Fire balloon LED display screen energy management method based on artificial intelligence optimization

Abstract

The invention discloses an artificial intelligence optimized hot-air balloon LED display screen energy management method, and relates to the technical field of energy management. Comprising the steps of collecting energy consumption data and storing the data as historical data; training an energy consumption prediction model based on machine learning on the basis of historical data, collecting energy consumption data in real time, inputting the energy consumption data into the energy consumption prediction model, predicting energy consumption demands in real time, intelligently dispatching battery use and charging strategies, preferentially supplying power to key display contents, and reasonably arranging power consumption; in the flying suspension and lifting process, an intelligent energy recovery mechanism is activated, kinetic energy is recovered and converted into electric energy, and the electric energy is stored in an auxiliary battery pack; and the generated electric power and energy consumption prediction data are synthesized, the electric energy distribution priority is dynamically adjusted, and it is ensured that the LED display screen can obtain the needed electric power. According to the method, the defects in the aspects of energy consumption prediction and resource scheduling in the prior art are effectively overcome.

Description

Technical Field

[0001] The invention relates to the technical field of energy management, and in particular to an artificial intelligence optimized hot air balloon LED display energy management method. Background Art

[0002] With the rapid development of intelligent technology, the requirements for energy management in the aviation field have become increasingly stringent, especially in light aircraft such as hot air balloons, where efficient use and management of energy have become key factors in improving flight safety and operational efficiency. In recent years, energy management technology has gradually developed in the direction of intelligence and automation, among which artificial intelligence (AI) and machine learning (ML) have made significant progress in the application of energy consumption prediction and management.

[0003] However, existing energy management technologies still have many shortcomings in practical applications. First, traditional energy consumption prediction models often rely on static data or simple linear regression methods, and lack the ability to accurately capture changes in energy demand under complex flight conditions. This lack of flexibility in prediction results in the inability to effectively support the power supply needs of the LED display at critical moments, affecting the normal operation of the aircraft. Secondly, current energy scheduling strategies are mostly based on manual adjustments, lacking an intelligent automatic adjustment mechanism, and are unable to respond quickly to real-time changes in power and energy consumption needs. Therefore, when the battery is low, the system may not be able to prioritize the power supply of key display content, increasing flight safety risks. Summary of the invention

[0004] In view of the problems existing in the above background technology, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to achieve accurate prediction and management of energy demand under flight conditions and activity states.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an artificial intelligence optimized hot air balloon LED display energy management method, which includes collecting energy consumption data in multiple historical flight missions and storing them as historical data; training a machine learning-based energy consumption prediction model based on the historical data to predict energy requirements under different flight conditions and activity states; in the flight mission, collecting energy consumption data in real time and inputting it into the energy consumption prediction model to predict energy consumption requirements in real time; based on the real-time predicted energy consumption requirements, intelligently scheduling battery usage and charging strategies, giving priority to powering key display content, and reasonably arranging power consumption; during the suspension and lifting process of the flight, activating the intelligent energy recovery mechanism, recovering kinetic energy and converting it into electrical energy, and storing it in an auxiliary battery pack; comprehensively generating power and energy consumption prediction data, dynamically adjusting the power allocation priority, and ensuring that the LED display can obtain the required power.

[0008] As a preferred solution of the artificial intelligence optimized hot air balloon LED display energy management method described in the present invention, the collected energy consumption data includes flight altitude, ambient light intensity and passenger activity status.

