Energy storage cabin intelligent thermal management system based on temperature partitioning and airflow guiding and control method
The intelligent thermal management system based on temperature zoning and airflow guidance solves the problems of uneven temperature, single airflow, control lag and high energy consumption in the air-cooled thermal management system of electrochemical energy storage power stations. It realizes precise temperature control and safe response in the energy storage compartment, and improves the energy efficiency and safety of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-18
- Publication Date
- 2026-03-24
AI Technical Summary
Existing air-cooled thermal management systems for electrochemical energy storage power stations suffer from problems such as uneven temperature distribution, single airflow guidance, lagging control strategies, high energy consumption, and untimely safety response, making it difficult to simultaneously meet the comprehensive requirements of temperature uniformity, optimal energy consumption, and timely safety response.
An intelligent thermal management system based on temperature zoning and airflow guidance is adopted, including a temperature zoning module, an airflow guidance module, an intelligent control module, a scheme generation module, a safety linkage module, a communication module, and a power supply module. Through a three-dimensional temperature field model, a BP neural network prediction model, and a hierarchical safety linkage mechanism, dynamic adjustment and active regulation are achieved.
It achieves precise temperature control within the energy storage compartment, avoids localized hotspots, improves system safety and energy efficiency, and enables proactive prediction and graded response to temperature changes.
Smart Images
Figure CN121726601A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of operation and maintenance and thermal management technology of electrochemical energy storage systems. Specifically, it relates to an intelligent thermal management system and control method for energy storage compartments based on temperature zoning and airflow guidance, which is applicable to temperature control and safety management of air-cooled energy storage compartments. Background Technology
[0002] Currently, electrochemical energy storage power stations generally employ air-cooling systems for thermal management. In existing technologies, typical air-cooling schemes rely on average temperature or a few measuring points for control, using PID algorithms to control the fan start / stop or speed. However, the following prominent problems exist in actual operation: 1. Uneven temperature distribution and complex airflow organization within the battery compartment, with temperature differences of 5~10℃ between the upper and lower layers and between the front and rear areas, and frequent occurrence of local hot spots, leading to decreased cell consistency and accelerated aging.
[0003] 2. The airflow direction is singular and cannot be adjusted. Existing air duct or guide vane designs are mostly fixed structures, which cannot dynamically adjust the direction and flow distribution of cold air according to the real-time temperature distribution, thus limiting the cooling effect.
[0004] 3. The control strategy is lagging and rigid. Traditional constant threshold or simple PID control cannot identify temperature change trends and can only respond passively. It lacks predictive adjustment capability in the early stage of temperature rise.
[0005] 4. There is a lack of a balance mechanism between energy consumption and safety. In order to prevent local overheating, some energy storage systems maintain high wind speed operation all year round, resulting in high energy consumption of the fans, and they may still not respond in time when the temperature rises suddenly.
[0006] 5. The safety linkage mechanism lacks intelligent hierarchical response. Existing systems mostly only alarm or link fire protection after the high temperature trigger point, lacking an active identification and hierarchical response mechanism for "temperature rise rate" or "zone hotspots".
[0007] Based on the above problems, existing thermal management systems are unable to simultaneously meet the comprehensive requirements of temperature uniformity, optimal energy consumption, and timely safety response. Summary of the Invention
[0008] The main objective of this invention is to provide an intelligent thermal management system and control method for energy storage compartments based on temperature zoning and airflow guidance, thereby solving the problems mentioned in the background art.
[0009] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: an intelligent thermal management system for energy storage compartments based on temperature zoning and airflow guidance, including a temperature zoning module, an airflow guidance module, an intelligent control module, a scheme generation module, a safety linkage module, a communication module, and a power supply module; The temperature zoning module is used to zonate and mesh the energy storage compartment, and to build a three-dimensional temperature field model to identify temperature hotspots. The intelligent control module, connected to the temperature zoning module, airflow guidance module, and scheme generation module, predicts the future temperature of the grid, outputs the predicted future temperature value, and sends the temperature prediction data to the scheme generation module. After receiving the scheme generated by the scheme generation module, this module also sends control commands to the airflow guidance module to control the airflow guidance module to execute the adjustment scheme. The scheme generation module is used to provide the adjustment scheme corresponding to the grid and send it to the intelligent control module. The airflow guiding module is used to execute the instructions of the intelligent control module to achieve the cooling operation of the specified grid. The security linkage module is used to perform risk prevention and control work; The communication module is used to enable communication between the various modules; The power supply module is used to supply power to each module.
