined, and the operation warning parameters are used to control the operation warning of the target bus duct. The technical problems of inaccurate bus duct operation status monitoring and untimely warning in the prior art are solved, and the technical effect of improving the accuracy and timeliness of bus duct operation monitoring is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a bus duct trend analysis and early warning method flow chart provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a bus duct trend analysis and early warning system provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: location analysis module 11 , data acquisition module 12 , calculation module 13 , integrated trend analysis module 14 , early warning control module 15 . DETAILED DESCRIPTION

[0016] The present application solves the technical problems of inaccurate bus duct operation status monitoring and untimely warning in the prior art by providing a bus duct trend analysis and early warning method, system and storage medium.

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0018] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0019] Embodiment 1, as Figure 1 As shown, the present application provides a bus duct trend analysis and early warning method, wherein the method comprises:

[0020] A key position analysis is performed on the target bus duct to determine N key positions of the bus duct, and sensor groups are respectively arranged at the N key positions of the bus duct to obtain a sensor monitoring network.

[0021] By comprehensively considering the bus duct design, operating environment, load distribution and other factors, N key locations that have a greater impact on operational safety and stability are identified. Sensor groups, including temperature, current and other sensors, are deployed at these N key locations of the bus duct to monitor the operating status of each location in real time. These sensors are connected through wired or wireless networks to form a complete sensor monitoring network that can continuously collect and transmit monitoring data. The establishment of the sensor monitoring network provides data support for subsequent trend analysis, anomaly detection and early warning mechanisms to ensure the safe and stable operation of the bus duct.

[0022] In terms of sensor network design, the present invention innovatively proposes a multi-level intelligent sensing system. The system not only includes traditional temperature and current sensors, but also introduces acoustic emission sensors and vibration sensors to form a multi-dimensional perception network. Acoustic emission sensors can capture tiny mechanical fluctuations inside the bus duct, which are often important indicators of early failures. Vibration sensors can monitor the mechanical stability of the bus duct and promptly detect potential problems such as looseness and deformation. This multi-dimensional perception greatly enhances the system's early warning capability.

[0023] Exemplary, specific implementation plan of multi-dimensional sensor network: adopt "multi-sensor coordination" layout at key positions of bus duct. For each monitoring point, configure the following sensor combination: the temperature sensor adopts PT100 platinum resistance, arranged on the surface of bus duct shell and joints to ensure the accuracy of temperature data; the current sensor adopts open Hall sensor, which can be detached and installed for easy maintenance; the acoustic emission sensor is installed on the shell surface at the joint to capture the sound wave signal generated by internal discharge and mechanical looseness; the vibration sensor is fixed at the bus duct bracket to monitor the mechanical vibration state during operation.

[0024] Furthermore, the determining of the N key positions of the bus ducts includes:

[0025] The structural design information of the target bus duct is obtained, and spatial modeling is performed based on the structural design information to generate a three-dimensional model of the bus duct; the three-dimensional model of the bus duct is divided by finite element according to a preset grid size to obtain a finite element grid model of the bus duct, and an initial operating structure position set is preset according to the finite element grid model of the bus duct; an impact simulation analysis is performed on the initial operating structure position set based on the finite element grid model of the bus duct to obtain an initial position operation impact parameter set; key positions of the initial operating structure position set are screened based on the initial position operation impact parameter set to determine the N key positions of the bus duct.

[0026] Specifically, the structural design information of the target bus duct is obtained from the design documents, drawings or databases, including size, material, connection method, conductor layout, etc.; computer-aided design (CAD) or 3D modeling software is used to generate a 3D bus duct model based on the structural design information. The 3D bus duct model provides an accurate geometric basis for subsequent monitoring and analysis, so that subsequent calculations and simulation analyses can be performed on the real structure; the 3D bus duct model is subjected to finite element division according to the preset grid size, that is, the continuum is divided into a finite number of interconnected but non-overlapping units, that is, the entire 3D bus duct model is divided into multiple small units, and a finite element grid model of the bus duct is obtained. The finite element grid model of the bus duct can more accurately analyze the stress and thermal deformation of each part; on the basis of the finite element grid model of the bus duct, the initial operating structure positions are preset, and these positions are based on the bus duct. Based on the design characteristics and operation requirements, areas that may need to be monitored are preliminarily selected, such as parts with large current density and significant temperature fluctuations. Based on the finite element mesh model of the bus duct and the preset initial operation structure position set, computer simulation software is used to perform impact simulation analysis on each position, including simulating the temperature distribution, current density distribution, electromagnetic field distribution, etc. of the bus duct under different operating conditions. The initial position operation influence parameter set of each position can be obtained through the simulation results. According to the initial position operation influence parameter set, a screening algorithm (for example, based on threshold screening, weighted scoring, etc.) is used to screen the key positions of the initial operation structure position set, and finally N key bus duct positions are determined. These key positions will be used as key focus areas in subsequent monitoring, and real-time data collection is carried out by deploying sensors so that abnormalities in these key positions can be discovered in time and early warning control can be carried out.

[0027] Optionally, digital twin technology is introduced when constructing the three-dimensional model of the bus duct, realizing the real-time mapping between the physical world and the digital world. By establishing a high-precision digital model, the system can reflect the operating status of the bus duct in real time. More importantly, the model has the ability to self-learn, and can continuously optimize its own parameters based on actual operating data to improve the accuracy of the model. Specifically, a geometric model of the bus duct is constructed using 3D modeling software to accurately depict its size and shape. Subsequently, actual material parameters and physical properties such as conductivity, thermal conductivity, and strength are imported to ensure that the model can accurately reflect the actual performance of the bus duct. Next, mathematical models of electrical, thermal, and mechanical properties are established, taking into account factors such as current distribution, temperature changes, and mechanical stress to fully simulate the operating status of the bus duct. These models can not only describe the relationship between various physical properties, but also perform real-time calculations during operation and dynamically update physical quantities, thereby monitoring the status of the bus duct in real time and supporting fault warning and optimization control. Through this digital modeling approach, the system can more accurately predict the behavior of the bus duct and improve its safety and efficiency.

