Battery management method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of battery management and unmanned ship energy management, and relates to a battery management method and device, computer equipment and a storage medium, and the method comprises the steps: receiving real-time state data, collected by a sensor network in real time, of a target battery; performing preprocessing operation on the real-time state data to obtain preprocessed state data; performing feature extraction operation on the preprocessed state data to obtain feature extraction data; calling an LSTM model, and inputting the feature extraction data into the LSTM model for power consumption prediction operation to obtain a real-time power consumption prediction result; and dynamically adjusting the discharge depth and the discharge rate of the target battery according to the real-time power consumption prediction result. According to the method, the LSTM model and rule correction are combined, so that the dynamic judgment and strategy optimization of the deep discharge condition of the battery are realized, and the accuracy and reliability of battery management can be remarkably improved in a complex environment.

Description

Technical Field

[0001] The present application relates to the fields of battery management technology and unmanned ship energy management technology, and in particular to a battery management method, device, computer equipment and storage medium. Background Art

[0002] At present, with the widespread application of unmanned boats in water cleaning, environmental monitoring, patrol inspection and other fields, higher requirements are put forward for their endurance, working stability, and battery life management. Especially in long-term working environments, battery life management and deep discharge strategy design have become key factors affecting the operation time and equipment durability of unmanned boats.

[0003] Traditional battery management systems mainly rely on static rule judgment and simple battery status monitoring to determine the charging and discharging strategy.

[0004] However, the applicant has found that in complex and changeable actual application environments, traditional battery management methods cannot effectively cope with nonlinear changes in battery status and dynamic fluctuations in environmental conditions. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a battery management method, apparatus, computer equipment and storage medium to solve the problem that traditional battery management methods cannot effectively cope with nonlinear changes in battery status and dynamic fluctuations in environmental conditions.

[0006] In order to solve the above technical problems, the present application provides a battery management method, which adopts the following technical solution:

[0007] Receive real-time status data of the target battery collected by the sensor network in real time;

[0008] Performing a preprocessing operation on the real-time status data to obtain preprocessing status data;

[0009] Performing a feature extraction operation on the preprocessed state data to obtain feature extraction data;

[0010] Calling the LSTM model, and inputting the feature extraction data into the LSTM model to perform a power consumption prediction operation, to obtain a real-time power consumption prediction result;

[0011] The discharge depth and discharge rate of the target battery are dynamically adjusted according to the real-time power consumption prediction result.

[0012] Furthermore, the step of performing a preprocessing operation on the real-time status data to obtain preprocessed status data specifically includes the following steps:

[0013] Performing a data cleaning operation on the real-time status data to obtain cleaned status data;

[0014] The cleaning state data is normalized to obtain the pre-processing state data.

[0015] Furthermore, after the step of calling the LSTM model and inputting the feature extraction data into the LSTM model to perform power consumption prediction operation to obtain a real-time power consumption prediction result, the following steps are also included:

[0016] Performing a rule correction operation on the real-time power consumption prediction result according to a preset rule to obtain a real-time rule correction result;

[0017] The step of dynamically adjusting the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result specifically includes the following steps:

[0018] When the real-time power consumption prediction result and the real-time rule correction result both meet the discharge condition, the discharge depth and discharge rate of the target battery are dynamically adjusted according to the real-time rule correction result.

[0019] Furthermore, the feature extraction data includes the battery voltage change rate ΔV, the unmanned ship speed change rate Δv, the wind speed and wind direction change Δw, the water flow direction and speed, and the task load ΔL, where:

[0020] The battery voltage change rate ΔV is expressed as:

[0021]

[0022] Where: V t and V t-1 They represent the voltage values ​​at time t and t-1 respectively, and ΔV represents the voltage change rate;

[0023] The speed change rate of the unmanned ship Δv is expressed as:

[0024]

[0025] Among them, v t and v t-1 They represent the speed of the unmanned ship at time t and time t-1 respectively, and Δv represents the speed change rate;

[0026] The change in wind speed and direction Δw is expressed as:

[0027]

[0028] Among them, w t and w t-1 They represent the wind speed at time t and time t-1 respectively, and Δw represents the wind speed change trend;

[0029] The task load ΔL is expressed as:

[0030]

[0031] Among them, L t and L t-1 They represent the task load power consumption at time t and t-1 respectively, and ΔL represents the load change rate.

[0032] Furthermore, the real-time power consumption prediction result E total It is expressed as:

[0033] E total =E motion +E environment +E load +E base

[0034] Among them, E motion Indicates the power consumption of the unmanned boat, E environment Indicates the impact of external environmental factors on power consumption, E load represents the power consumption of task load, E base Indicates basic power consumption.

[0035] Furthermore, the exercise power consumption E motion It is expressed as:

[0036] E motion =P motor ·t

[0037] Among them, P motor Indicates the power of the motor in watts, P motor =C drag ·v 3 , t represents the task execution time in hours, C drag represents a constant related to the ship's resistance, v represents the speed of the unmanned ship in meters per second;

[0038] The impact of external environmental factors on power consumption environment It is expressed as:

[0039] E environment =(F wind +F current )·v·t

[0040] Among them, F wind It represents the additional resistance caused by wind speed and wind direction to the unmanned ship, in Newton, F current represents the additional resistance caused by the water flow speed and direction to the unmanned ship, in Newtons, v represents the speed of the unmanned ship, in meters per second, and t represents the mission execution time;

[0041] Task load power consumption Eload It is expressed as:

[0042] E load =P load ·t

[0043] Among them, P load represents the power consumption of the task load, and t represents the task execution time;

[0044] Basic power consumption E base It is expressed as:

[0045] E base =P base ·t

[0046] Among them, P base represents the basic power consumption, and t represents the task execution time.

