Energy storage power station operation and maintenance management method and system fusing AI and Internet of Things

Abstract

The invention discloses an energy storage power station operation and maintenance management method fusing AI and Internet of Things, and the method employs an edge computing technology to carry out the preprocessing of state monitoring data, and the data is uploaded to an operation and maintenance management center after the preprocessing, thereby reducing the calculation resource occupation of the operation and maintenance management center, facilitating the shortening of the early warning response time, and improving the early warning efficiency. And when the state monitoring data is preprocessed, preliminary anomaly detection is performed through a matrix profile dynamic time warping algorithm, and suspicious data segments are marked, so that the computing resource occupation of an operation and maintenance management center can be further reduced, and the early warning response time is further shortened.

Description

Technical Field

[0001] The present invention relates to the field of energy storage power stations, and particularly to an operation and maintenance management method and system for an energy storage power station integrating AI and the Internet of Things. Background Art

[0002] With the vigorous development of the new energy industry and the continuous promotion of the construction of smart grids, as a key facility to ensure the stable operation of the power system, the importance of intelligent condition monitoring of energy storage power stations has become increasingly prominent. The traditional condition monitoring of energy storage power stations mainly relies on manual inspections and manual data monitoring. This mode is not only inefficient but also difficult to detect potential equipment failures in advance, increasing the operation and maintenance costs of energy storage power stations.

[0003] In recent years, the deep integration of artificial intelligence and Internet of Things technologies has provided a new solution for the condition monitoring of energy storage power stations. The wide deployment of Internet of Things sensors has realized the real-time collection and transmission of the operation data of various devices in the energy storage power station. Artificial intelligence algorithms can perform predictive analysis on the device status based on historical data, greatly improving the accuracy and timeliness of condition monitoring.

[0004] However, despite the remarkable achievements made by the application of these technologies, the intelligent condition monitoring of current energy storage power stations still faces many challenges. On the one hand, the structure of energy storage power stations is complex, involving multiple types of components such as energy storage battery packs, converter systems, cooling systems, and fire protection systems. The difficulty of data analysis and processing is high, affecting the accuracy of condition warning. On the other hand, existing intelligent monitoring algorithms have insufficient warning capabilities when facing tasks such as device performance degradation, and some algorithms have high requirements for hardware computing resources and are difficult to be efficiently deployed on the edge side, restricting the response speed of real-time condition monitoring. Summary of the Invention

[0005] The main advantage of the present invention is to provide an operation and maintenance management method for an energy storage power station integrating AI and the Internet of Things. It uses edge computing technology to preprocess the condition monitoring data, and only uploads the data to the operation and maintenance management center after preprocessing, reducing the computing resource occupancy of the operation and maintenance management center and facilitating the shortening of the warning response time.

[0006] Another advantage of the present invention is to provide an operation and maintenance management method for an energy storage power station integrating AI and the Internet of Things. When preprocessing the condition monitoring data, it performs preliminary anomaly detection through the matrix profile dynamic time warping algorithm and marks suspicious data segments, which can further reduce the computing resource occupancy of the operation and maintenance management center and further shorten the warning response time.

[0007] Another advantage of the present invention is that it provides an energy storage power station operation and maintenance management method that integrates AI and the Internet of Things. The time series prediction model of its intelligent early warning model includes a discrete cosine transform layer, a time convolution network layer, and a state space model layer. The false alarm rate of abnormal warnings is reduced through discrete cosine transform frequency domain feature extraction, time convolution network, and time domain-frequency domain matrix addition and fusion mechanism.

[0008] Accordingly, according to an embodiment of the present invention, a method for operation and maintenance management of an energy storage power station integrating AI and the Internet of Things having at least one of the aforementioned advantages comprises the following steps: S1. Use the Internet of Things technology to connect various devices in the energy storage power station into a network, collect the status monitoring data of key equipment in real time, and use edge computing technology to pre-process the status monitoring data. When pre-processing the status monitoring data, the matrix profile dynamic time warping algorithm is used to perform preliminary anomaly detection and mark suspicious data segments; S2, upload the pre-processed status monitoring data to the operation and maintenance management center; S3, the operation and maintenance management center uses the pre-processed status monitoring data to train the intelligent early warning model based on artificial intelligence algorithms; S4. Monitor the status of key equipment in the energy storage power station through an intelligent early warning model, wherein the intelligent early warning model includes a time series prediction model and a time series anomaly detection model. The time series prediction model obtains prediction data based on the input status monitoring data, and the time series anomaly detection model obtains the energy storage power station status warning result based on the input prediction data. The time series prediction model includes a discrete cosine transform layer, a time convolutional network layer, and a state space model layer. The discrete cosine transform layer is used to extract frequency domain features, and the state space model layer performs dynamic modeling based on the time domain-frequency domain matrix addition and fusion features; S5. When the status warning result of the energy storage power station is abnormal, the operation and maintenance disposal procedure is triggered.

