Visualization Device Battery Status Monitoring and Emergency Power Supply Installation Prediction Method and System

Abstract

This invention discloses a method and system for monitoring battery status and predicting emergency power supply installation in a visualization device. The method includes the following steps: S1, acquiring data on battery failures in a visualization device along a power transmission line, and establishing a prediction base dataset based on the battery failure type; S2, constructing battery status monitoring and prediction feature quantities for the visualization device along the power transmission line based on the prediction base dataset, and preprocessing the feature quantities to form a sample set of data on the battery operating environment and internal physical conditions of the visualization device; S3, inputting the sample set into a pre-constructed long short-term memory network model and a fully convolutional neural network model for prediction, obtaining a first predicted value and a second predicted value, and then weighted and fused the first predicted value and the second predicted value to obtain the final failure type prediction result. This invention has advantages such as accurate prediction and reduced battery maintenance costs.

Description

Technical Field

[0001] This invention mainly relates to the field of power transmission line technology, specifically to a method and system for monitoring battery status with a visualization device and predicting the installation of emergency power supplies. Background Technology

[0002] Currently, online monitoring of power transmission line corridors typically utilizes mature bullet or PTZ cameras as visualization devices. These cameras transmit images or real-time video over the network to monitor the environmental conditions of the transmission line corridors, ensuring the safe and stable operation of the transmission lines. However, since most transmission towers are located in mountainous areas, their online visualization devices usually employ a "solar power + battery" power supply model. Therefore, under favorable weather conditions, this power supply model generally meets the requirements for online monitoring, image transmission, and snapshot capture. However, in some areas, some transmission line towers are located in complex "microclimate" regions characterized by high altitudes, valleys, and heavy icing. These areas are prone to prolonged periods of continuous rain and high humidity, which can disrupt the power supply system of the visualization devices, directly affecting their normal operation and posing significant safety hazards to the environmental management of transmission line corridors.

[0003] With the continuous development of battery capacity and charge / discharge strategy control technologies, significant guidance has been provided for battery status detection and assessment in power transmission line channel visualization devices. Currently, traditional battery capacity monitoring focuses on two main approaches: first, the battery production stage, predicting capacity levels by analyzing various state data and battery capacity during production; and second, predicting remaining battery life by acquiring raw charge / discharge data and using multiple charge / discharge state data as training samples. Neither of these methods considers the impact of the actual battery operating environment on its capacity, and single charge / discharge state data only considers the number of charge / discharge cycles, failing to comprehensively consider factors such as battery internal resistance changes, output voltage and current, and operating time.

[0004] Meanwhile, the battery of the power transmission line channel visualization device determines whether the front-facing camera and network communication device can operate normally and effectively. When the visualization device is found to be offline during centralized management, it needs to be maintained in time. According to maintenance data statistics, more than 90% of the failures are due to battery failure, caused by continuous rainy weather, battery bulging or failure, etc., resulting in the equipment not being able to supply power effectively. Traditional maintenance methods usually involve a rough battery replacement or equipment replacement, but this has the following problems:

[0005] One option is to directly replace the battery. However, due to limited space in the equipment, the battery capacity is constrained by the available space. Furthermore, some batteries may still be in relatively good condition and could continue to function normally once the weather improves. Therefore, this method is highly likely to increase battery replacement and maintenance costs.

[0006] Secondly, directly replacing the equipment involves many steps and a long time for the new equipment to go through procurement, grid connection, and debugging, resulting in a significant increase in maintenance costs. Moreover, after a period of continuous rainy and severe weather, the equipment still cannot meet the requirements for online monitoring of the transmission line corridor environment.

[0007] Third, it did not take into account factors such as multiple battery manufacturers, fault types, and the special operating environments of different towers. Instead, it combined battery status monitoring data from the visualization device with weather forecasts to carry out "proactive" maintenance before the visualization device went offline, enabling the visualization device to maintain an orderly online transition under severe weather conditions such as continuous rain, heavy fog, and icing. Summary of the Invention

[0008] To address the technical problems existing in the prior art, this invention provides a visualization device for battery status monitoring and emergency power supply installation prediction, which offers accurate predictions and reduces battery maintenance costs.