[0047] In order to solve the above technical problems, the embodiment of the present application further provides a battery management device, which adopts the following technical solution:

[0048] A real-time data acquisition module is used to receive the real-time status data of the target battery collected by the sensor network in real time;

[0049] A preprocessing module, used for performing a preprocessing operation on the real-time status data to obtain preprocessed status data;

[0050] A feature extraction module, used for performing a feature extraction operation on the preprocessing state data to obtain feature extraction data;

[0051] A power consumption prediction module is used to call the LSTM model and input the feature extraction data into the LSTM model to perform a power consumption prediction operation to obtain a real-time power consumption prediction result;

[0052] A dynamic adjustment module is used to dynamically adjust the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result.

[0053] Furthermore, the preprocessing module includes:

[0054] A data cleaning submodule, used to perform a data cleaning operation on the real-time status data to obtain cleaned status data;

[0055] The normalization submodule is used to perform a normalization operation on the cleaning state data to obtain the pre-processing state data.

[0056] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0057] The invention comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the battery management method as described above when executing the computer-readable instructions.

[0058] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0059] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the battery management method described above are implemented.

[0060] The present application provides a battery management method, including: receiving real-time status data of a target battery collected in real time by a sensor network; performing a preprocessing operation on the real-time status data to obtain preprocessing status data; performing a feature extraction operation on the preprocessing status data to obtain feature extraction data; calling an LSTM model, and inputting the feature extraction data into the LSTM model to perform a power consumption prediction operation to obtain a real-time power consumption prediction result; dynamically adjusting the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result. Compared with the prior art, the present application avoids over-discharge and premature discharge operations of the battery through accurate deep discharge condition judgment and dynamic discharge strategy optimization, thereby extending the service life of the battery; in addition, the present application can accurately evaluate the battery status under variable environmental conditions (such as extreme temperature, wind speed, waves, etc.), and achieve the optimal discharge effect through rule correction and strategy adjustment; the present application can dynamically adjust the discharge strategy according to real-time environmental data to ensure that the battery discharge operation is performed under the safest conditions, effectively improving the overall operation stability of the unmanned ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0063] Figure 2 is a flowchart of the battery management method provided in the embodiment of the present application;

[0064] Figure 3 is a schematic diagram of the structure of a battery management device provided in an embodiment of the present application;

[0065] Figure 4It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0067] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0068] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0069] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0070] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0071] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0072] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0073] It should be noted that the battery management method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the battery management device is generally arranged in the server / terminal device.

[0074] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0075] Continue to refer Figure 2 , shows a flow chart of an embodiment of a battery management method according to the present application. The battery management method comprises: step S201, step S202, step S203, step S204, step S205, step S206 and step S207.

[0076] In step S201, real-time status data of a target battery collected in real time by a sensor network is received.

[0077] In the embodiment of the present application, in order to make accurate power consumption prediction, the system will collect multi-dimensional data generated by the unmanned ship during the task execution from multiple sources. These data provide input for the LSTM model and are used to determine the power consumption of the unmanned ship under different task conditions. Specifically, the real-time status data includes the unmanned ship status data and environmental data, among which:

[0078] Unmanned ship status data includes:

[0079] (1) Position and Attitude Data: The position and attitude data of the unmanned ship is obtained through GPS and inertial measurement unit (IMU), including the current position, heading angle, speed and acceleration of the unmanned ship;

[0080] The posture data can help the model evaluate the real-time movement status of the ship to predict the energy consumption at different speeds and movement directions;

[0081] (2) Battery Data: including real-time voltage, current, temperature, remaining capacity (SOC) and battery health status (SOH). The health of the battery will determine its actual available capacity and discharge efficiency under different working conditions.

[0082] Environmental data includes:

[0083] (1) Wind direction and wind speed: The wind speed sensor and wind vane are used to collect the current wind speed and wind direction data. These data determine the difference in power consumption of the unmanned boat in headwind, tailwind or crosswind conditions;

[0084] (2) Water flow direction and water flow speed:

[0085] The water flow direction and speed are collected through the flow meter. These data will directly affect the driving resistance of the unmanned boat in the water, thereby affecting the energy consumption.

[0086] (3) Weather conditions:

[0087] Weather data is obtained through the weather station, including temperature, humidity, air pressure, etc., especially the water temperature has a greater impact on the battery discharge characteristics. In a low temperature environment, the effective discharge capacity of the battery will decrease, thereby increasing energy consumption.

