Battery temperature intelligent dynamic optimization method and system of liquid cooling energy storage cabinet

Abstract

The invention discloses an intelligent dynamic optimization method and system for the battery temperature of a liquid cooling energy storage cabinet, and particularly relates to the technical field of dynamic optimization of the battery temperature, and the method comprises the steps: obtaining a temperature data set in a battery monitoring region in real time; obtaining a battery operation evaluation coefficient in real time, analyzing the battery operation evaluation coefficient, and determining the operation state of the battery; the operation state of the battery comprises a discharging state and a charging state, and a discharging normal instruction or a charging normal instruction is generated respectively; according to the method, the temperature data set and the battery operation evaluation coefficient are input into the pre-constructed neural network model, the future temperature change can be predicted, the temperature change in the discharging and charging processes is analyzed according to the generated discharging or charging optimization instruction, and the targeted temperature optimization strategy is obtained, so that the battery can be effectively optimized when the battery is discharged or charged. A cooling or current control strategy can be dynamically adjusted according to specific conditions, and the problem of battery overheating or low efficiency is prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic optimization of battery temperature, and more specifically, to a method and system for intelligent dynamic optimization of battery temperature in a liquid-cooled energy storage cabinet. Background Art

[0002] Liquid-cooled energy storage cabinets are widely used in the fields of new energy, power grid peak and frequency regulation, data center emergency power supply, industrial energy storage, etc. Traditional liquid-cooled energy storage cabinet battery temperature control technology solves the battery temperature problem by means of liquid cooling. Although it has higher heat dissipation efficiency, it usually relies on fixed control strategies, lacks dynamic adjustment capabilities, and responds slowly to changes in charge and discharge status.

[0003] In the prior art, for example, a Chinese patent application with publication number CN118472497A discloses a two-phase cold plate liquid cooling control method and system for energy storage, including obtaining the battery temperature of each battery pack unit in the battery cabinet, wherein the battery cabinet adopts a two-phase cold plate liquid cooling method and uses an insulating refrigerant as a coolant, and each battery pack unit is individually connected to a valve body; if any of the battery temperatures is greater than the preset battery temperature, the maximum battery temperature and the minimum battery temperature are determined from the battery temperatures; based on the maximum battery temperature and the minimum battery temperature, the valve body opening of the corresponding battery pack unit is adjusted to balance the resistance of each battery pack unit at different power consumption. Although the above method can realize the optimization of the battery temperature control strategy, thereby effectively improving the performance and safety of the battery, research and application of the above method and the prior art have found that the above method and the prior art have at least the following partial defects:

[0004] 1. Adjustment based on the current maximum and minimum battery temperatures is only applicable to real-time temperature control and cannot predict future temperature change trends, especially when the battery load changes rapidly, which can easily lead to temperature control lag problems.

[0005] 2. It is impossible to dynamically adjust the temperature control strategy according to the operating status and load changes of the liquid-cooled energy storage cabinet.

[0006] To this end, the present invention provides a method and system for intelligent dynamic optimization of battery temperature in a liquid-cooled energy storage cabinet. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet, comprising:

[0010] Step 1: acquiring a temperature data set in a battery monitoring area in real time; and acquiring a battery operation evaluation coefficient in real time, analyzing the battery operation evaluation coefficient, and determining the battery operation state; the battery operation state includes a discharge state and a charge state, and generating a discharge normal instruction or a charge normal instruction respectively;

[0011] Step 2: Receive the corresponding normal instruction, input the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, and predict the future temperature value; analyze the future temperature value to determine whether to generate a discharge optimization instruction or a charge optimization instruction;

[0012] Step 3: Receive the discharge optimization instruction, obtain the discharge optimization data of the battery, analyze the discharge optimization data, and obtain the temperature optimization strategy of the battery under the discharge state;

[0013] Step 4: Receive the charging optimization instruction, obtain the charging optimization data of the battery, analyze the charging optimization data, and obtain the temperature optimization strategy of the battery under charging state.

[0014] Further, the temperature data set includes Q continuous time series temperature values;

[0015] The method for obtaining the battery operation evaluation coefficient includes:

[0016] Acquiring operating characteristic data of the battery, wherein the operating characteristic data includes a power change rate, an internal resistance change rate, and a voltage change rate;

[0017] The operation characteristic data is calculated by formula to obtain the battery operation evaluation coefficient, and the calculation formula is:

[0018] ;

[0019] In the formula, represents the battery operation evaluation coefficient, represents the power change rate, represents the internal resistance change rate, Dy represents the voltage change rate, represents the weighting factor of the power change rate, The weight factor representing the rate of change of internal resistance, A weighting factor representing the rate of voltage change.

[0020] Furthermore, the method for obtaining the voltage change rate includes:

[0021] Step a1: collecting the real-time voltage value of the voltage at a preset time interval through a voltage sensor;

[0022] Step a2: Calculate the voltage change within the time interval, and calculate the difference between every two consecutive voltage values, marked as voltage difference: ; In the formula, Indicates the voltage difference, represents the voltage value at time t+1, represents the voltage value at time t;

[0023] Step a3: Record and The corresponding time interval is , and calculate the voltage change rate based on the voltage difference and time interval: ;

[0024] The calculation method of the power change rate and the internal resistance change rate is the same as the calculation method of the voltage change rate.