[0009] To solve the above-mentioned technical problems, the technical solution proposed by this invention is as follows:

[0010] A method for monitoring battery status and predicting emergency power supply installation using a visual device includes the following steps:

[0011] S1. Obtain data on battery failures in the visualization device for power transmission line channels, and establish a predictive basic dataset based on the battery failure type of the visualization device.

[0012] S2. Based on the prediction base dataset, construct the battery status monitoring and prediction feature quantity of the transmission line channel visualization device, and preprocess the feature quantity to form a sample set of data on the battery operating environment and internal physical conditions of the visualization device.

[0013] S3. Input the sample set into the pre-built long short-term memory network model and the fully convolutional neural network model respectively for prediction to obtain the first predicted value and the second predicted value. Then, the first predicted value and the second predicted value are weighted and fused to obtain the final fault type prediction result.

[0014] Preferably, the method further includes step S4: based on the analysis of the longitudinal prediction of a single device in the time series in steps S2 and S3, the correlation between different devices in the horizontal direction is constructed. Based on the status monitoring and prediction of a single transmission line channel visualization device, the correlation of different fault types of multiple visualization devices is clustered by combining the tower coordinates and five types of micro-region maps to form a mapping between the two micro-region maps and the equipment fault types. The five types include heavy icing area, galloping area, pollution area, lightning area and high altitude area. The two micro-regions are micro-topography and micro-climate.

[0015] Preferably, after step S4, step S5 is further included:

[0016] Based on the fault type and the One-Hot feature vector of the "two-micro-region map", the Jaccard distance D is calculated. jd ;

[0017] For the feature vector constructed in step S2, calculate the correlation coefficient D. coo ;

[0018] The improved K-Means clustering algorithm model distance D is derived from this, i.e.: D = ωD jd +(1-ω)D coo ;

[0019] ω is a coefficient;

[0020] The clustering results are obtained based on the improved K-Means clustering algorithm model. The actual on-site maintenance strategies are compared with the clustering results, and the number of centroids and the ω coefficient are optimized. Cases with large differences or inconsistent types are removed by whitelisting noise, forming a mapping relationship between W clusters and W types of actual on-site maintenance measures.

[0021] Preferably, before step S2, the M×N data matrix formed by a single device in step S1 for M hours is converted into a 1×L feature vector, where L is the number of features.

[0022] Preferably, in step S2, a longitudinal analysis of a single device is performed by grouping it by time. The data at the current fault time is recursively grouped with the data between the time of the last fault and the time of normal online maintenance after the last fault. Feature quantities and data samples are constructed for a single device by time series and fault group data.

[0023] Preferably, the specific process for constructing feature quantities and data samples is as follows:

[0024] By employing methods such as equal division, maximum / minimum values, and mean values ​​to preserve the characteristics of sample data, the state of charge, operating voltage, operating current, operating temperature data, and whether the data is online, collected by the visualization device battery, are discretized and converted.

[0025] Reconstruct features from battery manufacturers and weather data using One-Hot and classification methods.

[0026] The number of charge / discharge cycles, operating hours, number of snapshots, and number of image transmissions are summarized or fixed values ​​are adopted.

[0027] Preferably, principal component analysis (PCA) and normalization methods are used to preprocess the feature matrix to form a training sample set of data on the battery operating environment and internal physical conditions of the visualization device.

[0028] Preferably, corresponding to the visualized battery status type, the status types are set as Class A, Class B, Class C, Class D, and Class E; among which Class A, B, and C correspond to the emergency power supply installation strategy, but distinguish the emergency power supply capacity; Class D is included in the direct battery replacement category; Class E is non-battery fault.

[0029] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, the computer program performing the steps of the method described above when run by a processor.

[0030] The present invention further discloses a visualization device battery status monitoring and emergency power supply installation prediction system, including a memory and a processor connected to each other. The memory stores a computer program, which executes the steps of the method described above when run by the processor.

[0031] Compared with the prior art, the advantages of the present invention are as follows:

[0032] This invention leverages historical maintenance experience with transmission line channel visualization devices to focus on monitoring battery status, which has a high failure rate, and implementing corresponding emergency power supply strategies. Based on a large amount of historical operating data from channel visualization equipment, it reconstructs parameters such as state of charge (SOC), operating voltage, operating current, operating temperature data, and online status, converting them into training samples that combine operating environment and physical quantities. Principal component analysis and normalization are used to reduce the impact of noisy data, and an FCNN model is trained to achieve the monitoring of battery status of the visualization device and the proposal of corresponding strategies.