[0009] In some embodiments of the present invention, when preprocessing the condition monitoring data, the steps include: Establish dynamic data verification rules to verify the validity of the original data of the collected status monitoring data and eliminate abnormal data points; The sliding window mechanism is used to smooth the time series data of condition monitoring data and extract statistical features; Mark suspicious data segments by calculating the minimum dynamic time warping distance of a subsequence of time series data; Standardize the suspicious data segments to eliminate the dimensional differences between different features.

[0010] In some embodiments of the present invention, the calculation formula of the minimum dynamic time warping distance of a subsequence is: ,in, MP[i] is the minimum dynamic time warping distance of the i-th subsequence T i , where j is the traversal index of non-neighboring subsequences, is the neighboring exclusion radius, T i is the i-th subsequence with length , T j is the j-th subsequence, where j is not equal to i, and DTW is the dynamic alignment distance metric function.

[0011] In some embodiments of the present invention, step S2 specifically includes the steps of: Set the data synchronization frequency in the operation and maintenance management center to ensure that the status monitoring data of the energy storage power station can be uploaded regularly; Encrypt the preprocessed status monitoring data through the edge computing module of the energy storage power station, and securely manage and regularly update the encryption key through the operation and maintenance management center; After receiving the data from the energy storage power station, the operation and maintenance management center performs data quality inspection to ensure the integrity of the data.

[0012] In some embodiments of the present invention, when using the preprocessed status monitoring data to train the intelligent early warning model, the preprocessed status monitoring data is divided into non-overlapping training sets and test sets. The training set is used for training the intelligent early warning model, and the test set is used to evaluate the accuracy of the intelligent early warning model.

[0013] In some embodiments of the present invention, the time-domain frequency-domain matrix summation fusion feature is a hybrid feature formed by fusing the frequency-domain features output by the discrete cosine transform layer and the time-domain data of the status monitoring data through matrix summation operation.

[0014] In some embodiments of the present invention, the time convolutional network layer is a multi-layer dilated time convolutional network structure, which is used to extract the local details and long-term trends of the time series of the status monitoring data.

[0015] Correspondingly, the present invention further provides an energy storage power station operation and maintenance management system integrating AI and the Internet of Things, which is used to implement the above-mentioned energy storage power station operation and maintenance management method integrating AI and the Internet of Things, and includes: A data acquisition module, including sensors deployed on key monitoring nodes of the energy storage power station; An edge computing module deployed on the edge side of the system, equipped with an embedded processing unit with data cleaning function, matrix profile dynamic time warping anomaly detection function, and statistical feature extraction function; A prediction and decision support module deployed in the operation and maintenance management center, which is used to build an intelligent early warning model through machine learning algorithms and analysis techniques; and The operation and maintenance execution module deployed in the operation and maintenance management center integrates a work order management system, an emergency response device, and a maintenance decision support system, where the operation and maintenance management center is the cloud of the system.

[0016] Correspondingly, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the integrated AI and Internet of Things energy storage power station operation and maintenance management method as described above is implemented.

[0017] Correspondingly, the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the integrated AI and Internet of Things energy storage power station operation and maintenance management method as described above is implemented.

[0018] Combined with the following description and the accompanying drawings of the specification, the above and other advantages of the present invention will be fully manifested.

[0019] The above and other advantages and features of the present invention are fully manifested through the following detailed description of the present invention and the accompanying drawings of the specification.

[0020] The content of the invention is not regarded as an essential technical feature identifying the present invention, nor is it regarded as a limitation on the protection scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flowchart of the integrated AI and Internet of Things energy storage power station operation and maintenance management method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following description is provided to enable a person of ordinary skill in the art to implement the present invention. Other obvious substitutions, modifications, and deformations may occur to a person of ordinary skill in the art. Therefore, the protection scope of the present invention should not be limited by the exemplary embodiments described herein.

[0023] A person of ordinary skill in the art should understand that unless specifically stated herein, the term "one" should be understood as "at least one" or "one or more". That is, in one embodiment, the number of an element may be one, while in other embodiments, the number of the element may be multiple.

