A method and device for aircraft electrical load statistics and power supply capacity analysis

Abstract

The present invention discloses a method and apparatus for aircraft electrical load statistics and power capacity analysis, relating to the technical field of aircraft electrical load management. The method comprises: utilizing a differential method to analyze the variation in electrical load power at each time step, combining load coupling effects and power factor synergy effects, and optimizing power capacity requirements through a multi-objective optimization algorithm; utilizing a trend analysis method and an error feedback mechanism to identify electrical load power demand errors and trends in electrical load power demand fluctuations, combining the optimized power capacity requirements with a load matching algorithm for analysis, and obtaining the required power capacity for aircraft operation. The present invention effectively improves aircraft operating efficiency and safety by combining a long short-term memory network model, a dynamic time warping algorithm, and a spectrum analysis method, and achieving precise power capacity allocation through a load matching algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft electrical load management, and in particular to a method and device for aircraft electrical load statistics and power supply capacity analysis. Background Art

[0002] As a vital component of modern aircraft, the design and performance of aircraft electrical systems are directly linked to flight safety and operational efficiency. With the development of the aviation industry, aircraft electrical loads have become increasingly complex, expanding from traditional lighting and communications equipment to include high-tech equipment such as flight control computers, navigation systems, and radar. This not only increases the burden on power systems but also places higher demands on power management. In recent years, with advances in power electronics and intelligent control technologies, aircraft electrical systems have also undergone significant innovation. For example, microprocessor-based control systems enable more sophisticated power management and load monitoring; at the same time, the application of distributed power architectures improves system reliability and flexibility.

[0003] However, current aircraft electrical load statistics and power capacity analysis methods have some shortcomings. On the one hand, traditional methods often rely on static load models, which make it difficult to accurately reflect the dynamically changing load conditions in actual operation. This static model cannot fully consider the changing characteristics of load power demand in different flight phases, especially when facing non-periodic or sudden load changes, which may lead to inaccurate power capacity planning, thereby affecting the safety and economy of flight operations. On the other hand, existing analysis methods rarely consider the coupling effects and frequency response characteristics between loads. When multiple loads act simultaneously, the mutual influence between different electrical components may lead to increased overall energy consumption or reduced power efficiency, and these factors are crucial to ensuring the stable operation of the aircraft electrical system. Summary of the Invention

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

[0005] Therefore, the present invention provides a method and apparatus for aircraft electrical load statistics and power capacity analysis to solve the problem of inaccurate power capacity planning caused by dynamic load changes and coupling effects between loads.

[0006] The plan is as follows:

[0007] In a first aspect, the present invention provides a method for aircraft electrical load statistics and power capacity analysis, which includes: collecting aircraft operation data and preprocessing the aircraft operation data; converting the time series format through a sliding window method, constructing a load power demand prediction model based on a long short-term memory network model, and obtaining an electrical load power demand prediction value; based on the electrical load power demand prediction value, constructing a time series pair using a correlation analysis method, and aligning them using a dynamic time warping algorithm, analyzing the similarity of the time series pairs, obtaining load coupling effects and spectrum information based on the electrical load power demand prediction value using a Fourier transform method, analyzing the power density of the electrical load at different frequencies using a spectrum analysis method, and calculating the power factor synergy effect using a cross-power spectrum analysis method; using a difference method to analyze the change in electrical load power at each time step, combining the load coupling effect and the power factor synergy effect, and optimizing the power capacity demand through a multi-objective optimization algorithm; using a trend analysis method and an error feedback mechanism to identify the electrical load power demand error and the trend of electrical load power demand fluctuation, combined with the optimized power capacity demand, analyzing through a load matching algorithm, and obtaining the required power capacity during aircraft operation.

[0008] As a preferred embodiment of the method for aircraft electrical load statistics and power supply capacity analysis of the present invention, the aircraft operation data includes flight control data, environmental sensor data, and electrical load data;

[0009] The pre-processing of the aircraft operation data includes standardization, removal of noise data and removal of abnormal values.

