CN116776746A - Energy storage liquid cooling temperature control optimizing system based on fluid dynamics - Google Patents
Energy storage liquid cooling temperature control optimizing system based on fluid dynamics Download PDFInfo
- Publication number
- CN116776746A CN116776746A CN202311040877.9A CN202311040877A CN116776746A CN 116776746 A CN116776746 A CN 116776746A CN 202311040877 A CN202311040877 A CN 202311040877A CN 116776746 A CN116776746 A CN 116776746A
- Authority
- CN
- China
- Prior art keywords
- battery
- temperature
- cooling
- target
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 89
- 239000012530 fluid Substances 0.000 title claims abstract description 50
- 238000004146 energy storage Methods 0.000 title claims abstract description 28
- 239000007788 liquid Substances 0.000 title claims abstract description 25
- 239000000110 cooling liquid Substances 0.000 claims abstract description 75
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 73
- 238000005457 optimization Methods 0.000 claims abstract description 52
- 230000002787 reinforcement Effects 0.000 claims abstract description 43
- 230000000694 effects Effects 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 238000005265 energy consumption Methods 0.000 claims description 20
- 230000007613 environmental effect Effects 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 18
- 230000009471 action Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000000704 physical effect Effects 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 5
- 239000002826 coolant Substances 0.000 description 36
- 230000001105 regulatory effect Effects 0.000 description 10
- 239000012809 cooling fluid Substances 0.000 description 8
- 238000000034 method Methods 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 239000000126 substance Substances 0.000 description 6
- 238000011217 control strategy Methods 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 3
- 238000013021 overheating Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 230000002277 temperature effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Fluid Mechanics (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Secondary Cells (AREA)
Abstract
The application provides an energy storage liquid cooling temperature control optimizing system based on fluid dynamics and deep reinforcement learning, which aims to realize the efficient cooling and temperature equalizing effects of a battery; the system comprises a temperature control module, a flow rate adjusting module, a flow direction adjusting module and an optimizing algorithm module, wherein the temperature control module is responsible for monitoring the working state of the battery and providing data, and simultaneously determining the target flow rate and flow direction of the cooling liquid; the core optimization algorithm module combines a fluid dynamics model and a deep reinforcement learning algorithm, can predict the flowing state and temperature distribution of cooling liquid in the battery and generate an optimal cooling strategy, and the system provides a high-efficiency self-adaptive cooling solution, meets the cooling requirement of the battery and prolongs the service life of the battery.
Description
Technical Field
The application relates to the field of temperature control of energy storage devices, in particular to an energy storage liquid cooling temperature control optimizing system based on fluid dynamics.
Background
With the development of battery technology, batteries are increasingly used in a variety of fields, such as electric vehicles, renewable energy storage, portable electronic devices, and the like. Cooling techniques become critical in order to ensure battery performance and life. Conventional battery cooling systems often rely on empirical designs and static control strategies, which may be insufficient in some cases to cope with complex operating environments and dynamic load changes.
Fluid dynamics provides a tool for understanding and simulating coolant flow, but it is difficult to optimize complex battery cooling strategies in real time solely by fluid dynamics. On the other hand, deep reinforcement learning has recently demonstrated its potential for optimizing strategies in a number of fields, but its application in the field of battery cooling is still relatively small.
The operating state and temperature of the battery have a direct impact on its performance and life. Too high or too low a temperature can cause damage to the battery, leading to reduced battery life and even failure.
In order to overcome the challenges, the application provides an energy storage liquid cooling temperature control optimizing system based on fluid dynamics and deep reinforcement learning. The system aims to dynamically adjust the flow speed and the flow direction of the cooling liquid and realize the high-efficiency cooling and the uniform temperature effect of the battery.
Disclosure of Invention
The application provides an energy storage liquid cooling temperature control optimizing system based on fluid dynamics and deep reinforcement learning, which is used for improving the cooling efficiency and the temperature equalizing effect of a battery.
The application provides an energy storage liquid cooling temperature control optimizing system, which comprises:
the temperature control module is used for monitoring the working state of the battery and providing the monitored data for the optimization algorithm module; determining a target flow rate and a target flow direction of the cooling liquid according to a preset temperature target; the target flow velocity and the target flow direction are respectively sent to a flow velocity adjusting module and a flow direction adjusting module so as to dynamically adjust the flow velocity and the flow direction of the cooling liquid;
the flow rate adjusting module is used for receiving the target flow rate provided by the temperature control module and adjusting the flow rate of the cooling liquid according to the target flow rate; receiving an optimal cooling liquid flow rate strategy from an optimization algorithm module, and precisely controlling a cooling effect by adjusting the flow rate of cooling liquid;
the flow direction adjusting module is used for receiving the target flow direction provided by the temperature control module and adjusting the flow direction of the cooling liquid according to the target flow direction; receiving an optimal cooling liquid flow strategy from an optimization algorithm module, and realizing the temperature equalizing effect of the battery by adjusting the flow direction of cooling liquid;
the optimization algorithm module is used for receiving the working state data from the temperature control module; predicting the flowing state of the cooling liquid in the battery pack and the temperature distribution of the battery by using a fluid dynamic model; generating optimal cooling liquid flow velocity and flow direction strategies according to the predicted flowing state of cooling liquid in the battery pack and the temperature distribution of each battery by utilizing a deep reinforcement learning algorithm and combining the received working state data, and feeding back the strategies to a flow velocity adjusting module and a flow direction adjusting module; the deep reinforcement learning algorithm uses the predicted output of the fluid dynamic model as environmental feedback to update and optimize the decision strategy; the decision output of the deep reinforcement learning is used as the input of a fluid dynamics model to predict the temperature distribution of the battery in the next step.
Still further, the preset temperature target t_target is determined by the following formula:
；
where t_optimal is the average of the optimal operating temperatures of each battery in the battery, soc_avg is the average battery state of charge of the batteries in the battery, soc_std is the standard deviation of the battery state of charge of the batteries in the battery, I is the average operating current of the batteries in the battery, i_nominal is the average of the rated operating currents of the batteries in the battery, P is the power consumption of the cooling system, p_nominal is the rated power consumption of the cooling system, k1, k2, k3, k4 are adjustable coefficients.