[0088] In some optional implementations of the embodiments of the present application, the above-mentioned real-time status data may also include task condition data. Specifically, the task condition data includes: ① task route planning and moving route and ② task load, wherein:

[0089] Mission route planning and mobile route - path optimization and energy minimization

[0090] The aim is to reduce the energy consumption of unmanned ships during driving by selecting the most energy-efficient route. This process is achieved by analyzing the real-time position of the ship, environmental conditions (wind speed, water flow, etc.), and the preset mission route, and adjusting the movement strategy in real time, including:

[0091] (1) Calculation formula:

[0092] Based on the strategy of path optimization, it is necessary to calculate the energy consumed on different paths and select the path with the least energy consumption. Based on the above power consumption formula, the estimated energy consumption of each path is calculated under different route conditions.

[0093] For the energy consumption E on a certain path i i , the following formula can be used:

[0094]

[0095] in:

[0096] v i Indicates the driving speed on this path segment; t i Indicates the travel time of this route; F wind,i Indicates the additional resistance caused by wind speed and direction on this path segment; F current,i Represents the additional resistance to flow on this path segment.

[0097] (2) Route selection and adjustment:

[0098] ① Initial route planning:

[0099] According to the task requirements and preset task objectives, the system first plans the shortest path as the initial route.

[0100] Based on preset tasks (such as cleaning specific waters or inspecting fixed routes), the planned path is set according to the expected driving route.

[0101] ②Real-time path adjustment:

[0102] During actual navigation, the system can evaluate the energy consumption of the current route in real time based on changes in environmental data (wind speed, water flow, etc.). If it is detected that the wind speed is high or the water flow direction is opposite to the driving direction, the route can be dynamically adjusted to avoid relatively high energy consumption areas.

[0103] Calculate the energy consumption of each feasible route (according to the formula) and select the route with the lowest energy consumption. For example, the route can choose a section with favorable wind and favorable water to reduce resistance and reduce energy consumption.

[0104] Path optimization conditions: When it is detected that the wind speed, wind direction, or water flow speed changes on a certain path cause the power consumption to exceed the set threshold (for example, the estimated energy consumption is 20% higher than the planned energy consumption), the system will automatically recommend adjusting the route.

[0105] (3) Status judgment:

[0106] ①Condition 1: Energy consumption E of the current route current Is it close to or exceeds the preset threshold E threshold .

[0107] If E current >E threshold , it is recommended to adjust the route.

[0108] If E current ≤E threshold text{current}}, keep the current route.

[0109] ②Condition 2: Whether energy consumption can be further saved by adjusting the speed v.

[0110] If the energy consumption is expected to drop significantly with the adjustment of reducing the speed v, the system will automatically reduce the speed of the unmanned ship while ensuring its own working efficiency.

[0111] If the energy saving effect after speed adjustment is not expected to be significant, maintain the current speed.

[0112] Task load:

[0113] The mission load directly affects the power consumption of the battery. The larger the load, the higher the energy consumption of the unmanned ship when performing the mission. The load of the unmanned ship usually includes cleaning equipment, underwater cameras, detection instruments, etc. Therefore, by dynamically managing the start and stop of the load or reducing the use of the load, it is possible to save energy during the execution of the mission. The working status and power consumption of each mission load, including the power of the cleaning equipment, the working status of the camera, etc., will be monitored in real time. According to the current remaining battery power and health status, the load usage strategy will be dynamically adjusted. The calculation formula of the mission load is:

[0114] The power consumption of the task load is estimated by the following formula:

[0115] E load =P load ·t

[0116] in:

[0117] P load : The power consumption of the load device, in watts (W).

[0118] t: The working time of the load equipment, in hours (h).

[0119] When a task is executed, the total power consumption of the load can be calculated based on the usage of different devices:

[0120]

[0121] in:

[0122] P load,j : The power of the jth load device.

[0123] t j : The usage time of the jth load device.

[0124] In the embodiment of the present application, the load management strategy includes load priority management and load start and stop adjustment, wherein:

[0125] (1) Load priority management:

[0126] The system sets different load priorities according to the importance and power consumption of the task equipment. For high-power but low-priority equipment, the system will automatically shut down these equipment to save power when the battery is low.

[0127] For example, cleaning equipment consumes more power, while cameras consume less power. If the power is insufficient, the system can shut down the cleaning equipment first and keep the camera to complete basic inspection tasks.

[0128] (2) Load start and stop adjustment:

[0129] According to the battery status and the impact of the task load on the battery, the system can automatically adjust the load start and stop time. For example, when the remaining power drops to a certain threshold (such as the battery power is less than 30%), the system can prioritize shutting down some loads based on the importance of the task.

[0130] Specifically, status judgment:

[0131] Condition 1: Current battery power SOC current Is the SOC lower than the set threshold? threshold .

[0132] If SOC current <SOC threshold , enable load management and turn off non-essential loads.

[0133] If SOC current ≥SOC threshold , then keep the required load turned on.

[0134] Condition 2: Total load power P load,total Whether it exceeds the current available power of the battery.

[0135] If P load,total >P available , it will prioritize shutting down high-power-consuming devices and reducing unnecessary loads.

[0136] If P load,total ≤P available , the current load is maintained.

[0137] In actual task execution, path optimization and load management need to work together to ensure task completion while saving power to the greatest extent possible.

[0138] (1) Joint management of paths and loads:

[0139] The system will simultaneously monitor the energy consumption changes of the mission route and the power consumption of the mission load, and comprehensively evaluate the impact of the path and load on the battery.

