Remote AI monitoring management method and system of energy storage power station

Abstract

The invention relates to the technical field of power station monitoring, and discloses a remote AI monitoring management method and system for an energy storage power station, and the method comprises the steps: carrying out the real-time data collection of a working environment and an operation state of the energy storage power station, arranging the data according to a time sequence, and forming a monitoring data sequence; the pre-trained monitoring evaluation model is used for evaluating the health condition of the energy storage power station for the monitoring data sequence, a health analysis report of the energy storage power station is generated, real-time monitoring of the energy storage power station can be achieved, potential faults can be found in time, the safety and reliability of equipment operation are improved, and meanwhile through data-driven health analysis, the energy storage power station can be effectively protected. The operation and maintenance strategy can be optimized, the requirement for manual inspection is reduced, the maintenance cost is reduced, the overall operation efficiency of the energy storage power station is improved, and the problem that in the prior art, the efficiency of manually monitoring the energy storage power station is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power station monitoring, and in particular to a remote AI monitoring and management method and system for an energy storage power station. Background Art

[0002] Energy storage power stations are an indispensable part of modern power systems. They can effectively balance electricity supply and demand, improve energy efficiency and enhance the stability of the power grid. With the rapid development of renewable energy, the application of energy storage technology has become more and more extensive, and the operating efficiency and safety of energy storage power stations have become the focus of attention in the power industry.

[0003] In the prior art, traditional energy storage power station monitoring methods mainly rely on manual inspections and regular maintenance, which cannot reflect the operating status of the equipment and environmental changes in real time, resulting in late fault discovery, affecting the reliability and economy of the power station. Summary of the invention

[0004] The purpose of the present invention is to provide a remote AI monitoring and management method and system for an energy storage power station, aiming to solve the problem of low efficiency of manual monitoring of energy storage power stations in the prior art.

[0005] The present invention is implemented as follows. In a first aspect, the present invention provides a remote AI monitoring and management method for an energy storage power station, comprising: Collecting data on the working environment and operating status of the energy storage power station to obtain working environment parameters and operating status parameters of the energy storage power station; The obtained working environment parameters and operating status parameters are transmitted to a designated processing platform, so as to sequentially arrange the working environment parameters and operating status parameters of the energy storage power station at each moment according to the time sequence, and obtain a monitoring data sequence of the energy storage power station; The health status of the energy storage power station is analyzed on the monitoring data sequence by using the pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station. In a second aspect, the present invention provides a remote AI monitoring and management method system for an energy storage power station, which is used to implement the remote AI monitoring and management method for an energy storage power station described in any one of the first aspects, including: A data acquisition module is used to collect data on the working environment and operating status of the energy storage power station to obtain working environment parameters and operating status parameters of the energy storage power station; A data integration module, used to transmit the acquired working environment parameters and operating status parameters to a designated processing platform, so as to sequentially arrange the working environment parameters and operating status parameters of the energy storage power station at each moment according to the time sequence, and obtain a monitoring data sequence of the energy storage power station; The data analysis module is used to analyze the health status of the energy storage power station on the monitoring data sequence through a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station.

[0006] The present invention provides a remote AI monitoring and management method for an energy storage power station, which has the following beneficial effects: The present invention collects real-time data on the working environment and operating status of the energy storage power station, arranges the data in chronological order to form a monitoring data sequence, and uses a pre-trained monitoring and evaluation model to evaluate the health status of the energy storage power station on the monitoring data sequence to generate a health analysis report for the energy storage power station. This method can achieve real-time monitoring of the energy storage power station, timely discover potential faults, and improve the safety and reliability of equipment operation. At the same time, through data-driven health analysis, it can optimize operation and maintenance strategies, reduce the need for manual inspections, reduce maintenance costs, and improve the overall operating efficiency of the energy storage power station, solving the problem of low efficiency in manual monitoring of energy storage power stations in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a schematic diagram of the steps of a remote AI monitoring and management method for an energy storage power station provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a remote AI monitoring and management method system for an energy storage power station provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0009] The implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0010] Reference Figure 1 , Figure 2 As shown, a preferred embodiment of the present invention is provided.

[0011] In a first aspect, the present invention provides a remote AI monitoring and management method for an energy storage power station, comprising: S1: Collecting data on the working environment and operating status of the energy storage power station to obtain working environment parameters and operating status parameters of the energy storage power station; S2: transmitting the obtained working environment parameters and the operating status parameters to a designated processing platform, so as to sequentially arrange and process the working environment parameters and the operating status parameters of the energy storage power station at each moment according to the time sequence, and obtain a monitoring data sequence of the energy storage power station; S3: Analyze the health status of the energy storage power station on the monitoring data sequence using a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station.