[0010] Furthermore, the temperature zoning module meshes each zone with a basic spacing; For hot spots, the spacing will be adjusted.
[0011] Furthermore, the intelligent control module incorporates a BP neural network prediction model, including an input layer, a hidden layer, and an output layer; The input layer takes temperature gradient, historical temperature values, and power at the current and historical times as input; The output layer outputs the predicted temperature values for each grid point at future times.
[0012] Furthermore, the execution process of the solution generation module is as follows: A1. Determine the grid i The importance of grids i Importance by its weight Indicates that the grid i adjustment value The expression is: (1); in, , They are grids i The predicted temperature and the optimal temperature; A2. Find the largest adjustment value among all grids, and denote it as... And record the corresponding grid. r ,Will With preset adjustment threshold For comparison: when If the condition is met, it is determined that adjustment is needed; otherwise, it is determined that no adjustment is needed. When adjustment is deemed necessary, the mesh is retrieved from the solution library in the solution generation module. r After determining the adjustment plan, the plan is sent to the intelligent control module, which then issues control commands to complete the adjustment process. A3. Repeat step A2.
[0013] Furthermore, the airflow guiding module includes a ventilation system and an actuator; The angle of the adjustable guide plate and the opening of the louvered damper in the ventilation system can be precisely adjusted by the actuator.
[0014] Furthermore, the safety linkage module adopts a tiered system: when the grid temperature exceeds the low-risk threshold or the heating rate exceeds the low-risk threshold, local forced cooling or power limiting measures are automatically activated. When the grid temperature exceeds the high-risk threshold or the heating rate exceeds the high-risk threshold, the linkage fire protection system will issue an alarm and activate the fire extinguishing system.
[0015] Furthermore, the grid temperature in the hierarchical system includes the real-time temperature in the three-dimensional temperature field model and the future temperature prediction value output by the intelligent control module.
[0016] Furthermore, the communication module employs a combination of wired and wireless communication.
[0017] Furthermore, the power module uses a distributed power supply method.
[0018] This invention also provides an intelligent thermal management control method for energy storage compartments based on temperature zoning and airflow guidance. Based on the above system, the method includes the following steps: S1. The temperature zoning module controls the energy storage compartment to perform zoning and gridding operations. S2. Based on the temperature data collected by the array sensor, construct a three-dimensional temperature field model using spatial interpolation; S3, the intelligent control module, predicts the future temperature of the grid, outputs the predicted future temperature value, and sends the temperature prediction data to the scheme generation module and the safety linkage module; S4. The scheme generation module first determines whether adjustment is needed. If adjustment is needed, it combines the scheme library in the scheme generation module to provide the adjustment scheme corresponding to the grid point to be adjusted, and sends the adjustment scheme to the intelligent control module. S5. After receiving the scheme generated by the scheme generation module, the intelligent control module sends a control command to the airflow guidance module to control the airflow guidance module to execute the adjustment scheme. S6, the safety linkage module uses both real-time temperature and predicted temperature as the basis for protection and takes protective measures.
[0019] Beneficial effects: (1) The three-dimensional temperature field based on the grid can obtain the local temperature information of the energy storage compartment more accurately and avoid the occurrence of hot spots with extremely high local temperatures.
[0020] (2) The BP neural network prediction model can predict the future temperature of the temperature field, realize active adjustment, and avoid overheating of the temperature grid.
[0021] (3) The safety linkage module uses both real-time temperature and predicted temperature as the basis for protection, which can further improve the safety of the system.
