AGV intelligent charging method and system

Abstract

The embodiment of the invention discloses an AGV intelligent charging method and system. The method comprises the following steps: in the operation process of an AGV, obtaining the electric quantity, voltage and current of an AGV battery, and the position and motion state of the AGV to obtain operation data; a task demand is obtained, and the task demand comprises a task type, a task emergency degree and a task path length; inputting the operation data and the task demand into a power consumption prediction model to predict power consumption; determining an AGV charging plan according to the prediction result; wherein the power consumption prediction model is obtained by training a deep learning network by taking historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set. By implementing the method provided by the embodiment of the invention, the charging time and the charging amount can be optimized, so that the energy utilization rate and the operation efficiency are improved, and the working efficiency of the AGV and the overall operation efficiency of the production line are improved.

Description

Technical Field

[0001] The present invention relates to an AGV charging method, and more specifically to an AGV intelligent charging method and system. Background Art

[0002] With the continuous advancement of automation and intelligent manufacturing technologies, the application of automated guided vehicles (AGVs) in logistics, warehousing and manufacturing is becoming more and more common. However, the energy management and charging efficiency of AGVs are still key factors restricting their overall performance. Traditional charging systems usually rely on fixed schedules or simple periodic charging modes. This method cannot adjust the charging strategy in real time to adapt to the actual operating status and task requirements of the AGV, resulting in low charging efficiency and affecting the overall benefits of production and operations.

[0003] Therefore, it is necessary to design a new method to realize real-time monitoring and analysis of AGV's power consumption, operating status and task requirements, so as to optimize the charging time and charging amount, improve energy utilization and operating efficiency, and improve the working efficiency of AGV and the overall operation efficiency of the production line. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the prior art and provide an AGV intelligent charging method and system.

[0005] To achieve the above purpose, the present invention adopts the following technical solution: an AGV intelligent charging method, comprising:

[0006] During the operation of the AGV, the power, voltage, current, AGV position, and AGV motion status of the AGV battery are obtained to obtain operation data;

[0007] Obtaining task requirements, wherein the task requirements include task type, task urgency, and task path length;

[0008] Inputting the operation data and the task requirements into a power consumption prediction model to predict power consumption to obtain a prediction result;

[0009] Determine an AGV charging plan based on the prediction results;

[0010] Among them, the power consumption prediction model is obtained by training a deep learning network using the historical operation data of AGV, historical task requirements and corresponding power consumption data as a sample set.

[0011] The further technical solution is: the power consumption prediction model is obtained by training a deep learning network using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set, including:

[0012] Obtain the historical operation data, historical task requirements and corresponding power consumption data of AGV;

[0013] Performing data cleaning and normalization processing on the historical operation data of the AGV to obtain a preprocessing result;

[0014] Analyzing and extracting key factors affecting power consumption from the preprocessing results to obtain extraction results;

[0015] Build deep learning networks;

[0016] The extraction results, historical task requirements and corresponding power consumption data are used as a sample set to train the deep learning network to obtain a power consumption prediction model.

[0017] A further technical solution is: determining the AGV charging plan according to the prediction result includes:

[0018] Get the actual power consumption of AGV;

[0019] An AGV charging plan is dynamically generated based on the prediction results and the actual power consumption of the AGV.

[0020] A further technical solution is: the AGV charging plan includes charging timing, charging sites and charging time.

[0021] A further technical solution is: dynamically generating an AGV charging plan based on the prediction result and the actual power consumption of the AGV, including:

[0022] Compare the prediction result with the actual power consumption of the AGV to determine the charging timing and the charging demand of the AGV;

[0023] Determine the charging site based on the charging site, the current location of the AGV, and the scheduling of the current task;

[0024] Determine the charging time and charging capacity based on the AGV charging requirements and the charging speed of the charging station;

[0025] Dynamically adjust the AGV charging plan based on the charging equipment capacity and availability of the charging site and the urgency of the AGV's mission.

[0026] The further technical solution is: dynamically adjusting the AGV charging plan according to the charging equipment capacity and availability of the charging station and the urgency of the AGV task, including:

[0027] Optimization goals are set based on the charging equipment capacity and availability of the charging station and the urgency of the AGV's mission, and the AGV charging plan is dynamically adjusted through the optimization algorithm.

[0028] A further technical solution is: determining the charging time and charging power according to the charging demand of the AGV and the charging speed of the charging station includes:

[0029] The total charging time and charging power are determined according to the AGV charging requirements and the charging speed of the charging station, and a strategy of multiple short-term charging is adopted to divide the total charging time into segments according to the task intervals to obtain the charging time and charging power.

[0030] Its further technical solution is: after determining the AGV charging plan according to the prediction result, it also includes:

[0031] The AGV charging plan is sent to the AGV, and the real-time current during the charging process of the AGV is monitored. When the real-time current exceeds the maximum current threshold, the charging of the AGV is stopped.

[0032] The present invention also provides an AGV intelligent charging system, comprising:

[0033] The operation data acquisition unit is used to obtain the power, voltage, current, AGV position, and motion state of the AGV battery during the operation of the AGV to obtain the operation data;

[0034] A task requirement acquisition unit, used to acquire task requirements, wherein the task requirements include task type, task urgency, and task path length;

[0035] A prediction unit, used for inputting the operation data and the task requirements into a power consumption prediction model to predict the power consumption and obtain a prediction result;

[0036] A plan determination unit is used to determine the AGV charging plan according to the prediction result.

[0037] Its further technical solution is: also includes:

[0038] The model generation unit is used to train the deep learning network using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set to obtain a power consumption prediction model.