[0028] In order to continuously optimize the digital model, the accuracy and reliability of the model are first evaluated by collecting actual operating data and comparing it with the model's predicted results. Then, the model parameters are automatically adjusted using machine learning algorithms to continuously improve the model's predictive ability and adaptability based on the latest data. In addition, model verification and calibration are performed regularly to ensure that the model always conforms to actual operating conditions and avoid deviations caused by changes in environmental or operating conditions. Finally, a model update mechanism is established to update and adjust the model regularly or as needed to ensure that it maintains efficient and accurate performance over a long period of time. These optimization measures help ensure the accuracy and practicality of the digital model throughout its life cycle, thereby improving the operating efficiency and safety of the busbar system.

[0029] Optionally, in the identification of key locations, a multi-physics field coupling analysis method is used, which takes into account the interaction of thermal, electric and stress fields at the same time, and can more accurately identify potential failure points. By analyzing the coupling effects of these physical fields, the system can predict the performance of equipment under various complex working conditions.

[0030] The sensor monitoring network is used to collect and acquire N temperature time series data and N current time series data, and the N temperature time series data and the N current time series data are cached and indexed.

[0031] Through the deployed sensor monitoring network, real-time temperature and current data of N key locations are collected. For each key location, the sensor will regularly collect temperature and current values ​​within a specific time interval to form N temperature time series data and N current time series data.

[0032] In order to ensure effective storage and fast access to data, these N temperature time series data and N current time series data will be stored in the cache. The cache can not only temporarily save a large amount of sensor data, but also improve the data access speed and avoid processing delays caused by excessive data volume. In order to optimize data access and subsequent analysis, the N temperature time series data and N current time series data will be cached and indexed, and managed using data structures such as hash tables and tree structures; this cache index makes subsequent data query, update, and deletion operations more efficient. For example, the system can quickly locate the temperature and current data at a certain moment based on timestamps or other key parameters.

[0033] In terms of data collection and processing, the present invention designs an innovative edge computing architecture. By deploying edge computing units on site, data preprocessing and preliminary analysis are achieved. This distributed processing solution not only reduces the burden of data transmission, but also achieves a millisecond-level response speed. At the same time, an adaptive sampling strategy is adopted, and the system can dynamically adjust the sampling frequency according to the operating status of the equipment, optimizing system resource utilization while ensuring the monitoring effect.

[0034] In the data preprocessing stage, the collected raw data is first processed, including data cleaning, standardization, compression and verification. The data cleaning process aims to remove outliers and noise to ensure the purity and reliability of the data. Next, data standardization is performed to unify the format of data from different sensors for subsequent analysis and processing. Data compression is used to reduce the burden of storage and transmission and ensure that data can be efficiently transmitted and stored. In the data verification stage, the system will check the validity of the data to ensure that the collected data is accurate, complete, and consistent with the actual operation.

[0035] In the feature extraction stage, meaningful features are extracted from the processed data, which are divided into time domain features, frequency domain features, time-frequency features and combined features. Time domain features include statistical features such as mean, variance, peak value, etc., which are used to describe the basic distribution and volatility of data. Frequency domain features are obtained through Fourier transform, which can reveal the distribution of data in frequency and help analyze periodic changes. Time-frequency features use wavelet transform to analyze the common characteristics of data in time domain and frequency domain, providing more detailed analysis of time changes and frequency characteristics. Finally, combined features are analyzed by integrating multiple features to capture more complex patterns and relationships in the data. Through this series of feature extraction methods, the system can extract valuable information from the raw data and provide a solid foundation for subsequent analysis, prediction and decision-making.

[0036] Optionally, the data acquisition network architecture adopts a three-layer network architecture, including a field layer, a convergence layer, and a management layer. The field layer uses an RS485 bus to connect various sensors to form a local data acquisition network; the convergence layer uses an industrial Ethernet switch to aggregate data from multiple field networks; the management layer is connected to the monitoring center via a fiber optic network to achieve remote data transmission.

[0037] Optionally, an edge computing unit is configured in each monitoring area. The hardware configuration of the edge computing unit includes an industrial-grade computer (responsible for data processing and temporary storage), a field programmable controller (performs real-time data acquisition and control), and a local storage device (for data caching and backup). The software system of the edge computing unit includes a data acquisition unit (responsible for real-time acquisition and preprocessing of sensor data), a data analysis unit (performs preliminary data analysis and anomaly detection), a communication unit (responsible for data exchange with the upper system), and a local storage unit (manages local storage and backup of data).

[0038] A sliding window mechanism is used to calculate the temperature difference and the current change rate of the N temperature time series data to obtain the temperature change rates of N key positions and the current change rates of N key positions.

[0039] A sliding window is a fixed-size data set that slides on time series data, moving one data point or a fixed number of data points each time. For each key position of temperature time series data and current time series data, a fixed-length time window is defined, which slides with the passage of time. Each time it moves, the data in the window is updated. Usually, the window length can be adjusted according to actual needs, such as sliding once every 10 seconds, with a window size of 60 seconds. In each sliding window, the temperature difference and current change rate of the data in the window are calculated, and then the temperature change rates of N key positions and the current change rates of N key positions are obtained.