[0009] As a preferred solution of the energy management method of the hot air balloon LED display optimized by artificial intelligence of the present invention, the establishment of the energy consumption prediction model includes the following steps: collecting the flight altitude, ambient light intensity and passenger activity status data, generating a feature data set, and dividing the data according to different scenes to generate a feature combination X={h,l,a}, where h represents the flight altitude, l represents the light intensity, and a represents the passenger activity status; selecting the light intensity and flight altitude with priority learning features as additional inputs as the input layer, and considering the passenger activity status at the same time, designing the energy consumption prediction model:

[0010] E=α0+α1h+α2l+α3a+α4h 2 +α5l 2 +α6a 2 +α7(h×l)+α8(h×a)

[0011] +α9(l×a)+∈

[0012] Among them, α0 is a constant term, α1, α2, α3 are linear term coefficients, which respectively represent the direct effects of flight altitude, light intensity, and activity status; α4, α5, α6 are quadratic term coefficients, which are used to characterize the nonlinear effects of each variable; α7, α8, α9 are interaction term coefficients, which respectively represent the mutual influence between flight altitude and light intensity, flight altitude and activity status, and light intensity and activity status, and ∈ is a random error term. After the energy consumption prediction model is established, the remaining feature data sets are used to batch train the energy consumption prediction model. By gradually associating the flight altitude, ambient light intensity, passenger activity status, and actual energy consumption E under different conditions, the energy consumption prediction model is trained. act , update the energy consumption prediction model parameters.

[0013] As a preferred solution of the energy management method of the hot air balloon LED display optimized by artificial intelligence of the present invention, wherein: the batch training of the energy consumption prediction model using the remaining feature data set includes: calculating the loss function Loss in the batch training, calibrating the predicted energy consumption value and the actual energy consumption value E by minimizing the Loss function act After each batch of training is completed, each parameter αj is adaptively adjusted, and the weight update rule is:

[0014]

[0015] Among them, αj (t+1) and αj (t) are the parameter weights at the tth and t+1th iterations respectively, η is the learning rate, It is the gradient of the loss function with respect to the parameter αj, which is used to determine the update direction of the parameter.

[0016] As a preferred solution of the energy management method of the hot air balloon LED display optimized by artificial intelligence of the present invention, wherein: based on the real-time energy consumption demand, the intelligent scheduling battery use and charging strategy includes the following steps: based on the real-time energy consumption demand prediction data E real-time (t), analyze the power demand priority of the current flight phase, set the key display content of the LED display as the priority power supply object, and divide the power demand into high-priority power supply demand for key display content and low-priority power supply demand for non-key display content according to the flight phase and activity status; intelligently schedule the power output of the battery pack, give priority to providing stable power output for key display content, and dynamically allocate power for non-key display content; monitor the real-time power of the battery pack B(t), and according to the current power and the remaining time T of the flight mission re Dynamically adjust output power; in low-power situations, start auxiliary battery pack B aux , arrange charging strategy.

[0017] As a preferred solution of the energy management method of the hot air balloon LED display screen optimized by artificial intelligence of the present invention, the power output of the intelligent scheduling battery pack includes:

[0018] By adjusting the battery output power E output (t), meeting the real-time predicted energy consumption demand E real-time (t):

[0019]

[0020] Among them, α is the dynamic allocation factor, which is adjusted according to the real-time power situation.

[0021] As a preferred solution of the energy management method of the hot air balloon LED display optimized by artificial intelligence of the present invention, wherein: the current power and the remaining time T of the flight mission are re The formula for dynamically adjusting output power is expressed as:

[0022] E output (t) = min(B(t) / T re , E real-time (t))

[0023] Wherein, B(t) is the real-time power of the battery pack.

[0024] As a preferred solution of the energy management method of the hot air balloon LED display optimized by artificial intelligence of the present invention, the activation of the intelligent energy recovery mechanism to recover kinetic energy and convert it into electrical energy includes the following steps: during the suspension and lifting phases of the hot air balloon flight, the kinetic energy K(t) of the aircraft is collected by the installed kinetic energy recovery device, and the collected kinetic energy is converted into electrical energy E reco (t); generated electrical energy E reco (t)Stored in auxiliary battery pack B aux At this time, the total power of the auxiliary battery pack is updated as:

[0025] B aux (t)+1)=B aux (t)+E reco (t)×(1-γ×B aux (t) β )

[0026] Among them, B aux (t+1 ) is the updated total capacity of the auxiliary battery pack, and γ and β are the nonlinear adjustment parameters of charging control.