[0140] When a certain section of the route is expected to have high energy consumption, the system will simultaneously adjust the speed of the unmanned ship, optimize the route, and shut down some mission loads to ensure that the unmanned ship can still return safely when the battery is low.

[0141] (2) Return trip judgment:

[0142] The system determines whether the unmanned ship needs to return early based on the power consumption forecast and the current battery status. This judgment is based on the estimated energy consumption remaining on the mission route and the remaining battery power.

[0143] Return condition: If the total energy consumption of the remaining tasks is expected to be E task,remaining Greater than the remaining battery power E battery,remaining , then the unmanned boat triggers the return trip.

[0144] In step S202, a preprocessing operation is performed on the real-time status data to obtain preprocessed status data.

[0145] In an embodiment of the present application, after collecting the above-mentioned multi-dimensional data, the data needs to be preprocessed so that it becomes standardized features that can be input into the LSTM model.

[0146] In step S203, a feature extraction operation is performed on the preprocessing state data to obtain feature extracted data.

[0147] In the embodiment of the present application, feature extraction is mainly used to capture the changing trend of different data features to help the LSTM model accurately predict the power consumption of the unmanned ship. The specific extracted features include battery status, environmental factors and the rate of change of task load.

[0148] Battery voltage change rate: The change in battery voltage can reflect the discharge of the battery. Calculating the battery voltage change rate helps predict the discharge trend of the battery.

[0149]

[0150] in:

[0151] V t and V t-1 are the voltage values ​​at time t and t-1 respectively.

[0152] ΔV is the rate of change of voltage.

[0153] Speed ​​Change Rate of Unmanned Ship: Changes in ship speed directly affect power consumption, especially when accelerating or decelerating, power consumption will fluctuate significantly.

[0154]

[0155] in:

[0156] v t and v t-1 are the speeds of the unmanned ship at time t and t-1 respectively.

[0157] Δv is the rate of change of velocity.

[0158] Wind Speed ​​Trend: The change of wind speed has a significant impact on the driving resistance and energy consumption of the unmanned ship, especially in headwind or tailwind conditions. By calculating the change trend of wind speed, the additional energy consumption can be estimated.

[0159]

[0160] in:

[0161] w t and w t-1 are the wind speeds at time t and t-1 respectively.

[0162] Δw is the wind speed variation trend.

[0163] Load Variation: The load of a mission (such as the use of cleaning equipment or cameras) can dynamically affect the battery consumption of the drone. Feature extraction of load variation can help to more accurately estimate the energy consumption during mission execution.

[0164]

[0165] in:

[0166] L t and L t-1 are the task load power consumption at time t and t-1 respectively.

[0167] ΔL is the load change rate.

[0168] In step S204, the LSTM model is called, and the feature extraction data is input into the LSTM model to perform a power consumption prediction operation to obtain a real-time power consumption prediction result.

[0169] In the embodiment of the present application, the LSTM model is used in combination with preset rules to predict power consumption, and to evaluate in real time during the task execution whether the remaining battery power is sufficient to complete the task, wherein:

[0170] The LSTM model is mainly responsible for learning and predicting the power consumption of the unmanned ship under different conditions based on historical mission data. The preset rules are designed to deal with special or extreme situations (such as excessive wind speed, unfavorable water flow direction, etc.), and provide supplements and adjustments when the LSTM prediction is incomplete or inaccurate, thereby ensuring the safety of the unmanned ship's mission execution and the rational use of batteries.

[0171] The role of the LSTM model:

[0172] Time series learning: The LSTM model receives time series data (such as battery voltage change rate, wind speed change, speed, etc.) and learns energy consumption patterns under different environmental and task conditions from historical data.

[0173] Predicting power consumption: Based on the input current task conditions and environmental information, the model predicts future energy consumption trends and outputs the estimated total power consumption and remaining power of the current task.

[0174] Self-learning: The LSTM model gradually optimizes the prediction accuracy of power consumption during the task by continuously learning new task data.

[0175] In the embodiment of the present application, the LSTM model input is a multidimensional time series matrix with the dimension [time step, feature dimension]. The input data dimension specifically includes the above-mentioned key features:

[0176] ①Battery voltage change rate (Voltage Change Rate): reflects the current discharge rate of the battery.

[0177] A voltage drop that is too fast may mean that the mission is consuming too much power and requires adjusting the load or returning to the destination.

[0178] ② Speed ​​Change Rate of Unmanned Ship:

[0179] Speed ​​changes affect energy consumption, and rapid acceleration or high speed driving generally means higher energy consumption.

[0180] ③Wind Speed ​​and Direction Change:

[0181] Wind speed and direction directly affect the drag of the unmanned boat. For example, sailing against the wind will significantly increase power consumption.

[0182] ④Water Current and Speed:

[0183] When the direction of the water flow is consistent with the direction of movement of the unmanned boat, power consumption can be reduced; while going against the water flow increases resistance, resulting in increased energy consumption.

[0184] ⑤Task Load:

[0185] Power consumption of cleaning equipment or other task loads.

