Liquid-cooled energy storage cabinet intelligent monitoring method, system and device based on self-iterative deep learning algorithm and storage medium

Abstract

The application discloses a liquid-cooled energy storage cabinet intelligent monitoring method, system and device based on a self-iterative deep learning algorithm and a storage medium, relates to the technical field of intelligent battery management and energy storage system control, and comprises the following steps: collecting temperature data for prediction and storage; controlling and decision-making based on distributed liquid-cooled cabinet temperature monitoring; updating and training a model through a self-iterative deep learning algorithm; and early warning based on model predictive control. The liquid-cooled energy storage cabinet intelligent monitoring method based on the self-iterative deep learning algorithm provided by the application is controlled in real time and accurately by a mathematical model, and has high timeliness. The cloud platform can iteratively output corresponding mathematical models for different distributed energy storage cabinets, and can also integrate high-risk fault prediction data occurring in different places into deep learning models in other places, so that the problem of frequent alarms or missed alarms caused by excessively high or low threshold values due to artificial experience is reduced, and better effects are achieved in terms of timeliness, a missed alarm rate and a cost.

Description

Technical Field

[0001] This invention relates to the field of intelligent battery management and energy storage system control technology, specifically to an intelligent monitoring method, system, device, and storage medium for liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm. Background Technology

[0002] New energy power generation technologies, especially wind and solar power, are growing rapidly and gradually becoming the mainstay of new power generation capacity, with distributed photovoltaic power experiencing explosive growth. Currently, energy storage systems are receiving attention as a key technology for balancing supply and demand among distributed photovoltaic power, the power grid, and electricity users. As a crucial thermal management solution within energy storage systems, liquid-cooled energy storage cabinet technology is particularly suitable for applications with high battery pack energy density, fast charging and discharging speeds, and large ambient temperature variations due to its high heat dissipation efficiency, rapid heat dissipation speed, and good temperature uniformity.

[0003] Existing liquid-cooled energy storage cabinets mostly employ two operation and maintenance management solutions: local monitoring and cloud-based data upload. Control and management largely rely on simple threshold triggers and manual monitoring, failing to meet the growing demands for automation and intelligence. Local deployment offers strong real-time monitoring but is unsuitable for distributed scenarios and the deployment of corresponding data analysis services. Cloud-based data upload requires data acquisition through a collector, gateway, cloud server, and database for storage, followed by data querying and access through other clients. While historical data can be analyzed, real-time faults in the field are difficult to detect immediately, limiting the efficiency of remote monitoring. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that existing liquid-cooled energy storage cabinet operation and maintenance management methods cannot meet the growing demand for automation and intelligence, local deployment monitoring is not suitable for distributed scenarios and the deployment of corresponding data analysis services, data uploading to the cloud makes it difficult to analyze and process real-time faults on site in a timely manner, and limits the efficiency of remote monitoring.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: an intelligent monitoring method for liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm, comprising: collecting temperature data for prediction and storage; making control decisions based on distributed liquid-cooled cabinet temperature monitoring; updating and training the model through a self-iterative deep learning algorithm; and predictive control and early warning based on the model.

[0007] As a preferred embodiment of the intelligent monitoring method for liquid-cooled energy storage cabinets based on self-iterative deep learning algorithms described in this invention, the method for predicting and storing the collected temperature data includes sampling by the BMS system over time. Collect the real-time voltage of each battery. Real-time current and real-time temperature The data is fed into a local lightweight database, and the temperature of each battery in the next moment is predicted based on the BMS temperature model based on deep learning algorithms and real-time voltage and current data. The data is then stored in the database, and the current temperature data is then processed. Temperature predictions made at the previous moment and stored in the database The difference between the data is expressed as:

[0008] ,

[0009] in, This indicates the difference in current temperature data;

[0010] Store the difference and wait for the main controller to access it.

[0011] As a preferred embodiment of the intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm described in this invention, the control decision based on distributed liquid-cooled cabinet temperature monitoring includes the distributed liquid-cooled energy storage cabinet collecting real-time temperature data of the current liquid-cooled cabinet through a collector and transmitting it to the main controller.