[0039] The beneficial effects of the present invention compared with the prior art are as follows: when the AGV is running, the system collects data such as battery power, voltage, current, position and motion status, and obtains task requirements, and inputs these data into a power consumption prediction model. The model predicts power based on historical data, and according to the prediction results, the system formulates a charging plan to optimize the power management of the AGV, and realizes real-time monitoring and analysis of the AGV's power consumption, operating status and task requirements, thereby optimizing the charging time and charging amount, so as to improve energy utilization and operating efficiency, and enhance the working efficiency of the AGV and the overall operating efficiency of the production line.

[0040] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0042] Figure 1 A schematic diagram of an application scenario of an AGV intelligent charging method provided by an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of a flow chart of an AGV intelligent charging method provided by an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of a sub-process of an AGV intelligent charging method provided by an embodiment of the present invention;

[0045] Figure 4 A schematic diagram of a sub-process of an AGV intelligent charging method provided by an embodiment of the present invention;

[0046] Figure 5 A schematic diagram of a sub-process of an AGV intelligent charging method provided by an embodiment of the present invention;

[0047] Figure 6 A schematic diagram of a flow chart of an AGV intelligent charging method provided by another embodiment of the present invention;

[0048] Figure 7 A schematic block diagram of an AGV intelligent charging system provided in an embodiment of the present invention;

[0049] Figure 8 A schematic block diagram of a plan determination unit of an AGV intelligent charging system provided in an embodiment of the present invention;

[0050] Fig. 9 A schematic block diagram of a generation subunit of an AGV intelligent charging system provided in an embodiment of the present invention;

[0051] Fig.10 A schematic block diagram of an AGV intelligent charging system provided in another embodiment of the present invention;

[0052] Fig.11 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0055] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0056] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0057] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of an AGV intelligent charging method provided by an embodiment of the present invention; Figure 2A schematic flow chart of an AGV intelligent charging method provided in an embodiment of the present invention. The AGV intelligent charging method is used in a server, which exchanges data with an AGV controller and a charging station. In addition, the AGV controller is also connected to a current detection module and a battery. The AGV controller also exchanges data with the charging station. The AGV controller monitors the battery status, remaining power, current position and task priority in real time through a communication protocol. These data will be uploaded to the server in a timely manner to ensure that the scheduling system can obtain the latest power information and task requirements. Based on the collected data, the server uses a deep learning algorithm to analyze the operation mode and task requirements of the AGV and predict the best charging time and charging method. The charging strategy can be adjusted according to different task types and operation modes, such as selecting fast charging, slow charging or partial charging to optimize the charging efficiency and meet the actual needs of the AGV. At the same time, the server can directly control the charging current and voltage of the charging station to achieve the optimal charging effect. In addition, the operator can also monitor the charging status and efficiency of the AGV in real time through the cloud platform. The operator can adjust the charging strategy according to changes in production needs to ensure that the charging process adapts to the dynamic production environment. The AGV controller is connected to the current detection module to ensure the safety and stability of the battery during the charging process, and monitor the charging current in real time. If the current exceeds the set maximum safety threshold, the charging is stopped immediately to prevent equipment failure or safety risks. Real-time monitoring and analysis of the AGV's power consumption, operating status, and task requirements are achieved, thereby optimizing the charging time and charging amount to improve energy utilization and operating efficiency, and improve the work efficiency of the AGV and the overall operating efficiency of the production line.

[0058] Figure 2 FIG. 1 is a flow chart of an AGV intelligent charging method provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S140.

[0059] S110. During the operation of the AGV, the power, voltage, current, position, and motion status of the AGV battery are obtained to obtain operation data.

[0060] In this embodiment, the operating data refers to the power, voltage, current of the AGV battery, the AGV position, and the AGV motion status.

[0061] The power level refers to the remaining energy in the AGV battery, usually expressed as a percentage or power unit (such as milliampere-hour). The power level information is used to determine the AGV's endurance and charging needs to ensure that the mission is not interrupted due to insufficient power.

[0062] Voltage refers to the potential difference between the two ends of a battery, which affects the battery's discharge capacity and charging efficiency. Monitoring voltage can help assess the battery's health and whether charging is normal. Voltage that is too high or too low may affect battery performance or cause equipment failure.

[0063] Current refers to the intensity of the electrical current flowing through the battery, usually measured in amperes (A). Real-time current monitoring helps ensure that the battery remains within a safe range during charging and discharging, avoiding overload or over-discharge, thereby protecting battery life and device safety.

[0064] AGV position refers to the current position of the automated guided vehicle in the working environment, which is usually obtained through GPS, laser positioning or other sensor systems. Accurate position data is crucial for task planning and path optimization, helping the system to track the movement and status of the AGV in real time.

[0065] The motion status of an AGV includes information such as the speed, direction, acceleration, etc. of the AGV, and can also include path length, load weight, and running time, etc. Understanding the motion status helps optimize task scheduling, adjust driving routes, and ensure the stability and safety of the AGV during operation.

[0066] S120: Obtaining task requirements, wherein the task requirements include task type, task urgency, and task path length.

[0067] In this embodiment, the task requirement refers to the detailed information required to complete a specific task in the AGV system.

[0068] The task type describes the specific operation or work content that the AGV needs to perform. For example, this may include material handling, cargo distribution, assembly line feeding, cleaning, etc. Different task types may have different requirements for the AGV's movement, operation mode, and working environment. For example, a material handling task may require the AGV to move within a specific handling area and stop accurately, while an assembly line feeding task may require the AGV to deliver materials to the production line at a specific point in time.