Still further, the target flow rate F_speed is determined according to the following formula:
；
where t_current is the average temperature of the cells in the battery, t_target is the preset temperature target, Δt/Δt is the rate of change of the average temperature of the cells in the battery, and k5 and k6 are adjustable coefficients.
Further, the target flow directionAccording to the following formula:
；
wherein Ti is current Is the current temperature of cell i in the battery, ti target Is the target temperature of battery i in the battery pack, and n is the number of batteries.
Still further, the Ti is target The calculation formula of (2) is as follows:
；
where Ti_optimal is the optimal operating temperature of battery I in the battery, SOCi is the current state of charge of battery I in the battery, SOC_optimal is the optimal state of charge of battery I in the battery, ii is the current operating current of battery I in the battery, I_optimal is the optimal operating current of battery I in the battery, T_env_optimal is the optimal ambient temperature of battery I in the battery, k7, k8, and k9 are adjustable coefficients.
Still further, the hydrodynamic model uses a microscopic temperature model provided by COMSOL Multiphysics software to model each cell in the battery.
Still further, the inputs to the fluid dynamics model include physical properties of the cooling fluid, including density, viscosity, thermal conductivity; the structural characteristics of the battery pack include arrangement and connection modes of the batteries; and the flow rate and direction of the cooling liquid.
Still further, the actions in the deep reinforcement learning algorithm are defined as changing the flow rate and direction of the coolant.
Still further, the deep reinforcement learning reward function R is defined as:
；
wherein R_temp, R_efficiency, R_energy, and R_uniformity represent rewards in terms of battery temperature, cooling efficiency, energy consumption, and temperature equalizing effect, respectively, and w1, w2, w3, and w4 are weights thereof; the calculation of R_temp considers the operating temperature of the battery and provides a high prize value for the battery temperature in the ideal temperature range; r_efficiency is calculated based on cooling efficiency, which provides a high prize value when exceeding a set efficiency threshold; r_energy calculation considers the energy consumption of the cooling system, and provides a high rewarding value when the energy consumption is lower than a set energy consumption threshold value; the calculation of R_uniformity is based on the temperature equalizing effect, and provides a high rewarding value when the flow direction of the cooling liquid reaches a set temperature equalizing effect threshold value.
Furthermore, the deep reinforcement learning algorithm uses the predicted output of the fluid dynamics model as environmental feedback and uses the decision output of the deep reinforcement learning algorithm as the input of the fluid dynamics model, and the predicted output and the decision output form a closed loop, so that the battery temperature control optimization is realized through continuous interaction and learning.
Conventional temperature control systems typically rely on static strategies or manual intervention. The system provided by the application combines fluid dynamics with deep reinforcement learning, and provides a self-adaptive and dynamic method for battery cooling. This combination is itself innovative. The flow rate and direction of the cooling fluid may be dynamically adjusted using deep reinforcement learning predictive and optimized cooling strategies rather than employing a fixed or preset flow rate. There is an interactive feedback loop between the optimization algorithm module and the flow rate and direction adjustment module, so that the system is gradually optimized in multiple iterations, which is beyond the scope of a simple feed-forward control system.
The technical scheme provided by the application has the beneficial effects that:
(1) And (3) high-efficiency cooling: by dynamically adjusting the flow speed and flow direction of the cooling liquid, the system can rapidly and efficiently cool according to actual needs, thereby reducing energy waste and improving cooling efficiency.
(2) And (3) uniformly cooling: the flow direction regulating module ensures uniform cooling of the battery as a whole. The uniform cooling not only improves the performance of the battery, but also extends the service life of the battery, since it avoids the problem of local overheating of the battery.
(3) Prolonging the service life of the battery: too high or too low a temperature may cause damage to the battery. By optimizing the cooling strategy, the battery can operate within a desired temperature range, thereby extending its life.
(4) Automating and reducing manual intervention: the automatic optimization strategy based on deep reinforcement learning can reduce or eliminate the need for manual intervention, thereby reducing the operating cost and error rate.
Drawings
Fig. 1 is a schematic diagram of an energy storage liquid cooling temperature control optimization system based on fluid dynamics according to a first embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may be embodied in many other forms than those herein described, and those skilled in the art will readily appreciate that the present application may be similarly embodied without departing from the spirit or essential characteristics thereof, and therefore the present application is not limited to the specific embodiments disclosed below.
The first embodiment of the application provides an energy storage liquid cooling temperature control optimizing system based on fluid dynamics. Referring to fig. 1, a schematic diagram of a first embodiment of the present application is shown. A first embodiment of the present application is described in detail below with reference to fig. 1, where the system is an energy storage liquid cooling temperature control optimization system based on fluid dynamics.
The energy storage liquid cooling temperature control optimizing system is one specific cooling system and is used mainly in battery and other energy storage equipment to maintain the battery and other energy storage equipment in ideal operation temperature range. The energy storage liquid cooling temperature control optimizing system provided by the embodiment comprises a temperature control module 101, a flow speed adjusting module 102, a flow direction adjusting module 103 and an optimizing algorithm module 104.
The temperature control module 101 is configured to monitor an operating state of the battery, and provide the monitored data to the optimization algorithm module; determining a target flow rate and a target flow direction of the cooling liquid according to a preset temperature target; and the target flow velocity and the target flow direction are respectively sent to a flow velocity adjusting module and a flow direction adjusting module so as to dynamically adjust the flow velocity and the flow direction of the cooling liquid.
The temperature control module 101 may include a control unit and a sensor. The temperature control module 101 may include a plurality of sensors distributed at various critical locations of the battery. The sensors can monitor the working states of the battery, such as temperature, voltage, current and the like in real time. Among them, temperature sensors are the most critical parts, which can collect temperature data of the battery in real time and transmit the data to the control unit. In addition, in large battery systems, such as battery packs of electric vehicles or large energy storage systems, it is possible to include a plurality of batteries distributed in different locations.