[0040] Further, obtaining the temperature change rates of N key positions and the current change rates of N key positions includes:

[0041] A target sliding window is defined according to a sliding window mechanism, wherein the target sliding window includes a window size and a sliding step size; the target sliding window is used to perform temperature difference calculation on the N temperature time series data to obtain the temperature change rates of the N key positions; the target sliding window is used to perform current change rate calculation on the N temperature time series data to obtain the current change rates of the N initial positions; a data filtering mechanism is established, and data denoising is performed on the current change rates of the N initial positions based on the data filtering mechanism to obtain the current change rates of the N key positions.

[0042] Specifically, the size and sliding step of the target sliding window are defined according to actual needs. The window size determines the amount of data analyzed each time (i.e., the number of time points included in each window), while the sliding step defines the time interval for each forward sliding of the window. The target sliding window can be set according to the operating characteristics of the bus duct. For example, the window size can be 10 minutes and the sliding step can be 1 minute. After the sliding window is defined, the temperature time series data of each key position will be traversed and calculated. In each sliding window, the temperature difference at the beginning and end of the window will be calculated, and the temperature difference reflects the degree of temperature change in the window. By traversing all the temperature time series data, the temperature change rates of N key positions can be obtained, that is, the magnitude of temperature change over time. Similarly, the current time series data is traversed and calculated using a sliding window, and the current change rate in each window is calculated. By traversing the sliding window of the current time series data, the current change rates of N initial positions can be obtained.

[0043] This paper proposes an innovative adaptive data analysis framework. The framework adopts a dynamic sliding window mechanism, and the window size is automatically adjusted according to the data characteristics, which ensures the real-time and accuracy of the analysis. In terms of data processing, the time series decomposition technology is introduced to decompose the monitoring data into trend items, period items and random items, so as to have a deeper understanding of the law of data change.

[0044] In addition, in order to improve data quality, the present invention designs a multi-level data purification scheme. This scheme combines traditional filtering technology and modern machine learning algorithms, which can effectively identify and process abnormal data and ensure the reliability of subsequent analysis. In particular, when dealing with sudden interference, the system can respond quickly to maintain the continuity and reliability of data.

[0045] After calculating the current change rates of N initial positions, the data may fluctuate or be inaccurate due to factors such as sensor noise and external interference. In order to improve the accuracy and reliability of the data, it is necessary to establish a data filtering mechanism to remove these interference factors; the data filtering mechanism includes moving average filtering, median filtering, Kalman filtering, etc.; the data filtering mechanism is used to perform data denoising on the N initial position current change rates obtained by the preliminary calculation to obtain the current change rates of N key positions. The filtered current change rates of N key positions can more accurately reflect the real current changes in the operating state of the bus duct, further improving the accuracy of subsequent trend analysis and early warning.

[0046] Furthermore, obtaining the current change rates at N initial positions includes:

[0047] Construct the three-phase current root mean square calculation formula: ; Wherein, ia, ib, ic represent the A-phase current, B-phase current and C-phase current in the three-phase current respectively; the target sliding window is used to calculate the current root mean square value of the N temperature time series data in turn based on the three-phase current root mean square calculation formula to obtain N key position time series RMS values; the N key position time series RMS values ​​are calculated according to the time series information. The change rate is calculated to obtain the current change rate of the N initial positions.

[0048] The root mean square value of the three-phase current is an important measure of current change. It can reflect the amplitude and size of current fluctuations. The root mean square value (RMS) of the three-phase current can be expressed as: ; Among them, ia, ib, ic represent the A phase current, B phase current and C phase current in the three-phase current respectively.

[0049] After constructing the three-phase current root mean square calculation formula, the target sliding window is used to traverse and calculate the current time series data of each key position; for the three-phase current data in each sliding window, the three-phase current root mean square value (RMS) in the window is calculated according to the above formula; each time the sliding window moves, the calculated RMS value is updated to obtain the RMS time series data of each key position in different time periods, that is, N key position time series RMS values ​​are obtained, which represent the current fluctuations of each key position of the bus duct at different time points; by calculating the change rate of the obtained N key position time series RMS values, the current change rate of N initial positions is obtained.

[0050] An integrated trend analysis is performed on the temperature change rates of the N key positions and the current change rates of the N key positions to determine the abnormal operation trend results of the bus duct.

[0051] The temperature change rate and current change rate of each key position are integrated and analyzed, that is, the changes in multiple key positions are summarized to form an overall trend analysis; through the trend analysis of these data, it can be determined whether the bus duct has an abnormal operating trend, such as excessive temperature or excessive current fluctuations, and the abnormal operating trend results of the bus duct can be obtained.

[0052] Furthermore, the determination of the abnormal operation trend of the bus duct includes:

[0053] Acquire a historical bus duct operation data set, wherein the bus duct historical operation data set includes temperature change rate data, current change rate data and corresponding operation status data of multiple bus duct positions; perform shunt identification and trend prediction training on the bus duct historical operation data set according to the bus duct position, and generate multiple bus duct position abnormal trend prediction networks; evaluate the degree of abnormal impact of each bus duct position among the multiple bus duct positions, and obtain multiple bus duct position abnormal impact factors; integrate and fuse the multiple bus duct position abnormal trend prediction networks based on the multiple bus duct position abnormal impact factors, and obtain a bus duct abnormal trend prediction network; use the bus duct abnormal trend prediction network to perform abnormal trend analysis on the temperature change rates of the N key positions and the current change rates of the N key positions, and determine the abnormal operation trend result of the bus duct.