[0010] As a preferred embodiment of the method for aircraft electrical load statistics and power capacity analysis of the present invention, the steps of converting the time series format using a sliding window method and constructing a load power demand prediction model based on a long short-term memory network model are as follows:

[0011] The pre-processed historical aircraft operation data are converted into time series format using a sliding window method;

[0012] The model is based on the long short-term memory network model;

[0013] The input layer receives pre-processed historical aircraft operation data converted into time series format;

[0014] The LSTM layer uses memory cells and gate mechanisms to selectively remember and forget information, capturing long-term dependencies in time series.

[0015] The fully connected layer extracts features and reduces the dimension based on the output of the LSTM layer and maps it to the output layer;

[0016] Output the prediction results through the output layer;

[0017] Finally, a load power demand prediction model is constructed.

[0018] As a preferred embodiment of the method for aircraft electrical load statistics and power capacity analysis of the present invention, the steps of obtaining the predicted value of electrical load power demand are as follows:

[0019] Based on the pre-processed aircraft operation data converted into a time series format, the memory unit and gate mechanism in the LSTM model are used to learn the time series data to capture the temporal variation pattern of the electrical load power during aircraft operation.

[0020] Based on the temporal variation of electrical load power during aircraft operation, combined with the weighted coefficients and historical electrical load power values ​​at historical moments, the electrical load power demand is predicted. The expression is:

[0021]

[0022] Among them, P t is the predicted value of the electrical load power demand at time step t, f(i) is the weighting coefficient at the i-th historical moment, and y t,i is the historical electrical load power value at the i-th historical moment from time step t, W is the output weight matrix of the LSTM model, h t is the hidden state of the LSTM model at time step t, b is the bias term, t is the index variable of the time step, i is the index variable of the historical moment, and N is the number of historical moments.

[0023] As a preferred embodiment of the method for aircraft electrical load statistics and power capacity analysis of the present invention, the method comprises: constructing a time series pair based on the predicted value of electrical load power demand using a correlation analysis method, aligning the time series pair using a dynamic time warping algorithm, analyzing the similarity of the time series pair, obtaining load coupling effects, and obtaining spectrum information based on the predicted value of electrical load power demand using a Fourier transform method, analyzing the power density of the electrical load at different frequencies using a spectrum analysis method, and calculating the power factor synergy effect using a cross-power spectrum analysis method. The specific steps are as follows:

[0024] The actual value of electrical load power demand is obtained by using electrical load power data measured and recorded in real time by aircraft electrical load sensors and using power monitoring and data recording methods;

[0025] Based on the actual value of electrical load power demand and the predicted value of electrical load power demand, the two time series are selected through the correlation analysis method to construct a time series pair;

[0026] Based on the time series pair, the two time series are aligned using the dynamic time warping algorithm to analyze the similarity between the two time series. The expression is:

[0027]

[0028] Among them, D(P t ,Q t ) is the aligned time series pair (P t ,Q t ), Q t is the actual value of the electrical load power demand, T is the number of time steps;

[0029] Based on the aligned time series pairs (P t ,Q t ) and quantify the coupling effect between loads through the mutual information method to obtain the load coupling effect;

[0030] The Fourier transform method is used to perform Fourier transform on the time series of electrical load power demand forecast values ​​to obtain spectrum information;

[0031] By using the spectrum analysis method, the main frequency components in the spectrum information are analyzed to obtain the power density of the electrical load at different frequencies;

[0032] Based on the power density of electrical loads at different frequencies, the power factor synergy effect is calculated using the cross-power spectrum analysis method. The expression is:

[0033]

[0034] Among them, C xy (ω) is the power factor synergy effect of signal x and signal y at frequency ω, S xy (ω) is the cross power density of signal x and signal y at frequency ω, S x (ω) is the autopower density of signal x at frequency ω, S y (ω) is the autopower density of signal y at frequency ω, where ω is the frequency component of the signal.