[0069] Task urgency refers to the priority or time requirement for task execution. Typically, task urgency affects how the scheduling system allocates resources and schedules tasks. For example, some tasks may need to be prioritized to prevent production line shutdowns, while other tasks may be able to be executed according to regular scheduling. Task urgency is usually divided into different levels, such as high, medium, and low, and the system will adjust the execution order of tasks and resource allocation based on these levels.

[0070] The mission path length refers to the distance the AGV needs to travel when performing a mission. The calculation of the path length includes the total travel distance from the starting point to the end point. Knowing the mission path length is very important for calculating battery consumption, estimating completion time, and formulating the optimal path strategy. The system will optimize the AGV's driving route based on the path length to improve efficiency and reduce energy consumption. For example, a longer path may require planning more charging stations or adjusting the AGV's driving speed to ensure that the mission is completed on time.

[0071] In summary, the task type defines the work content of the AGV, the task urgency determines the priority and processing time limit of the task, and the task path length affects the driving distance and the overall planning of task execution. The system optimizes task scheduling, resource allocation, AGV operation efficiency, and AGV charging by integrating this information.

[0072] S130: Input the operation data and the task requirements into a power consumption prediction model to predict power consumption and obtain a prediction result.

[0073] In this embodiment, the prediction result refers to the power consumption of the AGV.

[0074] Based on the collected data, the system uses algorithms to analyze the AGV's operating mode and current mission requirements, thereby predicting the timing of charging and the corresponding charging method, etc. The system will adjust the charging strategy according to different operating modes and mission types, such as selecting fast charging, slow charging or partial charging to optimize charging efficiency and meet the actual use needs of the AGV. The server can directly control the charging current and voltage of the charging station to achieve these charging strategy adjustments.

[0075] Among them, the power consumption prediction model is obtained by training a deep learning network using the historical operation data of AGV, historical task requirements and corresponding power consumption data as a sample set.

[0076] In one embodiment, see Figure 3 The above-mentioned power consumption prediction model is obtained by training a deep learning network using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set, and includes steps S131 to S135.

[0077] S131, obtaining historical operation data, historical task requirements and corresponding power consumption data of the AGV.

[0078] In this embodiment, historical operation data refers to the previous operation data of the AGV, including power, voltage, current, AGV position, and AGV motion status; wherein the AGV motion status includes speed, direction, acceleration, path length, load weight, and operating time, etc.

[0079] Historical task requirements refer to past task requirements, including task type, urgency, and task path length.

[0080] S132: Perform data cleaning and normalization processing on the historical operation data of the AGV to obtain a preprocessing result.

[0081] In this embodiment, the preprocessing result refers to the result obtained after data cleaning and normalization processing of the historical operation data.

[0082] Specifically, the collected data is cleaned to remove outliers and missing values, and normalized to ensure that the data is in the same range to avoid bias in model training.

[0083] In this embodiment, outliers and missing values ​​are identified and removed. Outliers can be detected by statistical methods (such as Z scores), and missing values ​​can be handled by interpolation methods (such as mean filling); the data is scaled to the same range, such as by standardization (mean is 0, variance is 1) or minimum-maximum normalization (scaling the data to the [0, 1] interval) to reduce bias in model training.

[0084] S133, analyzing the preprocessing results and extracting key factors affecting power consumption to obtain extraction results.

[0085] In this embodiment, the extraction result refers to the key factor affecting the power consumption.

[0086] Specifically, the key factors affecting AGV power consumption are analyzed and relevant features are extracted. For example, factors such as speed, load weight, and running path may have a significant impact on power consumption.

[0087] In this embodiment, statistical methods and feature selection techniques (such as correlation analysis and principal component analysis) are used to identify factors that have a significant impact on power consumption. Key features such as speed, load weight, path length, etc. are extracted from the preprocessing results, which may have a significant impact on power consumption prediction.

[0088] S134. Build a deep learning network.

[0089] In this embodiment, an appropriate deep learning model is selected to predict the power consumption trend.

[0090] Specifically, the selection of a suitable deep learning model, such as a deep neural network (DNN), a convolutional neural network (CNN), or a recurrent neural network (RNN), depends on the nature of the data and the task requirements. The number of layers of the network, the number of neurons in each layer, the activation function, etc. are designed.

[0091] S135. Using the extraction results, historical task requirements and corresponding power consumption data as a sample set, the deep learning network is trained to obtain a power consumption prediction model.

[0092] In this embodiment, the historical operation data and the corresponding power consumption data are used to train the model. The data usually needs to be divided into a training set and a test set, and the performance of the model is evaluated through cross-validation.

[0093] Specifically, the extraction results, historical task requirements, and power consumption data are organized into training sets and test sets. The deep learning network is trained using the training set, and the network parameters are adjusted to minimize the prediction error. The generalization ability of the model is evaluated through cross-validation. The accuracy of the model is verified using the test set, and the hyperparameters and network structure are adjusted to optimize performance.

[0094] Afterwards, the trained power consumption prediction model is used to predict the currently acquired task requirements and operating data, and the power consumption trend of the AGV when performing a new task is output. The trained model is deployed to the AGV system so that it can predict power consumption in real time and dynamically adjust the AGV's task scheduling and charging plan based on the prediction results.

[0095] S140, determining an AGV charging plan according to the prediction result;

[0096] In this embodiment, the AGV charging plan includes charging timing, charging stations, and charging time. The charging timing refers to the time point or condition that determines when to charge the AGV. The factors to be considered include:

[0097] Charge level: Usually based on the remaining charge of the AGV, charging is initiated when the charge drops below a set threshold.

[0098] Mission planning: Charging can be scheduled during the period when the AGV is not performing tasks, such as after the task is completed or between tasks.