[0027] In a second aspect, an embodiment of the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the artificial intelligence optimized hot air balloon LED display energy management method as described in the first aspect of the present invention are implemented.

[0028] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the artificial intelligence optimized hot air balloon LED display energy management method as described in the first aspect of the present invention are implemented.

[0029] The beneficial effects of the present invention are as follows: the present invention realizes accurate prediction of energy demand under flight conditions and activity states through systematic collection and storage of energy consumption data in historical flight missions, combined with an energy consumption prediction model based on machine learning. During the flight, the energy consumption data collected in real time will be used as input to drive the energy consumption prediction model to make dynamic adjustments, ensure the intelligent scheduling of battery use and charging strategies, give priority to powering key display content, and reasonably arrange power consumption. In addition, during the suspension and lifting stages of the flight, by activating the intelligent energy recovery mechanism, kinetic energy is converted into electrical energy and stored in the auxiliary battery pack to cope with subsequent high energy consumption needs. The present invention effectively solves the shortcomings of the prior art in energy consumption prediction and resource scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 Flowchart of the energy management method for hot air balloon LED display optimized for artificial intelligence.

[0032] Figure 2 FIG. 1 is a schematic diagram of the structure of a terminal in the first embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0035] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0036] Example 1

[0037] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides an artificial intelligence optimized hot air balloon LED display energy management method, comprising:

[0038] S1: Collect energy consumption data (such as flight altitude, light intensity, and passenger activity status) in multiple historical flight missions and store them as historical data.

[0039] First, data is collected for multiple hot air balloon flight missions, and installed sensors are used to monitor factors such as the hot air balloon's flight altitude, ambient light intensity, and passenger activity status in real time.

[0040] For each flight mission, the energy consumption data of the LED display screen on the hot air balloon is recorded, and this energy consumption information is associated and stored with the corresponding flight conditions and passenger activity status, gradually establishing a historical database containing a large amount of energy consumption data.

[0041] During the data collection process, external factors such as flight altitude and light intensity will directly affect the brightness requirements and power consumption of the hot air balloon LED display. For example, under conditions of high light intensity at high altitudes, the LED display may need to adjust the brightness to ensure the display effect, thereby affecting the overall energy consumption.

[0042] Passenger activity also affects the use of equipment in the balloon, so recording data on such activity can help predict energy requirements under different conditions.

[0043] Through long-term data accumulation, an energy consumption data set covering various flight conditions and operating scenarios is gradually formed.

[0044] S2: Train an energy consumption prediction model based on historical data to predict energy demand under different flight conditions and activity states.

[0045] S2.1: Generate a feature data set based on the historical data of flight altitude and ambient light intensity in step S1, and consider the influence of passenger activity status. In order to meet the input requirements of the nonlinear prediction model, the feature data set should focus on important parameters with priority learning features, such as flight altitude and light intensity. Divide the data for different scenarios, such as flight altitude interval, time period (daytime, nighttime, sunrise / sunset), and passenger activity status (active, stationary, dining, etc.), and generate feature combinations X= based on these scenarios. { h,l,a } , where h represents the flight altitude, l represents the light intensity, and a represents the passenger activity status.

[0046] S2.2: Select important parameters with priority learning features (such as light intensity and flight altitude) as additional inputs as the input layer, and consider the activity state a of the passengers to design an energy consumption prediction model. Through the supervised learning method, generate the initial structure of the energy consumption prediction model of the LED display screen in different states during the flight.