[0035] As a preferred embodiment of the method for aircraft electrical load statistics and power capacity analysis of the present invention, the method utilizes a differential method to analyze the variation in electrical load power at each time step, combines load coupling effects and power factor synergy effects, and optimizes power capacity requirements using a multi-objective optimization algorithm. The specific steps are as follows:

[0036] Based on historical aircraft operation data, statistical analysis methods are used to analyze the average and peak electrical load requirements in each flight phase to obtain power capacity requirements;

[0037] Based on the pre-processed aircraft operation data, the change in electrical load power at each time step is analyzed by the difference method to obtain the change in electrical load power;

[0038] The load coupling effect reflects the relationship between different loads, the power factor synergy effect is used to reveal the interaction of power transmission at different frequencies, and the dynamic fluctuation of load demand is reflected by combining the change in electrical load power. The power capacity demand is optimized through a multi-objective optimization algorithm. The expression is:

[0039]

[0040] Among them, F is the optimized power capacity requirement, G PQ is the load coupling effect between time series P and time series Q, ω max is the maximum frequency, K is the target power factor synergy, ΔP t is the electrical load power variation, α1 is the weight coefficient of the load coupling effect, α2 is the weight coefficient of the power factor synergy effect, and α3 is the weight coefficient of the electrical load power variation.

[0041] As a preferred embodiment of the method for aircraft electrical load statistics and power capacity analysis of the present invention, the method utilizes a trend analysis method and an error feedback mechanism to identify the electrical load power demand error and the electrical load power demand fluctuation trend, combines the optimized power capacity demand with a load matching algorithm for analysis, and obtains the required power capacity during aircraft operation. The specific steps are as follows:

[0042] Formulate an initial power capacity allocation strategy based on the predicted electrical load power demand, load coupling effects, and power factor synergy effects;

[0043] Based on the actual value of the electrical load power demand and the predicted value of the electrical load power demand, the deviation is identified through the error feedback mechanism to obtain the electrical load power demand error;

[0044] By comparing the time series of the predicted values ​​of the electrical load power demand through trend analysis, the trend of fluctuation of the electrical load power demand can be identified;

[0045] Based on the error in the power demand of the electrical load and the trend of the fluctuation of the power demand of the electrical load, the initial allocation strategy of the power capacity is adjusted for fault tolerance;

[0046] Based on the adjusted power capacity allocation strategy, the electrical load demand in each time period is dynamically evaluated through time series analysis combined with flight plans, flight phases, and real-time electrical load data, ultimately obtaining the required power capacity during aircraft operation.

[0047] In the second aspect, the present invention provides a device for aircraft electrical load statistics and power capacity analysis, including: a data collection module, a model construction and prediction module, a load effect analysis module, a power capacity optimization module and a power capacity analysis module; the data collection module is used to collect aircraft operation data and pre-process the aircraft operation data; the model construction and prediction module is used to convert the time series format through a sliding window method, build a load power demand prediction model based on a long short-term memory network model, and obtain the electrical load power demand prediction value; the load effect analysis module is used to build a time series pair based on the electrical load power demand prediction value using a correlation analysis method, and align them through a dynamic time warping algorithm, analyze the similarity of the time series pair, and obtain The load coupling effect and the predicted value of the electrical load power demand are obtained using the Fourier transform method to obtain spectrum information, and the power density of the electrical load at different frequencies is analyzed using the spectrum analysis method, and the power factor synergy effect is calculated using the cross-power spectrum analysis method; the power capacity optimization module is used to use the difference method to analyze the change in the electrical load power at each time step, combine the load coupling effect and the power factor synergy effect, and optimize the power capacity demand through a multi-objective optimization algorithm; the power capacity analysis module is used to use the trend analysis method and error feedback mechanism to identify the electrical load power demand error and the trend of electrical load power demand fluctuation, and combine the optimized power capacity demand with the load matching algorithm for analysis to obtain the required power capacity during aircraft operation.

[0048] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for aircraft electrical load statistics and power supply capacity analysis as described in the first aspect of the present invention is implemented.