The control unit is the core of the temperature control module and is responsible for adjusting the flow rate and the flow direction of the cooling liquid according to the input signals of the sensor and a preset temperature target. Specifically, the control unit compares the measured battery temperature with a preset temperature target in real time, and determines a target flow rate and a target flow direction of the coolant based on the measured battery temperature and the preset temperature target. The target flow rate and the target flow direction are respectively sent to a flow rate adjusting module and a flow direction adjusting module to guide the flow rate and the flow direction of the cooling liquid to be adjusted. The preset temperature target is a temperature determined to be most suitable for the operation of the batteries in the battery pack according to the operation state of the batteries and the environmental conditions. The present embodiment provides a formula for calculating a preset temperature target as follows:
；
wherein:
t_target is a preset temperature target;
t_optimal is the average of the optimal operating temperatures of each cell in the battery;
soc_avg is the average battery state of charge of the batteries in the battery pack;
soc_std is the standard deviation of the battery state of charge of the batteries in the battery pack;
i is the average operating current of the cells in the battery pack, and I_nominal is the average of the rated operating currents of the cells in the battery pack;
p is the power consumption of the cooling system, and P_nominal is the rated power consumption of the cooling system;
k1 K2, k3 are adjustable coefficients representing the degree of influence of SOC, I, P on a preset temperature target;
k4 is a coefficient indicating the degree of influence of the SOC difference on the preset temperature target.
The formula comprehensively considers the actual working state of the battery, and can more accurately determine the preset temperature target, thereby realizing better temperature management.
Here, SOC is an abbreviation of "State of Charge", i.e., battery State of Charge. This is an important indicator of the remaining battery power, typically expressed as a percentage. For example, when a battery is fully charged, its SOC is 100%; when the battery is fully discharged, its SOC is 0%.
According to the real-time temperature of the battery and a preset temperature target, the temperature control module can determine the target flow rate and the target flow direction of the cooling liquid. For example, when the actual temperature of the battery is higher than the temperature target, the temperature control module may increase the flow rate of the cooling liquid or change the flow direction of the cooling liquid to enhance the cooling effect. When the actual temperature of the battery is lower than the temperature target, the temperature control module can reduce the flow rate of the cooling liquid or keep the flow direction of the cooling liquid unchanged so as to save energy.
The present embodiment proposes a method of calculating a target flow rate (F_speed) and a target flow direction (F direction ) The formula of (2) is as follows:
；
；
here, t_current is the average temperature of the cells in the battery packT_target is a preset temperature target, deltaT/Deltat is the rate of change of the average temperature of all cells, ti current Is the current temperature of battery i, ti target Is the target temperature of battery i, and n is the number of batteries. k5 And k6 is an adjustable coefficient.
In this formula, the flow rate of the coolant is adjusted according to the difference between the current battery temperature and the target temperature and the rate of change of the temperature. When the battery temperature is higher than the target temperature, or the temperature rise rate is too high, the flow rate of the cooling liquid is increased to enhance the cooling effect.
The flow direction of the cooling liquid is determined according to the average value of the difference between the current temperature and the target temperature of each battery cell. By adjusting the flow direction of the cooling liquid, it is possible to preferentially cool the battery having a temperature higher than the target temperature, thereby more effectively reducing the temperature of the entire battery.
The target temperature ti_target of the battery i may be determined according to various factors. Generally, this target temperature will depend on the operating state of the battery, the environmental conditions, and the chemical and physical properties of the battery.
(1) The operating state of the battery: the battery generates heat when charged and discharged. At high loads (e.g., high current charge or discharge), the battery may generate more heat, so we may need to set a lower target temperature to prevent the battery from overheating. At low loads (e.g., low current charge or discharge), the battery generates less heat, and therefore a higher target temperature may be set to improve energy efficiency.
(2) Environmental conditions: the temperature and humidity of the environment also affect the temperature of the battery. In a hot environment, it may be desirable to set a lower target temperature to prevent overheating of the battery. In cold environments, it may be desirable to set a higher target temperature to maintain battery performance.
(3) Chemical and physical properties of the battery: different types of batteries (e.g., lithium ion batteries, nickel hydrogen batteries, etc.) have different optimal operating temperature ranges. In addition, the capacity, shape, material, etc. of the battery also affect its thermal performance. Therefore, it is necessary to set an appropriate target temperature according to specific chemical and physical properties of the battery.
The present embodiment provides the following calculation of Ti target Is defined by the formula:
；
here, ti_optimal is the optimal operating temperature of battery I in the battery, SOCi is the current state of charge of battery I in the battery, soc_optimal is the optimal state of charge of battery I in the battery, i_optimal is the optimal operating current of battery I in the battery, and t_env_optimal is the optimal ambient temperature of battery I in the battery. k7 K8, and k9 are adjustable coefficients that can be adjusted according to the specific chemical and physical properties of the battery and the temperature control requirements.
In the above formulas, the optimum operating temperature (ti_optimal), the optimum state of charge (soc_optimal), the optimum operating current (i_optimal), and the optimum ambient temperature (t_env_optimal) are generally determined based on a large amount of experimental data, physical and chemical characteristics of the battery, and design and use requirements of the battery.
(1) Optimum operating temperature (t_optimal): the optimum operating temperature of a battery is generally determined at the stage of its design, which involves factors such as the chemical reaction rate of the battery material, the ion-conducting efficiency of the electrolyte, and the like. In the laboratory, the optimum operating temperature of a battery can be determined by testing its performance (e.g., charge/discharge efficiency, rate of capacity fade, etc.) at different temperatures.
(2) Optimal battery state of charge (soc_optimal): optimal battery state of charge generally refers to the state of charge at which the battery is able to reach its designed life, maintain good performance, and operate under safe conditions. It may be affected by various factors such as the chemical composition of the battery, structural design, charge/discharge strategy, etc. Laboratory tests and long-term tracking experiments can help determine this value.
(3) Optimum operating current (i_optimal): the optimal operating current generally means that at this current, the battery achieves the desired charge and discharge efficiency while maintaining good stability and safety. This value can be determined by laboratory testing and simulation.