[0054] Specifically, the bus duct historical operation data set is collected and acquired. The bus duct historical operation data set provides a comprehensive record of the temperature, current fluctuations and state changes of the bus duct under different operating conditions, and provides a comprehensive reference basis for the operation mode and potential abnormalities of the bus duct. The bus duct historical operation data set includes temperature change rate data, current change rate data and corresponding operation status data of multiple bus duct positions; the bus duct historical operation data set is shunt-marked according to the bus duct position, and trend prediction training is performed on the data at different positions respectively. By using machine learning or deep learning methods, multiple bus duct position abnormal trend prediction networks are generated. These networks can predict the future abnormal trend of each key position based on historical data; the abnormal impact degree of each position is evaluated, and the abnormal impact factors of multiple positions are obtained by evaluating the impact of the fault at each position on the overall system.

[0055] The abnormal impact degree of multiple bus duct positions is evaluated. The abnormal impact degree of each bus duct position depends on the impact of the fault at that position on the entire system. By evaluating the impact of temperature and current changes on system stability, multiple bus duct position abnormal impact factors can be obtained; based on multiple bus duct position abnormal impact factors, multiple bus duct position abnormal trend prediction networks are integrated and fused, and weighted average is used to ensure that the prediction results of each position are weighted according to its impact factor to generate a unified bus duct abnormal trend prediction network. The integrated bus duct abnormal trend prediction network is used to analyze the abnormal trend of the temperature change rate of N key positions and the current change rate of N key positions. The bus duct abnormal trend prediction network will perform real-time processing based on these input data to predict whether these key positions will have abnormal temperature rise, current fluctuations and other problems, and then output the abnormal operation trend results of the bus duct.

[0056] Furthermore, the generating of multiple bus duct position abnormal trend prediction networks includes:

[0057] The bus duct historical operation data set is shunt-marked according to the multiple bus duct positions to obtain multiple bus duct position operation data sets; the multiple bus duct position operation data sets are trained for abnormality labeling according to the bus duct application safety standards to obtain multiple bus duct position abnormality data sets and multiple bus duct position abnormality identifiers; the multiple bus duct position abnormality data sets are trained for operation trend prediction respectively to obtain multiple bus duct position trend predictors; the multiple bus duct position abnormality identifiers and the multiple bus duct position trend predictors are combined in series to generate the multiple bus duct position abnormality trend prediction networks.

[0058] Specifically, the collected historical operation data sets of the bus duct are shunted and marked according to different bus duct positions. The data of each bus duct position includes information such as its temperature change rate and current change rate. These data are divided into multiple sub-data sets (i.e., bus duct position operation data sets) according to the position. Each sub-data set represents a specific bus duct position, ensuring that the data of each position can independently and accurately reflect the operation status of the position; according to the bus duct application safety standards, each bus duct position operation data set is trained for abnormal labeling, and the standard for abnormal labeling can be set according to factors such as the design safety specifications of the equipment, the operating load standards, and historical fault records; by labeling the known abnormal conditions in the historical data, the system can identify which data belongs to the normal range and which is abnormal; through this training process, multiple bus duct position abnormal data sets and corresponding bus duct position abnormality identifiers are generated. These identifiers will be able to identify abnormal conditions of the bus duct in subsequent real-time monitoring. For each bus duct position abnormality data set, operation trend prediction training will be conducted. By using time series prediction models or regression analysis and other methods, the model is trained using the annotated abnormal data set, so that it can predict the future operation trend of the bus duct based on historical data; after the data set of each position is trained, the corresponding bus duct position trend predictor is generated. These predictors can predict the temperature and current change trends of the location and detect whether abnormal fluctuations will occur. Multiple bus duct position abnormality identifiers are combined in series with multiple bus duct position trend predictors to construct a global bus duct position abnormality trend prediction network. The bus duct position abnormality trend prediction network can achieve real-time and comprehensive monitoring and prediction, ensure the safety and stability of the bus duct under different operating conditions, and discover potential fault hazards in advance.

[0059] Optionally, an innovative deep learning framework is used for trend forecasting. This framework combines multiple advanced neural network structures and can process both time series data and spatial features. By introducing an attention mechanism, the system can automatically identify important data features and improve forecast accuracy. In particular, the model shows excellent performance when dealing with long-term trends.

[0060] Exemplarily, a prediction model is constructed using a deep learning framework, which specifically includes multiple levels of design. The data preprocessing layer is responsible for standardizing the raw data and extracting necessary features to provide clean and structured data for subsequent analysis. Next, the feature learning layer uses a convolutional neural network (CNN) to extract spatial features to help the model capture local patterns and structures in the data. The sequence analysis layer uses a long short-term memory network (LSTM) to specifically process time series features to capture time dependencies and dynamic changes in the data. Finally, the prediction output layer generates the final prediction results based on the previous feature learning and sequence analysis to provide a basis for subsequent decision-making. In the model training phase, historical operating data and fault cases need to be collected first, which provide rich input and target output for model training. Then, the system will construct a training data set and a validation data set to ensure the representativeness and diversity of the data to improve the generalization ability of the model. On this basis, a reasonable training strategy and parameter optimization scheme are designed to ensure the efficiency and effectiveness of the training process. Finally, model training and validation are performed, and model parameters are adjusted so that it can achieve good performance on historical data and validation data, ensuring that the model has strong prediction capabilities and practical application value.

[0061] Optionally, the present invention also innovatively constructs a dynamic fault pattern library, which not only contains static expert knowledge, but can also be continuously expanded and optimized through online learning. The system analyzes historical fault cases, extracts key features, and forms a fault feature fingerprint library, providing a reliable reference basis for abnormality identification.

[0062] An alarm mechanism is constructed, and based on the abnormal operation trend result of the bus duct, the alarm mechanism is triggered to perform classification matching, determine operation warning parameters, and perform operation warning control on the target bus duct through the operation warning parameters.