[0047] Specifically, the nonlinear prediction model of the energy consumption E of the LED display is defined as:

[0048] E=α0+α1h+α2l+α3a+α4h 2 +α5l 2 +α6a 2 +α7(h×l)+α8(h×a)

[0049] +α9(l×a)+∈

[0050] Among them, α0 is a constant term, α1, α2, α3 are linear term coefficients, representing the direct effects of flight altitude, light intensity, and activity status, respectively; α4, α5, α6 are quadratic term coefficients, used to characterize the nonlinear effects of each variable; α7, α8, α9 are interaction term coefficients, representing the mutual influence between flight altitude and light intensity, flight altitude and activity status, and light intensity and activity status, respectively, and ∈ is a random error term.

[0051] The initial structure uses a portion of historical data in the feature data set for training, optimizes the model weights, and ensures the accuracy of energy consumption prediction.

[0052] S2.3: Based on the initial training of the energy consumption prediction model, the remaining feature data sets are used to batch train the model by gradually associating the flight altitude h, ambient light intensity l, passenger activity status a and actual energy consumption E under different conditions. act , update the model parameters to calibrate the prediction results. The specific operations are as follows:

[0053] Calculate the loss function Loss in batch training. By minimizing the Loss function, not only the error between the predicted energy consumption value and the actual energy consumption value is calibrated, but also the complexity of the model is balanced through the regularization term;

[0054] In batch training, the model parameter weights are automatically adjusted by analyzing the performance of different batches of data:

[0055] After each batch of training is completed, each parameter αj is adaptively adjusted to adapt to the actual conditions of flight altitude, light intensity and activity state, where the weight update rule is:

[0056]

[0057] Among them, αj (t+1) and αj (t) are the parameter weights at the tth and t+1th iterations respectively, η is the learning rate, is the gradient of the loss function with respect to the parameter αj, which is used to determine the update direction of the parameter.

[0058] In addition, during the training process, the weights of features that have a significant impact on energy consumption (such as flight altitude or light intensity) are automatically amplified. For example, a threshold is set to determine the degree of impact of each feature on energy consumption. If the gradient of the loss function with respect to the parameter αj is greater than the set threshold, the corresponding parameter weight will be amplified.

[0059] After completing batch training and adaptive weight adjustment, the final energy consumption prediction model has the ability to accurately predict energy consumption under different flight altitudes, light intensities and passenger activity states.

[0060] S3: During the flight mission, energy consumption data is collected in real time and input into the energy consumption prediction model to make real-time predictions on energy consumption demand, providing accurate energy demand predictions for each flight stage and different passenger activity status.

[0061] Specifically, key data such as the current flight altitude, light intensity, and passenger activity status are continuously acquired, and the data is converted into the input feature format of the energy consumption prediction model to ensure the stability and accuracy of the collected data.

[0062] The real-time collected data such as flight altitude, light intensity and passenger activity status are input into the energy consumption prediction model trained in S2 to generate real-time energy consumption prediction data E according to the current flight conditions and passenger activity status. real-time (t).

[0063] S4: Based on real-time energy consumption needs, intelligently schedule battery usage and charging strategies, prioritize power supply for key display content, and reasonably arrange power consumption to extend battery life.

[0064] S4.1: Based on the real-time energy demand forecast data of step S3, analyze the power demand priority of the current flight phase, set the key display content of the LED display as the priority power supply object, and divide the power demand into high-priority power supply demand for key display content and low-priority power supply demand for non-key display content according to the flight phase and activity status.

[0065] S4.2: Intelligently schedule the battery pack's power output, giving priority to providing stable power output for key display content, while dynamically allocating power for non-key display content. By adjusting the battery pack output power E output (t), meeting the real-time predicted energy consumption demand E real-time (t):

[0066]

[0067] Among them, α is the dynamic allocation factor, which is adjusted according to the real-time power situation.

[0068] S4.3: Monitor the real-time power of the battery pack B(t), and calculate the current power and the remaining time of the flight mission T re Dynamically adjust output power E output (t), ensuring that energy allocation can support the full range of flight mission requirements, the formula is:

[0069] E output (t) = min(B(t) / T re , E real-time (t))

[0070] In order to dynamically adjust battery output and balance power consumption and battery life requirements.