(4) Optimum ambient temperature (t_env_optimal): optimal ambient temperature generally means the temperature at which the cooling or heating requirements of the battery system are minimal and the energy efficiency is highest. This value will typically be close to or equal to the optimal operating temperature of the battery.
The above four values are generally required to be determined by comprehensively considering various factors such as actual application scenes of the battery, user requirements, and design goals of the system. In practical applications, it may be necessary to dynamically adjust and optimize the battery in consideration of the aging degree of the battery, the change of the environmental conditions, and the like.
The flow rate adjusting module 102 is configured to receive the target flow rate provided by the temperature control module, and adjust the flow rate of the cooling liquid according to the target flow rate; and receiving an optimal cooling liquid flow rate strategy from the optimization algorithm module, and precisely controlling the cooling effect by adjusting the flow rate of the cooling liquid.
The flow rate adjustment module 102 is one of the core components of the hydrodynamically-based stored-energy-liquid cooling temperature control optimization system. The following is a detailed description of the flow rate adjustment module 102:
the flow rate adjustment module 102 is mainly composed of a control unit, a flow rate adjustment valve, a driving device (e.g., an electric or pneumatic motor), and a feedback sensor. The flow rate regulating valve is a main device for regulating the flow rate of the cooling liquid, and the opening degree thereof can be precisely controlled by a driving device. The feedback sensor is used for monitoring the flow rate of the cooling liquid in real time and feeding back the actual flow rate data to the control unit. The main function of the control unit is to receive and process information received from the respective sensors and to adjust the driving device according to these information and a predetermined control strategy, thereby affecting the opening degree of the flow rate adjustment valve and changing the flow rate of the coolant.
After receiving the flow rate adjustment command sent by the temperature control module 101, the flow rate adjustment module adjusts the flow rate of the cooling liquid by changing the opening of the flow rate adjustment valve. When the actual temperature of the battery is higher than the set temperature target, the flow rate adjustment module increases the flow rate of the cooling liquid to enhance the cooling effect. When the actual temperature of the battery is lower than the set temperature target, the flow rate adjusting module reduces the flow rate of the cooling liquid to save energy.
The flow control strategy refers to how the coolant flow rate should be adjusted to optimize cooling and energy efficiency. This strategy is not a constant one but is dynamically determined based on the real-time operating conditions of the battery and environmental factors.
This flow control strategy is determined by the optimization algorithm module 104. The optimization algorithm module 104 may take into account the real-time temperature of the battery, the operating conditions (e.g., current, voltage of the battery, etc.), the actual flow rate of the coolant, and possibly other factors.
The optimization algorithm module adopts a fluid dynamics model and a deep reinforcement learning algorithm. The fluid dynamics model predicts how the cooling effect and energy efficiency will change after changing the flow rate and flow direction of the cooling fluid. The deep reinforcement learning algorithm can learn some deep rules and relations from the historical data so as to make more accurate predictions.
The optimization algorithm module 104 combines these factors with the model to calculate the optimal coolant flow rate for the current situation and sends the optimal coolant flow rate to the flow adjustment module 102. The flow rate adjustment module 102 performs further optimal adjustment of the flow rate according to the received optimal coolant flow rate, thereby precisely controlling the cooling effect.
The flow rate adjusting module needs to interact with the temperature control module and the optimization algorithm module. The temperature control module determines a preset temperature target according to the working state of the battery and the environmental condition, and determines a target flow rate of the cooling liquid. The flow direction regulating module regulates the flow direction of the cooling liquid according to the target flow speed sent by the temperature control module, and the optimizing algorithm module regulates the working strategy of the flow speed regulating module according to the predicted battery temperature change condition.
The flow direction adjusting module 103 is configured to receive the target flow direction provided by the temperature control module, and adjust the flow direction of the cooling liquid according to the target flow direction; and receiving an optimal cooling liquid flow strategy from an optimization algorithm module, and realizing the temperature equalizing effect of the battery by adjusting the flow direction of the cooling liquid.
The main task of the flow direction adjustment module 103 is to adjust the flow direction of the cooling liquid in the battery pack to achieve the temperature equalizing effect of the cells, i.e. to make the temperature of each cell in the battery pack as close as possible.
The flow direction adjusting module 103 mainly includes a flow direction adjusting valve, a driving device (e.g., an electric or pneumatic motor), a feedback sensor, and the like. The flow direction regulating valve is a main device for regulating the flow direction of the cooling liquid, and it can change its position by driving the device, thereby changing the flow direction of the cooling liquid. The feedback sensor is responsible for monitoring the actual flow direction of the coolant in the battery pack and feeding back these information to the control unit.
Upon receiving the target flow direction from the temperature control module 101, the flow direction adjustment module 103 adjusts the flow direction of the coolant by changing the position of the flow direction adjustment valve. The flow direction adjustment strategy is provided by an optimization algorithm module 104 that calculates an optimal coolant flow direction based on the real-time temperature and operating conditions of the battery, and the actual coolant flow direction, using a fluid dynamics model and a deep reinforcement learning algorithm. The flow direction adjustment module 103 further adjusts the flow direction of the cooling fluid according to the optimal cooling fluid flow direction.
The flow direction of the cooling liquid directly affects the cooling effect of each battery. Some cells may be hotter than others, requiring more cooling. By changing the flow direction of the coolant, more coolant can be allowed to flow through the hotter cells, thereby improving their cooling effect. Conversely, if the temperature of some of the cells is already low enough, coolant flow through the cells may be reduced to conserve energy.
In actual operation, the flow direction adjustment module needs to continuously adjust the flow direction of the cooling liquid to cope with the continuous change of the battery temperature and the operating state. By means of the dynamic adjustment, the temperature distribution of the battery pack can be as uniform as possible, the performance and service life of the battery are improved, and the energy consumption is reduced.