[0063] By analyzing the abnormal operation trend results of the bus duct, determine which key indicators (such as temperature change rate, current fluctuation, etc.) are abnormal, or whether there is a continuous abnormal trend; once the system detects an abnormal trend, it will trigger the alarm mechanism, which will perform classification matching according to the preset threshold or classification rules. The classification matching can be matched according to different types of abnormal trends (such as temperature abnormalities, current fluctuation abnormalities, etc.), and the abnormalities are divided into different categories according to the matching results, such as "high-risk faults", "medium-risk faults" and "low-risk faults". Each category corresponds to different abnormal characteristics. For example, if the temperature change rate continues to increase and the current fluctuates violently, the system will judge it as a high-risk fault; each category corresponds to different operation warning parameters, which include threshold settings for key indicators such as temperature and current.

[0064] Based on the operation warning parameters, the system will take corresponding warning control measures. The operation warning parameters usually include thresholds of multiple key indicators such as temperature, current, and load. These thresholds are set according to the normal operating range of the equipment, historical fault data, and safety standards. When a parameter is detected to be close to or exceeds the preset threshold, the system will start the warning control and take appropriate countermeasures. For example, the system can alleviate abnormal conditions by adjusting the load, starting backup equipment, or reducing the operating speed to prevent further damage to the equipment. Through this alarm mechanism, the system can respond and control in a timely manner when the bus duct shows abnormal operating trends, reduce the possibility of failures, and ensure the safe and stable operation of the bus duct.

[0065] Furthermore, the determining of the operation warning parameters includes:

[0066] According to the alarm mechanism, the alarm type matching logic is obtained; based on the alarm type matching logic, the abnormal operation trend results of the bus duct are classified and matched to obtain the alarm signal type; according to the alarm signal type, the alarm mode level is determined; based on the alarm signal type and the alarm mode level, the operation warning parameters are determined.

[0067] Specifically, the alarm type matching logic is obtained according to the pre-set alarm mechanism. The alarm type matching logic defines how to classify according to different abnormal data (such as temperature changes, current fluctuations, etc.). For example, the system will determine the corresponding alarm type according to different types of abnormal data such as temperature exceeding a certain threshold, current sudden change, load overload, etc.; after obtaining the alarm type matching logic, the abnormal operation trend results of the bus duct will be classified and matched based on the alarm type matching logic. Through the matching logic, the system will classify abnormal data such as temperature change rate and current change rate at each key position, and generate corresponding alarm signal types. For example, if the temperature continues to rise and the current also has abnormal fluctuations, the system may identify an "overload risk" alarm signal; if the temperature slightly exceeds the standard but there is no obvious current change, it may be a "temperature abnormality" alarm signal. After determining the type of alarm signal, the system further determines the alarm mode level according to the type of alarm signal. The alarm mode level is usually set based on the severity and urgency of the alarm. For example, a serious fault warning (such as the risk of short circuit caused by overheating) may be set as a "high" level alarm, while some smaller fluctuations may be set as a "low" or "medium" level alarm. Based on the alarm signal type and the alarm mode level, the operation warning parameters are comprehensively determined. The operation warning parameters usually include specific operating thresholds, alarm triggering conditions, and subsequent control strategies. For example, for a "high" level alarm signal, the system may set a lower temperature threshold and trigger an emergency shutdown procedure; for a "medium" level alarm, the system may only adjust the load, reduce the current, etc.

[0068] The alarm mechanism is based on the abnormal operation trend of the bus duct, combined with the change trend of temperature and load, to determine whether an alarm signal needs to be issued. Exemplarily, the alarm mechanism includes two types: yellow alarm and red alarm; yellow alarm: when the temperature change rate of the equipment exceeds the threshold, but the change rate of the current load is small (that is, the load has not changed significantly), the system will issue a yellow alarm; the purpose of the yellow alarm is to prompt that the equipment may be in an abnormal state and requires the attention of the operation and maintenance personnel, but no emergency measures are required for the time being. The yellow alarm is not only triggered based on a single change, but also tracks the number of consecutive temperature changes through a counter. If the load of the equipment has not changed significantly for a long time, but shows a continuous temperature increase trend (such as multiple consecutive temperature increases), the system will issue a yellow alarm.

[0069] Red alarm: When both the temperature change rate and the load change rate exceed the set thresholds, or the number of yellow alarms of the device exceeds a certain threshold (for example, 7 consecutive temperature rises), the system will trigger a red alarm. A red alarm indicates that the device is in a serious abnormal state and may be at risk of failure, and immediate measures must be taken to deal with it. In addition to changes in temperature and load, the red alarm is also combined with the device's historical alarm records. For example, if a device triggers a yellow alarm multiple times in a short period of time, the system will automatically upgrade its alarm level to a red alarm. This design ensures that the system can not only identify short-term failure risks, but also discover long-term hidden dangers of the equipment.

[0070] In terms of early warning mechanism, the present invention proposes an intelligent multi-level early warning system. The system can automatically adjust the warning level according to the severity of the abnormality and formulate corresponding response strategies. The system also has an intelligent push function, which can select the most suitable notification method according to the user role and abnormality type.

[0071] Exemplarily, in the design of the early warning mechanism, a four-level early warning system is established. The first-level early warning is a prompt early warning, which is mainly used for daily monitoring to remind operators to pay attention to changes in the operating status of the equipment. It usually does not need to be dealt with immediately. The second-level early warning is a concern early warning, indicating that the equipment has some abnormal operating trends and needs to be paid special attention to prevent the problem from further deteriorating. The third-level early warning is a warning early warning. When the operating status of the equipment deviates from the normal range, it needs to be handled in time to avoid potential failures. The fourth-level early warning is an emergency early warning. When the operating status of the equipment is seriously abnormal and may cause failures or safety accidents, it needs to be handled immediately to ensure that the system safety is quickly restored.