[0025] Further, if the operating state of the battery is abnormal, a discharge warning instruction or a charge warning instruction is generated;

[0026] The method of analyzing the battery operation evaluation coefficient and determining the battery operation status includes:

[0027] A battery evaluation threshold is preset, and a battery operation evaluation coefficient is compared with the preset battery evaluation threshold;

[0028] If the power change rate is a positive value and the battery operation evaluation coefficient is less than the preset first evaluation threshold, the battery state is determined to be a discharge state, and a normal discharge instruction is generated;

[0029] If the power change rate is a positive value and the battery operation evaluation coefficient is greater than or equal to a preset first evaluation threshold, the battery state is determined to be a discharge state, and a discharge warning instruction is generated;

[0030] If the power change rate is a negative value and the battery operation evaluation coefficient is less than the preset second evaluation threshold, the battery state is determined to be a charging state, and a normal charging instruction is generated;

[0031] If the power change rate is a negative value and the battery operation evaluation coefficient is greater than or equal to the preset second evaluation threshold, the battery state is determined to be a charging state, and a charging warning instruction is generated;

[0032] The preset first evaluation threshold is greater than the preset second evaluation threshold.

[0033] Furthermore, the method for constructing the neural network model includes:

[0034] Acquire historical temperature training data, and divide the historical temperature training data into a temperature training set and a temperature test set; the historical temperature training data includes temperature characteristic data and its corresponding future temperature value; the temperature characteristic data includes a temperature data set and a battery operation evaluation coefficient;

[0035] The temperature data set in the temperature characteristic data is obtained by measuring the temperature data Q times in a time series by a temperature sensor, and each temperature value corresponding to the temperature data has a battery operation evaluation coefficient at the corresponding moment;

[0036] Construct a network regression model, use the temperature data set and battery operation evaluation coefficient in the temperature training set as input data of the network regression model, use the corresponding future temperature value in the temperature training set as output data of the network regression model, train the network regression model, and obtain an initial network regression model;

[0037] The initial network regression model is verified using a temperature test set, and an initial network regression model with a prediction error less than or equal to a preset prediction error is output as a neural network model; the initial network regression model is trained until the sum of the prediction errors reaches convergence, and the training is stopped; the neural network model is a random forest regression model, a long short-term memory network, or a gated recurrent unit algorithm.

[0038] Furthermore, the method of analyzing the future temperature value and determining whether to generate a discharge optimization instruction or a charge optimization instruction includes:

[0039] When the battery state is a discharge state, comparing the future temperature value with a preset first temperature threshold;

[0040] If the future temperature value is greater than or equal to a preset first temperature threshold, generating a discharge optimization instruction;

[0041] If the future temperature value is less than the preset first temperature threshold, no discharge optimization instruction is generated;

[0042] When the battery state is a charging state, comparing the future temperature value with a preset second temperature threshold;

[0043] If the future temperature value is greater than or equal to a preset second temperature threshold, generating a charging optimization instruction;

[0044] If the future temperature value is less than the preset second temperature threshold, no charging optimization instruction is generated;

[0045] The preset first temperature threshold is greater than the preset second temperature threshold.

[0046] Further, the discharge optimization data includes a discharge current and a first cooling flow rate;

[0047] The method of analyzing the discharge optimization data to obtain the temperature optimization strategy of the battery under the discharge state includes:

[0048] Step b1: obtaining discharge optimization data, simulating the discharge optimization data, taking the first cooling flow rate in the discharge optimization data as a quantitative value, the discharge current as a variable, and taking the current fluctuation value of the discharge current as E;

[0049] Step b2: Let , and record the current fluctuation value Test temperature value; is a constant;

[0050] Step b3: Repeat step b2 until the current fluctuation value Equal to the preset current fluctuation threshold, get the current fluctuation value The following G test temperature values ​​are obtained, and the process jumps to step b4, where G is an integer greater than zero;

[0051] Step b4: taking the discharge current in the discharge optimization data as the quantitative value, the first cooling flow rate as the variable, and taking the current fluctuation value of the first cooling flow rate as F;

[0052] Step b5: Let , and record the first flow rate fluctuation value Test temperature value; is a constant;

[0053] Step b6: Repeat step b5 until the first flow rate fluctuation value Equal to the preset first fluctuation threshold, the first flow rate fluctuation value is obtained H test temperature values ​​under the condition, H is an integer greater than zero;

[0054] Step b7: Count the current fluctuation value G test temperature values ​​and the first flow rate fluctuation value under The H test temperature values ​​under the condition are obtained to obtain L test temperature values, and the L test temperature values ​​are sorted from small to large in numerical value;

[0055] Step b8: The current fluctuation value and the first flow rate fluctuation value corresponding to the minimum test temperature value are used as a temperature optimization strategy for the battery in a discharge state.