The optimization algorithm module 104 receives the working state data from the temperature control module; predicting the flowing state of the cooling liquid in the battery pack and the temperature distribution of the battery by using a fluid dynamic model; generating optimal cooling liquid flow velocity and flow direction strategies according to the predicted flowing state of cooling liquid in the battery pack and the temperature distribution of each battery by utilizing a deep reinforcement learning algorithm and combining the received working state data, and feeding back the strategies to a flow velocity adjusting module and a flow direction adjusting module; the deep reinforcement learning algorithm uses the predicted output of the fluid dynamic model as environmental feedback to update and optimize the decision strategy; the decision output of the deep reinforcement learning is used as the input of a fluid dynamics model to predict the temperature distribution of the battery in the next step.
The optimization algorithm module 104 plays a core role in the whole energy storage liquid cooling temperature control optimization system. It is responsible for calculating and outputting the optimal coolant flow rate and direction by using a fluid dynamics model and a Deep Reinforcement Learning (DRL) algorithm based on input environmental state information such as the operating state of the battery, the actual flow rate of the coolant, etc. These optimal cooling strategies will then be applied to the flow rate and direction adjustment modules to control the flow of coolant to achieve efficient and accurate battery temperature control.
The following is a detailed description of the relationship between the optimization algorithm module 104 and the other modules:
(1) Relationship with the temperature control module 101: the temperature control module 101 is responsible for monitoring the operating state of the battery and it transmits these data to the optimization algorithm module. The optimization algorithm module 104 receives this data as an environmental condition input into a Deep Reinforcement Learning (DRL) algorithm for generating an optimal cooling strategy.
(2) Relationship with flow rate adjustment module 102: the optimization algorithm module 104 sends the calculated optimal coolant flow rate to the flow rate adjustment module. Upon receiving this information, the flow rate adjustment module 102 adjusts the opening of the flow rate adjustment valve to change the flow rate of the coolant. In addition, the flow adjustment module 102 also feeds actual coolant flow information back to the optimization algorithm module 104 for future cooling strategy calculations.
(3) Relationship with flow direction adjustment module 103: the optimization algorithm module sends the calculated optimal cooling fluid flow direction to the flow direction adjusting module. After the flow direction regulating module receives the information, the on-off state of the flow direction regulating valve is regulated, and the flow direction of the cooling liquid is changed, so that the temperature equalizing effect of the battery is realized.
The optimization algorithm module 104 plays a role of "brain" in this system, and is responsible for analyzing the environmental state, calculating the optimal strategy, and then directing other modules to act according to this strategy. The structure enables the system to realize dynamic and self-adaptive temperature control, thereby improving the working efficiency and the service life of the battery.
The optimization algorithm module 104 predicts battery temperature changes based on the fluid dynamics model and the deep reinforcement learning algorithm and optimizes the critical portions of the flow rate and direction of the coolant.
First, a hydrodynamic model will be described. Fluid dynamics is a branch of physics that investigates the movement of fluids (liquids and gases). In the present embodiment, a fluid dynamic model is used to describe and predict the case where the coolant flows inside the battery pack. This model requires consideration of physical properties of the coolant (such as density, viscosity, and thermal conductivity), the structure of the battery pack (such as arrangement and connection of the cells), and the flow rate and flow direction of the coolant. By solving the fluid dynamics equation, the flow state of the coolant inside the battery pack and the effect of this flow on the battery temperature can be obtained.
The present embodiment may use some fluid dynamic models, such as microscopic temperature models provided by COMSOL Multiphysics software, to model each cell in the battery, simulating flow and heat transfer conditions inside each cell, to improve model accuracy and predictive power.
In the hydrodynamic model, the inputs mainly include the following aspects:
(1) Physical properties of the coolant: this includes density, viscosity, thermal conductivity, etc., which can affect the flow and heat transfer effects of the cooling fluid inside the battery pack.
(2) The structure of the battery pack: including the arrangement and connection of the cells, and the design of the flow passages for the coolant, these structural characteristics can affect the flow path and distribution of the coolant.
(3) Flow rate and flow direction of the cooling liquid: the input comes from the following deep learning algorithm, which is a parameter controlled by the optimization algorithm module, for adjusting the cooling effect of the coolant.
The output of the fluid dynamics model is mainly the flow state of the cooling liquid inside the battery pack, including the flow rate and direction of the cooling liquid at each cell, and the temperature distribution of each cell. These output information are used as inputs to a deep learning model, which will be described below, to determine the optimal flow rates and directions by the optimization algorithm module 104.
Next, a deep reinforcement learning algorithm will be described. In this embodiment, the deep reinforcement learning algorithm is mainly used to determine the optimal flow rate and direction of the cooling liquid according to the real-time data of the battery and the prediction result of the fluid dynamics model. The deep reinforcement learning algorithm needs to be able to handle a large amount of data, including the real-time temperature of the battery, the operating state of the battery, the actual flow rate and direction of the coolant, etc., and also needs to be able to handle complex optimization problems.
The Deep Reinforcement Learning (DRL) algorithm is an advanced machine learning algorithm that is capable of learning optimal strategies through interactions with the environment. In this embodiment, the implementation of the DRL includes the following key steps:
(1) Environment definition: in the present embodiment, the operating environment of the battery may be defined as an environment. The current operating state (e.g., charge, discharge state, or charge, etc.) of the battery provided by the temperature control module 101, and the flowing state of the cooling liquid inside the battery pack provided by the fluid mechanics model, including the flow rate and flow direction of the cooling liquid at each battery, and the temperature distribution of each battery constitute the environmental state. Information of these environmental states is used as input to the deep reinforcement learning algorithm.
(2) Action definition: in this context, actions that may be taken include changing the flow rate and direction of the cooling fluid. These decisions can have an impact on the operating environment of the battery, which in turn affects the operating efficiency and life of the battery.
(3) The bonus function defines: the bonus function is an important component that is used to evaluate the effect of each action. The bonus function may be designed in this embodiment in combination with the characteristics of the battery and the performance of the cooling system. Specifically, the bonus function may be defined as a function of several aspects:
(a) Rewards in terms of battery temperature: the operating efficiency and life of a battery is largely dependent on its operating temperature. The ideal battery temperature can ensure the performance and the service life of the battery. Thus, a desired temperature range, for example, 35-40 ℃, may be set. If the battery temperature is within this range, the bonus function should return a high bonus value. At the same time, the battery temperature exceeds or falls below this range, and the prize value will decrease.