[0099] Workload: If the AGV has a high workload and operating time, more frequent charging or a more flexible charging strategy may be required.

[0100] Prediction model: Use the power consumption prediction model to predict the power usage trend of the AGV to optimize the charging time and avoid mission interruption due to low power.

[0101] A charging station is a specific location or charging facility where an AGV is charged. Selection factors include:

[0102] Geographic location: Charging stations should be located near routes that AGVs frequently travel, so that AGVs can charge smoothly during missions.

[0103] Facility conditions: The charging station needs to have sufficient power supply capacity to meet the charging needs of AGVs.

[0104] Quantity and distribution: Multiple charging stations should be reasonably arranged according to the number of AGVs and the working area to reduce the moving time of AGVs and improve charging efficiency.

[0105] Charging method: Consider different charging methods such as wireless charging and fast charging, and choose the charging station type that best suits the actual usage environment.

[0106] Charging time refers to the time required for each charge and generally depends on the battery capacity, charging power, and state of charge. Factors to consider include:

[0107] Battery type: Different types of batteries (such as lithium batteries, lead-acid batteries) have different charging time requirements.

[0108] Charging power: Charging power determines the charging speed. High-power charging can reduce charging time, but may require higher electricity costs and equipment support.

[0109] Charging status: Charging time is also affected by the AGV’s current charge level. For example, the time for a full charge and a supplemental charge may be different.

[0110] Charging strategy: Develop a charging plan based on the AGV's task schedule and charging needs, balancing charging time with working time to optimize the AGV's efficiency.

[0111] These factors together influence the AGV’s charging plan, ensuring that the AGV can perform its tasks efficiently while maintaining sufficient charge to avoid interruptions.

[0112] In one embodiment, see Figure 4 , the above-mentioned step S140 may include steps S141 to S142.

[0113] S141. Obtain actual power consumption of the AGV.

[0114] In this embodiment, the actual power consumption of the AGV refers to the actual power consumption of the AGV.

[0115] S142: Dynamically generate an AGV charging plan based on the prediction result and the actual power consumption of the AGV.

[0116] In one embodiment, see Figure 5 , the above-mentioned step S142 may include steps S1421 to S1424.

[0117] S1421. Compare the prediction result and the actual power consumption of the AGV to determine the charging timing and the charging demand of the AGV.

[0118] In this embodiment, the predicted data (such as future power usage trends) is compared with the actual power consumption of the AGV (such as real-time power usage) to identify the difference between the prediction and the actual; based on the comparison results, it is determined when charging should be started to ensure that the AGV will not interrupt its mission due to insufficient power; the gap between the current power and the predicted power is evaluated, and the charging demand is determined to meet the future operation needs of the AGV.

[0119] S1422. Determine a charging site according to the charging site, the current position of the AGV, and the scheduling of the current task.

[0120] In this embodiment, the location information, availability, and current status of the charging station are obtained; based on the current location and path of the AGV, the closest charging station is selected to reduce charging time and path deviation; combined with the schedule of the AGV's current task, ensure that charging is arranged during the task idle period to avoid affecting task execution; comprehensively consider the AGV location and the availability of the charging station to select the best charging station.

[0121] S1423. Determine the charging time and charging power according to the charging demand of the AGV and the charging speed of the charging station.

[0122] In this embodiment, the amount of electricity required to be charged is calculated based on the charging demand of the AGV; the time required for charging is determined according to the speed of the charging equipment at the charging station; the charging time is combined with the AGV task scheduling to ensure that charging does not affect other tasks of the AGV; the actual charging amount is set according to the power demand and charging time to ensure that the AGV can obtain enough power to complete the intended task.

[0123] In one embodiment, the total charging time and charging power are determined according to the AGV charging demand and the charging speed of the charging station, and a strategy of multiple short-time charging is adopted to segment the total charging time according to the task intervals to obtain the charging time and charging power.

[0124] Specifically, based on the power consumption trend and prediction results of AGV1, the total charging time required for AGV1 is calculated. For example, if it takes 1 hour for AGV1 to charge from 20% to 80% (charging speed is 60% per hour), then the total charging time is 1 hour; according to the total charging time and charging speed, the amount of power required to be charged is determined. For example, AGV1 needs to charge from 20% to 80%, and 60% of the power needs to be charged; since the task scheduling of AGV may not allow long-term charging, a short-time charging strategy can be adopted. The total charging time is divided into several short time periods. For example, if the charging time of 1 hour can be divided into 4 15-minute short-time charging segments, each charging can increase the power by 15%; analyze the task arrangement of AGV1 and find the task gap. For example, assuming that AGV1 has 10 minutes of idle time between task A and task B, 10 minutes of charging time can be arranged. If the charging power at this time is less than 5%, it can continue to charge in the next task gap until the required total charging power is reached; in actual operation, the power and task progress of AGV1 are monitored in real time, and the charging plan is adjusted dynamically. If the mission schedule changes, the short-term charging segment and charging time can be recalculated and adjusted to ensure that AGV1 meets the charging needs while maintaining efficient mission execution.

[0125] For example: Assuming that the power of AGV1 is 25%, the target charging power is 80%, charging demand = target power - current power = 80% - 25% = 55%; Assuming that the charging rate of charging station A is 2% of power per minute; Charging time = charging demand / charging speed = 55% / 2% per minute = 27.5 minutes; Analyze the task scheduling of AGV1 and identify the task gaps. For example, AGV1 has 10 minutes of idle time per hour. Divide the total charging time into segments and allocate them according to the length of the task gap. For example, if each task gap is 10 minutes, the 27.5-minute charging time can be divided into 2 10-minute charges and 1 7.5-minute charge. Each charge can increase the power. If charging 2% per minute, 10 minutes of charging increases by 20%, and 7.5 minutes of charging increases by 15%.