[0024] Those of ordinary skill in the art should understand that unless specifically stated herein, the orientations or positions referred to by terms such as "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientations or positions shown in the drawings. This is only for the convenience of describing the present invention and does not indicate or imply that the devices or elements involved must have a specific orientation or position. Therefore, the above terms should not be construed as limiting the present invention.

[0025] Referring to the attached drawings of the specification of the present invention Figure 1 , a method for operation and maintenance management of an energy storage power station integrating AI and the Internet of Things according to an embodiment of the present invention is illustrated. The method for operation and maintenance management of an energy storage power station integrating AI and the Internet of Things includes the following steps: S1. Use Internet of Things technology to connect various devices in the energy storage power station into a network, collect real-time status monitoring data of key devices, and use edge computing technology to preprocess the status monitoring data. When preprocessing the status monitoring data, perform preliminary anomaly detection through the matrix profile dynamic time warping algorithm and mark suspicious data segments; S2. Upload the preprocessed status monitoring data to the operation and maintenance management center; S3. The operation and maintenance management center trains an intelligent early warning model using the preprocessed status monitoring data based on an artificial intelligence algorithm; S4. Monitor the status of key devices in the energy storage power station through the intelligent early warning model. The intelligent early warning model includes a time series prediction model and a time series anomaly detection model. The time series prediction model obtains prediction data based on the input status monitoring data, and the time series anomaly detection model obtains an energy storage power station status early warning result based on the input prediction data. The time series prediction model includes a discrete cosine transform layer, a temporal convolutional network layer, and a state space model layer. The discrete cosine transform layer is used to extract frequency domain features, and the state space model layer performs dynamic modeling based on the sum and fusion of time domain-frequency domain matrix features; S5. When the energy storage power station status early warning result is abnormal, trigger the operation and maintenance disposal procedure.

[0026] It can be understood that through edge computing technology, data processing, etc. can be pushed from the traditional cloud to the edge side of the system, that is, a location closer to the data source or terminal device. In the present invention, the edge computing module deployed on the edge side of the system can preprocess the status monitoring data, and only upload the data to the operation and maintenance management center, that is, the cloud of the system, after preprocessing, reducing the computing resource occupancy of the operation and maintenance management center and facilitating shortening the warning response time. When preprocessing the status monitoring data, the edge computing module can also perform preliminary anomaly detection through the matrix profile dynamic time warping algorithm and mark suspicious data segments, which can further reduce the computing resource occupancy of the operation and maintenance management center and further shorten the warning response time.

[0027] It is worth mentioning that the status monitoring data is collected by sensors deployed on key monitoring nodes such as the energy storage system, converter system, and environmental monitoring nodes of the energy storage power station, including battery pack voltage / current data, energy storage converter input / output power, battery pack charge / discharge power, environmental temperature, humidity, harmful gas concentration, switch states such as circuit breakers and contactors in SCADA (supervisory control and data acquisition) data, and also including the voltage / temperature / SOC dispersion of single cells, total voltage / total current / insulation resistance / SOH of battery clusters, overvoltage, undervoltage, short-circuit protection records, battery internal resistance change trends, etc. in BMS (battery management system) data.

[0028] Specifically, when preprocessing the status monitoring data, the following steps are included: Establish dynamic data verification rules to verify the validity of the original data of the collected status monitoring data and eliminate abnormal data points; Adopt a sliding window mechanism to smooth the time series data of the status monitoring data and extract statistical features; Mark suspicious data segments by calculating the minimum dynamic time warping distance of subsequences of the time series data; Perform standardization operations on the suspicious data segments to eliminate the dimensional difference between different features.

[0029] More specifically, the dynamic data verification rule is based on sliding window statistical analysis, and determines whether the current data exceeds the dynamic upper and lower limit ranges constructed by the historical mean and standard deviation through adaptive threshold detection; if it exceeds, it is regarded as an abnormal data point, otherwise, further calculate the data change rate, and if the change rate exceeds the preset threshold, it is also determined as abnormal.

[0030] Preferably, in the dynamic data verification rule, if the amplitude of a data point is greater than or less than a set percentage of the average amplitude, it is regarded as an abnormal data point.

[0031] It can be understood that the statistical feature extraction includes, but is not limited to, the extraction of statistical features such as battery pack voltage / current data, energy storage converter input / output power, battery pack charge / discharge power, and ambient temperature.