[0012] The main controller queries the local database to check whether the difference between the temperature prediction and real-time data of each battery pack is within the difference range.

[0013] The difference range is within -5% between the temperature prediction and the real-time data. The range is 5%, while the normal operating temperature of the battery pack is 5~45℃;

[0014] If it is not within the difference range, an update message will be sent to the cloud platform;

[0015] If the data difference is still within the difference range, the main controller predicts the temperature data of the entire liquid-cooled energy storage cabinet for the next moment based on a deep learning algorithm.

[0016] As a preferred embodiment of the intelligent monitoring method for liquid-cooled energy storage cabinets based on self-iterative deep learning algorithms described in this invention, the control decision based on distributed liquid-cooled cabinet temperature monitoring includes making control decisions based on currently predicted temperature data. Taking into account whether it is necessary to increase or decrease the power of the liquid chiller Power depends on temperature data ;

[0017] like If the temperature difference is between 5 and 45°C, the current liquid chiller power will not be adjusted.

[0018] When predicting temperature data When using a simplified heat conduction model for adaptive adjustment, it can be expressed as:

[0019] ,

[0020] in, It is a direct proportionality coefficient, and the coefficient depends on the properties of the coolant, the flow rate, the heat capacity of the battery, and the heat exchange efficiency. This indicates the current power of the liquid chiller.

[0021] As a preferred embodiment of the intelligent monitoring method for liquid-cooled energy storage cabinets based on self-iterative deep learning algorithm described in this invention, the step of updating and training the model through self-iterative deep learning algorithm includes: after the cloud platform receives data from each distributed energy storage cabinet, the cloud platform queries the latest data in the database and updates the prediction model based on the self-iterative deep learning algorithm.

[0022] As a preferred embodiment of the intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm described in this invention, the method of updating and training the model through self-iterative deep learning algorithm includes backing up the latest data to a cloud database, which is divided into a training set and a test set. The BMS deep learning model uses the voltage and current data of each battery as variables, and the temperature of each battery is 0-40°C. As dependent variables, the network layers and activation functions of the deep learning algorithm are set separately and trained. After the trained data model reaches 95% accuracy after testing on the test set, it is transmitted back to each distributed master controller by the cloud platform. At the same time, if faulty data is detected, it will be returned to all distributed nodes.

[0023] As a preferred embodiment of the intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm described in this invention, the step of model-based predictive control and early warning includes the main controller receiving an updated mathematical model and applying it to the next acquisition, prediction, comparison and control of the BMS and liquid cooling system.

[0024] By predicting and controlling battery temperature in advance, temperature control is implemented for scenarios where an alarm is predicted to be required.

[0025] If the battery temperature cannot be controlled in advance, power will be cut off according to the threshold.

[0026] Another objective of this invention is to provide an intelligent monitoring system for liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm. This system can make control decisions through distributed liquid-cooled cabinet temperature monitoring, solving the problem that current liquid-cooled energy storage cabinet operation and maintenance management methods, which involve data uploading to the cloud, make it difficult to analyze and process real-time faults on-site in a timely manner.

[0027] As a preferred embodiment of the intelligent monitoring system for liquid-cooled energy storage cabinets based on self-iterative deep learning algorithms described in this invention, the system includes: a data acquisition module, a battery management system (BMS) module, a data processing module, a control module, and an output module. The data acquisition module is used to acquire key temperature and humidity parameters of the liquid-cooled energy storage cabinet in real time. The BMS module is used to acquire voltage, current, and temperature parameters of each battery pack in real time and manage the battery packs. The data processing module is used to clean the acquired data, perform edge computing using the trained deep learning model, and store the data. The control module is used to analyze the real-time data, predict the operating status of the energy storage cabinet, and automatically adjust the operating parameters of the liquid cooling system based on the status prediction results. The output module is used to train a deep neural network model based on historical data obtained from a distributed database, and iteratively optimize the deep learning prediction mathematical model corresponding to each distributed energy storage cabinet based on the latest difference.

[0028] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement a method for intelligent monitoring of a liquid-cooled energy storage cabinet based on a self-iterative deep learning algorithm.