(b) Rewards in terms of cooling efficiency: cooling efficiency is also an important factor. An efficient cooling system can quickly regulate the battery temperature to within a desired range. Thus, a threshold value for cooling efficiency may be set, and if the efficiency of the cooling system exceeds this threshold value, the bonus function should return a high bonus value.
(c) Rewards in terms of energy consumption: the operation of the cooling system also consumes energy. In order to maximize the energy efficiency of the overall system, the energy consumption of the cooling system should be minimized. Thus, a threshold value of energy consumption may be set, and if the energy consumption of the cooling system is below this threshold value, the bonus function should return a high bonus value.
(d) Rewards in terms of temperature equalization effect: in order to prevent temperature unevenness inside the battery pack, it is necessary to ensure that the cooling liquid can uniformly flow through each of the battery cells. Thus, a threshold value for the soaking effect can be set, and if the flow direction of the coolant can reach this threshold value, the bonus function should return a high bonus value.
In summary, the bonus weights of these four aspects may be added to obtain the final bonus function. For example, the reward function may be defined as:
；
wherein, R_temp, R_efficiency, R_energy and R_uniformity represent rewards in terms of battery temperature, cooling efficiency, energy consumption and temperature equalizing effect, and w1, w2, w3 and w4 are weights thereof, which can be adjusted according to actual demands.
The reward function defined in this way can simultaneously consider the working efficiency, cooling efficiency, energy consumption and temperature equalizing effect of the battery, and accords with the aim and the requirements of the patent. Meanwhile, by adjusting the weight, the method can flexibly adapt to different application scenes and requirements, and has strong practicability and flexibility.
(4) The DRL algorithm is implemented: once the context, action, and rewards functions are defined, the deep reinforcement learning algorithm may begin to be implemented. In each step, the DRL algorithm selects an action based on the current environmental state and then observes the results of the action, including the new environmental state and rewards. This information is used to update the algorithm's policies to optimize future action choices.
(5) Policy optimization: after multiple interactions and learning, the DRL algorithm will gradually find an optimal strategy that can select actions that maximize rewards under various environmental conditions. This strategy is the optimal cooling strategy described in this embodiment.
In this embodiment, deep reinforcement learning requires the use of the output of the fluid dynamics model (predicted battery temperature) as environmental feedback to update and optimize its decision strategy. On the other hand, the decision output of the deep reinforcement learning (the flow rate and the flow direction of the cooling liquid after adjustment) is used as the input of the fluid dynamics model for the next temperature prediction. Thus, the two forms a closed loop, and the aim of optimizing the battery temperature control is achieved through continuous interaction and learning.
This combination also provides a strong a priori knowledge for deep reinforcement learning. While conventional deep reinforcement learning generally requires a large number of trials and iterations to find an effective strategy, the fluid dynamic model provides a physical-based, reliable prediction, which greatly reduces the learning time required for deep reinforcement learning and improves learning efficiency.
Thus, the fluid dynamics model and deep reinforcement learning are interdependent and mutually motivated in this system, and their combination enables the battery temperature control system to achieve efficient and accurate temperature control.
The specific workflow of the DLR algorithm is illustrated below.
If a battery cooling system is provided, when the battery is in a high-intensity working state, such as quick charge or heavy current discharge, the temperature can rise rapidly, and the performance of the battery can be reduced or even the safety hidden trouble can be caused by the excessively high temperature. To ensure that the battery is operating within the desired temperature range, an optimization algorithm module that can intelligently adjust the coolant flow rate and direction is required.
(1) Initializing an environment:
the battery is currently at 40 ℃, and the target temperature range is 35-40 ℃. The current flow rate of the cooling liquid was 10L/min, and the flow direction was from the upper portion to the lower portion of the battery.
(2) Action selection:
the DRL algorithm decides the action to take based on the current battery temperature and the predictions of the fluid dynamics model. For example, the coolant flow rate is increased to 12L/min and the flow direction is changed from the left to the right of the battery.
(3) Performing an action, observing the result:
in a practical environment, after the strategy is applied, the battery temperature is reduced to 38 ℃, the cooling efficiency is improved, but the energy consumption is slightly increased.
(4) Prize calculation:
based on the defined reward function, the algorithm will calculate a reward value based on the battery temperature (R_temp), the cooling efficiency (R_efficiency), the energy consumption (R_energy), and the temperature uniformity effect (R_uniformity).
For example:
r_temp=0.8 (because the battery temperature is within the target range)
R_efficiency=0.7 (because of improved cooling efficiency)
R_energy=0.6 (because the energy consumption increases slightly)
R_uniformity=0.7 (assuming good temperature uniformity after flow direction adjustment)
Using the reward function above:
and obtaining the total rewards.
(5) Updating a strategy:
based on the prize value, the DRL algorithm updates its policy to get a higher prize in future decisions.
(6) Iteration:
the algorithm will repeat the above process through interactive learning with the environment, continuing to optimize the cooling strategy until a satisfactory result is achieved or other stopping conditions are met.
In this process, the fluid dynamic model provides critical information about the battery temperature change, and the DRL algorithm makes decisions intelligently based on this information to ensure that the battery is operating in the optimal temperature range, while taking into account cooling efficiency, energy consumption and temperature leveling effects.
In general, the optimization algorithm module 104 combines a fluid dynamics model and an artificial intelligence algorithm to realize the accuracy and optimization of battery temperature control, improve the performance and service life of the battery, and reduce the energy consumption. This is the core and the peculiarity of the application.
While the application has been described in terms of preferred embodiments, it is not intended to be limiting, but rather, it will be apparent to those skilled in the art that various changes and modifications can be made herein without departing from the spirit and scope of the application as defined by the appended claims.