[0056] Further, the charging optimization data includes charging power and cooling second flow rate;

[0057] The method of analyzing the charging optimization data to obtain the temperature optimization strategy of the battery under charging state includes:

[0058] Step c1: acquiring charging optimization data, and performing simulation on the charging optimization data, wherein the second cooling flow rate in the charging optimization data is used as a quantitative value, the charging power is used as a variable, and the current fluctuation value of the charging power is used as M;

[0059] Step c2: Let , and record the power fluctuation value Test temperature value; is a constant;

[0060] Step c3: Repeat step c2 until the power fluctuation value Equal to the preset power threshold, get the power fluctuation value The process then jumps to step c4, where K is an integer greater than zero.

[0061] Step c4: Taking the charging power in the charging optimization data as the quantitative value, the cooling second flow rate as the variable, and the current fluctuation value of the cooling second flow rate as the ;

[0062] Step c5: Let , and record the second flow rate fluctuation value Test temperature value; is a constant;

[0063] Step c6: Repeat step c5 until the second flow rate fluctuation value Equal to the preset second fluctuation threshold, the flow rate fluctuation value is obtained P test temperature values ​​under the condition where P is an integer greater than zero;

[0064] Step c7: Count the power fluctuation value K test temperature values ​​and the second flow rate fluctuation value under P test temperature values ​​under the condition are obtained to obtain W test temperature values, and the W test temperature values ​​are sorted from small to large in numerical value;

[0065] Step c8: The power fluctuation value and the second flow rate fluctuation value corresponding to the minimum test temperature value are used as a temperature optimization strategy for the battery in a charging state.

[0066] In a second aspect, the present invention provides a battery temperature intelligent dynamic optimization system for a liquid-cooled energy storage cabinet, which is used to implement the above-mentioned battery temperature intelligent dynamic optimization method for a liquid-cooled energy storage cabinet, comprising:

[0067] A data acquisition and analysis module is used to obtain a set of temperature data in a battery monitoring area in real time; and obtain a battery operation evaluation coefficient in real time, analyze the battery operation evaluation coefficient, and determine the battery operation state; the battery operation state includes a discharge state and a charge state, and generates a discharge normal instruction or a charge normal instruction respectively;

[0068] The prediction and judgment module is used to receive the corresponding normal instructions, input the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, and predict the future temperature value; analyze the future temperature value to determine whether to generate a discharge optimization instruction or a charge optimization instruction;

[0069] A discharge optimization module is used to receive a discharge optimization instruction, obtain discharge optimization data of the battery, analyze the discharge optimization data, and obtain a temperature optimization strategy for the battery under discharge;

[0070] The charging optimization module is used to receive charging optimization instructions, obtain battery charging optimization data, analyze the charging optimization data, and obtain a temperature optimization strategy for the battery under charging conditions.

[0071] In a third aspect, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0072] The processor executes the above-mentioned intelligent dynamic optimization method for battery temperature of the liquid-cooled energy storage cabinet by calling the computer program stored in the memory.

[0073] Technical effects and advantages of the present invention:

[0074] 1. The present invention can predict future temperature changes by inputting temperature data sets and battery operation evaluation coefficients into a pre-built neural network model, analyze temperature changes during discharge and charging according to the generated discharge or charge optimization instructions, and obtain targeted temperature optimization strategies, which is beneficial to dynamically adjust the cooling or current control strategy according to specific circumstances when the battery is discharged or charged, prevent battery overheating or inefficiency, and achieve preventive adjustment of battery temperature, thereby improving the battery's charge and discharge performance; greatly reducing unexpected failures and dangers, and improving the battery's operating efficiency and life.

[0075] 2. The present invention is fully automatic from real-time data collection, status evaluation, prediction to optimization and adjustment, which reduces the need for human intervention. Intelligent management reduces errors in operation, while improving the response speed and adjustment accuracy of the system, ensuring that the batteries of the liquid-cooled energy storage cabinet can always operate in the best condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 This is a flow chart of the intelligent dynamic optimization method for battery temperature of the liquid-cooled energy storage cabinet of Example 1;

[0077] Figure 2 A flow chart of a method for obtaining a temperature optimization strategy for a battery in a discharge state according to Example 1;

[0078] Figure 3 This is a schematic diagram of the structure of the battery temperature intelligent dynamic optimization system of the liquid-cooled energy storage cabinet of Example 2;

[0079] Figure 4 This is a schematic diagram of an electronic device according to Example 3. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0082] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0083] Example 1

[0084] See also Figure 1 As shown, this embodiment discloses a method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet, including:

[0085] Step 1: acquiring a temperature data set in a battery monitoring area in real time; and acquiring a battery operation evaluation coefficient in real time, analyzing the battery operation evaluation coefficient, and determining the battery operation state; the battery operation state includes a discharge state and a charge state, and generating a discharge normal instruction or a charge normal instruction respectively;

[0086] It should be noted that the battery monitoring area refers to the key area of ​​the battery and its surrounding environment, and multiple temperature sensors are arranged in the battery monitoring area to monitor the key points of the battery. The temperature sensors include thermocouples, thermistors and infrared sensors, etc., which are used to measure the temperature of the battery and the surrounding environment in real time. At the same time, load sensors, voltage sensors, power sensors and current sensors are provided in the liquid-cooled energy storage cabinet to monitor information such as the load of the liquid-cooled energy storage cabinet and the battery charge and discharge rate.

