Forklift power battery pack management method, device and equipment and storage medium

Abstract

The invention relates to the technical field of forklift power battery pack management, and discloses a forklift power battery pack management method, device and equipment and a storage medium and system, and the forklift power battery pack management system comprises a dynamic load prediction module, a multi-mode heat management module and a self-adaptive current control module. A dynamic load prediction model optimized through edge calculation is deeply coupled with a multi-mode thermal management system to form a real-time cooperative closed loop, and the problem of lagging of load change and battery temperature rise response is solved. And through closed-loop optimization of data streams among the modules, adaptive adjustment under multiple working conditions is realized, and the service life of the battery and the energy efficiency are remarkably improved under the hardware condition with limited resources. The mechanism of experimental calibration of cooling coefficient and real-time load coupling adjustment effectively balances cooling energy consumption and temperature control requirements, and significantly reduces system energy consumption. And meanwhile, the intelligent adaptability of the system is enhanced by long-term data recording and optimization iteration supported by the cloud platform, so that the system has the capability of continuously optimizing the performance in a complex operation environment.

Description

Technical Field

[0001] The present invention relates to a forklift power battery pack management method, device, equipment, storage medium and system, belonging to the technical field of vehicle battery management. Background Art

[0002] Forklift power battery packs are widely used in logistics, transportation, warehouse management and other fields. Their core function is to provide stable power support for forklifts under complex working conditions such as heavy loads and high-frequency start and stop. In existing technologies, the management of forklift power battery packs usually relies on traditional load prediction and static thermal management modes, aiming to extend battery life and improve energy utilization efficiency. However, these technologies still face many problems in practical applications.

[0003] In order to improve load adaptability, traditional methods use load prediction models based on fixed working conditions to guide the discharge strategy of the battery pack. However, these models lack real-time and dynamic adjustment capabilities, and cannot respond to load changes in a timely manner under rapidly changing working conditions (such as high-frequency start-stop or heavy-load operation), resulting in battery overload or uneven discharge. To solve this problem, the industry usually adopts increasing redundant battery capacity or designing complex control algorithms, but this inevitably increases hardware costs and system complexity.

[0004] In terms of thermal management, the existing technologies mostly use passive heat dissipation or simple air cooling or liquid cooling methods to adjust the cooling power according to the static heat dissipation mode. However, this method is difficult to cope with the dynamic thermal management requirements of complex working conditions, and it is easy to cause heat dissipation lag or excessive energy consumption. To overcome this defect, the industry has tried to optimize heat dissipation through preset cooling strategies based on historical working conditions. However, this preset method does not respond enough to sudden high loads and ambient temperature changes, and may still cause battery overheating or insufficient cooling, such as: 1. Traditional load prediction models lack real-time dynamic adjustment capabilities and cannot meet the load change requirements under complex working conditions. 2. Existing thermal management technologies have a delayed response, excessive energy consumption, and it is difficult to achieve accurate heat dissipation under dynamic conditions. 3. Insufficient collaboration between modules and data isolation lead to limited system optimization effects. Therefore, how to achieve the coordinated optimization of dynamic load prediction and multi-mode thermal management systems and significantly improve the comprehensive performance of forklift power battery packs has become a technical problem to be solved by the present invention. Summary of the invention

[0005] The present invention provides a forklift power battery pack management method, device, equipment and storage medium, the main purpose of which is to solve the problems of dynamic load response lag, low thermal management efficiency and insufficient inter-module collaboration.

[0006] To achieve the above-mentioned purpose, the present invention provides a forklift power battery pack management method, comprising the following management steps: Step 1, real-time data collection through a data acquisition module: real-time data collection of the voltage, current, temperature of the battery pack and the operating load data of the forklift through a distributed sensor module, wherein: the voltage data is used to evaluate the state of the battery unit; the current data is used to calculate the instantaneous load demand of the forklift; the temperature data is used to monitor the thermal stability of the battery pack; the operating load data is dynamically recorded based on the operating mode of the forklift; Step 2: Perform dynamic load forecasting through the dynamic load forecasting module: Based on the long short-term memory network (LSTM) algorithm, establish a forecasting model to segment the real-time collected load data; use historical load data to train the model weights, and update the model parameters in real time to optimize the forecasting accuracy; predict the load demand for the next period, specifically quantify the load fluctuation amplitude and frequency, and generate a load forecast value , the calculation formula is: ;in, and They are historical data weight and real-time data weight. is the hidden state value at the previous moment, is the current input data, is the bias term, is the activation function; Step 3: Perform multi-mode thermal management through the multi-mode thermal management module: Dynamically select the cooling mode based on real-time temperature data and load prediction values: When the temperature When the temperature is less than 30°C, the passive cooling mode is activated; when the temperature When the temperature is between 30°C and 45°C, the air cooling mode is activated and the cooling power is adjusted according to the formula: ;in, is the cooling power adjustment coefficient; when the temperature When the temperature exceeds 45°C, liquid cooling mode is activated and the cooling intensity is dynamically adjusted according to the load prediction value : ;in, is the load-dependent cooling factor; Step 4: Adaptive current control is performed through the adaptive current control module: according to the load prediction value and battery pack status parameters to adjust the discharge current of each battery cell in real time , to balance the load distribution among battery cells, the specific control rules are: ;in, is the number of battery cells, is the unit battery voltage; limits the unit battery current change rate to ensure that the change within one second does not exceed 5% of the rated value; Step 5, inter-module collaborative optimization: The dynamic load prediction module works with the multi-mode thermal management module to adjust the cooling mode in real time according to the load prediction value; the adaptive current control module dynamically optimizes the battery cell discharge strategy based on the load prediction and thermal management feedback; data is transmitted and processed through a unified edge computing device; Step 6, data feedback and system update: Data is transmitted to the cloud platform through edge computing devices. The cloud platform analyzes and predicts model performance and thermal management effects, and regularly updates model weights and cooling strategy parameters. The cloud platform generates a dynamic maintenance plan, including battery maintenance recommendations and cooling system optimization guidance.