[0033] This invention fully leverages historical operational data from visualization devices to enable battery status monitoring and prediction, proactively proposing emergency power supply installation strategies. This addresses the issues of inefficient and untargeted maintenance. Furthermore, by predicting and validating subsequent actual equipment operational data, the model is optimized and improved, enhancing prediction accuracy and robustness. Model iteration and optimization simplify battery status monitoring. This reduces battery maintenance costs by maximizing battery lifespan while ensuring effective power supply to equipment. Consequently, the cost of visualized battery maintenance for transmission line channels gradually decreases, making it easy to promote.

[0034] This invention is based on a deep learning algorithm model and takes into account the special operating environment of the channel visualization device on the transmission line tower. It combines different operating environments, battery operation data of different visualization devices and fault types to reconstruct the training sample set, optimize the matching of prediction model and emergency power supply installation strategy, and achieve low-cost and efficient support for the precise operation and maintenance of the transmission line channel visualization device.

[0035] This invention integrates factors affecting the normal power supply of batteries in power transmission line channel visualization devices, including battery manufacturers, state of charge (SOC), operating voltage and current, charge / discharge cycles, operating hours, number of snapshots, number of image transmissions, altitude, and meteorological data. It constructs data fusion training samples for different towers and visualization batteries. Using historical maintenance data, it labels the battery states in the training samples with fault categories. Data preprocessing and deep learning methods are used to monitor and assess the health status of the visualization device batteries. Different maintenance strategies are proposed for different battery states. For batteries still in a relatively good category, it suggests installing a circulating external emergency power supply to support normal power supply under severe weather conditions, differentiating between state and subsequent weather forecasts to provide different emergency power supply capacities. For batteries in the bulging or failed category, it proposes direct replacement or emergency power supply installation based on subsequent weather forecasts, achieving targeted maintenance and avoiding blind, high-cost maintenance. Attached Figure Description

[0036] Figure 1 This is a flowchart of the prediction method of the present invention in an embodiment. Detailed Implementation

[0037] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0038] like Figure 1 As shown, the visualization device for battery status monitoring and emergency power supply installation prediction method provided in this embodiment of the invention includes the following steps:

[0039] S1: Collect maintenance data of transmission line channel visualization devices (such as cameras) due to battery failure; based on the battery failure type of offline visualization devices, establish a predictive basic dataset including battery manufacturer, state of charge (SOC), operating voltage and current, number of charge and discharge cycles, number of operating hours, number of snapshots, fixed snapshot interval, number of image transmissions, online status, altitude, temperature, and weather; through the collection of historical data from the operational channel visualization maintenance equipment, and based on the current operation strategy of the visualization device, record one basic dataset per device per hour, that is, one device for M hours forms an M×N basic dataset matrix, where N is the number of recorded data entries, also known as the number of rows.

[0040] S2: Construct a visualization device for power transmission line channels to monitor and predict battery status features.

[0041] Considering the difference between continuous and discrete quantities, the M×N data matrix formed by a single device in step S1 after M hours needs to be converted into a 1×L feature vector, where L is the number of feature quantities.

[0042] Meanwhile, considering that this invention mainly focuses on the status monitoring of power transmission line corridor visualization devices, with a particular emphasis on the analysis and prediction of battery faults, the following approach is first used: longitudinal analysis of individual devices is performed, grouped by time. This involves recursively grouping data between the current fault time and the time between the last fault and the normal maintenance return time. Feature quantities and data samples are then constructed for each individual device based on the time series and fault grouping data. Specifically:

[0043] First, the characteristics of the sample data are preserved by equal division, maximum and minimum values, and mean values. The state of charge (SOC), operating voltage, operating current, operating temperature data, and whether the data is online are converted and processed according to the data collected by the visualization device battery. See Table 1 for details:

[0044] Table 1 Discretization of Continuous Basic Data Volume

[0045]

[0046] Second, the battery manufacturers and weather data were reconstructed into feature quantities according to the One-Hot and classification methods, as detailed in Table 2.