[0087] The temperature data set includes Q continuous time series temperature values;

[0088] In implementation, the method for obtaining the battery operation evaluation coefficient includes:

[0089] Acquiring operating characteristic data of the battery, wherein the operating characteristic data includes a power change rate, an internal resistance change rate, and a voltage change rate;

[0090] It should be noted that: the method for obtaining the voltage change rate includes:

[0091] Step a1: The voltage sensor collects the real-time voltage value at a preset time interval. The preset time interval can be milliseconds or seconds, which is specifically set by the staff.

[0092] Step a2: Calculate the voltage change within the time interval, and calculate the difference between every two consecutive voltage values, marked as voltage difference: ; In the formula, Indicates the voltage difference, represents the voltage value at time t+1, Represents the voltage value at time t.

[0093] Step a3: Record and The corresponding time interval is , and calculate the voltage change rate based on the voltage difference and time interval: .

[0094] The calculation method of the power change rate and the internal resistance change rate is the same as the calculation method of the voltage change rate, which will not be elaborated here.

[0095] The operation characteristic data is calculated by formula to obtain the battery operation evaluation coefficient calculation formula:

[0096] ;

[0097] In the formula, Represents the battery operation evaluation coefficient, represents the power change rate, represents the internal resistance change rate, Dy represents the voltage change rate, represents the weighting factor of the power change rate, The weight factor representing the rate of change of internal resistance, The weight factors representing the voltage change rate are set by those skilled in the art based on experience.

[0098] It should be noted that: when the power increases (whether charging or discharging), the battery's workload increases, so the evaluation coefficient increases relatively; as the internal resistance increases, the battery operation evaluation coefficient increases, indicating that the battery condition deteriorates.

[0099] It should also be noted that if the operating state of the battery is abnormal, a discharge warning instruction or a charge warning instruction is generated.

[0100] In implementation, the method of analyzing the battery operation evaluation coefficient and determining the battery operation state includes:

[0101] A battery evaluation threshold is preset, and a battery operation evaluation coefficient is compared with the preset battery evaluation threshold;

[0102] If the power change rate is a positive value and the battery operation evaluation coefficient is less than the preset first evaluation threshold, the battery state is judged to be a discharge state, and a normal discharge instruction is generated, indicating that the battery state is good;

[0103] If the power change rate is a positive value, and the battery operation evaluation coefficient is greater than or equal to the preset first evaluation threshold, the battery state is determined to be a discharge state, and a discharge warning instruction is generated, indicating that the battery state is poor during the discharge process and cannot be used further;

[0104] If the power change rate is a negative value and the battery operation evaluation coefficient is less than the preset second evaluation threshold, the battery state is judged to be a charging state, and a normal charging instruction is generated, indicating that the battery state is good;

[0105] If the power change rate is a negative value, and the battery operation evaluation coefficient is greater than or equal to the preset second evaluation threshold, the battery state is judged to be a charging state, and a charging warning instruction is generated, indicating that the battery state is poor during the charging process and cannot be used further;

[0106] It should be noted that the preset first evaluation threshold is greater than the preset second evaluation threshold because: during the battery charging and discharging process, the main task of the battery during discharge is to output stable electric energy. Relatively speaking, the requirements for the battery operating state allow it to have a larger battery operation evaluation coefficient, so the corresponding preset first evaluation threshold is larger; while during charging, if the battery operation evaluation coefficient is low, it often means that the internal resistance, temperature, etc. of the battery are not in good condition and the problems are more prominent, requiring stricter control, so the preset second evaluation threshold corresponding to the charging state is smaller. The preset first evaluation threshold and the preset second evaluation threshold are both determined by technicians in this field based on actual application needs and through analysis and summary of a large amount of experimental data.

[0107] This step ensures the safety and stability of the battery during the charging and discharging process by real-time monitoring of the battery system of the liquid-cooled energy storage cabinet, providing a data basis for optimizing the battery's thermal management strategy and thus extending the battery life.

[0108] Step 2: Receive the corresponding normal instruction, input the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, and predict the future temperature value; analyze the future temperature value to determine whether to generate a discharge optimization instruction or a charge optimization instruction;

[0109] In implementation, the method for constructing the neural network model includes:

[0110] Acquire historical temperature training data, and divide the historical temperature training data into a temperature training set and a temperature test set; the historical temperature training data includes temperature characteristic data and its corresponding future temperature value; the temperature characteristic data includes a temperature data set and a battery operation evaluation coefficient.

[0111] It should be noted that: the temperature data set in the temperature characteristic data is obtained by measuring the temperature data Q times in time series by the temperature sensor, and the temperature value corresponding to each temperature data has the battery operation evaluation coefficient at the corresponding moment; the future temperature value is obtained by averaging the temperature data at multiple future prediction moments within the preset prediction period. The unit of the preset prediction period is the same as the unit of the preset time interval.