[0072] Corresponding response plans have been formulated for different levels of warnings. For the first-level warning, the system will automatically notify the relevant responsible person to remind him to pay attention to the equipment status and monitor it well; for the second-level warning, in addition to automatic notification, the system also requires relevant personnel to strengthen monitoring and initiate the emergency handling process when necessary. In the case of a third-level warning, in addition to notifying the responsible person, the system will automatically initiate the emergency handling process and require immediate troubleshooting and repair. For a fourth-level warning, the system will immediately initiate the emergency response mechanism and automatically execute the handling measures to ensure that the normal operation of the equipment is restored in time. During the processing, the system will record the warning information and processing process in detail to ensure that all measures are tracked in time. Finally, all warning events will form a detailed warning report and analysis summary for subsequent reference and improvement. Through this four-level warning mechanism and response plan, it can ensure that the busbar equipment is handled promptly and effectively when an abnormality occurs, avoid fault expansion and system shutdown, and ensure the safe and stable operation of the power system.

[0073] Optionally, in terms of daily maintenance, develop a system maintenance plan to ensure the stable operation of the system. Check the status of sensors regularly to confirm whether they are working properly and replace or calibrate them in time to ensure the accuracy and reliability of data collection. Update system software and databases regularly to keep the latest version of the system to improve performance and security. Important data and configuration information should be backed up regularly to prevent data loss or enable quick recovery in the event of a system crash. Also check the network communication status regularly to ensure smooth communication between the system and various devices and sensors to avoid network failures affecting monitoring and control.

[0074] Optionally, in terms of fault handling, establish a fault handling mechanism to ensure that faults can be responded to quickly and effectively when they occur. First, develop a detailed fault emergency plan to clarify the emergency measures and response process when a fault occurs to reduce the impact of the fault on the system. Establish a standardized fault handling process to ensure that each fault can be handled quickly and effectively according to the prescribed steps to avoid delays in processing time due to human factors. In the process of handling faults, record detailed fault information and handling process to provide a basis for subsequent fault analysis. Finally, summarize the lessons learned from each fault, continuously improve the system and handling process to prevent similar problems from happening again, and improve the reliability and stability of the system. Through these maintenance and fault handling measures, the long-term stable operation of the system can be ensured and the impact of faults on production can be reduced.

[0075] Further, including:

[0076] When there are multiple bus duct devices, a multi-threaded processing mechanism is used to perform parallel trend analysis and parallel abnormality warning on the multiple bus duct devices.

[0077] When there are multiple bus duct devices, in order to improve data processing efficiency and early warning response speed, the system uses a multi-threaded processing mechanism to perform trend parallel analysis and abnormal parallel early warning on multiple bus duct devices. In this process, the system assigns an independent thread to each bus duct device, which is responsible for the trend analysis of the device's temperature change rate, current change rate and other time series data. Through the multi-threaded mechanism, the data analysis tasks of multiple devices can be carried out in parallel, which greatly improves the system's processing capacity and real-time performance. After each device completes the trend analysis, the system will immediately perform an abnormal detection on its operating status. If it is found that the temperature or current change of the device exceeds the set threshold, or the trend prediction shows that there is a risk of failure, the system will quickly trigger the parallel early warning mechanism. At the same time, the system ensures reasonable task allocation between threads through effective resource management and load balancing, avoids excessive resource consumption or task delays, and ensures efficient operation in the case of multiple devices. Through this multi-threaded parallel processing, the system can promptly identify and respond to abnormal conditions of each bus duct device, effectively ensuring the safety of the equipment and the stability of the power system.

[0078] In terms of parallel processing, the present invention designs an innovative distributed computing framework. The framework can automatically balance the computing load and ensure the optimal use of system resources. By introducing a fault-tolerant mechanism, the system can still maintain normal operation even if some nodes fail, greatly improving the reliability of the system.

[0079] In summary, the embodiments of the present application have at least the following technical effects:

[0080] First, the key positions of the target bus duct are analyzed to determine N key positions of the bus duct, and sensor groups are arranged at the key positions of the N bus ducts to obtain a sensor monitoring network. Then, N temperature time series data and N current time series data are collected and acquired through the sensor monitoring network, and the N temperature time series data and N current time series data are cached and indexed. Then, the sliding window mechanism is used to calculate the temperature difference and current change rate of the N temperature time series data to obtain the temperature change rate of N key positions and the current change rate of N key positions. Further, the temperature change rate of N key positions and the current change rate of N key positions are integrated trend analysis to determine the abnormal operation trend results of the bus duct. Finally, an alarm mechanism is constructed, and the alarm mechanism is triggered based on the abnormal operation trend results of the bus duct for classification matching, and the operation warning parameters are determined, and the operation warning parameters are used to control the operation warning of the target bus duct. The technical problems of inaccurate bus duct operation status monitoring and untimely warning in the prior art are solved, and the technical effect of improving the accuracy and timeliness of bus duct operation monitoring is achieved.