[0047] Table 2 Battery Manufacturers, Weather Data Feature Processing

[0048]

[0049] Third, for routine quantities such as charge / discharge cycles, operating hours, number of snapshots, and number of image transmissions, summarize them or adopt actual fixed values.

[0050] Furthermore, after the features are discretized and aggregated, the feature matrix becomes sparse and variable. Principal component analysis (PCA) and normalization methods are used to preprocess the feature matrix to form a training sample set of data on the battery operating environment and internal physical conditions of the visualization device.

[0051] Corresponding to the visualized battery status types, the initial status types are set as Class A, Class B, Class C, Class D, and Class E; among them, Class A, B, and C correspond to emergency power supply installation strategies, but distinguish between emergency power supply capacity; Class D is included in the direct battery replacement category; Class E is non-battery fault.

[0052] The training sample matrix X for a single device is formed by constructing the aforementioned feature vectors. ij , where i represents the number of failures per device (number of groups in the basic dataset), and j represents the number of feature vectors constructed from the M×N basic dataset according to grouping and feature values. The corresponding training sample Xij The data feature vector, fault state type label matrix Yi.

[0053] S3: The prediction model based on LSTM-FCNN is constructed for a single device. Considering that the failure of the transmission line channel visualization device is closely related to the device's operating time and the gradual influence of the environment, the Long Short-Term Memory Network (LSTM) model is selected for longitudinal prediction of time series.

[0054] Meanwhile, considering that the training sample set constructed in step S2 contains both quantities related to the strong physical principles of the battery and quantities related to the operating environment that affect the battery's operating state, which is a fusion of logical and relational relationships, a fully convolutional neural network (FCNN) model is simultaneously selected to train and predict the deep learning algorithm for the internal relationships of the data.

[0055] First, the training sample set constructed in step S2 is divided into a training set, a validation set, and a test set in a ratio of 6:2:2. Then, the LSTM-FCNN prediction model is used to predict the battery state type of the visualization device.

[0056] The prediction model was verified and optimized. Considering that FCNN is prone to slow convergence and distortion during training, the cross-entropy loss function was used to optimize and verify the model parameters.

[0057] This paper proposes a method to predict the fault type of a single transmission line channel visualization device by fusing the predictions of the Long Short-Term Memory (LSTM) network model (Ypre1) and the Fully Convolutional Neural Network (FCNN) model (Ypre2). The weighted value Y is then fused for prediction. pre A mapping relationship is established between the interval and the set state types A, B, C, D, and E, enabling the analysis and judgment of the fault type, i.e., the predicted value is: Y. pre =αY pre1i +(1-α)Y pre2i ;

[0058] Furthermore, the model is iteratively optimized using the training sample set to enhance its robustness.

[0059] S4: Feature clustering analysis of five types of faults was constructed using multiple devices. Considering that the basic performance and characteristics of the same type of channel visualization devices from the same manufacturer are not much different, the fault types are quite different due to the special operating environment of transmission line towers. In particular, due to the large differences in the topography and landforms of mountainous areas and transmission line towers, there are five types of "two micro" microclimates, namely heavy icing areas, galloping areas, pollution areas, lightning areas, and high-altitude areas (referred to as the five types). The two micros are micro-topography and microclimate.

[0060] Therefore, based on the longitudinal prediction of a single device in time series in steps S2 and S3, this invention constructs the correlation between different fault types of devices in the horizontal direction. Based on the status monitoring and prediction of a single transmission line channel visualization device, and combined with the tower coordinates and five types of "two micro" area maps, cluster analysis is performed on the correlation of different fault types of multiple visualization devices to form a mapping between the "two micro" area maps and the equipment fault types, providing a method and guidance for precise maintenance of the device in emergency maintenance.

[0061] S5: Multiple devices are used to build an improved K-Means clustering algorithm model based on Jaccard and correlation coefficients.

[0062] Based on step S2, construct a single training sample X. ij and fault state type label matrix Y i Match different types of "two micro" area maps to form training samples X from multiple full-scale devices. rt r represents the number of failures of multiple devices, and t represents X. ij The number of feature vectors constructed by expanding the corresponding regional features on the basic dataset. Among them, the feature vectors of the five fault types and the five "micro" regions are constructed using One-Hot, namely 001, 010, 011, 100, and 101 respectively.