[0112] Construct a network regression model, use the temperature data set and battery operation evaluation coefficient in the temperature training set as input data of the network regression model, use the corresponding future temperature value in the temperature training set as output data of the network regression model, train the network regression model, and obtain an initial network regression model;

[0113] The temperature test set is used to verify the initial network regression model, and the initial network regression model with a prediction error less than or equal to the preset prediction error is output as the neural network model; the prediction error is calculated as follows: ,in, is the prediction error, is the group number of the characteristic vector corresponding to the temperature characteristic data, For the The predicted future temperature value corresponding to the set of temperature feature data, For the The actual future temperature value corresponding to the group analysis data; the initial network regression model is trained until the sum of the prediction errors reaches convergence and the training is stopped; the neural network model is a random forest regression model, a long short-term memory network or a gated recurrent unit algorithm.

[0114] In implementation, the method of analyzing the future temperature value and determining whether to generate a discharge optimization instruction or a charge optimization instruction includes:

[0115] When the battery state is a discharge state, comparing the future temperature value with a preset first temperature threshold;

[0116] If the future temperature value is greater than or equal to the preset first temperature threshold, a discharge optimization instruction is generated; this indicates that the battery temperature will be too high during the future discharge process, and the system will generate a discharge optimization instruction, prompting that a cooling operation is required to prevent the battery temperature from being too high;

[0117] If the future temperature value is less than the preset first temperature threshold, no discharge optimization instruction is generated; this indicates that the temperature of the battery is within a safe range during the future discharge process and no additional adjustment is required, so no discharge optimization instruction is generated;

[0118] When the battery state is a charging state, comparing the future temperature value with a preset second temperature threshold;

[0119] If the future temperature value is greater than or equal to the preset second temperature threshold, a charging optimization instruction is generated; this indicates that the battery temperature is too high during the future charging process, and the system will generate a charging optimization instruction, prompting the need to reduce the charging power or strengthen cooling measures to prevent the battery from being damaged due to overheating during charging;

[0120] If the future temperature value is less than the preset second temperature threshold, no charging optimization instruction is generated; this indicates that the temperature during the charging process is within a safe range, the system does not generate a charging optimization instruction, and no additional adjustment is required.

[0121] It should be noted that the preset first temperature threshold is greater than the preset second temperature threshold; the reason why the preset first temperature threshold is greater than the preset second temperature threshold is that when the battery is discharged, the electrical energy caused by the internal resistance is converted into heat energy, especially when the battery is discharged at high power, the heat generated by the battery will increase accordingly. Therefore, the temperature threshold setting during the discharge process needs to take into account the maximum allowable temperature of the battery during discharge; when the battery is charged, especially when fast charging or high power charging, the electrochemical reaction inside the battery will generate heat, especially when the battery is close to full, the temperature rise is more obvious, therefore, the temperature threshold during the charging process will be lower to prevent overheating during the charging process.

[0122] This step monitors and manages the temperature in real time during the battery charging and discharging process to ensure that the battery operates within a safe and effective temperature range, thereby avoiding damage or safety issues caused by overheating, while optimizing the battery's charging and discharging efficiency.

[0123] Step 3: Receive the discharge optimization instruction, obtain the discharge optimization data of the battery, analyze the discharge optimization data, and obtain the temperature optimization strategy of the battery under the discharge state;

[0124] It should be noted that: the discharge optimization data includes discharge current and cooling first flow rate; the discharge current refers to the current released by the battery during the discharge process, which is measured and obtained by a current sensor installed in the battery circuit; the cooling first flow rate includes the coolant flow rate or the gas flow rate, which is collected by a flow sensor; the cooling first flow rate is used to cool the battery temperature during the discharge process; the discharge current and the cooling first flow rate fluctuation values ​​are adjusted in real time to ensure that the battery operates within the optimal temperature range.

[0125] See also Figure 2 As shown, in implementation, the method of analyzing the discharge optimization data to obtain the temperature optimization strategy of the battery in the discharge state includes:

[0126] Step b1: obtaining discharge optimization data, simulating the discharge optimization data, taking the first cooling flow rate in the discharge optimization data as a quantitative value, the discharge current as a variable, and taking the current fluctuation value of the discharge current as E;

[0127] Step b2: Let , and record the current fluctuation value Test temperature value; is a constant;

[0128] Step b3: Repeat step b2 until the current fluctuation value Equal to the preset current fluctuation threshold, get the current fluctuation value The following G test temperature values ​​are obtained, and the process jumps to step b4, where G is an integer greater than zero;

[0129] Step b4: taking the discharge current in the discharge optimization data as the quantitative value, the first cooling flow rate as the variable, and taking the current fluctuation value of the first cooling flow rate as F;

[0130] Step b5: Let , and record the first flow rate fluctuation value Test temperature value; is a constant;

[0131] Step b6: Repeat step b5 until the first flow rate fluctuation value Equal to the preset first fluctuation threshold, the first flow rate fluctuation value is obtained H test temperature values ​​under the condition, H is an integer greater than zero;

[0132] Step b7: Count the current fluctuation value G test temperature values ​​and the first flow rate fluctuation value under The H test temperature values ​​under the condition are obtained to obtain L test temperature values, and the L test temperature values ​​are sorted from small to large in numerical value;

[0133] Step b8: The current fluctuation value and the first flow rate fluctuation value corresponding to the minimum test temperature value are used as a temperature optimization strategy for the battery in a discharge state.