[0012] Specifically, in step S1 of the embodiment provided by the present invention, a variety of sensors are installed at key locations of the energy storage power station to monitor environmental parameters. These sensors may include: temperature sensors: used to monitor the temperature of batteries and equipment, humidity sensors: used to monitor air humidity to prevent moisture from affecting the equipment.

[0013] More specifically, according to the operating requirements of the energy storage power station, an appropriate data collection frequency (such as every second, every minute, or every hour) is set to ensure that environmental changes can be reflected in real time, and the collected environmental parameters are recorded in real time and stored in local data acquisition devices (such as PLC, edge computing devices) to ensure the integrity and accuracy of the data.

[0014] More specifically, through the intelligent monitoring equipment installed in the energy storage system (such as the BMS battery management system), the operating status parameters are obtained in real time, including: battery voltage: monitoring the voltage status of each battery pack, current: monitoring the current changes during the charging and discharging process, SOC (State of Charge): calculating the battery's charging status and evaluating the remaining power, SOH (State of Health): evaluating the battery's health status, including capacity decay and internal resistance changes.

[0015] More specifically, the operating status parameters are transmitted to the monitoring system in real time through the data bus (such as CAN bus, Modbus, etc.) to ensure that the status information of each device is updated synchronously, and thresholds are set to monitor key operating parameters (such as voltage, temperature, etc.). When they exceed the normal range, the alarm mechanism is triggered to enable timely fault detection and processing.

[0016] More specifically, environmental parameters and operating status parameters are integrated into a unified data platform (such as SCADA system, cloud platform, etc.) to facilitate subsequent data analysis and processing. The integrated data is stored in the form of time series to ensure data integrity and traceability, and to achieve real-time monitoring of the environment and operating status of the energy storage power station. Potential problems can be identified in a timely manner, reducing the possibility of failures. Through high-precision sensors and effective data collection strategies, the accuracy and reliability of the collected data can be ensured, providing a solid foundation for subsequent analysis.

[0017] Specifically, in step S2 of the embodiment provided by the present invention, the collected environmental parameters and operating status parameters are formatted to ensure that the data is transmitted in a unified format (such as JSON, CSV, etc.) to facilitate subsequent processing, and a timestamp is added to each piece of data to ensure that each data point can accurately reflect the time of collection, which is convenient for subsequent chronological sorting and analysis.

[0018] More specifically, according to the requirements of the processing platform, select appropriate communication protocols (such as HTTP, MQTT, WebSocket, etc.) for data transmission to ensure the real-time and reliability of the transmission, establish a network connection between the data acquisition device and the processing platform to ensure that the data can be transmitted smoothly, and write a data sending program to send the formatted data to the designated processing platform through the selected protocol. After receiving the data, the processing platform should send a confirmation message to the data sending device to ensure the success and completeness of the data transmission.

[0019] More specifically, after receiving the data, the processing platform stores it in a database (such as SQL or NoSQL database) for subsequent access and query, sorts the received environmental parameters and operating status parameters according to timestamps to ensure that the monitoring data sequence is arranged in chronological order, cleans the received data, removes duplicate data and outliers, ensures data accuracy and consistency, and integrates the cleaned environmental parameters and operating status parameters into a monitoring data sequence to form complete time series data.

[0020] It is understandable that through efficient data transmission and processing mechanisms, real-time monitoring of the environment and operating status of energy storage power stations can be achieved to ensure the accuracy and timeliness of the data. Through timestamps and sorting mechanisms, the integrity of the monitoring data sequence can be ensured so that each data point is arranged in chronological order to facilitate subsequent analysis. Through the analysis of monitoring data, potential faults and abnormal conditions can be identified in advance, early warning information can be provided, equipment failure rates can be reduced, and safety can be improved.

[0021] Specifically, in step S3 of the embodiment provided by the present invention, the previously acquired and processed monitoring data sequence is imported into the pre-trained energy storage power station monitoring and evaluation model to ensure that the data format meets the model input requirements. According to the requirements of the model, relevant features are selected and extracted, which may include environmental parameters, operating status parameters, historical operating data, etc., to facilitate model analysis.

[0022] More specifically, load the pre-trained energy storage power station monitoring and evaluation model, ensure that the model runs in the corresponding computing environment, input the pre-processed data into the health assessment model, and perform health status analysis. The model will evaluate the health status of the energy storage power station based on the patterns and rules learned during the training process. After the model analysis is completed, the health assessment results are output, and a health analysis report is generated based on the output results of the model.

[0023] It is understandable that by using trained models, an accurate assessment of the health status of energy storage power stations can be achieved, potential risks and failures can be identified in a timely manner, and health analysis reports provide data support for operation and maintenance decisions, making decisions more scientific and reasonable, and reducing the subjectivity of decisions. Through health status analysis, the operation and maintenance team can carry out targeted maintenance and reduce unnecessary downtime, thereby improving the overall operating efficiency of the energy storage power station. Potential problem identification based on model analysis can issue early warnings, reduce equipment failure rates, and improve system reliability.