[0186] In the embodiment of the present application, the LSTM model predicts the estimated power consumption at each time step during the task based on these input data, where the total power consumption is predicted:

[0187] E total =E motion +E environment +E load +E base

[0188] in:

[0189] E motion : The power consumption of unmanned boat (related to boat speed, posture, etc.):

[0190] E motion =P motor ·t

[0191] Among them, P motor Indicates the power of the motor in watts, P motor =C drag ·v 3 , t represents the task execution time in hours, C drag represents a constant related to the ship's resistance, v represents the speed of the unmanned ship in meters per second;

[0192] E environment :The impact of external environmental factors on power consumption (wind speed, wind direction, water flow, etc.):

[0193] E environment =(F wind +F current )·v·t

[0194] Among them, F wind It represents the additional resistance caused by wind speed and wind direction to the unmanned ship, in Newton, F current represents the additional resistance caused by the water flow speed and direction to the unmanned ship, in Newtons, v represents the speed of the unmanned ship, in meters per second, and t represents the mission execution time;

[0195] E load :Power consumption of task load (such as power consumption of cleaning equipment, cameras and other task equipment):

[0196] E load =P load ·t

[0197] Among them, P load represents the power consumption of the task load, and t represents the task execution time;

[0198] E base:Basic power consumption (power consumption for basic operation of unmanned ship equipment, such as control system, navigation system, etc.):

[0199] E base =P base ·t

[0200] Among them, P base represents the basic power consumption, and t represents the task execution time.

[0201] In step S205, the discharge depth and discharge rate of the target battery are dynamically adjusted according to the real-time power consumption prediction result.

[0202] In actual applications, suppose the unmanned boat performs a surface cleaning task. The current wind speed is 8m / s, the water flow speed is 2m / s, the boat speed is 1.5m / s, and the task load is 5kW. The LSTM model predicts that the cleaning task will consume a total of 20kWh of electricity based on the current data, and the remaining power is sufficient to complete the task. The preset rule is triggered: the wind speed suddenly increases to 12m / s, exceeding the rule threshold. The system adjusts the LSTM prediction result according to the rule. It is expected that the task power consumption will increase to 25kWh, and the remaining power is not enough to complete the task. Return decision: the system combines the energy consumption forecast after the wind speed adjustment and issues a return command to ensure the safe return of the unmanned boat.

[0203] In some optional implementations of the embodiments of the present application, after the above-mentioned step of calling the LSTM model and inputting the feature extraction data into the LSTM model for power consumption prediction operation to obtain the real-time power consumption prediction result, the following steps are also included:

[0204] Perform rule correction operations on the real-time power consumption prediction results according to preset rules to obtain real-time rule correction results;

[0205] The step of dynamically adjusting the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result specifically includes the following steps:

[0206] When the real-time power consumption prediction result and the real-time rule correction result both meet the discharge condition, the discharge depth and discharge rate of the target battery are dynamically adjusted according to the real-time rule correction result.

[0207] In the embodiment of the present application, the LSTM model can be used in combination with preset rules to predict power consumption, wherein the preset rules have the following functions:

[0208] ① Safety supplement mechanism: Although the LSTM model can accurately predict power consumption, it may make errors under some extreme conditions (such as sudden changes in wind speed or violent fluctuations in water flow). Preset rules are used to quickly detect such anomalies and correct the LSTM prediction results.

[0209] ②Conditional trigger rules: The preset rules are based on the safety of the mission and the protection of the battery. For example, when the wind speed is greater than a certain threshold and the ambient temperature is lower than the battery safety temperature, even if the LSTM predicts that the mission can be completed, the system will intervene according to the rules and suggest returning or adjusting the route.

[0210] In the implementation of this application, the power consumption prediction strategy can be a return decision:

[0211] The LSTM model uses the predicted total power consumption and the current remaining power to evaluate in real time whether the task can be completed. If the model determines that the remaining power is insufficient to complete the task or return, the return mechanism will be triggered. Return point calculation:

[0212]

[0213] in:

[0214] D return is the return distance.

[0215] E motion,return and E environment,return is the estimated motion and environmental energy consumption during the return flight.

[0216] In the embodiment of the present application, the power consumption predicted by the LSTM model will first be used as the basic evaluation result, but in order to ensure the safe execution of the task, the preset rules will correct and supplement some specific conditions. The following are several typical rule triggering conditions and strategies:

[0217] (1) Excessive wind speed:

[0218] Rule: If the wind speed v wind If the wind speed exceeds a preset threshold (e.g. 10 m / s), the energy consumption forecast is adjusted according to the wind speed.

[0219] Strategy: In the case of excessive wind speed, the system will increase redundant power, assuming that the energy consumption is 20%-30% more than the LSTM prediction, and issue a return command in advance.

[0220] (2) Battery temperature is too low:

[0221] Rule: When the battery temperature T battery If the temperature is below the set threshold (such as 0℃), the preset rules will take priority intervention.

[0222] Strategy: The LSTM model still predicts energy consumption, but the rules reduce the battery's available power to prevent the battery from discharging too quickly in cold conditions.

[0223] (3) Unfavorable water flow direction:

[0224] Rule: When the angle between the water flow direction and the navigation direction of the unmanned boat is θ currentWhen it is greater than 90°, it means traveling against the flow.

[0225] Strategy: According to the water flow resistance, adjust the prediction results of the LSTM model, assuming that the power consumption increases by 15%-25%.

[0226] (4) Task priority rules:

[0227] Rule: When the power consumption of a task exceeds the planned value, but the task has a high priority (such as a key area cleaning task), try to continue the task instead of returning immediately.