[0134] Step 4: Receive the charging optimization instruction, obtain the charging optimization data of the battery, analyze the charging optimization data, and obtain the temperature optimization strategy of the battery under charging state;

[0135] The charging optimization data includes charging power and cooling second flow rate; the charging power refers to the energy transfer rate received by the battery during the charging process; the cooling second flow rate is used to cool the battery temperature during the charging process; by real-time adjustment of the fluctuation value of the charging power and the cooling second flow rate, the battery is ensured to operate within the optimal temperature range.

[0136] In implementation, the method of analyzing charging optimization data to obtain a temperature optimization strategy for the battery under charging includes:

[0137] Step c1: acquiring charging optimization data, and performing simulation on the charging optimization data, wherein the second cooling flow rate in the charging optimization data is used as a quantitative value, the charging power is used as a variable, and the current fluctuation value of the charging power is used as M;

[0138] Step c2: Let , and record the power fluctuation value Test temperature value; is a constant;

[0139] Step c3: Repeat step c2 until the power fluctuation value Equal to the preset power threshold, get the power fluctuation value The process then jumps to step c4, where K is an integer greater than zero.

[0140] Step c4: Taking the charging power in the charging optimization data as the quantitative value, the cooling second flow rate as the variable, and the current fluctuation value of the cooling second flow rate as the ;

[0141] Step c5: Let , and record the second flow rate fluctuation value Test temperature value; is a constant;

[0142] Step c6: Repeat step c5 until the second flow rate fluctuation value Equal to the preset second fluctuation threshold, the flow rate fluctuation value is obtained P test temperature values ​​under the condition where P is an integer greater than zero;

[0143] Step c7: Count the power fluctuation value K test temperature values ​​and the second flow rate fluctuation value under P test temperature values ​​under the condition are obtained to obtain W test temperature values, and the W test temperature values ​​are sorted from small to large in numerical value;

[0144] Step c8: The power fluctuation value and the second flow rate fluctuation value corresponding to the minimum test temperature value are used as a temperature optimization strategy for the battery in a charging state.

[0145] This embodiment can predict future temperature changes by inputting the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, analyze the temperature changes during the discharge and charging process according to the generated discharge or charging optimization instructions, and obtain targeted temperature optimization strategies, which is beneficial for dynamically adjusting the cooling or current control strategy according to the specific situation when the battery is discharging or charging, preventing the battery from overheating or inefficiency, and realizing preventive adjustment of the battery temperature, thereby improving the battery's charging and discharging performance; greatly reducing unexpected failures and dangers, and improving the battery's operating efficiency and life.

[0146] This embodiment is fully automatic from real-time data collection, status evaluation, prediction to optimization and adjustment, which reduces the need for human intervention. Intelligent management reduces errors in operation, while improving the response speed and adjustment accuracy of the liquid-cooled energy storage cabinet, ensuring that the battery of the liquid-cooled energy storage cabinet can always operate in the best condition.

[0147] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by the technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0148] Example 2

[0149] See also Figure 3 As shown, this embodiment provides a battery temperature intelligent dynamic optimization system for a liquid-cooled energy storage cabinet, including a data acquisition and analysis module, a prediction and judgment module, a discharge optimization module, and a charging optimization module; each module is connected by wire and / or wireless means to achieve data transmission between modules;

[0150] A data acquisition and analysis module is used to obtain a set of temperature data in a battery monitoring area in real time; and obtain a battery operation evaluation coefficient in real time, analyze the battery operation evaluation coefficient, and determine the battery operation state; the battery operation state includes a discharge state and a charge state, and generates a discharge normal instruction or a charge normal instruction respectively;

[0151] The prediction and judgment module is used to receive the corresponding normal instructions, input the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, and predict the future temperature value; analyze the future temperature value to determine whether to generate a discharge optimization instruction or a charge optimization instruction;

[0152] A discharge optimization module is used to receive a discharge optimization instruction, obtain discharge optimization data of the battery, analyze the discharge optimization data, and obtain a temperature optimization strategy for the battery under discharge;

[0153] The charging optimization module is used to receive charging optimization instructions, obtain battery charging optimization data, analyze the charging optimization data, and obtain a temperature optimization strategy for the battery under charging conditions.

[0154] Example 3

[0155] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device of this embodiment includes: a processor 11 ( Figure 4Only one processor is shown in the figure), a memory 12, and a computer program 13 stored in the memory 12 and executable on the processor 11. When the processor 11 executes the computer program 13, the steps in the embodiment of the intelligent dynamic optimization method for battery temperature of the liquid-cooled energy storage cabinet are implemented, for example Figure 1 Alternatively, when the processor 11 executes the computer program 13, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 3 The module functions shown. Exemplarily, the computer program 13 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 12 and executed by the processor 11 to complete the present application. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 13 in the terminal device. Those skilled in the art can understand that Figure 4 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0156] The processor 11 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0157] The memory 12 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The memory 12 may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the terminal device. Further, the memory 12 may also include both an internal storage unit of the terminal device and an external storage device. The memory 12 is used to store the computer program and other programs and data required by the terminal device. The memory 12 may also be used to temporarily store data that has been output or is to be output.