[0024] The present invention provides a remote AI monitoring and management method for an energy storage power station, which has the following beneficial effects: The present invention collects real-time data on the working environment and operating status of the energy storage power station, arranges the data in chronological order to form a monitoring data sequence, and uses a pre-trained monitoring and evaluation model to evaluate the health status of the energy storage power station on the monitoring data sequence to generate a health analysis report for the energy storage power station. This method can achieve real-time monitoring of the energy storage power station, timely discover potential faults, and improve the safety and reliability of equipment operation. At the same time, through data-driven health analysis, it can optimize operation and maintenance strategies, reduce the need for manual inspections, reduce maintenance costs, and improve the overall operating efficiency of the energy storage power station, solving the problem of low efficiency in manual monitoring of energy storage power stations in the prior art.

[0025] Preferably, the step of collecting data on the working environment and operating status of the energy storage power station to obtain the working environment parameters and operating status parameters of the energy storage power station includes: S11: collecting data on the temperature and humidity of the energy storage power station at each time, and obtaining temperature data and humidity data with timestamps; S12: combining the temperature data and the humidity data at the same time according to the timestamp to obtain the working environment parameters at the time; S13: collecting data on the voltage, current and charge and discharge status of the energy storage power station at each time, and obtaining voltage data, current data and charge and discharge status marks with timestamps; S14: combining and processing the voltage data, the current data and the charge and discharge status mark at the same moment according to the timestamp to obtain the operating status parameter at the moment.

[0026] Specifically, temperature and humidity sensors are installed at key locations in the energy storage power station to ensure that they can accurately collect environmental data. The frequency of data collection is set (for example, every minute, every ten seconds) and the data collection program is started to record the temperature and humidity data at each time point. The data is ensured to contain a timestamp. The collected temperature and humidity data are stored in a database to ensure that the data format is consistent for subsequent processing.

[0027] More specifically, the temperature data and humidity data at the same time are aligned according to the timestamp to ensure that each time point has corresponding environmental parameters, and the aligned temperature data and humidity data are combined to form a working environment parameter data set with a timestamp.

[0028] More specifically, voltage and current sensors are installed on relevant equipment of the energy storage power station (such as the battery management system), and the charge and discharge status marks are obtained. The timed collection program of voltage, current and charge and discharge status is started, and the data at each time point is recorded, and it is ensured that the timestamp is included. The collected voltage data, current data and charge and discharge status are stored in the database to ensure data consistency.

[0029] More specifically, the voltage data, current data and charge and discharge status at the same time are aligned according to the timestamp, and the aligned voltage data, current data and charge and discharge status are combined to form an operation status parameter data set with a timestamp.

[0030] It is understandable that by setting up professional sensors to ensure the accuracy and real-time nature of the working environment and operating status data, a reliable basis is provided for subsequent analysis. Combined with temperature, humidity, voltage, current, and charge and discharge status, comprehensive monitoring of the environment and operating status of the energy storage power station is achieved, helping the operation and maintenance team to detect abnormalities in a timely manner. The collected data provides rich information support for subsequent health status analysis, performance evaluation, and fault diagnosis, and can better understand the operating status of the equipment. Based on real-time data of environmental and operating status parameters, the operation and maintenance team can formulate more scientific maintenance strategies and operating decisions to improve the efficiency and safety of the energy storage power station.

[0031] Preferably, the acquired working environment parameters and operating status parameters are transmitted to a designated processing platform, so as to sequentially arrange the working environment parameters and operating status parameters of the energy storage power station at each moment according to the time sequence, and the step of obtaining the monitoring data sequence of the energy storage power station includes: S21: transmitting the acquired working environment parameters and the operating status parameters to a designated processing platform via a communication network; S22: performing a format conversion operation on the working environment parameter and the operating status parameter based on the designated processing platform to obtain the working environment parameter and the operating status parameter that meet the prescribed format requirements; S23: constructing a time coordinate axis having a plurality of time nodes arranged in sequence; S24: Substituting the working environment parameters and the operating status parameters at each moment into the corresponding time nodes in the time coordinate axis respectively, so as to obtain a monitoring data sequence of the energy storage power station.

[0032] Specifically, ensure that a stable communication network connection is established between the energy storage power station and the designated processing platform. You can use a wired network (such as Ethernet) or a wireless network (such as Wi-Fi, 4G / 5G) to package the acquired working environment parameters and operating status parameters into a data packet. The data packet should contain a timestamp, working environment parameters (such as temperature and humidity) and operating status parameters (such as voltage, current, and charge and discharge status). The packaged data is transmitted to the designated processing platform through the communication network. REST API, MQTT or other suitable communication protocols can be used for data transmission.