[0228] Strategy: The system will delay the return point, allowing the unmanned ship to continue the mission until the minimum safe power is reached before returning.

[0229] In the embodiment of the present application, when the unmanned ship is performing a mission, the system will continue to collect new data and update the prediction of the LSTM model. The real-time prediction will be combined with the power consumption corrected by the preset rules to ensure the safety of mission completion.

[0230] LSTM dynamic update: The LSTM model receives continuously updated sensor data and makes real-time predictions about the next task time period to evaluate whether the current task can be completed within the remaining power.

[0231] Real-time rule triggering: If a rule is triggered during a mission (e.g., a sudden increase in wind speed or unfavorable water flow direction), the rule will immediately adjust the predicted value of the model output and recalculate the return point or the possibility of mission completion.

[0232] In an embodiment of the present application, a battery management method is provided, including: receiving real-time status data of a target battery collected in real time by a sensor network; performing a preprocessing operation on the real-time status data to obtain preprocessing status data; performing a feature extraction operation on the preprocessing status data to obtain feature extraction data; calling an LSTM model, and inputting the feature extraction data into the LSTM model to perform a power consumption prediction operation to obtain a real-time power consumption prediction result; dynamically adjusting the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result. Compared with the prior art, the present application avoids over-discharge and premature discharge operations of the battery through accurate deep discharge condition judgment and dynamic discharge strategy optimization, thereby extending the service life of the battery; in addition, the present application can accurately evaluate the battery status under variable environmental conditions (such as extreme temperature, wind speed, waves, etc.), and achieve the optimal discharge effect through rule correction and strategy adjustment; the present application can dynamically adjust the discharge strategy according to real-time environmental data to ensure that the battery discharge operation is performed under the safest conditions, effectively improving the overall operation stability of the unmanned ship.

[0233] In some optional implementations of the embodiments of the present application, the above-mentioned step of performing a preprocessing operation on the real-time status data to obtain the preprocessed status data specifically includes the following steps:

[0234] Performing data cleaning operation on the real-time status data to obtain cleaned status data;

[0235] The cleaning state data is normalized to obtain preprocessing state data.

[0236] In an embodiment of the present application, data cleaning includes data denoising. Specifically, the goal of data denoising is to ensure that the collected data is stable and accurate, and to remove sensor noise and occasional outliers. For the multi-dimensional data involved in unmanned ship operations, the denoising method used is Kalman Filter, which is good at processing time series data and can effectively eliminate short-term fluctuations and retain the main trends of the data. GPS data, speed, wind speed and other sensor data may jump or jitter due to equipment or external interference. Through Kalman filtering technology, the data is smoothed using prediction and measurement updates.

[0237] Kalman filter formula: Kalman filtering is a recursive process, which mainly includes two steps: prediction and update.

[0238] Prediction Steps:

[0239]

[0240] P k|k-1 =A·P k-1 ·A T +Q

[0241] The estimated value of the predicted state at time k.

[0242] A: The state transition matrix is ​​used to describe the evolution of a system from one state to the next.

[0243] u k : Control input (such as the acceleration of the unmanned ship).

[0244] P k|k-1 : Forecast error covariance matrix.

[0245] Q: Process noise covariance.

[0246] Update steps:

[0247] K k =P k|k-1 ·H T ·(H·P k|k-1 ·H T+R) -1

[0248]

[0249] P k =(IK k ·H)·P k|k-1

[0250] K k : Kalman gain.

[0251] z k :Measured value.

[0252] H: measurement matrix.

[0253] R: measurement noise covariance.

[0254] The updated state estimate at time k.

[0255] P k : The updated estimation error covariance matrix.

[0256] Through Kalman filtering, GPS data, speed data, etc. can be smoothed and abnormal jumps can be filtered out to ensure that the data input into the LSTM model is more representative and accurate.

[0257] In the embodiment of the present application, data normalization means that different dimensions of the unmanned ship mission operation data need to be normalized to the same standard to avoid large numerical features dominating the learning process of the model. The normalization method used is minimum-maximum normalization.

[0258] Normalize battery features such as voltage, current, and temperature to ensure they are on the same scale.

[0259] Physical quantities such as ship speed and wind speed also need to be normalized so that they are in the same range as the battery status data to ensure that the LSTM model can learn various features in a balanced manner.

[0260] Normalization formula: For a certain feature x, the minimum-maximum normalization transforms it into the interval [0,1], the formula is:

[0261]

[0262] in:

[0263] x' is the normalized eigenvalue.

[0264] x is the original eigenvalue.

[0265] x min and x maxare the minimum and maximum values ​​of the feature, respectively.

[0266] Normalized data input:

[0267] The normalized data will become the input of the LSTM model. Each feature dimension will be in the interval [0,1], forming a standardized feature matrix X with the shape of:

[0268]

[0269] Among them, m represents the time step and n represents the feature dimension.

[0270] In some optional implementations of the embodiments of the present application, in addition to power consumption prediction, the system can also combine the mission planning of the unmanned ship with dynamic environmental information to adjust the mission execution route and strategy in real time to achieve more efficient energy utilization.