[0071] S4.4: In case of low battery, start auxiliary battery pack B aux , reasonably arrange the charging strategy, suspend or reduce the power supply of non-critical display content, and give priority to the use of recycled electricity to supplement the power supply of LED display screens to improve battery utilization efficiency.

[0072] In addition, when the battery is low, the auxiliary battery pack is started and the power supply to non-critical display content is suspended. At this time, the power obtained through energy recovery should be evaluated at the same time so that the power supply to non-critical display content can be restored at an appropriate time.

[0073] S5: During the suspension and lifting process of flight, the intelligent energy recovery mechanism is activated to recover kinetic energy and convert it into electrical energy, which is stored in the auxiliary battery pack B aux In order to provide additional power for the LED display during peak energy consumption periods.

[0074] Preferably, during the suspension and lifting phases of the hot air balloon flight, the kinetic energy K(t) of the aircraft is collected by the installed kinetic energy recovery device, and the collected kinetic energy is converted into electrical energy E reco (t);

[0075] The generated electrical energy E reco (t)Stored in auxiliary battery pack B aux In order to support the LED display screen in the subsequent high energy consumption period, the total power of the auxiliary battery pack is updated to:

[0076] B aux (t+1)=B aux (t)+E reco (t)×(1-γ×B aux (t) β )

[0077] Among them, B aux (t+1) is the updated total power of the auxiliary battery pack, and γ and β are nonlinear adjustment parameters of charging control.

[0078] S6: Based on the power and consumption forecast data generated by comprehensive energy recovery, the power distribution priority is dynamically adjusted to ensure that the LED display can obtain the required power.

[0079] The S4 uses real-time energy demand forecasts to schedule battery usage and prioritize powering key display content, while the S6 builds on this by further integrating the power generated by energy recovery and dynamically adjusting power allocation priorities.

[0080] Specifically, when dynamically adjusting the power distribution priority, the amount of energy recovered and the real-time energy consumption demand are comprehensively considered to ensure that the LED display can obtain a stable power supply at any stage of flight.

[0081] First, according to the electric energy E recovered in step S5 reco (t) and the real-time energy consumption prediction data E in step S3 real-time (t) Generate the power distribution table for the current flight phase:

[0082]

[0083] Among them, f(E reco (t)) is the nonlinear gain function of recovered electric energy, which can be set as f(x) = ln(1 + x), k is the energy consumption adjustment coefficient, P c The minimum power threshold is set so that the power allocation priority can not only reflect the marginal contribution of the current recovered energy, but also dynamically respond to changes in actual demand.

[0084] The system should monitor the status and power level of the battery pack in real time and establish a feedback mechanism to ensure that the power distribution strategy can be adjusted in time to optimize the power supply efficiency when energy consumption demand changes or energy recovery efficiency fluctuates.

[0085] This embodiment also provides a computer device, which is suitable for the case of an artificial intelligence optimized hot air balloon LED display energy management method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the artificial intelligence optimized hot air balloon LED display energy management method proposed in the above embodiment.

[0086] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0087] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the hot air balloon LED display energy management method implementing artificial intelligence optimization as proposed in the above embodiment is implemented.

[0088] In summary, the present invention realizes accurate prediction of energy demand under flight conditions and activity states through the systematic collection and storage of energy consumption data in historical flight missions, combined with an energy consumption prediction model based on machine learning. During the flight, the energy consumption data collected in real time will be used as input to drive the energy consumption prediction model to make dynamic adjustments, ensure the intelligent scheduling of battery use and charging strategies, give priority to powering key display content, and reasonably arrange power consumption. In addition, during the suspension and lifting stages of the flight, by activating the intelligent energy recovery mechanism, kinetic energy is converted into electrical energy and stored in the auxiliary battery pack to cope with subsequent high energy consumption needs. The present invention effectively solves the shortcomings of the prior art in energy consumption prediction and resource scheduling.