[0022] (4) Introducing adjustment values can quantify the urgency of the adjustment and improve the rationality of the adjustment plan. Attached Figure Description
[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 This is a block diagram showing the connections between the modules of the system of this invention; Figure 2 This is a flowchart of the decision-making process in the solution generation module; Figure 3 This is a flowchart of the method steps of the present invention. Detailed Implementation
[0024] Example 1 like Figures 1-2 As shown, the intelligent thermal management system for energy storage compartments based on temperature zoning and airflow guidance includes: a temperature zoning module, an airflow guidance module, an intelligent control module, a scheme generation module, a safety linkage module, a communication module, and a power supply module. The temperature zoning module divides the energy storage compartment into upper, middle, and lower zones based on spatial location. Each zone is equipped with a temperature sensor array, with a density of one sensor per 0.5 m, to collect temperature data in real time. A three-dimensional temperature field model is constructed through spatial interpolation to identify temperature hotspots. This embodiment uses the inverse distance-weighted interpolation method as an example, and provides the detailed steps for constructing a three-dimensional temperature field model through spatial interpolation as follows: The sensor's coordinates are calibrated, with the lower left corner of the cabin as the origin. Then the... i The three-dimensional coordinates of the sensors are ( x i , y i , z i ),in, x axis y axis z The axes are the length, width, and height directions, respectively. The measured temperature of this sensor is denoted as... T i ; Outliers were removed using the 3σ criterion, where σ is the standard deviation of the measured temperature of each sensor layer. T 0 is the mean, for the th i One sensor: (1); At this time, the i The measured temperature of each sensor is an outlier and is removed. After removing all outliers, missing values need to be filled in. For a given missing location, the number of adjacent sensors is... k This position is adjacent to the first j The spatial location of each sensor is denoted as d j Then the fill value for the missing position T m for: (2); For each layer, a mesh is created, with the basic mesh spacing set as follows. x The foundation spacing of the shafts is 0.5m. y The foundation spacing of the shafts is 0.5m. z The base spacing of the shafts is 0.3m. This is suitable for areas prone to hotspots, such as areas with densely packed battery cells and ventilation dead zones. x axis y The shaft spacing was adjusted to 0.3m; For any target grid node on the grid in space ( x , y , z Temperature at this grid point T The expression is: (3); in, p This is the power exponent, usually taken as 2, but can be adjusted through cross-validation. The larger this value, the higher the weighting of the nearest point. n This represents the total number of sensors in this layer.
[0025] The intelligent control module predicts the future temperature of the grid, outputs the predicted future temperature value, and sends the temperature prediction data to the scheme generation module. After receiving the scheme generated by the scheme generation module, this module also sends control commands to the airflow guidance module to control the airflow guidance module to execute the adjustment scheme. The intelligent control module has a built-in prediction model based on a BP neural network, which includes an input layer, a hidden layer, and an output layer. The input layer has 8 neurons, which correspond to the temperature gradient, the temperature values at 5 historical time points, the load power at the current time point, and the load power at 1 historical time point, respectively. The hidden layers are divided into hidden layer 1 and hidden layer 2; The activation function for hidden layer 1 is the sigmoid function, whose expression is: (4); Hidden layer 1 has 24 neurons, and its output can be represented as: (5); in, x i For the first in a set of input data i One element, h j1 For the first hidden layer 1 j One output, w ij1 For the first hidden layer 1 i The input data corresponds to the first... j The weights of each neuron, b j1 For the second hidden layer j Bias of each neuron; The activation function for hidden layer 2 is the Leaky ReLU function, whose expression is: (6); in, It should be a small positive number, such as 0.01, to avoid the problem of the gradient being 0; Hidden layer 2 has 12 neurons, and its output can be represented as: (7); in, h j2 For the second hidden layer j One output, w ij2 For the second hidden layer i The input data corresponds to the first... j The weights of each neuron, b j2 For the second hidden layer j Bias of each neuron; The output layer outputs the predicted temperature for each grid cell over the next 3-5 minutes, with a step size of 30 seconds. Number of neurons and number of grids in the output layer m Consistent, its output expression is: (8); in, h jo For the output layer's first j One output, w ijo For the output layer iThe input data corresponds to the first... j The weights of each neuron, b jo For the output layer j Bias of each neuron; The grid-predicted temperatures output by the output layer can form a temperature prediction field; The total number of samples is 4000, the learning rate is 0.001, the batch size is 32, and the maximum number of training rounds is 200. During the training process, the samples are divided into training set and validation set in a ratio of 8:2. After one round of training on the training set, the validation set is used for validation. The loss function used in the model is the mean squared error (MSE), which measures the deviation between the predicted and actual values. The loss function expression for each batch of validation sets is as follows: (9); in, and These represent the actual and predicted temperature values, respectively. After traversing the validation set, the average of the loss function values for all batches of the validation set is calculated; this value is the weighted error. The model's validation set contains 800 samples, divided into 25 batches; therefore, the weighted error... The expression is: (10); The minimum number of training epochs is set to 100, and the training stopping strategy is: training stops when the maximum number of training epochs is reached. Once the minimum number of training rounds has been reached, the weighted error is assessed. If the weighted error decreases by less than the early stopping threshold 1e-6 for 15 consecutive rounds, training is stopped.