[0081] Embodiment 2, based on the same inventive concept as a bus duct trend analysis and early warning method in the above embodiment, Figure 2As shown, the present application provides a bus duct trend analysis and early warning system, wherein the system includes:

[0082] Position analysis module 11: perform key position analysis on the target bus duct, determine N key positions of the bus duct, and respectively arrange sensor groups at the N key positions of the bus duct to obtain a sensor monitoring network; data acquisition module 12: acquire N temperature time series data and N current time series data through the sensor monitoring network, and cache index the N temperature time series data and N current time series data; calculation module 13: use a sliding window mechanism to perform temperature difference calculation and current change rate calculation on the N temperature time series data to obtain N key position temperature change rates and N key position current change rates; integrated trend analysis module 14: perform integrated trend analysis on the N key position temperature change rates and N key position current change rates to determine the abnormal operation trend results of the bus duct; early warning control module 15: construct an alarm mechanism, trigger the alarm mechanism based on the abnormal operation trend results of the bus duct to perform classification matching, determine the operation early warning parameters, and perform operation early warning control on the target bus duct through the operation early warning parameters.

[0083] Furthermore, the location analysis module 11 is used to perform the following method:

[0084] The structural design information of the target bus duct is obtained, and spatial modeling is performed based on the structural design information to generate a three-dimensional model of the bus duct; the three-dimensional model of the bus duct is divided by finite element according to a preset grid size to obtain a finite element grid model of the bus duct, and an initial operating structure position set is preset according to the finite element grid model of the bus duct; an impact simulation analysis is performed on the initial operating structure position set based on the finite element grid model of the bus duct to obtain an initial position operation impact parameter set; key positions of the initial operating structure position set are screened based on the initial position operation impact parameter set to determine the N key positions of the bus duct.

[0085] Furthermore, the calculation module 13 is used to execute the following method:

[0086] A target sliding window is defined according to a sliding window mechanism, wherein the target sliding window includes a window size and a sliding step size; the target sliding window is used to perform temperature difference calculation on the N temperature time series data to obtain the temperature change rates of the N key positions; the target sliding window is used to perform current change rate calculation on the N temperature time series data to obtain the current change rates of the N initial positions; a data filtering mechanism is established, and data denoising is performed on the current change rates of the N initial positions based on the data filtering mechanism to obtain the current change rates of the N key positions.

[0087] Furthermore, the calculation module 13 is used to execute the following method:

[0088] Construct the three-phase current root mean square calculation formula:

[0089] ; Wherein, ia, ib, ic represent the A-phase current, B-phase current and C-phase current in the three-phase current respectively; the target sliding window is used to calculate the current root mean square value of the N temperature time series data in turn based on the three-phase current root mean square calculation formula to obtain N key position time series RMS values; the N key position time series RMS values ​​are calculated according to the time series information. The change rate is calculated to obtain the current change rate of the N initial positions.

[0090] Furthermore, the integrated trend analysis module 14 is used to perform the following method:

[0091] Acquire a historical bus duct operation data set, wherein the bus duct historical operation data set includes temperature change rate data, current change rate data and corresponding operation status data of multiple bus duct positions; perform shunt identification and trend prediction training on the bus duct historical operation data set according to the bus duct position, and generate multiple bus duct position abnormal trend prediction networks; evaluate the degree of abnormal impact of each bus duct position among the multiple bus duct positions, and obtain multiple bus duct position abnormal impact factors; integrate and fuse the multiple bus duct position abnormal trend prediction networks based on the multiple bus duct position abnormal impact factors, and obtain a bus duct abnormal trend prediction network; use the bus duct abnormal trend prediction network to perform abnormal trend analysis on the temperature change rates of the N key positions and the current change rates of the N key positions, and determine the abnormal operation trend result of the bus duct.

[0092] Furthermore, the integrated trend analysis module 14 is used to perform the following method:

[0093] The bus duct historical operation data set is shunt-marked according to the multiple bus duct positions to obtain multiple bus duct position operation data sets; the multiple bus duct position operation data sets are trained for abnormality labeling according to the bus duct application safety standards to obtain multiple bus duct position abnormality data sets and multiple bus duct position abnormality identifiers; the multiple bus duct position abnormality data sets are trained for operation trend prediction respectively to obtain multiple bus duct position trend predictors; the multiple bus duct position abnormality identifiers and the multiple bus duct position trend predictors are combined in series to generate the multiple bus duct position abnormality trend prediction networks.

[0094] Furthermore, the early warning control module 15 is used to execute the following method:

[0095] According to the alarm mechanism, the alarm type matching logic is obtained; based on the alarm type matching logic, the abnormal operation trend results of the bus duct are classified and matched to obtain the alarm signal type; according to the alarm signal type, the alarm mode level is determined; based on the alarm signal type and the alarm mode level, the operation warning parameters are determined.

[0096] Furthermore, the early warning control module 15 is used to execute the following method:

[0097] When there are multiple bus duct devices, a multi-threaded processing mechanism is used to perform parallel trend analysis and parallel abnormality warning on the multiple bus duct devices.

[0098] Embodiment 3, based on the same inventive concept as a bus duct trend analysis and early warning method in the above embodiment, this embodiment provides a computer-readable storage medium, which can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to a bus duct trend analysis and early warning method in the embodiment of the present application. The processor executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory, that is, realizing the above bus duct trend analysis and early warning method.

[0099] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0101] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A bus duct trend analysis and early warning method, characterized in that: The method comprises: Performing a key position analysis on the target bus duct to determine N key positions of the bus duct, and respectively placing sensor groups at the N key positions of the bus duct to obtain a sensor monitoring network; Acquire N temperature time series data and N current time series data through the sensor monitoring network, and cache index the N temperature time series data and the N current time series data; Using a sliding window mechanism to calculate the temperature difference and the current change rate of the N temperature time series data, to obtain the temperature change rates of N key positions and the current change rates of N key positions; Performing an integrated trend analysis on the temperature change rates of the N key positions and the current change rates of the N key positions to determine the abnormal operation trend results of the bus duct; Constructing an alarm mechanism, triggering the alarm mechanism to perform classification matching based on the abnormal operation trend result of the bus duct, determining operation warning parameters, and performing operation warning control on the target bus duct through the operation warning parameters; Obtaining a finite element mesh model of a bus duct, and presetting an initial operating structure position set according to the finite element mesh model of the bus duct; Performing an impact simulation analysis on the initial operation structure position set based on the bus duct finite element mesh model, including simulating the temperature distribution, current density distribution, and electromagnetic field distribution of the bus duct under different operating conditions to obtain an initial position operation impact parameter set; The initial operation structure position set is screened for key positions based on the initial position operation influencing parameter set to determine the N bus duct key positions.