[0158] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0159] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent dynamic optimization method for battery temperature of a liquid-cooled energy storage cabinet, characterized in that: include: Step 1: Acquire the temperature data set in the battery monitoring area in real time; and obtaining a battery operation evaluation coefficient in real time, analyzing the battery operation evaluation coefficient, and determining the battery operation state; the battery operation state includes a discharge state and a charge state, and generating a discharge normal instruction or a charge normal instruction respectively; Step 2: Receive the corresponding normal instruction, input the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, and predict the future temperature value; analyze the future temperature value to determine whether to generate a discharge optimization instruction or a charge optimization instruction; Step 3: Receive the discharge optimization instruction, obtain the discharge optimization data of the battery, analyze the discharge optimization data, and obtain the temperature optimization strategy of the battery under the discharge state; Step 4: Receive the charging optimization instruction, obtain the charging optimization data of the battery, analyze the charging optimization data, and obtain the temperature optimization strategy of the battery under charging state.

2. The intelligent dynamic optimization method for battery temperature of a liquid-cooled energy storage cabinet according to claim 1 is characterized in that: The temperature data set includes Q continuous time series temperature values; The method for obtaining the battery operation evaluation coefficient includes: Acquiring operating characteristic data of the battery, wherein the operating characteristic data includes a power change rate, an internal resistance change rate, and a voltage change rate; The operation characteristic data is calculated by formula to obtain the battery operation evaluation coefficient, and the calculation formula is: ； In the formula, Represents the battery operation evaluation coefficient, represents the power change rate, represents the internal resistance change rate, Dy represents the voltage change rate, represents the weighting factor of the power change rate, The weight factor representing the rate of change of internal resistance, A weighting factor representing the rate of voltage change.

3. The method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet according to claim 2 is characterized in that: The method for obtaining the voltage change rate includes: Step a1: collecting the real-time voltage value of the voltage at a preset time interval through a voltage sensor; Step a2: Calculate the voltage change within the time interval, and calculate the difference between every two consecutive voltage values, marked as voltage difference: ; In the formula, Indicates the voltage difference, represents the voltage value at time t+1, represents the voltage value at time t; Step a3: Record and The corresponding time interval is , and calculate the voltage change rate based on the voltage difference and time interval: ; The calculation method of the power change rate and the internal resistance change rate is the same as the calculation method of the voltage change rate.

4. The method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet according to claim 3 is characterized in that: If the operating state of the battery is abnormal, a discharge warning instruction or a charge warning instruction is generated; The method of analyzing the battery operation evaluation coefficient and determining the battery operation status includes: A battery evaluation threshold is preset, and a battery operation evaluation coefficient is compared with the preset battery evaluation threshold; If the power change rate is a positive value and the battery operation evaluation coefficient is less than the preset first evaluation threshold, the battery state is determined to be a discharge state, and a normal discharge instruction is generated; If the power change rate is a positive value and the battery operation evaluation coefficient is greater than or equal to a preset first evaluation threshold, the battery state is determined to be a discharge state, and a discharge warning instruction is generated; If the power change rate is a negative value and the battery operation evaluation coefficient is less than the preset second evaluation threshold, the battery state is determined to be a charging state, and a normal charging instruction is generated; If the power change rate is a negative value and the battery operation evaluation coefficient is greater than or equal to the preset second evaluation threshold, the battery state is determined to be a charging state, and a charging warning instruction is generated; The preset first evaluation threshold is greater than the preset second evaluation threshold.

5. The method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet according to claim 4 is characterized in that: The method for constructing the neural network model includes: Acquire historical temperature training data, and divide the historical temperature training data into a temperature training set and a temperature test set; the historical temperature training data includes temperature characteristic data and its corresponding future temperature value; the temperature characteristic data includes a temperature data set and a battery operation evaluation coefficient; The temperature data set in the temperature characteristic data is obtained by measuring the temperature data Q times in a time series by a temperature sensor, and each temperature value corresponding to the temperature data has a battery operation evaluation coefficient at the corresponding moment; Construct a network regression model, use the temperature data set and battery operation evaluation coefficient in the temperature training set as input data of the network regression model, use the corresponding future temperature value in the temperature training set as output data of the network regression model, train the network regression model, and obtain an initial network regression model; The initial network regression model is verified using a temperature test set, and an initial network regression model with a prediction error less than or equal to a preset prediction error is output as a neural network model; the initial network regression model is trained until the sum of the prediction errors reaches convergence, and the training is stopped; the neural network model is a random forest regression model, a long short-term memory network, or a gated recurrent unit algorithm.