Claims (10)
1. An energy storage liquid cooling control by temperature change optimizing system based on fluid dynamics and degree of depth reinforcement study, characterized by comprising:
the temperature control module is used for monitoring the working state of the battery and providing the monitored data for the optimization algorithm module; determining a target flow rate and a target flow direction of the cooling liquid according to a preset temperature target; the target flow velocity and the target flow direction are respectively sent to a flow velocity adjusting module and a flow direction adjusting module so as to dynamically adjust the flow velocity and the flow direction of the cooling liquid;
the flow rate adjusting module is used for receiving the target flow rate provided by the temperature control module and adjusting the flow rate of the cooling liquid according to the target flow rate; receiving an optimal cooling liquid flow rate strategy from an optimization algorithm module, and precisely controlling a cooling effect by adjusting the flow rate of cooling liquid;
the flow direction adjusting module is used for receiving the target flow direction provided by the temperature control module and adjusting the flow direction of the cooling liquid according to the target flow direction; receiving an optimal cooling liquid flow strategy from an optimization algorithm module, and realizing the temperature equalizing effect of the battery by adjusting the flow direction of cooling liquid;
the optimization algorithm module is used for receiving the working state data from the temperature control module; predicting the flowing state of the cooling liquid in the battery pack and the temperature distribution of the battery by using a fluid dynamic model; generating optimal cooling liquid flow velocity and flow direction strategies according to the predicted flowing state of cooling liquid in the battery pack and the temperature distribution of each battery by utilizing a deep reinforcement learning algorithm and combining the received working state data, and feeding back the strategies to a flow velocity adjusting module and a flow direction adjusting module; the deep reinforcement learning algorithm uses the predicted output of the fluid dynamic model as environmental feedback to update and optimize the decision strategy; the decision output of the deep reinforcement learning is used as the input of a fluid dynamics model to predict the temperature distribution of the battery in the next step.
2. The energy storage liquid cooling temperature control optimization system of claim 1, wherein the preset temperature target t_target is determined by the following formula:
；
where t_optimal is the average of the optimal operating temperatures of each battery in the battery, soc_avg is the average battery state of charge of the batteries in the battery, soc_std is the standard deviation of the battery state of charge of the batteries in the battery, I is the average operating current of the batteries in the battery, i_nominal is the average of the rated operating currents of the batteries in the battery, P is the power consumption of the cooling system, p_nominal is the rated power consumption of the cooling system, k1, k2, k3, k4 are adjustable coefficients.
3. The energy storage liquid cooling temperature control optimization system of claim 1, wherein the target flow rate f_speed is determined according to the following formula:
；
where t_current is the average temperature of the cells in the battery, t_target is the preset temperature target, Δt/Δt is the rate of change of the average temperature of the cells in the battery, and k5 and k6 are adjustable coefficients.
4. The energy storage liquid cooling temperature control optimization system of claim 1, wherein the target flow directionAccording to the following formula:
；
wherein Ti is current Is the current temperature of cell i in the battery, ti target Is the target temperature of battery i in the battery pack, and n is the number of batteries.
5. The energy storage liquid cooling temperature control optimization system of claim 4, wherein the Ti target The calculation formula of (2) is as follows:
；
where Ti_optimal is the optimal operating temperature of battery I in the battery, SOCi is the current state of charge of battery I in the battery, SOC_optimal is the optimal state of charge of battery I in the battery, ii is the current operating current of battery I in the battery, I_optimal is the optimal operating current of battery I in the battery, T_env_optimal is the optimal ambient temperature of battery I in the battery, k7, k8, and k9 are adjustable coefficients.
6. The energy storage liquid cooled temperature controlled optimization system of claim 1, wherein the fluid dynamics model models each cell in the battery using a microscopic temperature model provided by COMSOL Multiphysics software.
7. The energy storage liquid cooling temperature control optimization system of claim 1, wherein the inputs to the fluid dynamics model include physical characteristics of the cooling liquid, structural characteristics of the battery pack, and flow rate and direction of the cooling liquid; wherein the physical properties include density, viscosity, thermal conductivity; the structural characteristics include the arrangement and connection of the cells.
8. The energy storage liquid cooling temperature control optimization system of claim 1, wherein the actions in the deep reinforcement learning algorithm are defined as changing the flow rate and direction of the cooling liquid.
9. The energy storage liquid cooling temperature control optimization system of claim 1, wherein the deep reinforcement learning reward function R is defined as:
；
wherein R_temp, R_efficiency, R_energy, and R_uniformity represent rewards in terms of battery temperature, cooling efficiency, energy consumption, and temperature equalizing effect, respectively, and w1, w2, w3, and w4 are weights thereof; the calculation of R_temp considers the operating temperature of the battery and provides a high prize value for the battery temperature in the ideal temperature range; r_efficiency is calculated based on cooling efficiency, which provides a high prize value when exceeding a set efficiency threshold; r_energy calculation considers the energy consumption of the cooling system, and provides a high rewarding value when the energy consumption is lower than a set energy consumption threshold value; the calculation of R_uniformity is based on the temperature equalizing effect, and provides a high rewarding value when the flow direction of the cooling liquid reaches a set temperature equalizing effect threshold value.