[0029] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of an intelligent monitoring method for liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm.

[0030] The beneficial effects of this invention are as follows: The intelligent monitoring method for liquid-cooled energy storage cabinets based on self-iterative deep learning algorithms provided by this invention, compared with a completely local deployment scheme, can centrally manage distributed scenarios, achieve remote monitoring, and reduce the cost of local deployment equipment in multiple distributed scenarios. Compared with a completely cloud-based data solution, it can perform edge computing locally and execute mathematical models obtained from deep learning for real-time and precise control, resulting in high timeliness. The cloud platform can not only iterate and generate corresponding mathematical models for different distributed energy storage cabinets, but also integrate high-risk fault prediction data from different locations into deep learning models from other locations, perfectly suited for distributed control scenarios. This reduces the problem of frequent alarms or missed alarms caused by threshold settings that are too high or too low due to human experience. With more accurate predictions, it can greatly reduce the alarm frequency of small and medium-sized faults, and can also prevent major faults in advance. This invention achieves better results in terms of timeliness, missed alarm rate, and cost. Attached Figure Description

[0031] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 The diagram shows a multi-layer feedforward DNN fully connected training model for an intelligent monitoring method for liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm, as provided in the first embodiment of the present invention.

[0033] Figure 2 The image shows the prediction accuracy of a model after iterative optimization for an intelligent monitoring system for a liquid-cooled energy storage cabinet based on a self-iterative deep learning algorithm, as provided in the second embodiment of the present invention.

[0034] Figure 3 This is a comparison chart of a liquid-cooled energy storage cabinet intelligent monitoring system based on a self-iterative deep learning algorithm, provided in the second embodiment of the present invention, with the mainstream regression prediction models currently on the market.

[0035] Figure 4 The following is an overall flowchart of an intelligent monitoring system for a liquid-cooled energy storage cabinet based on a self-iterative deep learning algorithm, provided as a third embodiment of the present invention. Detailed Implementation

[0036] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0037] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for intelligent monitoring of liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm is provided, comprising:

[0038] S1: Collect temperature data for prediction and storage.

[0039] Furthermore, the BMS system samples data over time. Collect the real-time voltage of each battery. Real-time current and real-time temperature The data is fed into a local lightweight database, and the temperature of each battery in the next moment is predicted based on the BMS temperature model based on deep learning algorithms and real-time voltage and current data. The data is then stored in the database, and the current temperature data is then processed. Temperature predictions made at the previous moment and stored in the database The difference between the data is expressed as:

[0040] ,

[0041] in, This indicates the difference in current temperature data;

[0042] Store the difference and wait for the main controller to access it.

[0043] S2: Control decisions are made based on distributed liquid cooler temperature monitoring.

[0044] Furthermore, the distributed liquid-cooled energy storage cabinet collects real-time temperature data of the current liquid-cooled cabinet through a data acquisition device and transmits it to the main controller. Then, the main controller queries the local database to check whether the difference between the temperature prediction and the real-time data of each battery pack is within a reasonable range. The difference between the temperature prediction and the real-time data should be within the range of -5% to 5% to be considered reasonable. The normal operating ambient temperature of the battery pack is 5~45℃. If the difference is not within the range, an update message is sent to the cloud platform. If the data difference is still within the reasonable range, the main controller predicts the temperature data of the entire liquid-cooled energy storage cabinet for the next moment based on a deep learning algorithm, and comprehensively considers whether the power of the liquid chiller needs to be increased or decreased based on the currently measured temperature data.

[0045] It should be noted that this is based on the currently predicted temperature data. Taking into account whether it is necessary to increase or decrease the power of the liquid chiller The power here depends on the temperature data. ,if Within the normal operating range (5~45℃), the current liquid chiller power will not be adjusted. (Based on predicted temperature data...) When using a simplified heat conduction model for adaptive adjustment, it can be expressed as:

[0046] ,

[0047] in, It is a direct proportionality coefficient, and the coefficient depends on the properties of the coolant, the flow rate, the heat capacity of the battery, and the heat exchange efficiency. This indicates the current power of the liquid chiller.

[0048] S3: Update and train the model using a self-iterative deep learning algorithm.