[0033] More specifically, the designated processing platform receives the transmitted working environment parameters and operating status parameters, parses the received data, extracts the timestamp, working environment parameters and operating status parameters, and converts the data format according to the specified format requirements (such as JSON, XML or CSV, etc.) to ensure the consistency and readability of the data in subsequent processing.

[0034] More specifically, a time coordinate axis is constructed on the processing platform. The time coordinate axis should contain the time nodes of all acquisition moments and be arranged in chronological order. Ensure that the format of the time nodes is consistent with the timestamps in the working environment parameters and operating status parameters to prepare for subsequent data matching.

[0035] More specifically, the working environment parameters and operating status parameters at each moment are matched according to the timestamp and the time node in the time coordinate axis, and the matched data are arranged in the corresponding position of the time coordinate axis in sequence to form a time series. Each time node should contain the corresponding working environment parameters and operating status parameters, and the sorted data is saved as a monitoring data sequence, which can be in the form of an array or list, containing the parameter combination of all time nodes.

[0036] It is understandable that through effective data transmission and processing, real-time monitoring of energy storage power stations can be achieved, and the latest data on the working environment and operating status can be obtained in a timely manner. Through format conversion operations, it is ensured that all transmitted data meets the unified format requirements to avoid data parsing errors caused by inconsistent formats. The time coordinate axis arranged in sequence facilitates data management and analysis, making subsequent data query and processing more efficient.

[0037] Preferably, the step of analyzing the health status of the energy storage power station on the monitoring data sequence by using a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station includes: S31: performing data training on the energy storage power station monitoring and evaluation model in advance to obtain the trained energy storage power station monitoring and evaluation model; S32: performing abnormal data identification processing on the monitoring data sequence according to the energy storage power station monitoring and evaluation model to obtain abnormal data features in the monitoring data sequence; S33: Evaluate the health status of the energy storage power station according to the abnormal data characteristics to obtain the real-time health status of the energy storage power station; S34: Predicting potential faults of the energy storage power station according to the abnormal data characteristics to obtain potential fault problems of the energy storage power station; S35: Combine the real-time health status and potential fault problems of the energy storage power station to obtain a health analysis report of the energy storage power station.

[0038] Specifically, historical monitoring data is collected, including working environment parameters and operating status parameters under normal operating conditions, as well as abnormal data under fault conditions. The collected data is cleaned and preprocessed, including removing noise, filling missing values, standardization and normalization, etc., to improve the effect of model training, and important features are extracted from the monitoring data, such as operating temperature, charge and discharge efficiency, number of cycles, etc., to facilitate model learning.

[0039] More specifically, select a suitable machine learning or deep learning algorithm (such as random forest, support vector machine, neural network, etc.), use the processed data to train the model, adjust the hyperparameters to optimize the model performance, use cross-validation and other methods to verify the trained model, evaluate the accuracy, sensitivity and specificity of the model, and ensure that the model can effectively identify abnormal data.

[0040] More specifically, the monitoring data sequence collected in real time is input into the trained energy storage power station monitoring and evaluation model. The input data is analyzed according to the model to identify abnormal data features that deviate significantly from the normal operating state, such as voltage fluctuations beyond the set range, temperature anomalies, etc. The identified abnormal data features are extracted and recorded, including abnormal values, the time when the abnormality occurred, the type of abnormality and other information.

[0041] More specifically, based on the identified abnormal data features, the model is used to evaluate the overall health of the energy storage power station. The model can use a threshold-based method or a machine learning algorithm to score and output the real-time health status of the energy storage power station, including the type of health status assessment and the specific score assessment.

[0042] More specifically, based on the identified abnormal features, the model is used to predict potential faults, identify factors that may lead to future failures, and generate a list of potential fault problems for the energy storage power station, including possible fault types and their severity.

[0043] More specifically, the real-time health status and potential fault problems are comprehensively analyzed to form a comprehensive health analysis report.

[0044] It is understandable that through a well-trained model, abnormal data can be identified more accurately, improving the monitoring accuracy of the energy storage power station. Real-time health status assessment enables operation and maintenance personnel to timely understand the operating status of the energy storage power station, quickly take necessary measures, predict potential failure problems, help identify possible risks in advance, and reduce losses caused by sudden failures.