[0126] The specific charging process is as follows:

[0127] First charge: During the first 10 minutes of charging, the battery capacity increases from 25% to 45%.

[0128] Second charge: During the second 10-minute interval, the battery level increases from 45% to 65%.

[0129] Third charge: During the third gap, the battery was charged for 7.5 minutes and the power increased from 65% to 80%.

[0130] The purpose of this design is to minimize the interference of charging on task execution. Adjustments are made based on the availability of charging equipment and the urgency of the AGV's task to ensure that charging is completed in the shortest possible time.

[0131] Through this segmented charging strategy, the idle time of the AGV can be effectively utilized for charging, reducing the impact of charging on the actual task, while ensuring that the AGV has sufficient power to complete subsequent tasks.

[0132] S1424. Dynamically adjust the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV's task.

[0133] In this embodiment, an optimization target is formulated according to the charging equipment capacity and availability of the charging station and the mission urgency of the AGV, and the AGV charging plan is dynamically adjusted through an optimization algorithm.

[0134] In this embodiment, the equipment capacity and status of the charging station are monitored in real time to ensure that the charging facilities can meet the demand; the priority of the charging plan is adjusted according to the urgency of the AGV's task. For example, urgent tasks may require priority charging; set optimization goals, such as minimizing charging time, maximizing task execution efficiency, etc.; use optimization algorithms to dynamically adjust the charging plan in response to changes in equipment capacity, changes in task priority, and actual power consumption.

[0135] By following these steps, a flexible and efficient AGV charging plan can be developed to ensure smooth operation of the system and timely completion of tasks.

[0136] For example, in an AGV system, suppose there are two AGVs (AGV1 and AGV2) and two charging stations (station A and station B). According to the prediction model, the power consumption trend, that is, the corresponding prediction result, is as follows:

[0137] AGV1:

[0138] At t1: power level 80%;

[0139] At t2: power level 60%;

[0140] Time t3: Power 40%;

[0141] Time t4: Power 20%;

[0142] Time t5: Power 10%;

[0143] AGV2:

[0144] At t1: power level 90%;

[0145] At t2: power level 70%;

[0146] Time t3: Power 50%;

[0147] Time t4: Power 30%;

[0148] Time t5: Power 10%;

[0149] The specific steps to generate a charging plan are as follows:

[0150] First, the power consumption trends of AGV1 and AGV2 are predicted, and the above prediction results are obtained;

[0151] Next, during the operation of the AGV, the power consumption of AGV1 and AGV2 is monitored in real time and compared with the predicted results. Assume that the current time is t4, the actual power of AGV1 is 25%, while the predicted result is 20%. Then, based on the real-time monitored power consumption and the predicted results, the appropriate charging time is determined. Since the power of AGV1 is lower than the safety threshold, the charging plan is triggered.

[0152] Secondly, based on the distance between charging station A and station B, the current location of AGV1, and task scheduling, select the nearest and available charging station. Assume that station A is closer to AGV1 and available. When selecting a charging station, you need to consider the distance between charging stations, the current location of AGV, and task scheduling.

[0153] Thirdly, the charging time and the required power are determined based on the charging requirements of AGV1 and the charging speed of charging station A. Assume that according to the predicted power consumption trend, AGV1 needs 10 minutes of charging time and each charge requires 20% of power. In order to minimize the impact of charging time on task execution, a strategy of multiple short-term charging (such as segmented charging) can be adopted to use the gap time between AGV tasks for charging.

[0154] Finally, the strategy and optimization goal of the charging plan are formulated based on constraints such as the capacity of site A, the availability of charging equipment, the urgency of AGV1's mission, and the expected charging time. By using optimization algorithms such as genetic algorithms, the optimal charging plan is determined to ensure that AGV1 can complete as many tasks as possible during charging.

[0155] In a large manufacturing plant, AGV is responsible for transporting raw materials and finished products. The production process of the factory requires that AGV can complete the transportation task in a short time and does not allow long-term shutdown for charging. Therefore, the process of the method of this embodiment in actual application is as follows:

[0156] Predict the power status of the AGV after completing the current task, and calculate the required charging amount based on its remaining power and the upcoming task.

[0157] The charging mode is determined based on the prediction results. If the AGV needs to return to work quickly, the system starts the fast charging mode and charges with high current to shorten the charging time. If the AGV is idle, the slow charging mode is selected to extend the battery life.

[0158] Schedule the AGV to charge immediately after the mission is completed and assign its corresponding charging mode at the charging station.

[0159] In addition, operators can monitor the charging status and task execution of all AGVs in real time through the cloud platform management interface; if production demand changes, operators can adjust the charging strategy and give priority to charging preparations for AGVs that need to increase transportation tasks to ensure the smooth progress of production plans.

[0160] During the charging process, the battery temperature, voltage and current are monitored in real time. Once an abnormal situation is detected, such as excessive temperature or excessive current, charging will be stopped immediately and an alarm signal will be issued. At the same time, the fault information will be recorded for maintenance personnel to check and repair.

[0161] Through this method, the factory's AGV charging efficiency has been significantly improved, charging time has been reduced by an average of 30%, and battery life has been extended by 20%. Production line continuity has been guaranteed, AGV downtime has been reduced by 50%, and overall production efficiency has been increased by 15%.