[0026] The scheme generation module, based on the importance of the grid and the temperature of each grid, first determines whether adjustment is needed. If adjustment is required, it then uses the scheme library in the scheme generation module to provide adjustment schemes for the grid points to be adjusted. The determination process is as follows: A1. Determine the grid i The importance of grids i Importance by its weight express; A2. Determine whether the grid needs adjustment based on the judgment threshold. If adjustment is needed, identify the grid. r corresponds to The adjustment scheme was adopted to complete the adjustment process; A3. Repeat step A02.
[0027] Define the grid i The importance of grids i Importance by its weight Indicates that the grid i adjustment value The expression is: (11); in, , They are grids i The predicted temperature and the optimal temperature; Find the largest adjustment value among all grids, and denote it as... And record the corresponding grid. r ,Will With preset adjustment threshold For comparison: when If the condition is met, it is determined that adjustment is needed; otherwise, it is determined that no adjustment is needed. When adjustment is deemed necessary, the mesh is retrieved from the solution library in the solution generation module. r After determining the adjustment plan, the plan is sent to the intelligent control module, which then issues control commands to complete the adjustment process. After adjustment is completed, the scheme generation module continues to search for the largest adjustment value among all grids, determines whether adjustment is needed, and repeats this process to achieve automatic adjustment.
[0028] The airflow guiding module is installed at both the bottom and top of the energy storage compartment, and includes a ventilation system and an actuator. The actuator can precisely adjust the angle of the adjustable guide plate and the opening of the louvered damper in the ventilation system. The actuator adjusts the angle of the adjustable guide plate and the opening of the louvered damper according to the control commands output by the intelligent control module, thereby adjusting the airflow path and distribution ratio to achieve the cooling operation of the specified grid.
[0029] The safety linkage module adopts a tiered system: when the zone temperature exceeds the threshold of 50... o C or the rate of temperature increase exceeds the low-risk threshold 2. o When the temperature reaches C / min, local forced cooling or power limiting measures will be automatically activated. When the zone temperature exceeds the threshold of 70 o C or the rate of temperature increase exceeds the high-risk threshold 4 o When C / min, the fire suppression system will issue an alarm and activate the fire extinguishing system; The safety linkage module provides protection based not only on real-time temperature but also on predicted temperature, achieving dual protection.
[0030] The communication module is used for communication between various modules within the system; the communication module uses both wired and wireless communication methods.
[0031] The power supply module is used to supply power to the various modules inside the system; since the thermal management system is widely distributed, a distributed power supply method is used.
[0032] Example 2 like Figure 2 As shown in the figure, this embodiment presents an intelligent thermal management control method for energy storage compartments based on temperature zoning and airflow guidance, including the following steps: S1. The temperature zoning module controls the energy storage compartment to perform zoning and gridding operations. S2. Based on the temperature data collected by the array sensor, construct a three-dimensional temperature field model using spatial interpolation; S3, the intelligent control module, predicts the future temperature of the grid, outputs the predicted future temperature value, and sends the temperature prediction data to the scheme generation module and the safety linkage module; S4. The scheme generation module first determines whether adjustment is needed. If adjustment is needed, it combines the scheme library in the scheme generation module to provide the adjustment scheme corresponding to the grid point to be adjusted, and sends the adjustment scheme to the intelligent control module. S5. After receiving the scheme generated by the scheme generation module, the intelligent control module sends a control command to the airflow guidance module to control the airflow guidance module to execute the adjustment scheme. S6, the safety linkage module uses both real-time temperature and predicted temperature as the basis for protection and takes protective measures.
[0033] The above embodiments are merely preferred technical solutions of the present invention and should not be considered as limitations on the present invention. The scope of protection of the present invention should be limited to the technical solutions described in the claims, including equivalent substitutions of the technical features described in the claims. That is, equivalent substitutions and improvements within this scope are also within the scope of protection of the present invention.