[0045] Preferably, the step of pre-training the energy storage power station monitoring and evaluation model with data to obtain the trained energy storage power station monitoring and evaluation model includes: S311: Collecting historical data related to the energy storage power station; wherein the historical data includes analysis object data and analysis target data, the analysis object data includes the working environment data and the operating status data, and the analysis target data includes power station evaluation data; S312: Divide the historical data into sets to obtain a training set, a validation set, and a test set; S313: Constructing a monitoring and evaluation model for an energy storage power station consisting of an input layer, a multi-layer circulation layer, and an output layer; S314: Substituting the training set into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to perform feature analysis on the data mapping relationship between the analysis object data and the analysis target data according to the training set, so as to obtain the data mapping relationship between the analysis object data and the analysis target data; S315: Substituting the verification set into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to verify the data mapping relationship according to the verification set to obtain the confidence of the data mapping relationship; S316: adjusting the model parameters of the energy storage power station monitoring and evaluation model according to the confidence of the data mapping relationship to obtain a new data mapping relationship; S317: Substituting the test set into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to test the data mapping relationship according to the test set to obtain a data fitting status of the data mapping relationship; S318: When the data fitting condition of the data mapping relationship meets the training standard, the energy storage power station monitoring and evaluation model having the data mapping relationship is deployed to complete the training of the energy storage power station monitoring and evaluation model; S319: When the data fitting condition of the data mapping relationship does not meet the training standard, the data mapping relationship is trained again until the data mapping relationship whose data fitting condition meets the training standard is obtained.

[0046] Specifically, historical data related to energy storage power stations are collected, including: analysis object data: working environment data (such as temperature, humidity, air pressure, etc.), operation status data (such as battery power, load status, charge and discharge times, etc.); analysis target data: power station evaluation data (such as efficiency, failure rate, performance indicators, etc.) More specifically, the historical data is divided into sets to obtain: training set (for model training), validation set (for model validation), and test set (for model testing).

[0047] More specifically, a monitoring and evaluation model for an energy storage power station is constructed, and the model structure includes: an input layer (receiving analysis object data), a multi-layer circulation layer (performing feature extraction and data mapping), and an output layer (outputting analysis target data).

[0048] More specifically, the training set is substituted into the model for feature analysis, the data mapping relationship between the analysis object data and the analysis target data is analyzed based on the training set to obtain a preliminary mapping relationship, the validation set is substituted into the model for verification, the model output is evaluated based on the validation set, the confidence of the data mapping relationship is calculated, and the model parameters are adjusted based on the confidence to optimize the data mapping relationship and form a new mapping relationship.

[0049] More specifically, the test set is substituted into the model for testing, the model's fit to the test set is evaluated, and the accuracy of the mapping relationship is verified. If the fit of the data mapping relationship meets the predetermined training standards, the model deployment is completed and the energy storage power station monitoring and evaluation model is officially used. If the fit does not meet the training standards, the data mapping relationship is retrained and the above process is repeated until the standards are met.

[0050] It is understandable that through systematic training and verification, the operating characteristics of energy storage power stations can be accurately captured, and the evaluation model's ability to predict power station performance can be improved. The verified and adjusted model can provide data support for the operation and maintenance of the power station, helping managers make more reasonable decisions. The deployed model can achieve real-time monitoring and evaluation, and automatically generate reports, providing a basis for the intelligent management of the power station.

[0051] Preferably, the step of performing abnormal data identification processing on the monitoring data sequence according to the energy storage power station monitoring and evaluation model to obtain abnormal data features in the monitoring data sequence includes: S321: taking the monitoring data sequence as an analysis object, taking the data evaluation feature corresponding to the monitoring data sequence as an analysis target, substituting the analysis object into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to perform analysis processing corresponding to the target on the analysis object, and obtaining the data evaluation feature corresponding to the monitoring data sequence; S322: Classifying the data evaluation features according to a preset standard to classify the data evaluation features into normal evaluation features and abnormal evaluation features; S323: extracting corresponding data from the monitoring data sequence according to the abnormal assessment feature, and obtaining a portion of the monitoring data sequence corresponding to the abnormal assessment feature as an abnormal data feature.

[0052] Specifically, the monitoring data sequence of the energy storage power station is collected and organized to ensure the integrity and accuracy of the data. The monitoring data sequence is used as the analysis object to construct the input features: the monitoring data sequence contains time series data of multiple dimensions (such as voltage, current, temperature, etc.), and the corresponding evaluation features are determined. These features can be the target indicators that the model needs to analyze (such as efficiency, stability, etc.).

[0053] More specifically, the monitoring data sequence (analysis object) is substituted into the energy storage power station monitoring and evaluation model for analysis and processing: the model processes the input data, extracts features using machine learning or deep learning algorithms, and outputs corresponding evaluation features. More specifically, the obtained data evaluation features are classified according to preset standards (such as thresholds, statistical distributions, etc.): the evaluation features are divided into normal evaluation features and abnormal evaluation features. The preset standards can be based on statistical analysis of historical data, industry standards or expert experience.