[0007] Preferably, the long short-term memory network LSTM model in the dynamic load forecasting further includes: an embedding layer for reducing the dimension of the load data collected in real time; a bidirectional LSTM layer for simultaneously capturing the before and after time dependencies of the load data; and a densely connected layer for converting the output time series forecast value into the load forecast value at the next moment.

[0008] Preferably, the weight coefficient of the load prediction model is and The initial value of is determined by the following method: normalizing the historical load data; fitting the prediction error using the least squares method and calculating the gradient of each iteration; optimizing the weight coefficient based on the gradient descent algorithm until the prediction error converges to the preset threshold.

[0009] Preferably, the cooling power adjustment coefficient of the multi-mode thermal management system is and load-dependent cooling factor It is obtained through experimental calibration methods, specifically including: measuring the heat loss at the cooling mode switching point under different temperature conditions; calculating the energy consumption and heat dissipation ratio under each cooling mode, and optimizing the cooling coefficient.

[0010] Preferably, the discharge current of the adaptive current control module The adjustment strategy further includes: correcting the discharge current in real time according to the internal impedance change of the battery cell; the internal impedance change is calculated by collecting the voltage and current of the battery cell in real time, and the formula is: ;in, is the load terminal voltage.

[0011] Preferably, the collaborative optimization between the modules further includes the following steps: the dynamic load prediction module updates the prediction value every 1 second and transmits the prediction result to the multi-mode thermal management system; the multi-mode thermal management system updates the cooling strategy according to the load prediction value, and feeds back the actual cooling efficiency to the adaptive current control module; the adaptive current control module adjusts the discharge current in real time, and returns the adjustment result to the dynamic load prediction module to update the load model at the next moment.

[0012] Preferably, in the feedback update step, the following data are recorded through the cloud platform for model optimization: the actual error of each load prediction; the energy consumption and heat dissipation efficiency under each cooling mode; the discharge curve and life trend of the battery unit.

[0013] A device based on a forklift power battery pack management method includes: a data acquisition module for real-time acquisition of voltage, current, temperature of a battery pack and forklift operation load data; a prediction module for predicting the load demand at the next moment based on a long short-term memory network (LSTM) model; a thermal management module for dynamically adjusting a cooling mode according to load prediction values ​​and temperature data; a current control module for real-time adjustment of the discharge current of a battery cell; and an edge computing module for realizing data transmission and collaborative optimization between modules.

[0014] A device based on a forklift power battery pack management method, the device comprising: at least one device, the device comprising a data acquisition module, a prediction module, a thermal management module, a current control module and an edge computing module; a communication module, used to communicate with a cloud platform to achieve data uploading and feedback sending; a storage module, used to store load data, temperature data and model optimization parameters.

[0015] A storage medium based on a forklift power battery pack management method stores computer-readable instructions. When the instructions are executed by a computing device, the computing device implements the following steps: collecting real-time data of the battery pack and inputting it into a long short-term memory network model; adjusting the cooling strategy and discharge current according to the load prediction value output by the model; transmitting the data to a cloud platform to optimize the model parameters; and updating the operating parameters of the device according to the feedback from the cloud platform.

[0016] Compared with the problems described in the background technology, the beneficial effects of the present invention are: through the lightweight dynamic load prediction model optimized by edge computing, the real-time load prediction is deeply coupled with the multi-mode thermal management system, breaking through the limitations of single module optimization, and realizing the two-way adjustment of the dynamic correlation between load change and temperature rise, which not only improves the prediction accuracy of the system, but also significantly reduces the response lag of the cooling system, so that load prediction and thermal management form a real-time collaborative closed loop; the system integrates dynamic load prediction, adaptive current control and multi-mode thermal management modules, and realizes adaptive optimization of multiple working conditions (such as high-frequency start and stop, heavy-load transportation, and low-temperature operation) under resource-constrained hardware conditions through closed-loop optimization of real-time data flow between modules. This collaborative optimization strategy effectively balances the complex contradictions of battery life, discharge efficiency and system energy consumption, and shows a comprehensive balance of multi-dimensional performance improvement; the dynamic adjustment mechanism of experimental calibration cooling coefficient coupled with real-time load prediction is adopted to achieve the optimal balance between cooling energy consumption and battery life. Especially under frequent heavy load or low temperature conditions, this mechanism can reduce overheating or low temperature losses through precise thermal management strategies, providing technical support for extending battery life while reducing additional energy consumption; through long-term data recording and analysis on the cloud platform, the system can continuously optimize the prediction model weights and thermal management strategy parameters based on actual operating data, so that the entire management method has the ability to continuously improve performance in multiple scenarios and dynamic conditions. This function significantly enhances the stability and intelligence of the system in complex operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the dynamic load prediction and thermal management system of the present invention.

[0018] Figure 2 The data interaction and workflow diagram between various modules in the forklift power battery pack management system of the present invention.

[0019] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0021] See also Figure 1 and Figure 2 The present application embodiment provides a forklift power battery pack management method, device, equipment and storage medium. It includes the following management steps: Step 1, real-time data collection through the data acquisition module: the voltage, current, temperature of the battery pack and the operating load data of the forklift are collected in real time through the distributed sensor module, wherein: the voltage data is used to evaluate the state of the battery unit; the current data is used to calculate the instantaneous load demand of the forklift; the temperature data is used to monitor the thermal stability of the battery pack; the operating load data is dynamically recorded based on the operating mode of the forklift; Step 2: Perform dynamic load forecasting through the dynamic load forecasting module: Based on the long short-term memory network (LSTM) algorithm, establish a forecasting model to segment the real-time collected load data; use historical load data to train the model weights, and update the model parameters in real time to optimize the forecasting accuracy; predict the load demand for the next period, specifically quantify the load fluctuation amplitude and frequency, and generate a load forecast value , the calculation formula is: ;in, and They are historical data weight and real-time data weight. , is the hidden state value at the previous moment, is the current input data, is the bias term, is the activation function; The hidden state value at the previous moment ( ) is the output state of the LSTM model, which is used to store the association information between the current prediction value and historical data. Its calculation formula is: ;in, is the hidden state weight, is the input weight, is the input data at the current moment, is the bias term, is an activation function (such as tanh). For example, in forklift power battery load prediction, the hidden state value is used to record the trend of load change at the previous moment, guiding the selection of subsequent cooling mode and optimization of discharge path.

[0022] Step 3: Perform multi-mode thermal management through the multi-mode thermal management module: Dynamically select the cooling mode based on real-time temperature data and load prediction values: When the temperature When the temperature is less than 30°C, the passive cooling mode is activated; when the temperature When the temperature is between 30°C and 45°C, the air cooling mode is activated and the cooling power is adjusted according to the formula: ;in, is the cooling power adjustment coefficient; when the temperature When the temperature exceeds 45°C, liquid cooling mode is activated and the cooling intensity is dynamically adjusted according to the load prediction value : ;in, The multi-mode thermal management module provides real-time feedback on cooling efficiency and adjusts the cooling strategy to avoid energy waste. Cooling efficiency ( ) is calculated based on cooling energy consumption and temperature change, the formula is: ;in, is the temperature difference before and after cooling, is the energy consumed in cooling mode. The cooling efficiency is monitored by the sensor module in real time with temperature and power data, and transmitted to the thermal management module through the edge computing module. It adjusts the cooling strategy path, such as: when the cooling efficiency is lower than the preset threshold (e.g. ), the thermal management module switches to a more efficient cooling mode (such as switching from air cooling to liquid cooling) and adjusts the cooling intensity according to the real-time load prediction value: ;in, is the cooling coefficient, is the load prediction value.

[0023] Step 4: Adaptive current control is performed through the adaptive current control module: according to the load prediction value and battery pack status parameters to adjust the discharge current of each battery cell in real time , to balance the load distribution among battery cells, the specific control rules are: ;in, is the number of battery cells, is the unit battery voltage; limits the unit battery current change rate to ensure that the change within one second does not exceed 5% of the rated value; the rated value The designed discharge capacity of the battery cell is provided by the manufacturer. The current change rate is calculated as follows: ;in, seconds. Real-time monitoring of the unit battery current value, if the current change rate exceeds the limit value ( ), by adjusting the output value of the load prediction module, the discharge current distribution is dynamically optimized to ensure the operating safety of each battery unit.

[0024] Step 5, inter-module collaborative optimization: The dynamic load prediction module works with the multi-mode thermal management module to adjust the cooling mode in real time according to the load prediction value; the adaptive current control module dynamically optimizes the battery cell discharge strategy based on the load prediction and thermal management feedback; data is transmitted and processed through a unified edge computing device to achieve collaborative optimization of each module; among them, the dynamic optimization of the battery cell discharge strategy is based on the real-time load prediction value , battery cell status parameters (such as voltage 、Internal resistance ) and the cooling efficiency fed back by the thermal management module. The discharge current calculation formula is: ; and corrected according to the change of internal resistance: The edge computing device is responsible for aggregating sensor data, running short-term prediction models, transmitting control instructions, and realizing collaborative optimization between modules through a unified communication protocol. The collaborative optimization between modules includes real-time update of the dynamic load prediction module, adjustment of the cooling strategy of the thermal management module, and optimization of the discharge current of the adaptive current control module, ensuring the real-time and high efficiency of the system.

[0025] Step 6, data feedback and system update: data is transmitted to the cloud platform through the edge computing device, the cloud platform analyzes and predicts model performance and thermal management effects, and regularly updates model weights and cooling strategy parameters; the cloud platform generates a dynamic maintenance plan, including battery maintenance recommendations and cooling system optimization guidance. Preferably, the long short-term memory network LSTM model in the dynamic load forecasting further includes: an embedding layer for dimensionality reduction of the load data collected in real time; a bidirectional LSTM layer for simultaneously capturing the before and after time dependencies of the load data; and a densely connected layer for converting the output time series forecast value into the load forecast value for the next moment.

[0026] Preferably, the weight coefficient of the load prediction model is and The initial value of is determined by the following method: normalizing the historical load data; fitting the prediction error using the least squares method and calculating the gradient of each iteration; optimizing the weight coefficient based on the gradient descent algorithm until the prediction error converges to a preset threshold. Preferably, the cooling power adjustment coefficient of the multi-mode thermal management system is and load-dependent cooling factor It is obtained through experimental calibration methods, specifically including: measuring the heat loss at the cooling mode switching point under different temperature conditions; calculating the energy consumption and heat dissipation ratio under each cooling mode, and optimizing the cooling coefficient.

[0027] Preferably, the discharge current of the adaptive current control module The adjustment strategy further includes: correcting the discharge current in real time according to the internal impedance change of the battery cell; the internal impedance change is calculated by collecting the voltage and current of the battery cell in real time, and the formula is: ;in, is the load terminal voltage.

[0028] Preferably, the collaborative optimization between the modules further includes the following steps: the dynamic load prediction module updates the prediction value every 1 second and transmits the prediction result to the multi-mode thermal management system; the multi-mode thermal management system updates the cooling strategy according to the load prediction value, and feeds back the actual cooling efficiency to the adaptive current control module; the adaptive current control module adjusts the discharge current in real time, and returns the adjustment result to the dynamic load prediction module to update the load model at the next moment.

[0029] Preferably, in the feedback update step, the following data are recorded through the cloud platform for model optimization: the actual error of each load prediction; the energy consumption and heat dissipation efficiency under each cooling mode; the discharge curve and life trend of the battery unit.

[0030] A device based on a forklift power battery pack management method includes: a data acquisition module for real-time acquisition of voltage, current, temperature of a battery pack and forklift operation load data; a prediction module for predicting the load demand at the next moment based on a long short-term memory network (LSTM) model; a thermal management module for dynamically adjusting a cooling mode according to load prediction values ​​and temperature data; a current control module for real-time adjustment of the discharge current of a battery cell; and an edge computing module for realizing data transmission and collaborative optimization between modules.

[0031] A device based on a forklift power battery pack management method, the device comprising: at least one device, the device comprising a data acquisition module, a prediction module, a thermal management module, a current control module and an edge computing module; a communication module, used to communicate with a cloud platform to achieve data uploading and feedback sending; a storage module, used to store load data, temperature data and model optimization parameters.

[0032] A storage medium based on a forklift power battery pack management method stores computer-readable instructions. When the instructions are executed by a computing device, the computing device implements the following steps: collecting real-time data of the battery pack and inputting it into a long short-term memory network model; adjusting the cooling strategy and discharge current according to the load prediction value output by the model; transmitting the data to a cloud platform to optimize the model parameters; and updating the operating parameters of the device according to the feedback from the cloud platform.

[0033] Example 1: This example provides a forklift power battery pack management method based on dynamic load prediction and multi-scenario optimization, taking a large-scale logistics warehousing environment as an application scenario to demonstrate the specific implementation of the technical solution. For example, in a logistics park, forklifts need to perform frequent loading and unloading operations, and the operation scenarios include: high-frequency start-stop operation scenario: used to transport goods from storage shelves to loading and unloading areas, frequent start-stop during operation causes significant fluctuations in battery pack current; heavy-load long-distance transportation scenario: used to transport heavy goods to remote storage areas, the battery pack needs to withstand high loads for a long time, and the battery temperature rises rapidly; low-temperature environment operation scenario: outdoor cargo loading and unloading operations under low temperature conditions in winter, the battery performance is significantly reduced by the low temperature.

[0034] To solve the problems in the above scenarios, this embodiment adopts the following steps: by collecting forklift operation data in real time, including current, voltage, load weight and position information, load prediction is performed based on a bidirectional LSTM (long short-term memory network) model. The LSTM model inputs historical operating condition data and current real-time data to predict the load demand in the short term in the future. For example, in the frequent start-stop scenario, the prediction module estimates the current impact that the battery pack may suffer in advance, and combines the predicted value after the load weight coefficient is optimized to guide the adaptive current control module to dynamically adjust the discharge path, balance the battery unit load, and avoid current overshoot. In the heavy-load long-distance transportation scenario, the system dynamically selects a suitable cooling mode (air cooling or liquid cooling) based on the future load demand value provided by the load prediction module. After the cooling coefficient is experimentally calibrated, the cooling power is adjusted in combination with the real-time temperature and load prediction value to optimize the cooling energy consumption and temperature rise control; specifically, in the early stage of high-load operation, the system preferentially uses the high-efficiency liquid cooling mode to quickly reduce the battery temperature rise; when the load decreases, the system switches to the low-energy air cooling mode to achieve a dynamic balance between cooling efficiency and energy consumption.

[0035] In low temperature environments, the system combines load prediction and battery internal impedance calculation, optimizes the discharge current path, and gives priority to battery cells with lower impedance to participate in discharge, thereby reducing the impact of battery temperature rise on performance. At the same time, the current distribution is adjusted through real-time feedback to ensure the discharge uniformity of all battery cells and extend battery life; and the system transmits operating data to the cloud platform through the Internet of Things module. The cloud platform conducts long-term analysis of load prediction errors, cooling energy consumption, and battery life data during operation, and iteratively optimizes the load prediction model weights and thermal management parameters. For example, in frequent start-stop scenarios, the cloud platform adjusts model parameters based on historical data of high load impacts to optimize prediction accuracy; in low temperature scenarios, the cooling coefficient is optimized through historical temperature rise curves to improve heat dissipation. Through this embodiment, the following significant improvements have been achieved in actual applications in logistics parks: in high-frequency start-stop operations, current impact is reduced by about 20%, and the battery unit life is extended by 15%; in heavy-load scenarios, the dynamic switching of liquid cooling mode and air cooling mode reduces cooling energy consumption by 25% and battery temperature rise by about 30%; in low-temperature environments, discharge efficiency is increased by 10%, and operational stability is significantly enhanced; the optimization and iteration of the cloud platform enables the overall system to have the ability to continuously learn and improve in complex scenarios, demonstrating higher intelligent adaptability.

[0036] Embodiment 2: This embodiment optimizes the cooling mode switching conditions in the multi-mode thermal management module to enhance its applicability under extremely high and low temperature conditions. Specifically, in the cooling mode selection logic, based on the battery pack temperature and load forecast value , dynamically select cooling mode: when When, keep the passive cooling mode; when When the air cooling mode is activated, the cooling power adjustment formula is: ;when When the air cooling mode is used first, liquid cooling is dynamically introduced as a supplement. The mixed cooling power is calculated as: ;in, Indicates the air cooling ratio, which is adjusted dynamically based on the real-time load forecast value. Indicates the cooling power in air cooling mode. Indicates the cooling power in liquid cooling mode; when When the liquid cooling mode is fully activated, the cooling intensity is dynamically adjusted according to the load prediction value: ; The cooling coefficient calibration method is: and The calibration is completed through the following steps: simulating different temperature and load conditions in a laboratory environment, recording the heat dissipation efficiency and energy consumption data; optimizing the cooling coefficient based on the minimum energy consumption and optimal heat dissipation ratio to ensure that the model is suitable for different working conditions.

[0037] At the same time, in order to eliminate ambiguity, the source and meaning of the parameters in the formula are further clarified, such as the weight coefficient in the prediction model in the load prediction formula optimization. and Determined by: Training with a gradient descent algorithm, using historical load data to optimize initial weights; weight updates based on the following formula: ;in, is the learning rate, is the prediction error function, represents the weight at the current moment, represents the updated weight, is the model weight matrix. In addition, the temperature control threshold is optimized by simulating the temperature rise curve in the actual working conditions to ensure the applicability of the temperature control strategy in high-frequency start-stop, heavy load and low temperature scenarios. In this embodiment, the edge computing module further enhances the data collaboration capability, such as real-time data processing, and introduces a distributed computing framework on the edge device to achieve the following functions: dynamically aggregate sensor data (including voltage, current, temperature and location information); use a local cache mechanism to accelerate the execution of short-term prediction models; and, in terms of collaborative optimization between modules, such as the interaction between the dynamic load prediction module and the multi-mode thermal management module is managed by a unified data stream protocol to reduce latency; the edge computing device periodically transmits the optimization parameters (such as cooling coefficient and prediction model weight) to the cloud platform for long-term optimization; the adaptive fault handling mechanism of the edge computing module is added, and when a module fails to work properly, the system automatically switches to the backup strategy. The temperature control strategy of this embodiment is more flexible: it covers a wider temperature range, significantly reduces battery temperature rise and cooling energy consumption; the edge computing capability is improved: it improves data processing efficiency and collaborative optimization effect between modules, and enhances system stability.

[0038] Example 3: This example specifically describes the source and calibration method of variable parameters, as well as the specific implementation path of the cloud platform optimization model. In terms of multi-dimensional cooling coefficient calibration, for example, three typical working conditions, high-frequency start-stop, heavy-load long-distance transportation, and low-temperature environment, are simulated in the laboratory, and the temperature rise curve and energy consumption data under each working condition are recorded through edge computing equipment. The cooling coefficient is calculated using the following formula and : ;in, represents the energy consumed in the cooling process, is the temperature change, is the load prediction value; according to the experimental results, the cooling coefficient is optimized to achieve the best heat dissipation efficiency and energy consumption ratio. In terms of the implementation of the cloud platform optimization model, such as data upload and analysis: the operating data collected in real time by the edge computing module, including load prediction error, cooling power usage and battery life data, is periodically transmitted to the cloud platform; weight update mechanism: based on the gradient descent algorithm, the cloud platform optimizes the model weight, the formula is as follows: ,in, is the learning rate, is the load prediction error function, is the model weight, represents the model weight before optimization, Indicates the optimized model weight. Cooling strategy adjustment: Combine historical operation data to optimize the temperature control threshold for cooling mode switching. For example, adjust the threshold in a low temperature scenario: ; Ensure that the cooling power meets the requirements of low temperature environment. In terms of parameter range and value, such as cooling coefficient The value range is: 0.1-2.0, which is suitable for heat dissipation requirements under different load conditions; the learning rate of weight update : The value range is 0.001-0.01, ensuring the stability of model optimization convergence; the operation data collection cycle is 1 second, ensuring real-time performance and data integrity. In addition, in terms of edge computing and module collaboration, such as real-time fault handling: when the edge computing device detects a sensor abnormality, it automatically switches to the redundant module to avoid data loss; data flow closed-loop optimization: the prediction module and the thermal management module interact through a unified protocol to reduce data delay. In order to verify the technical effect of this embodiment, the experimental scenarios conducted by the present invention include three typical working conditions: high-frequency start-stop, heavy-load transportation, and low-temperature operation. The detailed settings are as follows: High-frequency start-stop scenario: the forklift performs repeated cargo loading and unloading within a range of 300 meters to simulate the current impact caused by high-frequency start-stop. The collected data includes battery cell voltage, current change rate and temperature rise curve; heavy-load transportation scenario: the forklift transports heavy goods exceeding 50% of the rated load, and the driving distance exceeds 1 kilometer, which is used to evaluate the adaptability of load prediction and cooling management; low-temperature operation scenario: outdoor operation is performed under ambient temperature of -10°C to test the efficiency of the thermal management system and the stability of battery performance.