10. The energy storage liquid cooling temperature control optimization system according to claim 1, wherein the deep reinforcement learning algorithm uses the predicted output of the fluid dynamics model as environmental feedback and uses the decision output thereof as the input of the fluid dynamics model, both of which form a closed loop, and the battery temperature control optimization is realized through continuous interaction and learning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311040877.9A CN116776746B (en) | 2023-08-18 | 2023-08-18 | Energy storage liquid cooling temperature control optimizing system based on fluid dynamics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311040877.9A CN116776746B (en) | 2023-08-18 | 2023-08-18 | Energy storage liquid cooling temperature control optimizing system based on fluid dynamics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116776746A true CN116776746A (en) | 2023-09-19 |
| CN116776746B CN116776746B (en) | 2024-02-23 |
Family
ID=87989790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311040877.9A Active CN116776746B (en) | 2023-08-18 | 2023-08-18 | Energy storage liquid cooling temperature control optimizing system based on fluid dynamics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116776746B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075483A (en) * | 2023-10-16 | 2023-11-17 | 厦门海辰储能科技股份有限公司 | State monitoring method and device of liquid cooling energy storage system and storage medium |
| CN117410625A (en) * | 2023-11-16 | 2024-01-16 | 信者能源科技有限公司 | High-energy-density liquid-cooled energy storage system based on active equalization BMS |
| CN118102683A (en) * | 2024-04-18 | 2024-05-28 | 深圳市光为光通信科技有限公司 | Self-adaptive thermal management system of multi-mode liquid cold light module |
| CN118117214A (en) * | 2024-04-28 | 2024-05-31 | 内蒙古中电储能技术有限公司 | Liquid-air mixed heat dissipation power control method and system for energy storage battery pack |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017152302A (en) * | 2016-02-26 | 2017-08-31 | 三菱自動車工業株式会社 | Method for predicting temperature tendency of battery module, predictor, and prediction program |
| WO2018237340A1 (en) * | 2017-06-23 | 2018-12-27 | Johnson Controls Technology Company | Building equipment with predictive control |
| CN115408957A (en) * | 2022-09-01 | 2022-11-29 | 中国科学院重庆绿色智能技术研究院 | Data center refrigeration equipment control method based on multi-agent reinforcement learning |
| WO2023001097A1 (en) * | 2021-07-22 | 2023-01-26 | 中国第一汽车股份有限公司 | Coolant circulation system for transmission oil, control method, vehicle, and storage medium |
| CN115774929A (en) * | 2022-11-23 | 2023-03-10 | 江苏大学 | Electric automobile thermal management control system and method considering energy conservation and battery life |
-
2023
- 2023-08-18 CN CN202311040877.9A patent/CN116776746B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017152302A (en) * | 2016-02-26 | 2017-08-31 | 三菱自動車工業株式会社 | Method for predicting temperature tendency of battery module, predictor, and prediction program |
| WO2018237340A1 (en) * | 2017-06-23 | 2018-12-27 | Johnson Controls Technology Company | Building equipment with predictive control |
| WO2023001097A1 (en) * | 2021-07-22 | 2023-01-26 | 中国第一汽车股份有限公司 | Coolant circulation system for transmission oil, control method, vehicle, and storage medium |
| CN115408957A (en) * | 2022-09-01 | 2022-11-29 | 中国科学院重庆绿色智能技术研究院 | Data center refrigeration equipment control method based on multi-agent reinforcement learning |
| CN115774929A (en) * | 2022-11-23 | 2023-03-10 | 江苏大学 | Electric automobile thermal management control system and method considering energy conservation and battery life |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075483A (en) * | 2023-10-16 | 2023-11-17 | 厦门海辰储能科技股份有限公司 | State monitoring method and device of liquid cooling energy storage system and storage medium |
| CN117075483B (en) * | 2023-10-16 | 2024-01-26 | 厦门海辰储能科技股份有限公司 | State monitoring method and device of liquid cooling energy storage system and storage medium |
| CN117410625A (en) * | 2023-11-16 | 2024-01-16 | 信者能源科技有限公司 | High-energy-density liquid-cooled energy storage system based on active equalization BMS |
| CN117410625B (en) * | 2023-11-16 | 2024-06-04 | 信者能源科技有限公司 | High-energy-density liquid-cooled energy storage system based on active equalization BMS |
| CN118102683A (en) * | 2024-04-18 | 2024-05-28 | 深圳市光为光通信科技有限公司 | Self-adaptive thermal management system of multi-mode liquid cold light module |
| CN118117214A (en) * | 2024-04-28 | 2024-05-31 | 内蒙古中电储能技术有限公司 | Liquid-air mixed heat dissipation power control method and system for energy storage battery pack |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116776746B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116776746B (en) | Energy storage liquid cooling temperature control optimizing system based on fluid dynamics | |
| KR102667239B1 (en) | Method and a battery system for thermal management | |
| Tang et al. | Temperature sensitivity characteristics of PEM fuel cell and output performance improvement based on optimal active temperature control | |
| Chen et al. | Temperature and humidity management of PEM fuel cell power system using multi-input and multi-output fuzzy method | |
| Anbarasu et al. | Novel enhancement of energy management in fuel cell hybrid electric vehicle by an advanced dynamic model predictive control | |
| Chen et al. | Temperature and voltage dynamic control of PEMFC Stack using MPC method | |
| CN111129548A (en) | Improved particle swarm optimization fuzzy PID fuel cell temperature control method | |
| CN114335625B (en) | Fuel cell stack temperature control method, device, model predictive controller and system | |
| CN112181008B (en) | Intelligent control method, device and medium for heat source power of high-temperature formed cabinet | |
| CN113036261A (en) | Energy storage system and temperature control method of battery system thereof | |
| Qi et al. | Design of the PID temperature controller for an alkaline electrolysis system with time delays | |
| CN117996293B (en) | Temperature control and optimization method and system for immersed energy storage battery | |
| CN114335648A (en) | Control method and control system of all-vanadium redox flow battery system | |
| CN118316168A (en) | Self-adaptive charge and discharge rate control method and system for super-capacity energy storage unit | |
| CN117879115B (en) | Intelligent power supply buffer module with high energy conversion efficiency and implementation method | |
| CN116605098A (en) | Battery thermal management method and device for vehicle, storage medium and vehicle | |
| Liu et al. | Adaptive look-ahead model predictive control strategy of vehicular PEMFC thermal management | |
| Hannan et al. | Lithium ion battery thermal management system using optimized fuzzy controller | |
| Zhang et al. | Research on modeling and control of PEMFC cooling system | |
| CN117410623A (en) | Temperature control method and device of energy storage system, energy storage system and storage medium | |
| Yufit et al. | Development and application of an actively controlled hybrid proton exchange membrane fuel cell—Lithium-ion battery laboratory test-bed based on off-the-shelf components | |
| Ma et al. | Collaborative thermal management of power battery and passenger cabin for energy efficiency optimization | |
| Han et al. | Fuzzy logic-based control of cooling valves for energy-efficient hydrogen vehicles with evaluation in a WHVC mode | |
| CN113442795B (en) | Control method of fuel cell hybrid power system based on layered MPC | |
| CN114982041A (en) | Battery thermal conditioning circuit and method, computer readable storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |