A method for intelligently controlling heat dissipation power of an electric energy storage system

Abstract

The present invention discloses a method for intelligently controlling heat dissipation power of an electric energy storage system, relates to the technical field of electric energy storage control, realizes heat dissipation management and control of the electric energy storage system, uses a machine learning model to predict the future workload state, thereby predicting the temperature distribution of the equipment through a dynamic thermal model, and obtaining the trend temperature index Tzs, thereby ensuring the accuracy and efficiency of heat dissipation regulation and control, and being able to timely adjust the equipment heat dissipation regulation and control evaluation strategy scheme when the temperature changes. In addition, the secondary evaluation mechanism of heat dissipation regulation and control further improves the heat dissipation efficiency of the system and the stability of equipment operation by analyzing and optimizing the execution results of the heat dissipation strategy, making up for the lack of accuracy of heat dissipation management and limited real-time response capability in traditional systems, so that the electric energy storage system has higher adaptability and stability when responding to emergencies, and makes the heat dissipation process more personalized and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy storage control, and in particular to an intelligent control method for heat dissipation power of an electric energy storage system. Background Art

[0002] Chinese Patent Publication No.: CN202410398590.1, control system and method for new energy storage system, the system includes energy scheduling module, dynamic throttling module, energy demand prediction control module, impact analysis module, energy consumption prediction module, heat dissipation optimization module, and system monitoring module. In the present invention, by adopting non-dominated sorting genetic algorithm II for multi-objective optimization, the energy scheduling module of the new energy storage system can capture a better balance between energy efficiency, cost minimization and system stability. It is particularly suitable for the uncertainty of the power market and renewable energy supply, thereby significantly improving the adaptability and economic benefits of the system. The dynamic throttling module adopts an autoregressive moving average model to predict instant energy demand changes, and designs a dynamic throttling control strategy, so that the system can respond to energy demand fluctuations and optimize energy flow more sensitively and efficiently. Improve the system's ability to respond to emergencies.

[0003] It can be seen that although the energy scheduling module of the energy storage system can capture a better balance between energy efficiency, cost minimization and system stability, it has shortcomings in processing the real-time temperature and usage rate data when the energy storage system equipment converts and uses energy. For the real-time adjustment of heat dissipation, there is a lack of a special mechanism to ensure the accurate collection and real-time response of temperature data. As a result, in the process of rapid response to fluctuations in energy demand, the heat dissipation management may not be able to accurately adapt to changes in system temperature, resulting in insufficient or excessive heat dissipation, which may seriously lead to equipment failure and fire-related emergencies. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method for intelligently controlling heat dissipation power of an electric energy storage system, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for intelligently controlling heat dissipation power of an electric energy storage system, comprising the following steps:

[0006] Step 1: Use temperature sensors to collect temperature data and equipment utilization rate U of multiple equipment operation areas in the power energy storage system in real time i (t), synchronously collect external environment temperature data to form a temperature feature vector TFV;

[0007] Step 2: Convert the temperature history data T histCombined with the temperature feature vector TFV, the machine learning model is used to predict the workload status in the future fixed period to obtain the predicted load power P(t);

[0008] Step 3: Establish a dynamic thermal model by predicting the load power P(t), predict the temperature distribution of the equipment in a future fixed period, and obtain the trend temperature index Tzs of the power storage system equipment;

[0009] Step 4: Match the trend temperature index Tzs with the preset device heat dissipation adjustment threshold S to obtain the device heat dissipation control evaluation strategy plan, and perform specific device heat dissipation control according to the content of the device heat dissipation control evaluation strategy plan;

[0010] Step 5: Collect the execution results of the equipment heat dissipation control evaluation strategy plan, conduct a secondary heat dissipation evaluation by counting and analyzing the temperature change trend, obtain the equipment heat dissipation control secondary evaluation strategy plan, and make secondary adjustments to the equipment heat dissipation control according to the content of the equipment heat dissipation control secondary evaluation strategy plan.

[0011] Preferably, in step 1, temperature sensors are arranged in different equipment areas of the power energy storage system to collect temperature data and equipment utilization rate U of each component in real time. i (t), an ambient temperature sensor is installed to collect the temperature of the external environment. The collected data includes the temperature data of the battery pack, inverter and radiator components, and then the data is marked and time synchronized to form a temperature feature vector TFV. The collected data is synchronously classified and stored as temperature history data according to the unique device tag information carried by the collected data, and the temperature history data of the energy storage device is updated in real time;

[0012] Among them, the equipment utilization rate U i (t) is obtained by the following calculation formula:

[0013]

[0014] Where U i (t) represents the device utilization rate, specifically the utilization rate of the i-th device at time t, Wi(t) represents the actual power consumption of the i-th device at time t, specifically reflecting the workload status of the device i at time t, and W max，i Indicates the rated power of the i-th device, i represents the device number index, which is specifically used to indicate different devices in the energy storage system;

[0015] Data tagging and time synchronization specifically add device tags and timestamps to each collected temperature data, so that the temperature data of different devices can be distinguished and synchronized with the time axis. The marked temperature data is expressed as: T i,t and T enu,t , Ti,t represents the temperature value of the i-th energy storage system device at time t, T enu,t Represents the temperature value of the external environment at time t;

[0016] The temperature feature vector TFV is specifically TFV={TFV1, TFV2, ..., TFV t}Temperature feature vector TFV of several acquisition times t , TFV t Specifically, i,t , T enu,t , U i (t)}.

[0017] Preferably, in step 2, the temperature history data T hist Combined with the temperature feature vector TFV, the feature matrix X(t) is formed, specifically X = {T hist , TFV}, temperature history data T hist By intercepting the temperature history data within a fixed period, the machine learning model is used to predict the workload status within the future fixed period to obtain the predicted load power P(t).

[0018] Preferably, the predicted load power P(t) is obtained by the following calculation formula:

[0019]

[0020] In the formula, c o represents a constant term, n represents the number of temperature collection time points within a fixed period, k represents the kth temperature collection time point within a fixed period, Represents the sum of historical temperatures, specifically the cumulative temperature impact during n acquisition times. represents the square term of the sum of historical temperatures, specifically the nonlinear cumulative effect of historical temperatures, It represents the product of the external ambient temperature value and the historical temperature sum. It is specifically used to represent the influence between the external ambient temperature value and the historical temperature. It represents the product of the equipment utilization rate and the cumulative sum of historical temperatures. It is used to reflect the impact between equipment utilization rate and historical temperatures. c4*T unu 2 Represents the square term of the external ambient temperature, specifically used to represent the nonlinear effect of the external ambient temperature, c5*U i (t) 2 It represents the square term of the equipment utilization rate, which is specifically used to reflect the nonlinear effect of the equipment utilization rate. c1, c2, c3, c4 and c5 represent preset weight values.

[0021] Preferably, a dynamic thermal model is established based on the predicted load power P(t), the thermal capacity information of the equipment and the preset time step Δt are input into the dynamic thermal model, and the predicted temperature T of the equipment is obtained after training and analysis. pred (t) To predict the temperature distribution of the equipment within a fixed period in the future and reflect the temperature changes of the equipment under different load conditions;

[0022] The heat capacity information of the equipment specifically represents the physical characteristic parameters of the equipment and is used to describe the ability of the equipment to absorb heat, which is extracted through equipment specifications and experimentally determined;

[0023] Synchronously predict the temperature T through the device pred (t) and calculate the average temperature T of N time steps avg Fitting is performed to obtain the trend temperature index Tzs of the power energy storage system equipment.

[0024] Preferably, the device predicts the temperature T pred (t) is obtained by the following calculation formula:

[0025]

[0026] Where, T pred (t) represents the predicted temperature, specifically the predicted temperature value of the device at time t, T(t-1) represents the time-temperature value of the device at time t-1, C represents the thermal capacity of the device, specifically the ability of the device to absorb heat, Δt represents the time step, specifically the time interval for calculating the temperature change.

[0027] Preferably, the trend temperature index Tzs is obtained by the following calculation formula:

[0028]

[0029] Where Tzs represents the trend temperature index, which specifically indicates the change trend of the device temperature within the predicted fixed period, N represents the number of time steps within the predicted fixed period, and T pred (t) represents the predicted temperature, specifically the predicted temperature value of the device at time t, T avg Represents the average temperature value for the number of time steps N within the forecast fixed period.

[0030] Preferably, the device heat dissipation control evaluation strategy solution is obtained by the following matching method:

[0031] When the trend temperature index Tzs is less than the device heat dissipation adjustment threshold S, the qualified evaluation result of the device heat dissipation status is obtained and the current heat dissipation power and heat dissipation strategy are maintained;

[0032] If the trend temperature index Tzs is greater than or equal to the device heat dissipation adjustment threshold S, an unqualified evaluation result of the device heat dissipation status is obtained, and the current heat dissipation power and heat dissipation strategy are adjusted, including starting the operation of additional cooling equipment and adjusting the operating power of the heat dissipation equipment.

[0033] Preferably, the temperature change rate ΔT(t) is obtained by statistically analyzing the temperature change trend, and the temperature change trend index T is obtained by statistically analyzing the temperature change rate ΔT(t). trend , and then perform a secondary heat dissipation evaluation match with the preset heat dissipation control post-evaluation threshold HP to obtain the equipment heat dissipation control secondary evaluation strategy plan;

[0034] The temperature change rate ΔT(t) is obtained by the following calculation formula:

[0035] ΔT(t)=T exec (t)-T exec (t-1);

[0036] Where, T exec (t) represents the device temperature value at time t after executing the device heat dissipation control evaluation strategy, T exec (t-1) represents the device temperature value at time t-1 after executing the device heat dissipation control evaluation strategy;

[0037] The temperature change trend index T trend Obtained through the following calculation formula:

[0038]

[0039] Where M represents the number of time steps in the evaluation cycle after executing the device heat dissipation control evaluation strategy.

[0040] Preferably, the device heat dissipation control secondary evaluation strategy solution is obtained by the following matching method:

[0041] Temperature change trend index T trend < Heat dissipation control post-evaluation threshold HP, obtain the qualified result of the second evaluation after the heat dissipation control of the equipment, and do not implement the second control strategy plan;

[0042] Temperature change trend index T trend ≥ HP, the evaluation threshold after heat dissipation control is used to obtain the unqualified result of the second evaluation after heat dissipation control of the device, and to execute the second control strategy plan, including the second adjustment of the current heat dissipation power and heat dissipation strategy.

[0043] The present invention provides a method for intelligently controlling heat dissipation power of an electric energy storage system, which has the following beneficial effects:

[0044] (1) Through steps 1 to 5, the heat dissipation management and control of the power energy storage system is realized. The machine learning model is used to predict the future workload state, so that the temperature distribution of the equipment is predicted through the dynamic thermal model to obtain the trend temperature index Tzs, ensuring the accuracy and efficiency of the heat dissipation control. The heat dissipation control evaluation strategy of the equipment can be adjusted in time when the temperature changes. In addition, the secondary evaluation mechanism of heat dissipation control further improves the heat dissipation efficiency of the system and the stability of equipment operation by analyzing and optimizing the execution results of the heat dissipation strategy, making up for the lack of accuracy of heat dissipation management and limited real-time response capabilities in traditional systems, making the power energy storage system have higher adaptability and stability when responding to emergencies. At the same time, fine-grained control at the device level makes the heat dissipation process more personalized and accurate, ensuring that each device can operate within the optimal temperature range.

[0045] (2) By collecting the temperature and usage rate of each device in real time and combining it with the external ambient temperature information, a comprehensive temperature feature vector TFV is constructed. The data is marked and time-synchronized to clearly distinguish the data of different devices. The future workload status is predicted through a machine learning model to obtain the predicted load power P(t). The feature matrix X(t) combines the historical temperature data with the current feature vector TFV, which helps to make load predictions more accurate. By considering the device usage rate, ambient temperature and its nonlinear effects, this method not only improves the understanding and prediction capabilities of the device operating status, but also optimizes the device's power consumption and heat dissipation strategy, thereby improving the energy efficiency and stability of the overall system.

[0046] (3) Using the thermal capacity information of the equipment and the preset time step for simulation, the system can accurately predict the temperature change of the equipment under different load conditions and calculate the predicted temperature T of the equipment. pred (t), by the average temperature T of the time step avg Fitting is performed to obtain the trend temperature index Tzs to reflect the temperature change trend of the equipment, evaluate the heat dissipation status of the equipment, and decide whether it is necessary to adjust the equipment heat dissipation control evaluation strategy. It can dynamically respond to changes in the thermal status of the equipment and ensure that the equipment operates under optimal temperature conditions, thereby improving energy efficiency, extending equipment life, and avoiding performance degradation or failure due to overheating.

[0047] (4) By statistically analyzing the temperature change trend, the temperature change rate ΔT(t) is calculated, and the temperature change trend index T is further obtained. trend, and then match it with the preset heat dissipation control post-evaluation threshold HP to obtain the secondary evaluation strategy scheme for the equipment heat dissipation control. When the temperature change trend index is lower than the threshold, it means that the heat dissipation control effect is good and no additional control strategy needs to be executed; when the index is higher than the threshold, the system will execute the secondary control strategy, including adjusting the heat dissipation power and strategy to ensure that the equipment operates within the optimal temperature range, improve the heat dissipation efficiency, and significantly reduce the risk of equipment overheating, ensuring that the system can operate stably under various load conditions. In addition, reducing unnecessary control operations helps to extend the life of the equipment and reduce energy consumption, improving the economy and environmental protection of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention is a schematic diagram of the steps of a method for intelligently controlling heat dissipation power of an electric energy storage system. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] The present invention provides a method for intelligently controlling the heat dissipation power of an electric energy storage system. Figure 1 , including the following steps:

[0052] Step 1: Use temperature sensors to collect temperature data and equipment utilization rate U of multiple equipment operation areas in the power energy storage system in real time i (t), synchronously collect external environment temperature data to form a temperature feature vector TFV;

[0053] Step 2: Convert the temperature history data T hist Combined with the temperature feature vector TFV, the machine learning model is used to predict the workload status in the future fixed period to obtain the predicted load power P(t);

[0054] Step 3: Establish a dynamic thermal model by predicting the load power P(t), predict the temperature distribution of the equipment in a future fixed period, and obtain the trend temperature index Tzs of the power storage system equipment;

[0055] Step 4: Match the trend temperature index Tzs with the preset device heat dissipation adjustment threshold S to obtain the device heat dissipation control evaluation strategy plan, and perform specific device heat dissipation control according to the content of the device heat dissipation control evaluation strategy plan;

[0056] Step 5: Collect the execution results of the equipment heat dissipation control evaluation strategy plan, conduct a secondary heat dissipation evaluation by counting and analyzing the temperature change trend, obtain the equipment heat dissipation control secondary evaluation strategy plan, and make secondary adjustments to the equipment heat dissipation control according to the content of the equipment heat dissipation control secondary evaluation strategy plan.

[0057] In this embodiment, through steps one to five, the heat dissipation management and control of the electric energy storage system is realized, and the machine learning model is used to predict the future workload state, so that the temperature distribution of the equipment is predicted through the dynamic thermal model, and the trend temperature index Tzs is obtained, thereby ensuring the accuracy and efficiency of the heat dissipation regulation, and being able to timely adjust the equipment heat dissipation regulation evaluation strategy when the temperature changes. In addition, the secondary evaluation mechanism of heat dissipation regulation further improves the heat dissipation efficiency of the system and the stability of equipment operation by analyzing and optimizing the execution results of the heat dissipation strategy, making up for the lack of accuracy of heat dissipation management and limited real-time response capabilities in traditional systems, so that the electric energy storage system has higher adaptability and stability when responding to emergencies. At the same time, fine-grained control at the device level makes the heat dissipation process more personalized and accurate, ensuring that each device can operate within the optimal temperature range.

[0058] Example 2

[0059] This embodiment is explained in Example 1, please refer to Figure 1 Specifically: In step 1, temperature sensors are arranged in different equipment areas of the power energy storage system to collect temperature data and equipment utilization rate U of each component in real time. i (t), an ambient temperature sensor is installed to collect the temperature of the external environment. The collected data includes the temperature data of the battery pack, inverter and radiator components, and then the data is marked and time synchronized to form a temperature feature vector TFV. The collected data is synchronously classified and stored as temperature history data according to the unique device tag information carried by the collected data, and the temperature history data of the energy storage device is updated in real time;

[0060] Among them, the equipment utilization rate U i (t) is obtained by the following calculation formula:

[0061]

[0062] Where U i (t) represents the device utilization rate, specifically the utilization rate of the i-th device at time t, Wi(t) represents the actual power consumption of the i-th device at time t, specifically reflecting the workload status of the device i at time t, and W max，iIndicates the rated power of the i-th device, i represents the device number index, which is specifically used to indicate different devices in the energy storage system;

[0063] Data tagging and time synchronization specifically add device tags and timestamps to each collected temperature data, so that the temperature data of different devices can be distinguished and synchronized with the time axis. The marked temperature data is expressed as: T i,t and T enu,t , T i,t represents the temperature value of the i-th energy storage system device at time t, T enu,t Represents the temperature value of the external environment at time t;

[0064] The temperature feature vector TFV is specifically TFV={TFV1, TFV2, ..., TFV t}Temperature feature vector TFV of several acquisition times t , TFV t Specifically, i,t , T enu,t , U i (t)}Collect.

[0065] In the step 2, the temperature history data T hist Combined with the temperature feature vector TFV, the feature matrix X(t) is formed, specifically X = {T hist , TFV}, temperature history data T hist By intercepting the temperature history data within a fixed period, the machine learning model is used to predict the workload status within the future fixed period to obtain the predicted load power P(t).

[0066] Among them, the predicted load power P(t) is obtained by the following calculation formula:

[0067]

[0068] In the formula, c o represents a constant term, n represents the number of temperature collection time points within a fixed period, k represents the kth temperature collection time point within a fixed period, Represents the sum of historical temperatures, specifically the cumulative temperature impact during n acquisition times. represents the square term of the sum of historical temperatures, specifically the nonlinear cumulative effect of historical temperatures, It represents the product of the external ambient temperature value and the historical temperature sum. It is specifically used to represent the influence between the external ambient temperature value and the historical temperature. It represents the product of the equipment utilization rate and the cumulative sum of historical temperatures. It is used to reflect the impact between equipment utilization rate and historical temperatures. c4*T unu 2Represents the square term of the external ambient temperature, specifically used to represent the nonlinear effect of the external ambient temperature, c5*U i (t) 2 It represents the square term of the equipment utilization rate, which is specifically used to reflect the nonlinear effect of the equipment utilization rate. c1, c2, c3, c4 and c5 represent preset weight values.

[0069] In this embodiment, the temperature and usage rate of each device are collected in real time, combined with the external environment temperature information, to form a comprehensive temperature feature vector TFV, the data is marked and time synchronized, so that the data of different devices can be clearly distinguished, and the future workload state is predicted through a machine learning model to obtain the predicted load power P(t), wherein the feature matrix X(t) combines the historical temperature data with the current feature vector TFV, which helps to make load predictions more accurately. By considering the equipment usage rate, ambient temperature and its nonlinear effects, this method not only improves the understanding and prediction capabilities of the equipment operating status, but also optimizes the power consumption and heat dissipation strategy of the equipment, and improves the energy efficiency and stability of the overall system.

[0070] Example 3

[0071] This embodiment is explained in Example 2. Please refer to Figure 1 Specifically: a dynamic thermal model is established based on the predicted load power P(t), the thermal capacity information of the equipment and the preset time step Δt are input into the dynamic thermal model, and the predicted temperature T of the equipment is obtained after training and analysis. pred (t) To predict the temperature distribution of the equipment within a fixed period in the future and reflect the temperature changes of the equipment under different load conditions;

[0072] The heat capacity information of the equipment specifically represents the physical characteristic parameters of the equipment and is used to describe the ability of the equipment to absorb heat, which is extracted through equipment specifications and experimentally determined;

[0073] Synchronously predict the temperature T through the device pred (t) and calculate the average temperature T of N time steps avg Fitting is performed to obtain the trend temperature index Tzs of the power energy storage system equipment.

[0074] Among them, the equipment predicted temperature T pred (t) is obtained by the following calculation formula:

[0075]

[0076] Where, T pred(t) represents the predicted temperature, specifically the predicted temperature value of the device at time t, T(t-1) represents the time-temperature value of the device at time t-1, C represents the thermal capacity of the device, specifically the ability of the device to absorb heat, Δt represents the time step, specifically the time interval for calculating the temperature change.

[0077] Among them, the trend temperature index Tzs is obtained by the following calculation formula:

[0078]

[0079] Where Tzs represents the trend temperature index, which specifically indicates the change trend of the device temperature within the predicted fixed period, N represents the number of time steps within the predicted fixed period, and T pred (t) represents the predicted temperature, specifically the predicted temperature value of the device at time t, T avg Represents the average temperature value for the number of time steps N within the forecast fixed period.

[0080] Among them, the equipment heat dissipation control evaluation strategy solution is obtained through the following matching method:

[0081] When the trend temperature index Tzs is less than the device heat dissipation adjustment threshold S, the qualified evaluation result of the device heat dissipation status is obtained and the current heat dissipation power and heat dissipation strategy are maintained;

[0082] If the trend temperature index Tzs is greater than or equal to the device heat dissipation adjustment threshold S, an unqualified evaluation result of the device heat dissipation status is obtained, and the current heat dissipation power and heat dissipation strategy are adjusted, including starting the operation of additional cooling equipment and adjusting the operating power of the heat dissipation equipment.

[0083] In this embodiment, the thermal capacity information of the equipment and the preset time step are used for simulation. The system can accurately predict the temperature change of the equipment under different load conditions and calculate the predicted temperature T of the equipment. pred (t), by the average temperature T of the time step avg Fitting is performed to obtain the trend temperature index Tzs to reflect the temperature change trend of the equipment, evaluate the heat dissipation status of the equipment, and decide whether it is necessary to adjust the equipment heat dissipation control evaluation strategy. It can dynamically respond to changes in the thermal status of the equipment and ensure that the equipment operates under optimal temperature conditions, thereby improving energy efficiency, extending equipment life, and avoiding performance degradation or failure due to overheating.

[0084] Example 4

[0085] This embodiment is explained in Example 3, please refer to Figure 1 Specifically: The temperature change rate ΔT(t) is obtained by statistically analyzing the temperature change trend, and the temperature change trend index T is obtained by statistically analyzing the temperature change rate ΔT(t). trend, and then perform a secondary heat dissipation evaluation match with the preset heat dissipation control post-evaluation threshold HP to obtain the equipment heat dissipation control secondary evaluation strategy plan;

[0086] The temperature change rate ΔT(t) is obtained by the following calculation formula:

[0087] ΔT(t)=T exec (t)-T exec (t-1);

[0088] Where, T exec (t) represents the device temperature value at time t after executing the device heat dissipation control evaluation strategy, T exec (t-1) represents the device temperature value at time t-1 after executing the device heat dissipation control evaluation strategy;

[0089] The temperature change trend index T trend Obtained through the following calculation formula:

[0090]

[0091] Where M represents the number of time steps in the evaluation cycle after executing the device heat dissipation control evaluation strategy.

[0092] The device heat dissipation control secondary evaluation strategy solution is obtained through the following matching method:

[0093] Temperature change trend index T trend < Heat dissipation control post-evaluation threshold HP, obtain the qualified result of the second evaluation after the heat dissipation control of the equipment, and do not implement the second control strategy plan;

[0094] Temperature change trend index T trend ≥ HP, the evaluation threshold after heat dissipation control is used to obtain the unqualified result of the second evaluation after heat dissipation control of the device, and to execute the second control strategy plan, including the second adjustment of the current heat dissipation power and heat dissipation strategy.

[0095] In this embodiment, by statistically analyzing the temperature change trend, the temperature change rate ΔT(t) is calculated, and the temperature change trend index T is further obtained. trend , and then match it with the preset heat dissipation control post-evaluation threshold HP to obtain the secondary evaluation strategy scheme for the equipment heat dissipation control. When the temperature change trend index is lower than the threshold, it means that the heat dissipation control effect is good and no additional control strategy needs to be executed; when the index is higher than the threshold, the system will execute the secondary control strategy, including adjusting the heat dissipation power and strategy to ensure that the equipment operates within the optimal temperature range, improve the heat dissipation efficiency, and significantly reduce the risk of equipment overheating, ensuring that the system can operate stably under various load conditions. In addition, reducing unnecessary control operations helps to extend the life of the equipment and reduce energy consumption, improving the economy and environmental protection of the system.

[0096] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligently controlling heat dissipation power of an electric energy storage system, characterized in that: The following steps are involved: Step 1: Use temperature sensors to collect temperature data and equipment utilization rate U of multiple equipment operation areas in the power energy storage system in real time i (t), synchronously collect external environment temperature data to form a temperature feature vector TFV; In step 1, temperature sensors are arranged in different equipment areas of the power energy storage system to collect temperature data and equipment utilization rate U of each component in real time. i (t), an ambient temperature sensor is installed to collect the temperature of the external environment. The collected data includes the temperature data of the battery pack, inverter and radiator components, and then the data is marked and time synchronized to form a temperature feature vector TFV. The collected data is synchronously classified and stored as temperature history data according to the unique device tag information carried by the collected data, and the temperature history data of the energy storage device is updated in real time; Among them, the equipment utilization rate U i (t) is obtained by the following calculation formula: Where U i (t) represents the device utilization rate, specifically the utilization rate of the i-th device at time t, Wi(t) represents the actual power consumption of the i-th device at time t, specifically reflecting the workload status of the device i at time t, and W max，i Indicates the rated power of the i-th device, i represents the device number index, which is specifically used to indicate different devices in the energy storage system; Data tagging and time synchronization specifically add device tags and timestamps to each collected temperature data, so that the temperature data of different devices can be distinguished and synchronized with the time axis. The marked temperature data is expressed as: T i,t and T enu,t , T i,t represents the temperature value of the i-th energy storage system device at time t, T enu,t Represents the temperature value of the external environment at time t; The temperature feature vector TFV is specifically TFV={TFV1, TFV2, ..., TFV t }Temperature feature vector TFV of several acquisition times t , TFV t Specifically, i,t , T enu,t , U i (t)}; Step 2: Convert the temperature history data T hist Combined with the temperature feature vector TFV, the machine learning model is used to predict the workload status in the future fixed period to obtain the predicted load power P(t); In the step 2, the temperature history data T hist Combined with the temperature feature vector TFV, the feature matrix X(t) is formed, specifically X = {T hist , TFV}, temperature history data T hist By intercepting the temperature history data within a fixed period, the machine learning model is used to predict the workload status within the future fixed period to obtain the predicted load power P(t); Among them, the predicted load power P(t) is obtained by the following calculation formula: In the formula, c o represents a constant term, n represents the number of temperature collection time points within a fixed period, k represents the kth temperature collection time point within a fixed period, Represents the sum of historical temperatures, specifically the cumulative temperature impact during n acquisition times. represents the square term of the sum of historical temperatures, specifically the nonlinear cumulative effect of historical temperatures, It represents the product of the external ambient temperature value and the historical temperature sum. It is specifically used to represent the influence between the external ambient temperature value and the historical temperature. It represents the product of the equipment utilization rate and the cumulative sum of historical temperatures. It is used to reflect the impact between equipment utilization rate and historical temperatures. c4*T unu 2 Represents the square term of the external ambient temperature, specifically used to represent the nonlinear effect of the external ambient temperature, c5*U i (t) 2 represents the square term of the equipment utilization rate, which is specifically used to reflect the nonlinear effect of the equipment utilization rate. c1, c2, c3, c4 and c5 represent preset weight values; Step 3: Establish a dynamic thermal model by predicting the load power P(t), predict the temperature distribution of the equipment in a future fixed period, and obtain the trend temperature index Tzs of the power storage system equipment; Step 4: Match the trend temperature index Tzs with the preset device heat dissipation adjustment threshold S to obtain the device heat dissipation control evaluation strategy plan, and perform specific device heat dissipation control according to the content of the device heat dissipation control evaluation strategy plan; Step 5: Collect the execution results of the equipment heat dissipation control evaluation strategy plan, conduct a secondary heat dissipation evaluation by counting and analyzing the temperature change trend, obtain the equipment heat dissipation control secondary evaluation strategy plan, and make secondary adjustments to the equipment heat dissipation control according to the content of the equipment heat dissipation control secondary evaluation strategy plan.

2. The method for intelligently controlling heat dissipation power of an electric energy storage system according to claim 1, characterized in that: A dynamic thermal model is established based on the predicted load power P(t), and the thermal capacity information of the equipment and the preset time step Δt are input into the dynamic thermal model. After training and analysis, the predicted temperature T of the equipment is obtained. pred (t) To predict the temperature distribution of the equipment within a fixed period in the future and reflect the temperature changes of the equipment under different load conditions; The heat capacity information of the equipment specifically represents the physical characteristic parameters of the equipment and is used to describe the ability of the equipment to absorb heat, which is extracted through equipment specifications and experimentally determined; Synchronously predict the temperature T through the device pred (t) and calculate the average temperature T of N time steps avg Fitting is performed to obtain the trend temperature index Tzs of the power energy storage system equipment.

3. The method for intelligently controlling heat dissipation power of an electric energy storage system according to claim 2, characterized in that: in, Equipment predicted temperature T pred (t) is obtained by the following calculation formula: Where, T pred (t) represents the predicted temperature, specifically the predicted temperature value of the device at time t, T(t-1) represents the time-temperature value of the device at time t-1, C represents the thermal capacity of the device, specifically the ability of the device to absorb heat, Δt represents the time step, specifically the time interval for calculating the temperature change.

4. The method for intelligently controlling heat dissipation power of an electric energy storage system according to claim 3 is characterized in that: in, The trend temperature index Tzs is obtained by the following calculation formula: Where Tzs represents the trend temperature index, which specifically indicates the change trend of the device temperature within the predicted fixed period, N represents the number of time steps within the predicted fixed period, and T pred (t) represents the predicted temperature, specifically the predicted temperature value of the device at time t, T avg Represents the average temperature value for the number of time steps N within the forecast fixed period.

5. The method for intelligently controlling heat dissipation power of an electric energy storage system according to claim 1, characterized in that: in, The device heat dissipation control evaluation strategy solution is obtained through the following matching methods: When the trend temperature index Tzs is less than the device heat dissipation adjustment threshold S, the qualified evaluation result of the device heat dissipation status is obtained and the current heat dissipation power and heat dissipation strategy are maintained; If the trend temperature index Tzs is greater than or equal to the device heat dissipation adjustment threshold S, an unqualified evaluation result of the device heat dissipation status is obtained, and the current heat dissipation power and heat dissipation strategy are adjusted, including starting the operation of additional cooling equipment and adjusting the operating power of the heat dissipation equipment.

6. The method for intelligently controlling heat dissipation power of an electric energy storage system according to claim 5, characterized in that: in, The temperature change rate ΔT(t) is obtained by statistically analyzing the temperature change trend, and the temperature change trend index T is obtained by statistically analyzing the temperature change rate ΔT(t). trend , and then perform a secondary heat dissipation evaluation match with the preset heat dissipation control post-evaluation threshold HP to obtain the equipment heat dissipation control secondary evaluation strategy plan; The temperature change rate ΔT(t) is obtained by the following calculation formula: ΔT(t)=T exec (t)-T exec (t-1); Where, T exec (t) represents the device temperature value at time t after executing the device heat dissipation control evaluation strategy, T exec (t-1) represents the device temperature value at time t-1 after executing the device heat dissipation control evaluation strategy; The temperature change trend index T trend Obtained through the following calculation formula: Where M represents the number of time steps in the evaluation cycle after executing the device heat dissipation control evaluation strategy.

7. The method for intelligently controlling heat dissipation power of an electric energy storage system according to claim 6, characterized in that: The device heat dissipation control secondary evaluation strategy solution is obtained through the following matching method: Temperature change trend index T trend < Heat dissipation control post-evaluation threshold HP, obtain the qualified result of the second evaluation after the heat dissipation control of the equipment, and do not implement the second control strategy plan; The temperature change trend index Ttrend ≥ the evaluation threshold HP after heat dissipation control. The unqualified result of the secondary evaluation after heat dissipation control of the device is obtained, and the secondary control strategy is executed, including secondary adjustment of the current heat dissipation power and heat dissipation strategy.

Images