6. The method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet according to claim 5 is characterized in that: The method of analyzing the future temperature value and determining whether to generate a discharge optimization instruction or a charge optimization instruction includes: When the battery state is a discharge state, comparing the future temperature value with a preset first temperature threshold; If the future temperature value is greater than or equal to a preset first temperature threshold, generating a discharge optimization instruction; If the future temperature value is less than the preset first temperature threshold, no discharge optimization instruction is generated; When the battery state is a charging state, comparing the future temperature value with a preset second temperature threshold; If the future temperature value is greater than or equal to a preset second temperature threshold, generating a charging optimization instruction; If the future temperature value is less than the preset second temperature threshold, no charging optimization instruction is generated; The preset first temperature threshold is greater than the preset second temperature threshold.

7. The method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet according to claim 6, characterized in that: The discharge optimization data includes a discharge current and a first cooling flow rate; The method of analyzing the discharge optimization data to obtain the temperature optimization strategy of the battery under the discharge state includes: Step b1: obtaining discharge optimization data, simulating the discharge optimization data, taking the first cooling flow rate in the discharge optimization data as a quantitative value, the discharge current as a variable, and taking the current fluctuation value of the discharge current as E; Step b2: Let , and record the current fluctuation value Test temperature value; is a constant; Step b3: Repeat step b2 until the current fluctuation value Equal to the preset current fluctuation threshold, get the current fluctuation value The following G test temperature values ​​are obtained, and the process jumps to step b4, where G is an integer greater than zero; Step b4: taking the discharge current in the discharge optimization data as the quantitative value, the first cooling flow rate as the variable, and taking the current fluctuation value of the first cooling flow rate as F; Step b5: Let , and record the first flow rate fluctuation value Test temperature value; is a constant; Step b6: Repeat step b5 until the first flow rate fluctuation value Equal to the preset first fluctuation threshold, the first flow rate fluctuation value is obtained H test temperature values ​​under the condition, H is an integer greater than zero; Step b7: Count the current fluctuation value G test temperature values ​​and the first flow rate fluctuation value under The H test temperature values ​​under the condition are obtained to obtain L test temperature values, and the L test temperature values ​​are sorted from small to large in numerical value; Step b8: The current fluctuation value and the first flow rate fluctuation value corresponding to the minimum test temperature value are used as a temperature optimization strategy for the battery in a discharge state.

8. The method for intelligent dynamic optimization of battery temperature of a liquid-cooled energy storage cabinet according to claim 7, characterized in that: The charging optimization data includes charging power and cooling second flow rate; The method of analyzing the charging optimization data to obtain the temperature optimization strategy of the battery under charging state includes: Step c1: acquiring charging optimization data, and performing simulation on the charging optimization data, wherein the second cooling flow rate in the charging optimization data is used as a quantitative value, the charging power is used as a variable, and the current fluctuation value of the charging power is used as M; Step c2: Let , and record the power fluctuation value Test temperature value; is a constant; Step c3: Repeat step c2 until the power fluctuation value Equal to the preset power threshold, get the power fluctuation value The process then jumps to step c4, where K is an integer greater than zero. Step c4: Taking the charging power in the charging optimization data as the quantitative value, the cooling second flow rate as the variable, and the current fluctuation value of the cooling second flow rate as the ; Step c5: Let , and record the second flow rate fluctuation value Test temperature value; is a constant; Step c6: Repeat step c5 until the second flow rate fluctuation value Equal to the preset second fluctuation threshold, the flow rate fluctuation value is obtained P test temperature values ​​under the condition where P is an integer greater than zero; Step c7: Count the power fluctuation value K test temperature values ​​and the second flow rate fluctuation value under P test temperature values ​​under the condition are obtained to obtain W test temperature values, and the W test temperature values ​​are sorted from small to large in numerical value; Step c8: The power fluctuation value and the second flow rate fluctuation value corresponding to the minimum test temperature value are used as a temperature optimization strategy for the battery in a charging state.

9. A battery temperature intelligent dynamic optimization system for a liquid-cooled energy storage cabinet, used to implement the battery temperature intelligent dynamic optimization method for a liquid-cooled energy storage cabinet according to any one of claims 1 to 8, characterized in that: include: Data acquisition and analysis module, used to obtain temperature data sets in the battery monitoring area in real time; and obtaining a battery operation evaluation coefficient in real time, analyzing the battery operation evaluation coefficient, and determining the battery operation state; the battery operation state includes a discharge state and a charge state, and generating a discharge normal instruction or a charge normal instruction respectively; A prediction and judgment module is used to receive the corresponding normal instructions, input the temperature data set and the battery operation evaluation coefficient into the pre-built neural network model, and predict the future temperature value; Analyze the future temperature value to determine whether to generate a discharge optimization instruction or a charge optimization instruction; A discharge optimization module is used to receive a discharge optimization instruction, obtain discharge optimization data of the battery, analyze the discharge optimization data, and obtain a temperature optimization strategy for the battery under discharge; The charging optimization module is used to receive charging optimization instructions, obtain battery charging optimization data, analyze the charging optimization data, and obtain a temperature optimization strategy for the battery under charging conditions.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the intelligent dynamic optimization method for battery temperature of the liquid-cooled energy storage cabinet according to any one of claims 1 to 8 by calling the computer program stored in the memory.

Images