[0162] Optimize the charging strategy according to the real-time status and task requirements of the AGV to solve the charging efficiency problem, thereby improving production and operation results; by reducing production downtime and energy waste, improve the overall production efficiency and equipment life. Through real-time data analysis and optimization of charging strategies, the operating efficiency and energy utilization of AGVs are significantly improved, downtime and energy waste are reduced, thereby enhancing production efficiency and equipment life.

[0163] The above-mentioned AGV intelligent charging method collects data such as battery power, voltage, current, position and motion status when the AGV is running, and obtains task requirements, and inputs these data into the power consumption prediction model. The model predicts power based on historical data. According to the prediction results, the system formulates a charging plan to optimize the power management of the AGV, realizes real-time monitoring and analysis of the AGV's power consumption, operating status and task requirements, thereby optimizing the charging time and charging amount, so as to improve energy utilization and operating efficiency, and improve the work efficiency of the AGV and the overall operation efficiency of the production line.

[0164] Figure 6 FIG. 1 is a flow chart of an AGV intelligent charging method provided by another embodiment of the present invention. Figure 6As shown, the AGV intelligent charging method of this embodiment includes step S250. Steps S210-S240 are similar to steps S110-S140 in the above embodiment, and are not repeated here. The added step S250 in this embodiment is described in detail below.

[0165] S250, sending an AGV charging plan to the AGV, and monitoring the real-time current during the charging process of the AGV, and when the real-time current exceeds a maximum current threshold, stopping the charging of the AGV.

[0166] In this embodiment, while sending the AGV charging plan, the current during the charging process is monitored in real time. If it is detected that the real-time current exceeds the set maximum current threshold, the charging operation will be stopped immediately. This measure is intended to ensure the safety and stability of the battery during the charging process, thereby avoiding equipment failure or safety risks caused by excessive current.

[0167] Figure 7 FIG. 3 is a schematic block diagram of an AGV intelligent charging system 300 provided in an embodiment of the present invention. Figure 5 As shown, corresponding to the above AGV intelligent charging method, the present invention also provides an AGV intelligent charging system 300. The AGV intelligent charging system 300 includes a unit for executing the above AGV intelligent charging method, and the system can be configured in a server. Figure 7 The AGV intelligent charging system 300 includes an operation data acquisition unit 301, a task requirement acquisition unit 302, a prediction unit 303 and a plan determination unit 304.

[0168] The operation data acquisition unit 301 is used to obtain the power, voltage, current, AGV position, and AGV motion status of the AGV battery during the operation of the AGV to obtain the operation data; the task requirement acquisition unit 302 is used to obtain the task requirement, wherein the task requirement includes the task type, task urgency, and task path length; the prediction unit 303 is used to input the operation data and the task requirement into the power consumption prediction model to predict the power consumption to obtain the prediction result; the plan determination unit 304 is used to determine the AGV charging plan according to the prediction result.

[0169] In one embodiment, the above-mentioned AGV intelligent charging system 300 further includes:

[0170] The model generation unit is used to train the deep learning network using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set to obtain a power consumption prediction model.

[0171] In one embodiment, the model generation unit includes:

[0172] A data acquisition subunit is used to acquire the historical operation data, historical task requirements and corresponding power consumption data of the AGV; a preprocessing subunit is used to perform data cleaning and normalization on the historical operation data of the AGV to obtain a preprocessing result; an extraction subunit is used to analyze the preprocessing result and extract key factors affecting power consumption to obtain an extraction result; a construction subunit is used to construct a deep learning network; a training subunit is used to use the extraction results, historical task requirements and corresponding power consumption data as a sample set to train the deep learning network to obtain a power consumption prediction model.

[0173] In one embodiment, if Figure 8 As shown, the plan determination unit 304 includes an actual consumption acquisition subunit 3041 and a generation subunit 3042 .

[0174] The actual consumption acquisition subunit 3041 is used to acquire the actual power consumption of the AGV; the generation subunit 3042 is used to dynamically generate an AGV charging plan based on the prediction result and the actual power consumption of the AGV.

[0175] In one embodiment, if Fig. 9 As shown, the generating subunit 3042 includes a comparing module 30421 , a site determining module 30422 , a time and power determining module 30423 and a dynamic adjusting module 30424 .

[0176] The comparison module 30421 is used to compare the prediction result and the actual power consumption of the AGV to determine the charging time and the charging demand of the AGV; the site determination module 30422 is used to determine the charging site according to the charging site, the current position of the AGV and the scheduling of the current task; the time and power determination module 30423 is used to determine the charging time and charging power according to the charging demand of the AGV and the charging speed of the charging site; the dynamic adjustment module 30424 is used to dynamically adjust the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV task.

[0177] In one embodiment, the dynamic adjustment module 30424 is used to formulate optimization goals according to the charging equipment capacity and availability of the charging site and the urgency of the AGV's task, and dynamically adjust the AGV charging plan through an optimization algorithm.

[0178] In one embodiment, the time and power determination module 30423 is used to determine the total charging time and charging power according to the AGV charging requirements and the charging speed of the charging station, and adopt a strategy of multiple short-time charging to segment the total charging time according to the task intervals to obtain the charging time and charging power.

[0179] Fig.10FIG. 3 is a schematic block diagram of an AGV intelligent charging system 300 provided in another embodiment of the present invention. Fig.10 As shown, the AGV intelligent charging system 300 of this embodiment is based on the above embodiment and adds a sending unit 305.

[0180] The sending unit 305 is used to send the AGV charging plan to the AGV, and monitor the real-time current during the charging process of the AGV. When the real-time current exceeds the maximum current threshold, the charging of the AGV is stopped.

[0181] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned AGV intelligent charging system 300 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0182] The AGV intelligent charging system 300 can be implemented in the form of a computer program. Fig.11 The electronic device shown is running.