[0039] From the experimental results, cooling energy consumption optimization: In the heavy-load transportation scenario, based on the cooling coefficient , The system achieves efficient switching between air cooling and liquid cooling through dynamic adjustment. The cooling energy consumption is reduced by 20% compared with the existing technology, and the temperature rise is controlled within 10°C, which significantly reduces the risk of battery overheating. Extended battery life: The adaptive current control module balances the discharge of battery cells. Experimental data show that the battery life is extended by 15% in high-frequency start-stop scenarios, reducing cell losses caused by current overshoot. Load prediction accuracy: The dynamic load prediction module is combined with the long short-term memory network (LSTM) algorithm. Based on 3,000 sets of load data collected in the experiment, the load prediction accuracy is improved from 87% of the traditional method to 95%, significantly reducing the impact of prediction deviation on the cooling strategy. Improved optimization efficiency: The collaborative optimization cycle of edge computing devices and cloud platforms is shortened from 72 hours to 48 hours, mainly due to the real-time tuning of cooling parameters by the edge computing module and the rapid iteration capability of the cloud platform. In addition, during the experiment, all data is collected by edge computing devices and transmitted to the cloud platform for analysis. The cooling energy consumption is recorded by the real-time power output of the thermal management module, the battery life is estimated by the changing trend of the cell voltage and internal impedance, and the load prediction accuracy is calculated based on the error between the predicted value and the actual load.

[0040] Example 4: In this example, the dynamic load prediction module adopts a dynamic load prediction model based on the long short-term memory network (LSTM) algorithm, and further refines the model's parameter optimization process and data preprocessing method. In order to improve the accuracy of load prediction, we introduced the following key technical steps: Historical data normalization: All input load data (current, voltage, temperature, forklift operating load) are first normalized to eliminate the dimensional differences between different data sources to ensure efficient training of the LSTM model. Data segmentation processing: Real-time load data is segmented according to timing, and the load fluctuation frequency and amplitude in each time period are calculated separately as the input of the LSTM model. By dividing the load data into multiple time periods for analysis, the complexity of a single calculation can be reduced, and the calculation speed and real-time performance can be improved. LSTM model parameter optimization: Use the gradient descent algorithm to optimize the model weights and update the historical load weights in the LSTM model. and real-time data weight , the weight update formula is as follows: ;in, is the learning rate, is the load prediction error function. This process dynamically adjusts the weights in the LSTM model through the back propagation algorithm to optimize the prediction accuracy; Load prediction value calculation: Based on the output of the LSTM model, the load demand for the future period is generated , and dynamically adjust the prediction results through the following formula: ;in, , is the hidden state of the previous moment, is the input data at the current moment, is the activation function, and the definition and function of each variable have been clearly explained above.

[0041] Furthermore, in order to better adapt to complex working environments, this embodiment refines the cooling mode selection and adjustment of the multi-mode thermal management module to ensure the optimal balance between energy efficiency and thermal control under different load conditions. Cooling mode selection basis: The cooling mode selection is based on the real-time load prediction value. and the current temperature of the battery pack , the specific cooling mode selection logic is as follows: , enable passive cooling mode. , enable air cooling mode, cooling power Adjust according to the formula: ;in, is the cooling coefficient of the air cooling mode. , enable liquid cooling mode, cooling intensity Dynamic adjustment based on load forecast value: ;in, is the load-related cooling coefficient. Cooling coefficient calibration: Cooling coefficient and Obtained through experimental calibration. In the experiment, by simulating different temperature and load conditions, recording the heat dissipation efficiency and energy consumption in each cooling mode, optimizing the cooling coefficient, and achieving the best balance between the heat dissipation effect and energy consumption. And in order to further improve the performance of the battery pack and extend the battery life, this embodiment optimizes the adaptive current control module. The specific implementation steps are as follows: Discharge current adjustment: According to the real-time load prediction value and the state parameters of the battery cells to adjust the discharge current of each battery cell in real time , to balance the load distribution between battery cells. The specific adjustment formula is: ;in, is the number of battery cells, is the voltage of the unit cell. This formula ensures balanced discharge of the battery pack, thus extending the service life of the battery.

[0042] Battery internal resistance compensation: Considering the impact of battery internal impedance changes on discharge current, this embodiment further introduces an internal resistance compensation mechanism. Specifically, the internal resistance of the battery cell By monitoring the battery voltage in real time and current It is calculated that the change of internal resistance will lead to the correction of discharge current. The formula for calculating internal resistance is: ;in, is the load terminal voltage. This mechanism can effectively avoid the influence of changes in battery internal resistance on current control and maintain the stability of the discharge process. This embodiment has made further optimizations in the inter-module collaborative optimization to ensure that the collaboration of each module is efficient and without delay. The specific optimization steps are as follows: Inter-module data transmission mechanism: Each module (dynamic load prediction, thermal management, current control) works together through a unified data stream protocol. The load prediction module updates the prediction results every 1 second and passes them to the thermal management module to facilitate real-time adjustment of the cooling strategy. The thermal management module adjusts the cooling mode in real time according to the load prediction results, and the cooling efficiency is fed back to the adaptive current control module to dynamically optimize the discharge current of the battery cell. Edge computing optimization: The edge computing module is responsible for real-time aggregation, processing and transmission of all sensor data to ensure low latency and high efficiency of data processing. The collaborative optimization between modules is accelerated through the local computing function of the edge device, which reduces the time of data transmission and ensures the real-time response of the system.

[0043] The introduction of the cloud platform enables the system to be optimized in real time based on the data during operation. The specific operation steps are as follows: Data upload and analysis: The data collected in real time by the edge computing module (including load prediction error, cooling efficiency, battery life data, etc.) is periodically transmitted to the cloud platform. The cloud platform analyzes this data and continuously optimizes the load prediction model and thermal management strategy. Optimization mechanism: Based on the historical data analyzed by the cloud platform, the gradient descent algorithm is used to dynamically adjust the weight of the load prediction model and the cooling coefficient of the cooling strategy. The model update formula is as follows: ;Through continuous learning and optimization, the cloud platform can improve the system's prediction accuracy and energy efficiency, allowing the system to always maintain optimal performance under complex working conditions.

[0044] Example 5: This example further refines the specific implementation path of the dynamic load prediction and multi-mode thermal management collaborative optimization in the forklift power battery pack management method, especially in the cooling coefficient calibration, inter-module data coordination and load prediction model optimization, to ensure that the functions and effects of each module are fully demonstrated, and to enhance the operability and feasibility of the system. In order to improve the cooling efficiency and ensure the stability of the battery pack under different load and temperature conditions, this example dynamically calibrates the cooling coefficient. Cooling coefficient and The present invention completes the calibration of the cooling coefficient by simulating different temperature and load conditions in the laboratory and recording the heat loss and energy consumption data in each cooling mode. and load forecast value Under different working conditions, the optimal cooling coefficient is determined through data regression analysis and , and its calculation formula is as follows: ;in, is the energy consumed in the cooling process, is the temperature change, is the load prediction value. This method ensures the balance between cooling effect and energy consumption. In actual application, the system and load forecast value Adjust the cooling intensity. For example, when When the system activates liquid cooling mode and adjusts the cooling intensity according to the load prediction value: ; This adjustment mechanism ensures that the battery pack is cooled in time under high load or extreme temperature conditions to avoid overheating or energy waste. In this embodiment, the load prediction module uses the long short-term memory network (LSTM) algorithm for prediction. In order to improve the prediction accuracy and the adaptability of the system, the present invention proposes the following optimization steps: normalize the historical load data to ensure the dimensional consistency between different data sources. Use historical data to train the load prediction model and dynamically update it in combination with real-time data. Weight coefficient and The update is optimized by the gradient descent method, and the update formula is: ;in, is the learning rate, is the load prediction error function. This formula ensures the real-time adjustment capability of the model under different working conditions. Load prediction value This will directly affect the selection and adjustment of the cooling strategy. By combining real-time temperature and load prediction, the system can dynamically select air cooling or liquid cooling mode and adjust the cooling coefficient and cooling intensity to optimize the operating efficiency of the battery pack.

[0045] Collaborative optimization between modules is one of the key innovations of the present invention. The dynamic load prediction module works in conjunction with the multi-mode thermal management module to achieve delay-free data transmission through a unified data stream protocol. The specific steps are as follows: Update the load prediction value once a second and pass it to the multi-mode thermal management module. The multi-mode thermal management module adjusts the cooling strategy according to the load prediction value and feeds back the actual cooling efficiency to the adaptive current control module. The adaptive current control module adjusts the discharge current of the battery cell according to the feedback cooling efficiency to ensure the stability of the battery under different load and temperature conditions. In order to reduce system latency and improve data processing efficiency, this embodiment uses edge computing technology to perform real-time processing and collaborative optimization of data from each module. The edge computing module is responsible for receiving and processing data from sensors, including voltage, current, temperature and other information, and accelerating the calculation of the load prediction model through local caching. All optimization results will be periodically transmitted to the cloud platform for long-term data recording and model updating.

[0046] The system described in this embodiment includes the following hardware components: Sensor module: used to collect the voltage, current, temperature and forklift operation load data of the battery pack in real time. Edge computing module: used to process data locally and support real-time load prediction and cooling management. Cloud platform: used for long-term data storage and model optimization, supporting continuous improvement of system performance. In the specific steps of its implementation path, data acquisition: the status data of the battery pack is collected in real time through sensors and transmitted to the edge computing module. Load prediction and cooling management: based on the load prediction results and real-time temperature, the edge computing module transmits the data to the thermal management module to adjust the cooling strategy. Current control: based on the load prediction and temperature control feedback, the current control module adjusts the discharge current of the battery unit in real time to maintain balanced discharge of the battery. System feedback and optimization: all operating data are regularly transmitted to the cloud platform for historical data analysis and optimization of prediction models and cooling strategies.