[0049] Furthermore, after receiving data from each distributed energy storage unit, the cloud platform queries the latest data in the database and updates the prediction model based on a self-iterative deep learning algorithm. The latest data is backed up to the cloud database and then divided into training and testing sets. The BMS deep learning model uses the voltage and current data of each battery as variables, and the temperature of each battery (0-40°C) as a control. As the dependent variable, the network layers and activation functions of the deep learning algorithm are set respectively, and then training is performed. After the trained data model reaches 95% accuracy after testing on the test set, it is transmitted back to each distributed master controller by the cloud platform. At the same time, if abnormal high-risk fault data is identified, it will be returned to all distributed nodes.

[0050] It should be noted that, firstly, the overall framework of the DNN algorithm is established, such as... Figure 2 As shown, the current DNN network consists of three layers: an input layer, a hidden layer, and an output layer. The hidden layer uses... The input layer contains 4 neurons, and a linear rectified function is used as the activation function for the neurons.

[0051] Real-time current Real-time voltage Real-time temperature And the power of the current liquid chiller After normalization, it is used as the input for the first layer. The output of the hidden layer is:

[0052] ,

[0053] in, Indicates the input layer weights. This represents the offset of each neuron in the hidden layer. After setting initial values, the two variables will be obtained by outputting the loss function based on the difference between the predicted output and the actual output during training, and then feeding it back.

[0054] The output of the output layer is:

[0055] ,

[0056] in, Indicates the hidden layer weights. This represents the offset of each neuron in the output layer;

[0057] The error between the predicted value and the actual system value is obtained simultaneously. ,

[0058] Furthermore, utilizing the gradient descent principle, the weights and offsets of each neuron in each layer are iteratively updated as follows:

[0059] ,

[0060] in, The step size.

[0061] S4: Model-based predictive control and early warning.

[0062] Furthermore, upon receiving the updated mathematical model, the main controller will apply it to the next data acquisition, prediction, comparison, and control of the BMS and liquid cooling system. This saves on the losses of the liquid cooler and achieves more precise control. On the other hand, it can also control the battery temperature in advance through such predictions, increasing or decreasing the cooling for scenarios that are predicted to trigger an alarm. If the desired effect is not achieved, power will be cut off according to the threshold, effectively reducing the number of manual interventions and triggers for low-level faults, and reducing missed and false alarms.

[0063] It should be noted that the normal operating temperature range for the battery pack is 5-45°C, which can be set as the comparison condition for predictive adjustment. However, -20°C and 60°C are considered detrimental to the battery pack and should be set as alarm thresholds. Once the prediction model has been trained and loaded into local deployment, the main controller will first calculate the difference between the predicted value from the previous moment and the current actual temperature. If the temperature is within a reasonable range (-5% to 5%), and if so, the current model is considered reliable. Predict the temperature value for the next moment based on the prediction model. If in If the normal operating ambient temperature range is 5~45°C, then no operation is required; if the temperature is above 45°C or below 5°C, then the liquid chiller power should be adjusted according to the heat conduction model in reply 4. If the predicted value exceeds the alarm threshold... This will directly trigger emergency measures such as alarms and power outages. If the predicted value is outside the reasonable range, the main controller will send interactive information to the cloud server, which will then read the latest data from the database to update the deep learning prediction model and return it to the main controller.

[0064] Example 2, refer to Figures 2-3 As an embodiment of the present invention, a method for intelligent monitoring of liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiment.

[0065] First, this experiment simulates real-time temperature monitoring and control of different battery packs in a distributed liquid-cooled energy storage system. Voltage, current, and temperature data for each battery pack are collected through a BMS system and stored in a local lightweight database. The system first establishes a temperature prediction model for the battery packs, based on a deep learning algorithm, trained using real-time collected voltage and current data, aiming to accurately predict the temperature change of the batteries in the next moment. The main controller accesses the database in real time, comparing the current temperature data with the previously stored temperature data and calculating the difference. If the difference is too large, the system sends a data update request to the cloud platform; if it is within a reasonable range, the main controller dynamically adjusts the power of the liquid cooling system based on the BMS-predicted next-moment temperature and the current temperature, thereby achieving precise temperature control.