[0183] See also Fig.11 , Fig.11 1 is a schematic block diagram of an electronic device provided in an embodiment of the present application. The electronic device 500 may also be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0184] See also Fig.11 The electronic device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0185] The non-volatile storage medium 503 may store an operating system 5031 and a program 5032. The program 5032 includes program instructions, and when the program instructions are executed, the processor 502 may execute a computer device method.

[0186] The processor 502 is used to provide computing and control capabilities to support the operation of the entire electronic device 500 .

[0187] The internal memory 504 provides an environment for the operation of the program 5032 in the non-volatile storage medium 503. When the program 5032 is executed by the processor 502, the processor 502 can execute a computer program method.

[0188] The network interface 505 is used to communicate with other devices over the network. Fig.11The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device 500 to which the scheme of the present application is applied. The specific electronic device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0189] The processor 502 is used to run the program 5032 stored in the memory to implement the following steps:

[0190] During the operation of the AGV, the power, voltage, current, AGV position, and AGV motion state of the AGV battery are obtained to obtain operation data; task requirements are obtained, wherein the task requirements include task type, task urgency, and task path length; the operation data and the task requirements are input into a power consumption prediction model to predict power consumption to obtain a prediction result; and an AGV charging plan is determined according to the prediction result;

[0191] Among them, the power consumption prediction model is obtained by training a deep learning network using the historical operation data of AGV, historical task requirements and corresponding power consumption data as a sample set.

[0192] In one embodiment, when the processor 502 implements the step of training a deep learning network using the historical operation data, historical task requirements, and corresponding power consumption data of the AGV as a sample set to implement the power consumption prediction model, the processor 502 specifically implements the following steps:

[0193] Acquire the historical operation data, historical task requirements and corresponding power consumption data of the AGV; perform data cleaning and normalization on the historical operation data of the AGV to obtain a preprocessing result; analyze and extract the key factors affecting power consumption from the preprocessing result to obtain an extraction result; construct a deep learning network; use the extraction results, historical task requirements and corresponding power consumption data as a sample set to train the deep learning network to obtain a power consumption prediction model.

[0194] In one embodiment, when the processor 502 implements the step of determining the AGV charging plan according to the prediction result, the processor 502 specifically implements the following steps:

[0195] The actual power consumption of the AGV is obtained; and a charging plan for the AGV is dynamically generated according to the prediction result and the actual power consumption of the AGV.

[0196] The AGV charging plan includes charging timing, charging sites and charging time.

[0197] In one embodiment, when the processor 502 implements the step of dynamically generating the AGV charging plan according to the prediction result and the actual power consumption of the AGV, the processor 502 specifically implements the following steps:

[0198] Compare the prediction result with the actual power consumption of the AGV to determine the charging timing and the charging demand of the AGV; determine the charging site according to the charging site, the current position of the AGV and the scheduling of the current task; determine the charging time and charging power according to the charging demand of the AGV and the charging speed of the charging site; dynamically adjust the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV's task.

[0199] In one embodiment, the processor 502 implements the following steps when implementing the step of dynamically adjusting the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV task:

[0200] Optimization goals are set based on the charging equipment capacity and availability of the charging station and the urgency of the AGV's mission, and the AGV charging plan is dynamically adjusted through the optimization algorithm.

[0201] In one embodiment, when the processor 502 implements the step of determining the charging time and charging power according to the AGV charging demand and the charging speed of the charging station, the processor 502 specifically implements the following steps:

[0202] The total charging time and charging power are determined according to the AGV charging requirements and the charging speed of the charging station, and a strategy of multiple short-term charging is adopted to divide the total charging time into segments according to the task intervals to obtain the charging time and charging power.

[0203] In one embodiment, after implementing the step of determining the AGV charging plan according to the prediction result, the processor 502 further implements the following steps:

[0204] The AGV charging plan is sent to the AGV, and the real-time current during the charging process of the AGV is monitored. When the real-time current exceeds the maximum current threshold, the charging of the AGV is stopped.

[0205] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0206] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a program. The program includes program instructions, and the program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0207] Therefore, the present invention also provides a storage medium. The storage medium can be a storage medium readable by an electronic device. The storage medium stores a program, wherein when the program is executed by a processor, the processor executes the following steps:

[0208] During the operation of the AGV, the power, voltage, current, AGV position, and AGV motion state of the AGV battery are obtained to obtain operation data; task requirements are obtained, wherein the task requirements include task type, task urgency, and task path length; the operation data and the task requirements are input into a power consumption prediction model to predict power consumption to obtain a prediction result; and an AGV charging plan is determined according to the prediction result;

[0209] Among them, the power consumption prediction model is obtained by training a deep learning network using the historical operation data of AGV, historical task requirements and corresponding power consumption data as a sample set.

[0210] In one embodiment, when the processor executes the program to implement the step of obtaining the power consumption prediction model by training a deep learning network using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set, the processor specifically implements the following steps:

[0211] Acquire the historical operation data, historical task requirements and corresponding power consumption data of the AGV; perform data cleaning and normalization on the historical operation data of the AGV to obtain a preprocessing result; analyze and extract the key factors affecting power consumption from the preprocessing result to obtain an extraction result; construct a deep learning network; use the extraction results, historical task requirements and corresponding power consumption data as a sample set to train the deep learning network to obtain a power consumption prediction model.

[0212] In one embodiment, when the processor executes the program to implement the step of determining the AGV charging plan according to the prediction result, the processor specifically implements the following steps:

[0213] The actual power consumption of the AGV is obtained; and a charging plan for the AGV is dynamically generated according to the prediction result and the actual power consumption of the AGV.