[0089] Example 2

[0090] Referring to Table 1 and Table 2, the second embodiment of the present invention provides an artificial intelligence optimized hot air balloon LED display energy management method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0091] In order to verify the energy consumption prediction accuracy and energy allocation efficiency of the "artificial intelligence optimized hot air balloon LED display energy management method" described in the present invention in different flight missions, multiple flight experiments were carried out, and the flight altitude, ambient light intensity, passenger activity status and actual energy consumption data of the LED display were recorded in detail for each mission.

[0092] Through this process, a historical energy consumption database covering various flight conditions and operating scenarios was constructed. The specific experimental steps are as follows:

[0093] The flight missions were carried out under different meteorological conditions (sunny, cloudy, and night), and environmental variables such as flight altitude, light intensity, and passenger activity status were recorded in real time through sensors. At the same time, the real-time energy consumption of the LED display was monitored and the data was stored separately according to the context of each flight mission.

[0094] According to different combinations of flight altitude, light intensity and passenger activity status, historical data are classified according to feature variables. For example, flight altitude is divided into "low altitude, medium altitude, high altitude", light intensity is divided into "weak light, medium light, strong light", and passenger activity status is divided into "active, stationary".

[0095] These data features are input into the energy consumption prediction model, the weight parameters of the model are gradually optimized, and finally the energy consumption prediction model of the LED display screen under different conditions is completed.

[0096] During the flight mission, the energy consumption data of the LED display screen is collected in real time and input into the prediction model. The energy consumption prediction model analyzes the real-time collected flight conditions (flight altitude, light intensity, passenger activity status) and predicts the energy demand at each stage in real time. At the same time, in order to ensure the display effect, the priority power demand of key and non-key display content is intelligently allocated.

[0097] According to the real-time predicted energy demand, the battery pack output is intelligently scheduled to provide stable power for key display content when the power demand is high priority, and to regulate the power of non-key display content when the power demand is low priority. In addition, through the kinetic energy recovery equipment, kinetic energy is recovered during the suspension and lifting stages, and the generated electricity is stored in the auxiliary battery pack for emergency use during peak energy consumption periods.

[0098] After the experiment, the collected data was organized into a table for further analysis of the energy consumption characteristics of the LED display screen under different conditions and the effect of the present invention in energy saving management. The following is a record of the data collected in some experiments:

[0099] Table 1 Energy consumption data of historical flight missions

[0100]

[0101] Table 2 Comparison of predicted and actual energy consumption

[0102]

[0103]

[0104] From the above experimental data analysis, it can be seen that the energy management method optimized by artificial intelligence in the present invention has achieved a high level of prediction accuracy for the energy consumption of the hot air balloon LED display screen under different flight altitudes, light intensities and passenger activity states, with an average error of less than 2%. This shows that the designed energy consumption prediction model has a stable and accurate prediction effect in various flight missions.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An artificial intelligence optimized hot air balloon LED display energy management method, characterized by: include, Collect energy consumption data in multiple historical flight missions and store them as historical data; Training a machine learning-based energy consumption prediction model based on the historical data to predict energy demand under different flight conditions and activity states; During the flight mission, energy consumption data is collected in real time and input into the energy consumption prediction model to make a real-time prediction of energy consumption demand; Based on the real-time predicted energy consumption demand, intelligently schedule battery usage and charging strategies, prioritize power supply for key display content, and reasonably arrange power consumption; During the suspension and lifting process of flight, the intelligent energy recovery mechanism is activated to recover kinetic energy and convert it into electrical energy, which is stored in the auxiliary battery pack; Comprehensively generate power and energy consumption forecast data to dynamically adjust power distribution priorities to ensure that the LED display can obtain the required power.

2. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 1, characterized in that: The collected energy consumption data includes flight altitude, ambient light intensity and passenger activity status.

3. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 2, characterized in that: The establishment of the energy consumption prediction model includes the following steps: Collect the flight altitude, ambient light intensity and passenger activity status data to generate a feature data set, and divide the data into different scenes to generate a feature combination X={h,l,a}, where h represents the flight altitude, l represents the light intensity, and a represents the passenger activity status; Selecting light intensity and flight altitude with priority learning features as additional inputs as the input layer, and considering the activity status of passengers, design an energy consumption prediction model: E=α0+α1h+α2l+α3a+α4h 2 +α5l 2 +α6a 2 +α7(h×l)+α8(h×a) +α9(l×a)+∈ Among them, α0 is a constant term, α1, α2, α3 are linear term coefficients, representing the direct effects of flight altitude, light intensity, and activity state, respectively; α4, α5, α6 are quadratic term coefficients, used to characterize the nonlinear effects of each variable; α7, α8, α9 are interaction term coefficients, representing the mutual effects between flight altitude and light intensity, flight altitude and activity state, and light intensity and activity state, respectively; ∈ is a random error term; After the energy consumption prediction model is established, the remaining feature data sets are used to batch train the energy consumption prediction model. By gradually associating the flight altitude, ambient light intensity, passenger activity status, and actual energy consumption E under different conditions, the energy consumption prediction model is trained. act , update the energy consumption prediction model parameters.

4. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 3, characterized in that: The adopting the remaining feature data sets to perform batch training on the energy consumption prediction model comprises: Calculate the loss function Loss in batch training, and calibrate the predicted energy consumption value and the actual energy consumption value E by minimizing the Loss function act The error of After each batch of training is completed, each parameter αj is adaptively adjusted, and the weight update rule is: Among them, αj (t+1) and αj (t) are the parameter weights at the tth and t+1th iterations respectively, η is the learning rate, is the gradient of the loss function with respect to the parameter αj.

5. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 4, characterized in that: Based on real-time energy demand, intelligent scheduling of battery usage and charging strategy includes the following steps: Based on real-time energy demand forecast data E real-time (t) Analyze the power demand priority of the current flight phase, set the key display content of the LED display screen as the priority power supply object, and divide the power demand into high-priority power supply demand of key display content and low-priority power supply demand of non-key display content according to the flight phase and activity status; Intelligently schedule the power output of the battery pack, giving priority to providing stable power output for key display content, while dynamically allocating power for non-key display content; Monitor the real-time battery power B(t) of the battery pack and calculate the remaining time T of the flight mission according to the current power re Dynamically adjust output power; In case of low battery, start auxiliary battery pack B aux , arrange charging strategy.

6. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 5, characterized in that: The power output of the intelligent scheduling battery pack includes: By adjusting the battery output power E output (t), meeting the real-time predicted energy consumption demand E real-time (t): Among them, α is the dynamic allocation factor, which is adjusted according to the real-time power situation.

7. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 6, characterized in that: According to the current power and the remaining time T of the flight mission re The formula for dynamically adjusting output power is expressed as: E output (t)=min(B(t) / T re ,E real-time (t)) Wherein, B(t) is the real-time power of the battery pack.

8. The method for energy management of hot air balloon LED display screen optimized by artificial intelligence as claimed in claim 6, characterized in that: Activating the intelligent energy recovery mechanism to recover kinetic energy and convert it into electrical energy comprises the following steps: During the suspension and lifting phases of a hot air balloon flight, the kinetic energy K(t) of the aircraft is collected through the installed kinetic energy recovery equipment, and the collected kinetic energy is converted into electrical energy E reco (t); The generated electrical energy E reco (t)Stored in auxiliary battery pack B aux At this time, the total power of the auxiliary battery pack is updated as: B aux (t+1)=B aux (t)+E reco (t)×(1-γ×B aux (t) β ) Among them, B aux (t+1) is the updated total power of the auxiliary battery pack, and γ and β are nonlinear adjustment parameters of charging control.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the artificial intelligence optimized hot air balloon LED display energy management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the artificial intelligence optimized hot air balloon LED display energy management method according to any one of claims 1 to 7 are implemented.

Images