[0054] More specifically, based on the identified abnormal assessment features, the corresponding data of the monitoring data sequence is extracted: those data records related to the abnormal assessment features are extracted, and these data are the abnormal data features. The extracted abnormal data features are sorted and output to form an abnormal data report to facilitate subsequent analysis and processing, and a visual chart is generated to intuitively display the distribution and characteristics of the abnormal data.

[0055] It is understandable that by applying the energy storage power station monitoring and evaluation model, it is possible to effectively identify anomalies in the data, improve the accuracy of anomaly detection, achieve real-time analysis and feedback of monitoring data, and respond quickly to abnormal situations to ensure the safe operation of the power station.

[0056] Preferably, the step of evaluating the health status of the energy storage power station according to the abnormal data characteristics to obtain the real-time health status of the energy storage power station includes: S331: Analyze the abnormal characteristics of the working environment and the operating state of the energy storage power station according to the abnormal data characteristics to obtain abnormal characteristics of the working environment and abnormal characteristics of the operating state; S332: performing an abnormality evaluation process on the energy storage power station according to the abnormal operation status characteristics to obtain the abnormal operation type of the energy storage power station, and performing a degree analysis on the abnormal operation status characteristics according to the abnormal operation type to obtain an abnormal degree index corresponding to the abnormal operation type; S333: combining the operation abnormality type with the abnormality degree index to obtain a preliminary health assessment; S334: Performing environmental interference analysis on the energy storage power station according to the abnormal working environment characteristics to obtain environmental interference characteristics, and correcting the preliminary health assessment according to the environmental interference characteristics to obtain the real-time health status of the energy storage power station.

[0057] Specifically, based on the abnormal data features extracted previously, an in-depth analysis of the working environment and operating status of the energy storage power station is conducted: abnormal characteristics of the working environment are identified (such as abnormal fluctuations in indicators such as temperature, humidity, and noise), and abnormal characteristics of the operating status are identified (such as abnormal conditions of indicators such as battery charging and discharging efficiency and equipment operating frequency).

[0058] More specifically, an evaluation and processing of the abnormality type is performed based on the abnormal characteristics in the operating status: different types of operating abnormalities (such as overload, short circuit, fault, etc.) are identified and classified, the degree of each operating abnormality type is analyzed, and the abnormality degree index is calculated (such as using a scoring system or threshold judgment).

[0059] More specifically, the operation abnormality type is combined with the abnormality degree index to form a preliminary health assessment. According to the severity and frequency of different abnormality types, the overall health status of the energy storage power station is evaluated to generate a preliminary health assessment result (such as a health score or status level).

[0060] More specifically, based on the identified abnormal characteristics of the working environment, the environmental interference of the energy storage power station is analyzed to identify the impact of environmental factors on equipment operation, such as whether excessive temperature causes equipment performance to decline. The environmental interference characteristics are associated with the operating status to evaluate the impact of environmental factors.

[0061] More specifically, the preliminary health assessment results are corrected based on the environmental interference characteristics, the impact of environmental factors is taken into account, the health assessment results are adjusted to obtain a more accurate real-time health status, and a final health status assessment report is formed and provided to the operation and maintenance team.

[0062] It is understandable that by comprehensively considering abnormal data characteristics and environmental factors, the health status of the energy storage power station can be more accurately reflected, misjudgment can be reduced, and real-time monitoring and evaluation can quickly identify potential risks and improve the safety and reliability of the power station.

[0063] Preferably, the step of predicting potential faults of the energy storage power station according to the abnormal data characteristics to obtain potential fault problems of the energy storage power station includes: S341: performing factor matching processing on the abnormal data features according to a plurality of preset fault factors to obtain factor matching degrees of the abnormal data features corresponding to various fault factors; S342: performing factor verification processing on various fault factors according to the monitoring data sequence to obtain factor verification degrees of the monitoring data sequence corresponding to various fault factors; S343: Comprehensively analyzing various fault factors according to the factor matching degree and factor verification degree of various fault factors, and generating possibility indexes of various fault factors according to the result of the comprehensive analysis; S344: Evaluate and process the probability index of various fault factors according to preset standards to obtain potential fault problems of the energy storage power station.

[0064] Specifically, the monitoring system collects the operating data of the energy storage power station, obtains abnormal data features (such as battery voltage, temperature, charging and discharging efficiency, etc.), and performs factor matching on the abnormal data features according to several preset fault factors (such as overheating, overload, short circuit, aging, etc.). The algorithm (such as similarity calculation) is used to evaluate the correlation between each abnormal data feature and the preset fault factor to obtain the factor matching degree.

[0065] More specifically, based on the monitoring data sequence, various fault factors are verified. By comparing with historical monitoring data, the performance of each fault factor in the current monitoring data is verified to obtain the factor verification degree. The factor matching degree of each fault factor is combined with the factor verification degree for comprehensive analysis. Weighted calculation or other comprehensive evaluation methods are used to generate the possibility index of various fault factors to reflect the potential risk level of each fault.