[0271] 1. Task completion evaluation:

[0272] The LSTM model combines the power consumption prediction of the current task to dynamically evaluate the possibility of completing the task. If the model predicts that the current power cannot complete the task, it recommends that the unmanned ship adjust its route or return to shore for charging.

[0273] The model can combine the priority of the task to decide whether to continue to execute high-power tasks (such as working against the wind) or skip some non-essential tasks. If the task is of high priority and the current power is sufficient to complete some tasks, the important task can be executed first. If the task is of low priority, it is recommended to skip the high-power tasks to save power.

[0274] 2. Path optimization and adjustment:

[0275] Combining external environmental factors such as wind direction, water flow direction, and water temperature, the system can adjust the movement route of the unmanned boat in real time. For example, in areas with strong winds or rapid water flow, the model can suggest that the unmanned boat avoid routes with high energy consumption.

[0276] By optimizing the path, the unmanned ship can complete the scheduled task under more energy-saving conditions and improve battery utilization efficiency.

[0277] 3. Return point calculation:

[0278] The LSTM model can calculate the return point in real time based on the current position and power status of the unmanned boat. The calculation takes into account factors such as headwind, water flow direction, and boat load to ensure that the unmanned boat can safely return to the shore or charging station.

[0279] 4. Instantiate the scene:

[0280] Mission completion assessment: The unmanned ship is performing a surface inspection mission. The LSTM model predicts that the current power cannot support the completion of all inspection tasks, but the mission priority is high. The system recommends skipping some low-priority inspection points, completing the inspection of key areas first, and planning to return.

[0281] Path optimization: During the inspection, the system detected that the water flow in the area ahead was strong and the wind was against it. LSTM predicted that energy consumption would increase significantly. The system suggested taking a detour to another route, which was slightly farther but consumed less energy.

[0282] Return point calculation: As the inspection task progresses, the LSTM model updates the return point in real time based on the current power, task load, wind speed, and water flow. Before the task is completed, the system finds that the wind speed is gradually increasing, and the energy consumption will increase during the return trip. Therefore, the system issues a return command in advance to ensure that the unmanned boat returns to the shore safely.

[0283] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0284] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0285] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0286] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0287] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a battery management device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0288] like Figure 3 As shown, the battery management device 200 of the embodiment of the present application includes:

[0289] A real-time data acquisition module 210 is used to receive real-time status data of the target battery collected by the sensor network in real time;

[0290] The preprocessing module 220 is used to perform preprocessing operations on the real-time status data to obtain preprocessed status data;

[0291] The feature extraction module 230 is used to perform feature extraction operation on the preprocessing state data to obtain feature extraction data;

[0292] The power consumption prediction module 240 is used to call the LSTM model and input the feature extraction data into the LSTM model to perform power consumption prediction operations to obtain real-time power consumption prediction results;

[0293] The dynamic adjustment module 250 is used to dynamically adjust the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result.

[0294] In an embodiment of the present application, a battery management device 200 is provided, including: a real-time data acquisition module 210, used to receive real-time status data of a target battery collected in real time by a sensor network; a preprocessing module 220, used to perform a preprocessing operation on the real-time status data to obtain preprocessed status data; a feature extraction module 230, used to perform a feature extraction operation on the preprocessed status data to obtain feature extraction data; a power consumption prediction module 240, used to call an LSTM model and input the feature extraction data into the LSTM model to perform a power consumption prediction operation to obtain a real-time power consumption prediction result; a dynamic adjustment module 250, used to dynamically adjust the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result. Compared with the prior art, the present application avoids over-discharge and premature discharge of the battery through precise deep discharge condition judgment and dynamic discharge strategy optimization, thereby extending the battery life; in addition, the present application can accurately evaluate the battery status under changing environmental conditions (such as extreme temperature, wind speed, waves, etc.), and achieve the optimal discharge effect through rule correction and strategy adjustment; the present application can dynamically adjust the discharge strategy according to real-time environmental data to ensure that the battery discharge operation is performed under the safest conditions, effectively improving the overall operation stability of the unmanned ship.

[0295] In some optional implementations of the embodiments of the present application, the preprocessing module includes:

[0296] The data cleaning submodule is used to perform data cleaning operations on the real-time status data to obtain cleaned status data;

[0297] The normalization submodule is used to perform a normalization operation on the cleaning state data to obtain pre-processing state data.

[0298] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0299] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0300] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0301] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer readable instructions of the battery management method, etc. In addition, the memory 310 can also be used to temporarily store various data that have been output or will be output.

[0302] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions or process data stored in the memory 310, such as computer-readable instructions for running the battery management method.

[0303] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0304] The computer equipment provided by the present application avoids over-discharge and premature discharge of the battery through precise deep discharge condition judgment and dynamic discharge strategy optimization, thereby extending the battery life; in addition, the present application can accurately evaluate the battery status under changing environmental conditions (such as extreme temperature, wind speed, waves, etc.), and achieve the optimal discharge effect through rule correction and strategy adjustment; the present application can dynamically adjust the discharge strategy according to real-time environmental data to ensure that the battery discharge operation is performed under the safest conditions, effectively improving the overall operation stability of the unmanned ship.

[0305] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the battery management method as described above.