[0063] The initial centroids for K-Means clustering are determined to be W, with W ranging from 3 to 5. These centroids represent the types of emergency power supplies and maintenance strategies to be implemented. The traditional K-Means algorithm's Euclidean distance calculation method is improved by considering the training samples X. rt Since there are differences in preprocessing before and after the construction of sample feature quantities, the Jaccard distance D is calculated for the One-Hot feature vectors of fault types and "two micro-region maps". jd ;

[0064] For the feature vector constructed in step S2, calculate the correlation coefficient D. coo ;

[0065] The improved K-Means clustering algorithm model distance D is derived from this, i.e.: D = ωD jd +(1-ω)D coo .

[0066] The actual on-site maintenance strategies are compared with the clustering results, and the number of centroids and the ω coefficient are optimized. Cases with large differences or inconsistent types are removed by whitelisting noise, forming a mapping relationship between W clusters and W types of overall on-site maintenance measures, supporting the precise implementation of battery operation and maintenance of the transmission line channel visualization device.

[0067] In practical applications, the visualization equipment on the large side of the 220 kV Rongkuang line #086 of the State Grid Chenzhou Power Supply Company was used to monitor and predict battery problems. During the on-site verification process, a bulging failure was found, and the battery was directly replaced and repaired on-site.

[0068] This invention leverages historical maintenance experience with transmission line channel visualization devices to focus on monitoring battery status, which has a high failure rate, and implementing corresponding emergency power supply strategies. Based on a large amount of historical operating data from channel visualization equipment, it reconstructs parameters such as state of charge (SOC), operating voltage, operating current, operating temperature data, and online status, converting them into training samples that combine operating environment and physical quantities. Principal component analysis and normalization are used to reduce the impact of noisy data, and an FCNN model is trained to achieve the monitoring of battery status of the visualization device and the proposal of corresponding strategies.

[0069] This invention fully leverages historical operational data from visualization devices to enable battery status monitoring and prediction, proactively proposing emergency power supply installation strategies. This addresses the issues of inefficient and untargeted maintenance. Furthermore, by predicting and validating subsequent actual equipment operational data, the model is optimized and improved, enhancing prediction accuracy and robustness. Model iteration and optimization simplify battery status monitoring. This reduces battery maintenance costs by maximizing battery lifespan while ensuring effective power supply to equipment. Consequently, the cost of visualized battery maintenance for transmission line channels gradually decreases, making it easy to promote.

[0070] This invention is based on a deep learning algorithm model and takes into account the special operating environment of the channel visualization device on the transmission line tower. It combines different operating environments, battery operation data of different visualization devices and fault types to reconstruct the training sample set, optimize the matching of prediction model and emergency power supply installation strategy, and achieve low-cost and efficient support for the precise operation and maintenance of the transmission line channel visualization device.

[0071] This invention integrates factors affecting the normal power supply of batteries in power transmission line channel visualization devices, including battery manufacturers, state of charge (SOC), operating voltage and current, charge / discharge cycles, operating hours, number of snapshots, number of image transmissions, altitude, and meteorological data. It constructs data fusion training samples for different towers and visualization batteries. Using historical maintenance data, it labels the battery states in the training samples with fault categories. Data preprocessing and deep learning methods are used to monitor and assess the health status of the visualization device batteries. Different maintenance strategies are proposed for different battery states. For batteries still in a relatively good category, it suggests installing a circulating external emergency power supply to support normal power supply under severe weather conditions, differentiating between state and subsequent weather forecasts to provide different emergency power supply capacities. For batteries in the bulging or failed category, it proposes direct replacement or emergency power supply installation based on subsequent weather forecasts, achieving targeted maintenance and avoiding blind, high-cost maintenance.

[0072] The present invention also discloses a computer-readable storage medium storing a computer program thereon, which, when run by a processor, executes the steps of the method described above. Further embodiments of the present invention provide a visual device for battery status monitoring and emergency power supply installation prediction system, including a memory and a processor interconnected thereon, wherein the memory stores a computer program, which, when run by a processor, executes the steps of the method described above.