[0066] More specifically, the probability index of various failure factors is evaluated according to preset standards (such as thresholds, scoring systems, etc.), possible failure problems are identified, and a list of potential failure problems of the energy storage power station is formed. The potential failure problems are displayed in a visual form and provided to the operation and maintenance team for decision-making reference. Regular reports are generated to help management understand the system operation status and potential risks.

[0067] It is understandable that through factor matching and verification, potential fault problems can be accurately identified, the accuracy of fault prediction can be improved, potential faults can be identified in a timely manner, and the operation and maintenance team can be helped to take measures in advance, thereby reducing the risk of equipment failure.

[0068] Reference Figure 2 As shown, in a second aspect, the present invention provides a remote AI monitoring and management method system for an energy storage power station, which is used to implement a remote AI monitoring and management method for an energy storage power station as described in any one of the first aspects, including: A data acquisition module is used to collect data on the working environment and operating status of the energy storage power station to obtain working environment parameters and operating status parameters of the energy storage power station; A data integration module, used to transmit the acquired working environment parameters and operating status parameters to a designated processing platform, so as to sequentially arrange the working environment parameters and operating status parameters of the energy storage power station at each moment according to the time sequence, and obtain a monitoring data sequence of the energy storage power station; The data analysis module is used to analyze the health status of the energy storage power station on the monitoring data sequence through a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station.

[0069] In this embodiment, for the specific implementation of each module in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote AI monitoring and management method for an energy storage power station, characterized in that: include: Collecting data on the working environment and operating status of the energy storage power station to obtain working environment parameters and operating status parameters of the energy storage power station; The obtained working environment parameters and operating status parameters are transmitted to a designated processing platform, so as to sequentially arrange the working environment parameters and operating status parameters of the energy storage power station at each moment according to the time sequence, and obtain a monitoring data sequence of the energy storage power station; The health status of the energy storage power station is analyzed on the monitoring data sequence through a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station.

2. The remote AI monitoring and management method for an energy storage power station according to claim 1, characterized in that: The step of collecting data on the working environment and operating status of the energy storage power station to obtain the working environment parameters and operating status parameters of the energy storage power station includes: Collect data on the temperature and humidity of the energy storage power station at each moment to obtain temperature and humidity data with timestamps; Combining and processing the temperature data and the humidity data at the same time according to the timestamp to obtain the working environment parameters at the time; Collect data on the voltage, current and charge / discharge status of the energy storage power station at each moment to obtain voltage data, current data and charge / discharge status marks with timestamps; The voltage data, the current data and the charge and discharge status mark at the same moment are combined and processed according to the timestamp to obtain the operating status parameter at the moment.

3. The remote AI monitoring and management method for an energy storage power station according to claim 1, characterized in that: The steps of transmitting the acquired working environment parameters and the operating status parameters to a designated processing platform, and sequentially arranging and processing the working environment parameters and the operating status parameters of the energy storage power station at each moment according to the time sequence, and obtaining the monitoring data sequence of the energy storage power station include: Transmitting the acquired working environment parameters and the operating status parameters to a designated processing platform via a communication network; Performing a format conversion operation on the working environment parameter and the operating status parameter based on the designated processing platform to obtain the working environment parameter and the operating status parameter that meet the prescribed format requirements; Construct a time coordinate axis with a number of time nodes arranged in sequence; The working environment parameters and the operating status parameters at each moment are respectively substituted into the corresponding time nodes in the time coordinate axis to obtain a monitoring data sequence of the energy storage power station.

4. The remote AI monitoring and management method for an energy storage power station according to claim 1, characterized in that: The steps of analyzing the health status of the energy storage power station on the monitoring data sequence by using a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station include: Pre-training the energy storage power station monitoring and evaluation model with data to obtain a trained energy storage power station monitoring and evaluation model; Performing abnormal data identification processing on the monitoring data sequence according to the energy storage power station monitoring and evaluation model to obtain abnormal data features in the monitoring data sequence; Performing a health status assessment on the energy storage power station according to the abnormal data characteristics to obtain a real-time health status of the energy storage power station; Predicting potential faults of the energy storage power station according to the abnormal data characteristics to obtain potential fault problems of the energy storage power station; The real-time health status and potential fault problems of the energy storage power station are processed in combination to obtain a health analysis report of the energy storage power station.