Claims
1. An intelligent thermal management system for energy storage compartments based on temperature zoning and airflow guidance, characterized in that, It includes a temperature zoning module, an airflow guidance module, an intelligent control module, a solution generation module, a safety linkage module, a communication module, and a power supply module; The temperature zoning module is used to zonate and mesh the energy storage compartment, and to build a three-dimensional temperature field model to identify temperature hotspots. The intelligent control module, connected to the temperature zoning module, airflow guidance module, and scheme generation module, predicts the future temperature of the grid, outputs the predicted future temperature value, and sends the temperature prediction data to the scheme generation module. After receiving the scheme generated by the scheme generation module, this module also sends control commands to the airflow guidance module to control the airflow guidance module to execute the adjustment scheme. The scheme generation module is used to provide the adjustment scheme corresponding to the grid and send it to the intelligent control module. The airflow guiding module is used to execute the instructions of the intelligent control module to achieve the cooling operation of the specified grid. The security linkage module is used to perform risk prevention and control work; The communication module is used to enable communication between the various modules; The power supply module is used to supply power to each module.
2. The thermal management system according to claim 1, characterized in that, The temperature zoning module meshes each zone using a basic spacing. For hot spots, the spacing will be adjusted.
3. The thermal management system according to claim 1, characterized in that, The intelligent control module has a built-in BP neural network prediction model, including an input layer, a hidden layer, and an output layer. The input layer takes temperature gradient, historical temperature values, and power at the current and historical times as input; The output layer outputs the predicted temperature values for each grid point at future times.
4. The thermal management system according to claim 1, characterized in that, The execution process of the solution generation module is as follows: A1. Determine the grid i The importance of grid i Importance by its weight Indicates that the grid i adjustment value The expression is: （1）； in, , They are grids i The predicted temperature and the optimal temperature; A2. Find the largest adjustment value among all grids, and denote it as... And record the corresponding grid. r ,Will With preset adjustment threshold For comparison: when If the condition is met, it is determined that adjustment is needed; otherwise, it is determined that no adjustment is needed. When adjustment is deemed necessary, the mesh is retrieved from the solution library in the solution generation module. r After determining the adjustment plan, the plan is sent to the intelligent control module, which then issues control commands to complete the adjustment process. A3. Repeat step A2.
5. The thermal management system according to claim 1, characterized in that, The airflow guidance module includes a ventilation system and an actuator; The angle of the adjustable guide plate and the opening of the louvered damper in the ventilation system can be precisely adjusted by the actuator.
6. The thermal management system according to claim 1, characterized in that, The safety linkage module adopts a graded system: when the grid temperature exceeds the low danger threshold or the heating rate exceeds the low danger threshold, local strong cooling or power limiting measures are automatically activated. When the grid temperature exceeds the high-risk threshold or the heating rate exceeds the high-risk threshold, the linkage fire protection system will issue an alarm and activate the fire extinguishing system.
7. The thermal management system according to claim 6, characterized in that, The grid temperature in the hierarchical system includes the real-time temperature in the three-dimensional temperature field model and the future temperature prediction value output by the intelligent control module.
8. The thermal management system according to claim 1, characterized in that, The communication module uses both wired and wireless communication.
9. The thermal management system according to claim 1, characterized in that, The power module uses a distributed power supply method.
10. A method for intelligent thermal management control of an energy storage compartment based on temperature zoning and airflow guidance, used in the system according to any one of claims 1 to 9, comprising the following steps: S1. The temperature zoning module controls the energy storage compartment to perform zoning and gridding operations. S2. Based on the temperature data collected by the array sensor, construct a three-dimensional temperature field model using spatial interpolation; S3, the intelligent control module, predicts the future temperature of the grid, outputs the predicted future temperature value, and sends the temperature prediction data to the scheme generation module and the safety linkage module; S4. The scheme generation module first determines whether adjustment is needed. If adjustment is needed, it combines the scheme library in the scheme generation module to provide the adjustment scheme corresponding to the grid point to be adjusted, and sends the adjustment scheme to the intelligent control module. S5. After receiving the scheme generated by the scheme generation module, the intelligent control module sends a control command to the airflow guidance module to control the airflow guidance module to execute the adjustment scheme. S6, the safety linkage module uses both real-time temperature and predicted temperature as the basis for protection and takes protective measures.