[0214] The AGV charging plan includes charging timing, charging sites and charging time.

[0215] In one embodiment, when the processor executes the program to implement the step of dynamically generating an AGV charging plan according to the prediction result and the actual power consumption of the AGV, the processor specifically implements the following steps:

[0216] Compare the prediction result with the actual power consumption of the AGV to determine the charging timing and the charging demand of the AGV; determine the charging site according to the charging site, the current position of the AGV and the scheduling of the current task; determine the charging time and charging power according to the charging demand of the AGV and the charging speed of the charging site; dynamically adjust the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV's task.

[0217] In one embodiment, when the processor executes the program to implement the step of dynamically adjusting the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV task, the processor specifically implements the following steps:

[0218] Optimization goals are set based on the charging equipment capacity and availability of the charging station and the urgency of the AGV's mission, and the AGV charging plan is dynamically adjusted through the optimization algorithm.

[0219] In one embodiment, when the processor executes the program to implement the step of determining the charging time and charging power according to the AGV charging demand and the charging speed of the charging station, the processor specifically implements the following steps:

[0220] The total charging time and charging power are determined according to the AGV charging requirements and the charging speed of the charging station, and a strategy of multiple short-term charging is adopted to divide the total charging time into segments according to the task intervals to obtain the charging time and charging power.

[0221] In one embodiment, after executing the program to implement the step of determining the AGV charging plan according to the prediction result, the processor further implements the following steps:

[0222] The AGV charging plan is sent to the AGV, and the real-time current during the charging process of the AGV is monitored. When the real-time current exceeds the maximum current threshold, the charging of the AGV is stopped.

[0223] The storage medium may be a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which is a storage medium readable by an electronic device and can store program codes.

[0224] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0225] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0226] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the system of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0227] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling an electronic device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0228] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An AGV intelligent charging method, characterized in that: include: During the operation of the AGV, the power, voltage, current, AGV position, and AGV motion status of the AGV battery are obtained to obtain operation data; Obtaining task requirements, wherein the task requirements include task type, task urgency, and task path length; Inputting the operation data and the task requirements into a power consumption prediction model to predict power consumption to obtain a prediction result; Determine an AGV charging plan based on the prediction results; Among them, the power consumption prediction model is obtained by training a deep learning network using the historical operation data of AGV, historical task requirements and corresponding power consumption data as a sample set.

2. The AGV intelligent charging method according to claim 1, characterized in that: The power consumption prediction model is obtained by training a deep learning network using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set, and includes: Obtain the historical operation data, historical task requirements and corresponding power consumption data of AGV; Performing data cleaning and normalization processing on the historical operation data of the AGV to obtain a preprocessing result; Analyzing and extracting key factors affecting power consumption from the preprocessing results to obtain extraction results; Build deep learning networks; The extraction results, historical task requirements and corresponding power consumption data are used as a sample set to train the deep learning network to obtain a power consumption prediction model.

3. The AGV intelligent charging method according to claim 1, characterized in that: Determining the AGV charging plan according to the prediction result includes: Get the actual power consumption of AGV; An AGV charging plan is dynamically generated based on the prediction results and the actual power consumption of the AGV.

4. The AGV intelligent charging method according to claim 3, characterized in that: The AGV charging plan includes charging opportunity, charging site and charging time.

5. The AGV intelligent charging method according to claim 4, characterized in that: The dynamically generating an AGV charging plan according to the prediction result and the actual power consumption of the AGV includes: Compare the prediction result with the actual power consumption of the AGV to determine the charging timing and the charging demand of the AGV; Determine the charging site based on the charging site, the current location of the AGV, and the scheduling of the current task; Determine the charging time and charging capacity based on the AGV charging requirements and the charging speed of the charging station; Dynamically adjust the AGV charging plan based on the charging equipment capacity and availability of the charging site and the urgency of the AGV's mission.

6. The AGV intelligent charging method according to claim 5, characterized in that: The method of dynamically adjusting the AGV charging plan according to the charging equipment capacity and availability of the charging site and the urgency of the AGV task includes: Optimization goals are set based on the charging equipment capacity and availability of the charging station and the urgency of the AGV's mission, and the AGV charging plan is dynamically adjusted through the optimization algorithm.

7. The AGV intelligent charging method according to claim 6, characterized in that: Determining the charging time and charging power according to the AGV charging demand and the charging speed of the charging station includes: The total charging time and charging power are determined according to the AGV charging requirements and the charging speed of the charging station, and a strategy of multiple short-term charging is adopted to divide the total charging time into segments according to the task intervals to obtain the charging time and charging power.

8. The AGV intelligent charging method according to claim 1, characterized in that: After determining the AGV charging plan according to the prediction result, the method further includes: The AGV charging plan is sent to the AGV, and the real-time current during the charging process of the AGV is monitored. When the real-time current exceeds the maximum current threshold, the charging of the AGV is stopped.

9. An AGV intelligent charging system, characterized in that: include: The operation data acquisition unit is used to obtain the power, voltage, current, AGV position, and motion state of the AGV battery during the operation of the AGV to obtain the operation data; A task requirement acquisition unit, used to acquire task requirements, wherein the task requirements include task type, task urgency, and task path length; A prediction unit, used for inputting the operation data and the task requirements into a power consumption prediction model to predict the power consumption and obtain a prediction result; A plan determination unit is used to determine the AGV charging plan according to the prediction result.

10. The AGV intelligent charging system according to claim 9, characterized in that: Also includes: The model generation unit is used to train the deep learning network by using the historical operation data, historical task requirements and corresponding power consumption data of the AGV as a sample set to obtain a power consumption prediction model.

Images