[0032] Preferably, the calculation formula for the minimum dynamic time warping distance of a subsequence is: , where MP[i] is the minimum dynamic time warping distance of the i-th subsequence T i , j is the traversal index of non-neighboring subsequences, is the neighboring exclusion radius, T i is the i-th subsequence with length , T j is the j-th subsequence, j is not equal to i, and DTW is the dynamic alignment distance metric function.

[0033] Specifically, the present invention collects the status monitoring data of key equipment in the energy storage power station in real time by deploying sensors. First, based on dynamic data verification rules (such as when the amplitude of a data point exceeds the historical mean ±A%, it is determined as abnormal and excluded), combined with a sliding window mechanism, the time series data is smoothed and statistical features are extracted; subsequently, the Matrix Profile with Dynamic Time Warping (MP-DTW) algorithm is used to mark suspicious data segments (such as battery voltage mutations or temperature sudden rises, etc.) by calculating the minimum DTW distance of subsequences, and the cleaned data is standardized to eliminate the dimension difference.

[0034] Furthermore, step S2 of the energy storage power station operation and maintenance management method integrating AI and the Internet of Things according to the present invention specifically includes the steps of: Set the data synchronization frequency in the operation and maintenance management center to ensure that the status monitoring data of the energy storage power station can be uploaded regularly; Encrypt the preprocessed status monitoring data through the edge computing module of the energy storage power station, and perform secure management and regular update of the encryption key through the operation and maintenance management center; After receiving the data from the energy storage power station, the operation and maintenance management center implements data quality inspection to ensure the integrity of the data.

[0035] Preferably, encryption can be performed through the Advanced Encryption Standard encryption algorithm. More preferably, the key length is set to 192 bits. It is worth mentioning that the Advanced Encryption Standard (AES) encryption algorithm is a symmetric encryption algorithm officially adopted by the National Institute of Standards and Technology (NIST) of the United States in 2001, replacing the old DES (Data Encryption Standard). It is one of the most widely used encryption algorithms globally.

[0036] Preferably, after receiving data from the energy storage power station, the operation and maintenance management center performs data quality inspection using the SHA algorithm. It is worth mentioning that the SHA algorithm (Secure Hash Algorithm) is a set of cryptographic hash functions designed by the National Security Agency (NSA) of the United States and published by the National Institute of Standards and Technology (NIST), widely used in fields such as data integrity verification, digital signatures, and password storage.

[0037] Furthermore, when training the intelligent early warning model using the preprocessed condition monitoring data, the preprocessed condition monitoring data is divided into non-overlapping training sets and test sets. The training set is used for training the intelligent early warning model, and the test set is used to evaluate the accuracy of the intelligent early warning model, thus avoiding negative impacts on the training and accuracy evaluation of the model caused by data contamination.

[0038] Furthermore, the time-domain frequency-domain matrix summation fusion feature is a hybrid feature formed by fusing the frequency-domain features output by the discrete cosine transform layer and the time-domain data of the condition monitoring data through matrix summation operations. The specific formula is: ; F fusion =X+F freq ; In the formula, X is the condition monitoring data, T is the sequence length, c is the number of sensor channels, and F freq is the frequency-domain feature output by the discrete cosine transform layer; F fusion is the time-domain frequency-domain matrix summation fusion feature.

[0039] Even further, the time convolutional network layer is a multi-layer dilated time convolutional network structure, used to extract the local details and long-term trends of the time series of the condition monitoring data, which is beneficial to improving the early warning accuracy of the intelligent early warning model. Among them, the formula for the multi-layer dilated time convolutional network is: ; In the formula, H (l) is the output of the l-th layer, is the convolutional kernel weight of the l-th layer, and 2 l-1 is the dilation factor.

[0040] It can be understood that the present invention reduces the false alarm rate of abnormal early warning through discrete cosine transform frequency-domain feature extraction, temporal convolutional network and time-domain frequency-domain matrix summation fusion mechanism.