[0306] The computer-readable storage medium provided by the present application avoids over-discharge and premature discharge operations of the battery through precise deep discharge condition judgment and dynamic discharge strategy optimization, thereby extending the service life of the battery; in addition, the present application can accurately evaluate the battery status under changing environmental conditions (such as extreme temperature, wind speed, waves, etc.), and achieve the optimal discharge effect through rule correction and strategy adjustment; the present application can dynamically adjust the discharge strategy according to real-time environmental data to ensure that the battery discharge operation is performed under the safest conditions, effectively improving the overall operating stability of the unmanned ship.

[0307] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0308] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A battery management method, characterized in that: The method is applied to shore-based battery management of unmanned ships, and comprises the following steps: Receive real-time status data of the target battery collected by the sensor network in real time; Performing a preprocessing operation on the real-time status data to obtain preprocessing status data; Performing a feature extraction operation on the preprocessed state data to obtain feature extraction data; Calling the LSTM model, and inputting the feature extraction data into the LSTM model to perform a power consumption prediction operation, to obtain a real-time power consumption prediction result; The discharge depth and discharge rate of the target battery are dynamically adjusted according to the real-time power consumption prediction result.

2. The battery management method according to claim 1, characterized in that: The step of performing a preprocessing operation on the real-time status data to obtain preprocessed status data specifically includes the following steps: Performing a data cleaning operation on the real-time status data to obtain cleaned status data; The cleaning state data is normalized to obtain the pre-processing state data.

3. The battery management method according to claim 1, characterized in that: After the step of calling the LSTM model and inputting the feature extraction data into the LSTM model to perform power consumption prediction operation to obtain a real-time power consumption prediction result, the following steps are also included: Performing a rule correction operation on the real-time power consumption prediction result according to a preset rule to obtain a real-time rule correction result; The step of dynamically adjusting the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result specifically includes the following steps: When the real-time power consumption prediction result and the real-time rule correction result both meet the discharge condition, the discharge depth and discharge rate of the target battery are dynamically adjusted according to the real-time rule correction result.

4. The battery management method according to claim 1, characterized in that: The feature extraction data includes the battery voltage change rate ΔV, the unmanned ship speed change rate Δv, the wind speed and wind direction change Δw, the water flow direction and speed ΔL and the task load, where: The battery voltage change rate ΔV is expressed as: Where: V t and V t-1 They represent the voltage values ​​at time t and t-1 respectively, and ΔV represents the voltage change rate; The speed change rate of the unmanned ship Δv is expressed as: Among them, v t and v t-1 They represent the speed of the unmanned ship at time t and time t-1 respectively, and Δv represents the speed change rate; The change in wind speed and direction Δw is expressed as: Among them, w t and w t-1 They represent the wind speed at time t and time t-1 respectively, and Δw represents the wind speed change trend; The task load ΔL is expressed as: Among them, L t and L t-1 They represent the task load power consumption at time t and t-1 respectively, and ΔL represents the load change rate.

5. The battery management method according to claim 1, characterized in that: The real-time power consumption prediction result E total It is expressed as: AND total =And motion +E environment +E load +E base Among them, E motion represents the power consumption of the unmanned boat, E environment Indicates the impact of external environmental factors on power consumption, E load represents the power consumption of task load, E base Indicates basic power consumption.

6. The battery management method according to claim 5, characterized in that: The exercise power consumption E motion It is expressed as: E motion =P motor ·t Among them, P motor Indicates the power of the motor in watts, P motor =C drag ·v 3 , t represents the task execution time in hours, C drag represents a constant related to the ship's resistance, v represents the speed of the unmanned ship in meters per second; The impact of external environmental factors on power consumption environment It is expressed as: E environment =(F wind +F current )·v·t Among them, F wind It represents the additional resistance caused by wind speed and wind direction to the unmanned ship, in Newton, F current represents the additional resistance caused by the water flow speed and direction to the unmanned ship, in Newtons, v represents the speed of the unmanned ship, in meters per second, and t represents the mission execution time; Task load power consumption E load It is expressed as: E load =P load ·t Among them, P load represents the power consumption of the task load, and t represents the task execution time; Basic power consumption E base It is expressed as: E base =P base ·t Among them, P base represents the basic power consumption, and t represents the task execution time.

7. A battery management device, characterized in that: The device is applied to shore-based battery management of unmanned ships, including: A real-time data acquisition module is used to receive the real-time status data of the target battery collected by the sensor network in real time; A preprocessing module, used for performing a preprocessing operation on the real-time status data to obtain preprocessed status data; A feature extraction module, used for performing a feature extraction operation on the preprocessing state data to obtain feature extraction data; A power consumption prediction module, used for calling the LSTM model and inputting the feature extraction data into the LSTM model to perform power consumption prediction operation to obtain a real-time power consumption prediction result; A dynamic adjustment module is used to dynamically adjust the discharge depth and discharge rate of the target battery according to the real-time power consumption prediction result.

8. The battery management device according to claim 7, characterized in that: The preprocessing module comprises: A data cleaning submodule, used to perform a data cleaning operation on the real-time status data to obtain cleaned status data; The normalization submodule is used to perform a normalization operation on the cleaning state data to obtain the pre-processing state data.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and the processor implements the steps of the battery management method according to any one of claims 1 to 6 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the battery management method according to any one of claims 1 to 6 are implemented.

Images