5. The remote AI monitoring and management method for an energy storage power station according to claim 4, characterized in that: The step of pre-training the energy storage power station monitoring and evaluation model with data to obtain the trained energy storage power station monitoring and evaluation model includes: Collecting historical data related to the energy storage power station; wherein the historical data includes analysis object data and analysis target data, the analysis object data includes working environment data and operating status data, and the analysis target data includes power station evaluation data; Dividing the historical data into sets to obtain a training set, a validation set, and a test set; Construct a monitoring and evaluation model for energy storage power stations consisting of an input layer, a multi-layer circulation layer, and an output layer; Substituting the training set into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to perform feature analysis on the data mapping relationship between the analysis object data and the analysis target data according to the training set, so as to obtain the data mapping relationship between the analysis object data and the analysis target data; Substituting the verification set into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to verify the data mapping relationship according to the verification set to obtain the confidence of the data mapping relationship; Adjusting the model parameters of the energy storage power station monitoring and evaluation model according to the confidence of the data mapping relationship to obtain a new data mapping relationship; Substituting the test set into the energy storage power station monitoring and evaluation model, allowing the energy storage power station monitoring and evaluation model to test the data mapping relationship according to the test set to obtain the data fitting status of the data mapping relationship; When the data fitting status of the data mapping relationship meets the training standard, the energy storage power station monitoring and evaluation model having the data mapping relationship is deployed to complete the training of the energy storage power station monitoring and evaluation model; When the data fitting condition of the data mapping relationship does not meet the training standard, the data mapping relationship is trained again until the data mapping relationship whose data fitting condition meets the training standard is obtained.

6. The remote AI monitoring and management method for an energy storage power station according to claim 4, characterized in that: The step of performing abnormal data identification processing on the monitoring data sequence according to the energy storage power station monitoring and evaluation model to obtain abnormal data features in the monitoring data sequence includes: Taking the monitoring data sequence as the analysis object, taking the data evaluation characteristics corresponding to the monitoring data sequence as the analysis target, substituting the analysis object into the energy storage power station monitoring and evaluation model, and allowing the energy storage power station monitoring and evaluation model to perform analysis processing corresponding to the target on the analysis object, and obtaining the data evaluation characteristics corresponding to the monitoring data sequence; Performing feature classification on the data evaluation features according to a preset standard to classify the data evaluation features into normal evaluation features and abnormal evaluation features; The monitoring data sequence is subjected to corresponding data extraction processing according to the abnormal assessment feature, so as to obtain a part of the monitoring data sequence corresponding to the abnormal assessment feature as the abnormal data feature.

7. The remote AI monitoring and management method for an energy storage power station according to claim 4, characterized in that: The steps of evaluating the health status of the energy storage power station according to the abnormal data characteristics to obtain the real-time health status of the energy storage power station include: Analyzing abnormal characteristics of the working environment and operating state of the energy storage power station according to the abnormal data characteristics to obtain abnormal characteristics of the working environment and abnormal characteristics of the operating state; According to the abnormal operation status characteristics, the energy storage power station is evaluated for an abnormal type to obtain an abnormal operation type of the energy storage power station, and according to the abnormal operation type, the abnormal operation status characteristics are analyzed to obtain an abnormal degree index corresponding to the abnormal operation type; Combining the operation abnormality type with the abnormality degree index to obtain a preliminary health assessment; According to the abnormal working environment characteristics, an environmental interference analysis is performed on the energy storage power station to obtain environmental interference characteristics, and the preliminary health assessment is corrected according to the environmental interference characteristics to obtain the real-time health status of the energy storage power station.

8. The remote AI monitoring and management method for an energy storage power station according to claim 4, characterized in that: The step of predicting potential faults of the energy storage power station according to the abnormal data characteristics to obtain potential fault problems of the energy storage power station includes: Performing factor matching processing on the abnormal data features according to several preset fault factors to obtain factor matching degrees of the abnormal data features corresponding to various fault factors; Performing factor verification processing on various fault factors according to the monitoring data sequence to obtain factor verification degrees of the monitoring data sequence corresponding to various fault factors; Comprehensively analyzing various fault factors according to the factor matching degree and factor verification degree of various fault factors, and generating possibility indexes of various fault factors according to the results of the comprehensive analysis; The probability index of various fault factors is evaluated and processed according to preset standards to obtain potential fault problems of the energy storage power station.

9. A remote AI monitoring and management method system for an energy storage power station, characterized in that: A remote AI monitoring and management method for an energy storage power station according to any one of claims 1 to 8, comprising: A data acquisition module is used to collect data on the working environment and operating status of the energy storage power station to obtain working environment parameters and operating status parameters of the energy storage power station; A data integration module, used to transmit the acquired working environment parameters and operating status parameters to a designated processing platform, so as to sequentially arrange the working environment parameters and operating status parameters of the energy storage power station at each moment according to the time sequence, and obtain a monitoring data sequence of the energy storage power station; The data analysis module is used to analyze the health status of the energy storage power station on the monitoring data sequence through a pre-trained energy storage power station monitoring and evaluation model to obtain a health analysis report of the energy storage power station.

Images