[0041] Specifically, the intelligent early warning model of the present invention includes a time series prediction model and a time series anomaly detection model. After the state monitoring data is input into the time series prediction model, predicted data is obtained. The predicted data is input into the time series anomaly detection model, and finally the state early warning result of the energy storage power station is obtained. The time series prediction model of the present invention includes a discrete cosine transform (Discrete Cosine Transform, DCT) layer, a temporal convolutional network (Temporal Convolutional Network, TCN) layer and a state space model layer. The preprocessed multi-dimensional feature data is transformed to the frequency domain through the DCT layer to extract periodic fluctuation features, and then input into a multi-layer dilated TCN structure to further extract the local details and long-term trends of the time series. The frequency domain features output by the TCN and the time domain data of the state monitoring data are fused through matrix summation operation to form mixed features, and then input into the state space model layer for dynamic modeling to output the predicted data for the next moment. The time series anomaly detection model of the present invention divides the time series of the predicted data into non-overlapping subsequences of a fixed length and transforms them into D-dimensional embedding vectors through a learnable mapping process, where D is a hyperparameter of the model, representing the dimension of the embedding space. In the pre-training stage, these embedding vectors are randomly masked and replaced with special mask embeddings (MASK). The goal of pre-training is to let the model reconstruct the original input from the unmasked part to improve its understanding ability of the time series structure. By using a lightweight Transformer model architecture, the model effectively learns the patterns of the time series and uses the reconstruction error as a measure to identify anomalies. If there is a significant difference between the reconstructed time series and the original series, it indicates that there may be an abnormal situation, and then the state early warning mechanism of the energy storage power station is triggered to realize the early warning of the abnormal state of the energy storage power station.

[0042] Preferably, the early warning of the abnormal state of the energy storage power station of the present invention adopts a multi-level early warning trigger mechanism, including early warning, mid-term warning and emergency warning, where Early warning: When the output result of the intelligent early warning model indicates that there are slight abnormal changes in the state of key equipment but has not reached the level of failure, remind the operation and maintenance personnel to pay attention to the operation status of relevant equipment and check in time to discover potential hidden dangers in the early stage; Medium-term Warning: When the output of the intelligent warning model indicates an obvious abnormal change in the status of key equipment, predicting that the equipment is about to fail or there are significant safety risks, the medium-term warning is initiated to prompt the operation and maintenance personnel to attach great importance and immediately take corresponding measures, such as strengthening equipment inspections, conducting detailed fault troubleshooting, preparing necessary maintenance tools and spare parts, etc., and at the same time, making preparations for emergency response; Emergency Warning: When the output of the intelligent warning model indicates a serious fault in the key equipment, a series of emergency response measures are initiated, and at the same time, an emergency alarm is sent to all relevant personnel to notify professional departments such as fire protection and emergency rescue to come.

[0043] According to another aspect of the present invention, the present invention further provides an energy storage power station operation and maintenance management system integrating AI and the Internet of Things for implementing the energy storage power station operation and maintenance management method integrating AI and the Internet of Things, including: A data acquisition module, including sensors deployed on key monitoring nodes of the energy storage power station; An edge computing module deployed on the edge side of the system, equipped with an embedded processing unit with data cleaning function, matrix profile dynamic time warping anomaly detection function, and statistical feature extraction function; A prediction and decision support module deployed in the operation and maintenance management center for constructing an intelligent warning model through machine learning algorithms and analysis techniques; and An operation and maintenance execution module deployed in the operation and maintenance management center, integrating a work order management system, an emergency response device, and a maintenance decision support system, where the operation and maintenance management center is the cloud of the system.

[0044] Specifically, the energy storage power station operation and maintenance management system integrating AI and the Internet of Things of the present invention adopts a cloud-edge-end collaborative architecture. The end side is the sensor for collecting the status monitoring data of the key equipment of the energy storage power station. The edge side deploys an embedded processing unit responsible for the preprocessing of the status monitoring data and matrix profile dynamic time warping anomaly detection. The cloud side is the operation and maintenance management center responsible for the training and use of the intelligent warning model and executing the corresponding level of disposal plan according to the output result of the intelligent warning model.

[0045] According to another aspect of the present invention, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the energy storage power station operation and maintenance management method integrating AI and the Internet of Things.

[0046] According to another aspect of the present invention, the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the energy storage power station operation and maintenance management method integrating AI and the Internet of Things.

[0047] Those skilled in the art will appreciate that the above embodiments are merely examples, wherein features of different embodiments may be combined with each other to obtain implementation methods that are easily conceivable based on the contents disclosed in the present invention but are not explicitly indicated in the drawings.