2. A bus duct trend analysis and early warning method according to claim 1, characterized in that: The obtaining of the bus duct finite element mesh model comprises: Acquire structural design information of the target bus duct, perform spatial modeling based on the structural design information, and generate a three-dimensional model of the bus duct; The bus duct three-dimensional model is divided by finite element according to a preset grid size to obtain a bus duct finite element grid model.

3. A bus duct trend analysis and early warning method according to claim 1, characterized in that: The obtaining of the temperature change rates of N key positions and the current change rates of N key positions includes: Defining a target sliding window according to a sliding window mechanism, wherein the target sliding window includes a window size and a sliding step size; Use the target sliding window to perform temperature difference calculation on the N temperature time series data to obtain the temperature change rates of the N key positions; Use the target sliding window to perform current change rate calculation on the N temperature time series data to obtain N initial position current change rates; A data filtering mechanism is established, and data denoising is performed on the current change rates of the N initial positions based on the data filtering mechanism to obtain the current change rates of the N key positions.

4. A bus duct trend analysis and early warning method as claimed in claim 3, characterized in that: The obtaining of N initial position current change rates comprises: Construct the three-phase current root mean square calculation formula: ； Among them, ia, ib, ic represent the A phase current, B phase current and C phase current of the three-phase current respectively; Using the target sliding window and based on the three-phase current root mean square calculation formula, the current root mean square values ​​of the N temperature time series data are calculated in sequence to obtain N key position time series RMS values; The change rates of the N key position timing RMS values ​​are calculated according to the timing information to obtain the current change rates of the N initial positions.

5. A bus duct trend analysis and early warning method according to claim 1, characterized in that: The determining of the abnormal operation trend result of the bus duct includes: Collect and obtain a historical bus duct operation data set, wherein the historical bus duct operation data set includes temperature change rate data, current change rate data and corresponding operation status data at multiple bus duct locations; The bus duct historical operation data set is subjected to shunt identification and trend prediction training according to the bus duct position, and multiple bus duct position abnormal trend prediction networks are generated; Evaluate the degree of abnormal impact of each bus duct position among the multiple bus duct positions to obtain multiple bus duct position abnormal impact factors; Based on the multiple bus duct position abnormality influencing factors, the multiple bus duct position abnormality trend prediction networks are integrated and merged to obtain a bus duct abnormality trend prediction network; The bus duct abnormal trend prediction network is used to perform abnormal trend analysis on the temperature change rates of the N key positions and the current change rates of the N key positions to determine the abnormal operation trend result of the bus duct.

6. A bus duct trend analysis and early warning method as claimed in claim 5, characterized in that: The generating of multiple bus duct position abnormal trend prediction networks comprises: Dividing and marking the bus duct historical operation data set according to the multiple bus duct positions to obtain multiple bus duct position operation data sets; Performing abnormality annotation training on the plurality of bus duct position operation data sets according to the bus duct application safety standard to obtain a plurality of bus duct position abnormality data sets and a plurality of bus duct position abnormality identifiers; Performing operation trend prediction training on the multiple bus duct position abnormality data sets respectively to obtain multiple bus duct position trend predictors; The multiple bus duct position abnormality identifiers and the multiple bus duct position trend predictors are combined in series to generate the multiple bus duct position abnormality trend prediction networks.

7. A bus duct trend analysis and early warning method according to claim 1, characterized in that: The step of determining the operation warning parameters includes: According to the alarm mechanism, obtaining the alarm type matching logic; Classify and match the abnormal operation trend results of the bus duct based on the alarm type matching logic to obtain the alarm signal type; According to the alarm signal type, an alarm mode level is determined, and based on the alarm signal type and the alarm mode level, the operation warning parameter is determined.

8. A bus duct trend analysis and early warning method according to claim 1, characterized in that: The method comprises: When there are multiple bus duct devices, a multi-threaded processing mechanism is used to perform parallel trend analysis and parallel abnormality warning on the multiple bus duct devices.

9. A bus duct trend analysis and early warning system, characterized in that: A bus duct trend analysis and early warning method for implementing any one of claims 1 to 8, the system comprising: Position analysis module: perform key position analysis on the target bus duct, determine N key positions of the bus duct, and respectively arrange sensor groups at the N key positions of the bus duct to obtain a sensor monitoring network; Data acquisition module: acquires N temperature time series data and N current time series data through the sensor monitoring network, and caches and indexes the N temperature time series data and the N current time series data; Calculation module: using a sliding window mechanism to perform temperature difference calculation and current change rate calculation on the N temperature time series data, and obtain temperature change rates of N key positions and current change rates of N key positions; Integrated trend analysis module: performs integrated trend analysis on the temperature change rates of the N key positions and the current change rates of the N key positions to determine the abnormal operation trend results of the bus duct; Early warning control module: construct an alarm mechanism, trigger the alarm mechanism to perform classification matching based on the abnormal operation trend results of the bus duct, determine the operation early warning parameters, and perform operation early warning control on the target bus duct through the operation early warning parameters.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a bus duct trend analysis and early warning method as described in any one of claims 1 to 8 is implemented.

Images