[0066] In the experimental design, after receiving data from the distributed energy storage cabinets, the cloud platform updates the dataset and optimizes the temperature prediction model to ensure its accuracy in different scenarios. After training, the prediction model achieved an accuracy of over 95% and was applied to different distributed nodes, such as... Figure 3 The figure shows the prediction accuracy of the model after iterative optimization.

[0067] In addition, to reduce the inefficiency of on-site human intervention and avoid equipment damage, the control system uses edge computing mode for real-time processing, thereby reducing upload latency and enabling each distributed energy storage cabinet to perform edge computing and adjustment independently. The cloud platform ensures the consistency and accuracy of control of each node through centralized data iteration updates.

[0068] Table 1 Experimental Data

[0069] test subjects Voltage (V) Current (A) Real-time temperature (°C) Predicted temperature (°C) Temperature difference (°C) Liquid cooling power adjustment (%) Battery Pack A 3.7 5.1 35.2 35.5 0.3 5 Battery pack B 3.65 4.9 34.8 35 0.2 3 Battery pack C 3.72 5 35 35.2 0.2 4 Battery pack D 3.68 5.2 34.7 34.9 0.2 2 Battery pack E 3.7 5.1 35.1 35.3 0.2 4 Battery pack F 3.66 4.8 34.9 35 0.1 3

[0070] The table data shows that the voltage and current parameters of each battery pack are recorded in real time during implementation, and the system can perform efficient temperature prediction on edge devices based on different parameters. The difference between the temperature prediction model and the real-time temperature data indicates that this invention has high prediction accuracy, avoiding false alarms caused by excessive temperature differences. Figure 4 As shown, compared with the mainstream regression prediction models currently on the market, the model in this paper has higher prediction accuracy.

[0071] Furthermore, the liquid cooling system's power adjustment is based on predicted temperature changes, enabling flexible responses to the temperature status of each battery pack. This distributed edge control approach ensures the accuracy and timeliness of temperature control.

[0072] Compared to fully localized deployment, this invention enables centralized management of information from each distributed energy storage cabinet. The cloud platform, through iterative deep learning models, improves the accuracy of system temperature prediction and reduces the cost of local equipment deployment. Compared to a fully cloud-based solution, the local edge computing mode offers advantages in timeliness and computational cost. Real-time processing reduces latency, allowing each distributed energy storage cabinet to independently control temperature in different scenarios. Furthermore, the iteratively updated model of the cloud platform, through the integrated processing of abnormal fault data, enables cross-regional abnormality early warning for distributed energy storage cabinets, effectively reducing the risk of missed and false alarms. This makes the system's prediction of high-risk faults more accurate, further reducing the alarm frequency and equipment wear and tear associated with minor and medium-sized faults.

[0073] Example 3, referring to Figure 4 As an embodiment of the present invention, an intelligent monitoring system for liquid-cooled energy storage cabinet based on a self-iterative deep learning algorithm is provided, including a data acquisition module, a BMS module, a data processing module, a control module, and an output module.

[0074] The data acquisition module is used to collect key temperature and humidity parameters of the liquid-cooled energy storage cabinet in real time. The BMS module is used to collect voltage, current and temperature parameters of each battery pack in real time and manage the battery packs. The data processing module is used to clean the collected data, perform edge computing using the trained deep learning model and store the data. The control module is used to analyze the real-time data, predict the operating status of the energy storage cabinet, and automatically adjust the operating parameters of the liquid cooling system based on the status prediction results. The output module is used to train a deep neural network model based on historical data obtained from a distributed database, and iteratively optimize the deep learning prediction mathematical model corresponding to each distributed energy storage cabinet based on the latest difference.