[0048] Those skilled in the art should understand that the above description and the embodiments shown in the drawings are only for illustrative explanation of the present invention, rather than for limitation of the present invention. All equivalent implementations, modifications and improvements within the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for operation and maintenance management of an energy storage power station integrating AI and the Internet of Things, characterized in that, Including the steps: S1. Use Internet of Things technology to connect various devices in the energy storage power station into a network, collect real-time status monitoring data of key devices, and use edge computing technology to preprocess the status monitoring data. When preprocessing the status monitoring data, perform preliminary anomaly detection through the matrix profile dynamic time warping algorithm and mark suspicious data segments; S2. Upload the preprocessed status monitoring data to the operation and maintenance management center; S3. The operation and maintenance management center trains an intelligent early warning model based on artificial intelligence algorithms using the preprocessed status monitoring data; S4. Monitor the status of key devices in the energy storage power station through the intelligent early warning model. The intelligent early warning model includes a time series prediction model and a time series anomaly detection model. The time series prediction model obtains prediction data based on the input status monitoring data, and the time series anomaly detection model obtains the energy storage power station status early warning result based on the input prediction data. The time series prediction model includes a discrete cosine transform layer, a temporal convolutional network layer, and a state space model layer. The discrete cosine transform layer is used to extract frequency domain features, and the state space model layer performs dynamic modeling based on the sum and fusion of time domain-frequency domain matrix features; S5. When the energy storage power station status early warning result is abnormal, trigger the operation and maintenance disposal procedure.

2. The operation and maintenance management method of the energy storage power station integrating AI and the Internet of Things according to claim 1, characterized in that When preprocessing the status monitoring data, it includes the steps: Establish dynamic data verification rules, verify the validity of the original data of the collected status monitoring data, and eliminate abnormal data points; Adopt a sliding window mechanism to smooth the time series data of the status monitoring data and extract statistical features; Mark suspicious data segments by calculating the minimum dynamic time warping distance of subsequences of the time series data; Perform standardization operations on the suspicious data segments to eliminate the dimensional differences between different features.

3. The operation and maintenance management method of the energy storage power station integrating AI and the Internet of Things according to claim 2, wherein, The calculation formula for the minimum dynamic time warping distance of the subsequence is: , wherein, MP[i] is the minimum dynamic time warping distance of the i-th subsequence T i , where j is the traversal index of non-neighboring subsequences, is the neighboring exclusion radius, and T i is the i-th subsequence with length , T j is the j-th subsequence, where j is not equal to i, and DTW is the dynamic alignment distance metric function.

4. The operation and maintenance management method of the energy storage power station integrating AI and the Internet of Things according to claim 2, characterized in that, Step S2 specifically includes the steps: Set the data synchronization frequency in the operation and maintenance management center to ensure that the status monitoring data of the energy storage power station can be uploaded regularly; Encrypt the preprocessed status monitoring data through the edge computing module of the energy storage power station, and the operation and maintenance management center performs secure management and regular update of the encryption key; After receiving the data from the energy storage power station, the operation and maintenance management center implements data quality inspection to ensure the integrity of the data.

5. The operation and maintenance management method of the energy storage power station integrating AI and the Internet of Things according to claim 2, wherein, When training the intelligent early warning model using the preprocessed status monitoring data, divide the preprocessed status monitoring data into non-overlapping training sets and test sets. The training set is used for training the intelligent early warning model, and the test set is used to evaluate the accuracy of the intelligent early warning model.

6. The energy storage power station operation and maintenance management method integrating AI and the Internet of Things according to claim 2, characterized in that, The time domain-frequency domain matrix sum and fusion feature is a hybrid feature formed by fusing the frequency domain features output by the discrete cosine transform layer and the time domain data of the status monitoring data through matrix summation operation.

7. The operation and maintenance management method of the energy storage power station integrating AI and the Internet of Things according to claim 2, wherein, The temporal convolutional network layer is a multi-layer dilated temporal convolutional network structure for extracting local details and long-term trends of the time series of status monitoring data.

8. An energy storage power station operation and maintenance management system integrating AI and the Internet of Things is used to implement the energy storage power station operation and maintenance management method integrating AI and the Internet of Things described in any one of claims 1-7, and is characterized in that, Including: A data acquisition module, including sensors deployed on key monitoring nodes of the energy storage power station; An edge computing module deployed on the edge side of the system, equipped with an embedded processing unit having data cleaning function, matrix profile dynamic time warping anomaly detection function, and statistical feature extraction function; A prediction and decision support module deployed in the operation and maintenance management center, for constructing an intelligent early warning model through machine learning algorithms and analysis techniques; and An operation and maintenance execution module deployed in the operation and maintenance management center, integrating a work order management system, an emergency response device, and a maintenance decision support system, wherein the operation and maintenance management center is the cloud of the system.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the integrated AI and IoT energy storage power station operation and maintenance management method according to any one of claims 1-7.

10. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the integrated AI and IoT energy storage power station operation and maintenance management method according to any one of claims 1-7.

Images