[0047] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A forklift power battery pack management method, characterized in that: The method comprises the following management steps: Step 1, real-time data collection through a data collection module: real-time data collection of voltage, current, temperature of a battery pack and operation load data of a forklift through a distributed sensor module, wherein: voltage data is used to evaluate the state of a battery cell; current data is used to calculate the instantaneous load demand of a forklift; temperature data is used to monitor the thermal stability of a battery pack; and operation load data is dynamically recorded based on the operation mode of the forklift; Step 2: Perform dynamic load forecasting through the dynamic load forecasting module: Based on the long short-term memory network (LSTM) algorithm, establish a forecasting model to segment the real-time collected load data; use historical load data to train the model weights, and update the model parameters in real time to optimize the forecasting accuracy; predict the load demand for the next period, specifically quantify the load fluctuation amplitude and frequency, and generate a load forecast value , the calculation formula is: ;in, and They are historical data weight and real-time data weight. is the hidden state value at the previous moment, is the current input data, is the bias term, is the activation function; Step 3: Perform multi-mode thermal management through the multi-mode thermal management module: Dynamically select the cooling mode based on real-time temperature data and load prediction values: When the temperature When the temperature is less than 30°C, the passive cooling mode is activated; when the temperature When the temperature is between 30°C and 45°C, the air cooling mode is activated and the cooling power is adjusted according to the formula: ;in, is the cooling power adjustment coefficient; when the temperature When the temperature exceeds 45°C, liquid cooling mode is activated and the cooling intensity is dynamically adjusted according to the load prediction value : ;in, is the load-dependent cooling factor; Step 4: Adaptive current control is performed through the adaptive current control module: according to the load prediction value and battery pack status parameters to adjust the discharge current of each battery cell in real time , to balance the load distribution among battery cells, the specific control rules are: in, is the number of battery cells, is the unit battery voltage; limits the unit battery current change rate to ensure that the change within one second does not exceed 5% of the rated value; Step 5, inter-module collaborative optimization: The dynamic load prediction module works with the multi-mode thermal management module to adjust the cooling mode in real time according to the load prediction value; the adaptive current control module dynamically optimizes the battery cell discharge strategy based on the load prediction and thermal management feedback; data is transmitted through a unified edge computing device; Step 6, data feedback and system update: Data is transmitted to the cloud platform through edge computing devices. The cloud platform analyzes and predicts model performance and thermal management effects, and regularly updates model weights and cooling strategy parameters. The cloud platform generates a dynamic maintenance plan, including battery maintenance recommendations and cooling system optimization guidance.

2. The forklift power battery pack management method according to claim 1, characterized in that: The long short-term memory network LSTM model in the dynamic load forecasting further includes: an embedding layer for reducing the dimension of the load data collected in real time; a bidirectional LSTM layer for simultaneously capturing the before and after time dependencies of the load data; and a dense connection layer for converting the output time series forecast value into the load forecast value at the next moment.

3. The forklift power battery pack management method according to claim 1, characterized in that: The weight coefficient of the load prediction model and The initial value of is determined by the following method: normalizing the historical load data; fitting the prediction error using the least squares method and calculating the gradient of each iteration; optimizing the weight coefficient based on the gradient descent algorithm until the prediction error converges to the preset threshold.

4. The forklift power battery pack management method according to claim 1, characterized in that: Cooling power adjustment coefficient of the multi-mode thermal management system and load-dependent cooling factor It is obtained through experimental calibration methods, specifically including: measuring the heat loss at the cooling mode switching point under different temperature conditions; calculating the energy consumption and heat dissipation ratio under each cooling mode, and optimizing the cooling coefficient.

5. The forklift power battery pack management method according to claim 1, characterized in that: The discharge current of the adaptive current control module The adjustment strategy further includes: correcting the discharge current in real time according to the internal impedance change of the battery cell; the internal impedance change is calculated by collecting the voltage and current of the battery cell in real time, and the formula is: ;in, is the load terminal voltage.

6. The forklift power battery pack management method according to claim 1, characterized in that: The collaborative optimization between the modules further includes the following steps: the dynamic load prediction module updates the prediction value every 1 second and transmits the prediction result to the multi-mode thermal management system; the multi-mode thermal management system updates the cooling strategy according to the load prediction value, and feeds back the actual cooling efficiency to the adaptive current control module; the adaptive current control module adjusts the discharge current in real time, and returns the adjustment result to the dynamic load prediction module to update the load model at the next moment.

7. The forklift power battery pack management method according to claim 1, characterized in that: In the feedback update step, the following data are recorded through the cloud platform for model optimization: the actual error of each load prediction; the energy consumption and heat dissipation efficiency under each cooling mode; the discharge curve and life trend of the battery unit.

8. A device based on the forklift power battery pack management method according to claim 1, characterized in that: include: Data acquisition module, used to collect voltage, current, temperature of battery pack and forklift operation load data in real time; The prediction module is used to predict the load demand at the next moment based on the long short-term memory network (LSTM) model; the thermal management module is used to dynamically adjust the cooling mode according to the load prediction value and temperature data; the current control module is used to adjust the discharge current of the battery unit in real time; the edge computing module is used to realize data transmission and collaborative optimization between modules.

9. A device based on the forklift power battery pack management method according to claim 1, characterized in that: The device includes: at least one device, which includes a data acquisition module, a prediction module, a thermal management module, a current control module and an edge computing module; a communication module, which is used to communicate with a cloud platform to upload data and send feedback; and a storage module, which is used to store load data, temperature data and model optimization parameters.

10. A storage medium based on the forklift power battery pack management method according to claim 1, characterized in that: The storage medium stores computer-readable instructions. When the instructions are executed by a computing device, the computing device implements the following steps: collecting real-time data of the battery pack and inputting it into a long short-term memory network model; adjusting the cooling strategy and discharge current according to the load prediction value output by the model; transmitting the data to a cloud platform to optimize the model parameters; and updating the operating parameters of the device according to feedback from the cloud platform.

Images