[0073] The present invention can implement all or part of the processes in the methods of the above embodiments, or it can be implemented by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium includes: any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. The memory is used to store computer programs and / or modules. The processor implements various functions by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may include high-speed random access memory, as well as non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0074] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring battery status and predicting emergency power supply installation using a visual device, characterized in that, Including the following steps: S1. Obtain data on battery failures in the power transmission line channel visualization device, and establish a prediction base dataset based on the battery failure type of the visualization device. S2. Based on the prediction base dataset, construct the battery status monitoring and prediction feature quantity of the transmission line channel visualization device, and preprocess the feature quantity to form a sample set of data on the battery operating environment and internal physical conditions of the visualization device. S3. Input the sample set into the pre-built long short-term memory network model and the fully convolutional neural network model respectively for prediction to obtain the first prediction value and the second prediction value. Then, the first prediction value and the second prediction value are weighted and fused to obtain the final fault type prediction result. It also includes step S4: Based on the analysis of the longitudinal prediction of a single device in the time series in steps S2 and S3, the correlation between different devices in the horizontal direction is constructed. Based on the status monitoring and prediction of a single transmission line channel visualization device, the correlation of different fault types of multiple visualization devices is clustered by combining the tower coordinates and the five types of micro-region maps to form a mapping between the two micro-region maps and the equipment fault types. The five types include heavy icing area, galloping area, pollution area, lightning area and high altitude area; the two micro-regions are micro-topography and micro-climate.

2. The method for monitoring battery status and predicting emergency power supply installation using a visualization device according to claim 1, characterized in that, Following step S4, step S5 is also included: Based on the fault type and the One-Hot feature vectors of the two micro-region maps, the Jaccard distance D is calculated. jd ; For the feature vector constructed in step S2, calculate the correlation coefficient D. coo ; The improved K-Means clustering algorithm model distance D is derived from the combined results, namely: ; ω is a coefficient; The clustering results are obtained based on the improved K-Means clustering algorithm model. The actual on-site maintenance strategies are compared with the clustering results, and the number of centroids and the ω coefficient are optimized. Cases with large differences or inconsistent types are removed by whitelisting noise, forming a mapping relationship between W clusters and W types of actual on-site maintenance measures.

3. The method for monitoring battery status and predicting emergency power supply installation using a visualization device according to claim 1 or 2, characterized in that, Before step S2, the M×N data matrix formed by a single device in step S1 for M hours is converted into a 1×L feature vector, where L is the number of features.

4. The method for monitoring battery status and predicting emergency power supply installation using a visualization device according to claim 3, characterized in that, In step S2, a longitudinal analysis of individual devices is performed by grouping them by time. The data at the current fault time is recursively grouped with the data between the time of the last fault and the time of normal online maintenance after the previous fault. Feature quantities and data samples are constructed for individual devices by time series and fault group data.

5. The method for monitoring battery status and predicting emergency power supply installation using a visualization device according to claim 4, characterized in that, The specific process of constructing feature quantities and data samples is as follows: By employing methods such as equal division, maximum / minimum values, and mean values ​​to preserve the characteristics of sample data, the state of charge, operating voltage, operating current, operating temperature data, and whether the data is online, collected by the visualization device battery, are discretized and converted. Reconstruct features from battery manufacturers and weather data using One-Hot and classification methods. The number of charge / discharge cycles, operating hours, number of snapshots, and number of image transmissions are summarized or fixed values ​​are adopted.

6. The method for monitoring battery status and predicting emergency power supply installation using a visualization device according to claim 4, characterized in that, Principal component analysis (PCA) and normalization methods were used to preprocess the feature matrix to form a training sample set of data on the battery operating environment and internal physical conditions of the visualization device.

7. The method for monitoring battery status and predicting emergency power supply installation using a visualization device according to claim 4, characterized in that, Corresponding to the visualized battery status type, the status types are set as Class A, Class B, Class C, Class D, and Class E; among them, Class A, B, and C correspond to the emergency power supply installation strategy, but distinguish the emergency power supply capacity; Class D is included in the direct battery replacement category; Class E is non-battery fault.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor, it executes the steps of the visualization device battery status monitoring and emergency power supply installation prediction method as described in any one of claims 1-7.

9. A visual device for battery status monitoring and emergency power supply installation prediction system, comprising a memory and a processor interconnected, wherein the memory stores a computer program, characterized in that, When the computer program is run by the processor, it executes the steps of the visualization device battery status monitoring and emergency power supply installation prediction method as described in any one of claims 1-7.

Images