[0075] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0077] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0078] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0079] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent monitoring of liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm, characterized in that, include: Collect temperature data for prediction and storage; Temperature data acquisition for prediction and storage includes time-based sampling by the BMS system. Collect the real-time voltage of each battery. Real-time current and real-time temperature The data is fed into a local lightweight database, and the temperature of each battery in the next moment is predicted based on the BMS temperature model based on deep learning algorithms and real-time voltage and current data. The data is then stored in the database, and the current temperature data is then processed. Temperature predictions made at the previous moment and stored in the database The difference between the data is expressed as: ， in, This indicates the difference in current temperature data; Store the difference and wait for the main controller to access it; Control decisions are based on distributed liquid cooler temperature monitoring. Control decisions based on distributed liquid-cooled cabinet temperature monitoring include the distributed liquid-cooled energy storage cabinet collecting real-time temperature data of the liquid-cooled cabinet through a data acquisition unit and transmitting it to the main controller; The main controller queries the local database to check whether the difference between the temperature prediction and real-time data of each battery pack is within the difference range. The difference range is between -5% and 5% between the temperature prediction and the real-time data, while the normal operating ambient temperature of the battery pack is 5~45℃. If it is not within the difference range, an update message will be sent to the cloud platform; If the data difference is still within the difference range, the main controller will predict the temperature data of the entire liquid-cooled energy storage cabinet at the next moment based on the deep learning algorithm. Control decisions based on distributed liquid cooler temperature monitoring include decisions based on currently predicted temperature data. Taking into account whether it is necessary to increase or decrease the power of the liquid chiller Power depends on temperature data ; like If the temperature difference is between 5 and 45°C, the current liquid chiller power will not be adjusted. When predicting temperature data When using a simplified heat conduction model for adaptive adjustment, it can be expressed as: ， in, It is a direct proportionality coefficient, and the coefficient depends on the properties of the coolant, the flow rate, the heat capacity of the battery, and the heat exchange efficiency. Indicates the current power of the liquid chiller; The model is updated and trained using a self-iterative deep learning algorithm; Model-based predictive control and early warning.

2. The intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm as described in claim 1, characterized in that: The process of updating and training the model using a self-iterative deep learning algorithm includes the cloud platform receiving data from each distributed energy storage cabinet, querying the latest data in the database, and updating the prediction model based on the self-iterative deep learning algorithm.

3. The intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm as described in claim 1 or 2, characterized in that: The process of updating and training the model using a self-iterative deep learning algorithm includes backing up the latest data to a cloud database, which is divided into a training set and a test set. The BMS deep learning model uses the voltage and current data of each battery as variables and the temperature of each battery (0-40℃) as the dependent variable. The network layers and activation functions of the deep learning algorithm are set separately and then trained. After the trained data model reaches 95% accuracy through testing on the test set, it is transmitted back to each distributed master controller by the cloud platform. At the same time, if fault data is detected, it will be returned to all distributed nodes.

4. The intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm as described in claim 3, characterized in that: The model-based predictive control and early warning system includes the main controller receiving an updated mathematical model, which will then be applied to the next data acquisition, prediction, comparison, and control of the BMS and liquid cooling system. By predicting and controlling battery temperature in advance, temperature control is implemented for scenarios where an alarm is predicted to be required. If the battery temperature cannot be controlled in advance, power will be cut off according to the threshold.

5. A liquid-cooled energy storage cabinet intelligent monitoring system based on a self-iterative deep learning algorithm, employing the intelligent monitoring method for liquid-cooled energy storage cabinets based on a self-iterative deep learning algorithm as described in any one of claims 1 to 4, characterized in that: It includes a data acquisition module, a BMS module, a data processing module, a control module, and an output module; The acquisition module is used to acquire key temperature and humidity parameters of the liquid-cooled energy storage cabinet in real time. The BMS module is used to collect the voltage, current and temperature parameters of each battery pack in real time and to manage the battery packs. The data processing module is used to clean the collected data, perform edge computing using the trained deep learning model, and store the data. The control module is used to analyze real-time data, predict the operating status of the energy storage cabinet, and automatically adjust the operating parameters of the liquid cooling system based on the status prediction results. The output module is used to train a deep neural network model based on historical data obtained from a distributed database, and to iteratively optimize the deep learning prediction mathematical model corresponding to each distributed energy storage cabinet based on the latest difference.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent monitoring method for liquid-cooled energy storage cabinet based on self-iterative deep learning algorithm as described in any one of claims 1 to 4.

Images