[0049] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for aircraft electrical load statistics and power supply capacity analysis as described in the first aspect of the present invention is implemented.

[0050] The present invention offers the following benefits: By combining a long short-term memory network model with a dynamic time warping algorithm and spectrum analysis, it accurately predicts aircraft electrical load power requirements and analyzes load coupling and power factor synergy effects, providing accurate and dynamic input for optimizing power capacity requirements. This approach optimizes power capacity through a multi-objective optimization algorithm and achieves precise power capacity allocation through a load matching algorithm, effectively improving aircraft operational efficiency and safety, ensuring that power configuration can be flexibly adjusted based on actual flight data, and enhancing overall energy utilization and system adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 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 paying any creative work.

[0052] Figure 1 This is a flow chart of the method for aircraft electrical load statistics and power supply capacity analysis in Example 1.

[0053] Figure 2 Schematic diagram of the device for aircraft electrical load statistics and power supply capacity analysis in Example 1. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. 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.

[0056] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0057] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for aircraft electrical load statistics and power supply capacity analysis, comprising the following steps:

[0058] S1. Aircraft operation data includes flight control data, environmental sensor data, and electrical load data.

[0059] S1.1. Preprocessing of aircraft operation data includes standardization, removal of noise data and removal of outliers.

[0060] It should be noted that the aircraft operation data is preprocessed through standardization, noise removal, and outlier removal. The specific process is as follows:

[0061] Normalization: First, for each feature (such as engine speed, fuel flow, etc.), calculate its mean and standard deviation in the entire aircraft operation data set. Then, for each specific data point of the feature, subtract the feature's mean from the original value, and then divide the result by the feature's standard deviation. Through this transformation, the data distribution of each feature will be adjusted to have zero mean and unit standard deviation, thus ensuring that all features are on the same scale;

[0062] Remove noisy data: Use filtering techniques or smoothing algorithms to mitigate the effects of random fluctuations, such as using moving averages or low-pass filters. Statistical methods are also used to identify and correct data points caused by measurement errors or transient disturbances to ensure the accuracy and consistency of the data set.

[0063] Removing outliers: First, define the normal data range. This can be done by calculating the distribution characteristics of aircraft operation data, such as using the interquartile range in a box plot to determine the upper and lower limits. Then, apply statistical tests or machine learning models to detect data points that are outside the normal range. For identified outliers, it is necessary to evaluate whether they actually represent erroneous data. If so, choose an appropriate method to handle them, such as directly deleting them, replacing them with neighboring values, or regressing them to a reasonable numerical range.

[0064] S2. The time series format is converted through the sliding window method, and a load power demand prediction model is constructed based on the long short-term memory network model.

[0065] S2.1. Convert the pre-processed historical aircraft operation data into time series format using the sliding window method.

[0066] It should be noted that a time window of fixed length is first determined. The window will slide sequentially on the historical aircraft operation data according to the set time step. For each position, the data points in the window are collected and used as a time series sample. These samples contain the characteristic values ​​in the continuous time period.

[0067] S2.2, based on the long short-term memory network model;

[0068] The input layer receives pre-processed historical aircraft operation data converted into time series format;

[0069] The LSTM layer uses memory cells and gate mechanisms to selectively remember and forget information, capturing long-term dependencies in time series.

[0070] The fully connected layer extracts features and reduces the dimension based on the output of the LSTM layer and maps it to the output layer;

[0071] Output the prediction results through the output layer;

[0072] Finally, a load power demand prediction model is constructed.

[0073] It should be noted that the reason for building a load power demand prediction model based on the long short-term memory network (LSTM) model is that the LSTM model is particularly good at processing and predicting long-term dependencies in time series data, and can effectively capture the complex patterns of aircraft electrical load changes over time. Through its unique memory unit and gating mechanism, the LSTM model can learn and remember past data features while selectively forgetting irrelevant information. This makes it perform well when processing correlated data with long time intervals, thereby providing more accurate and reliable load power demand predictions, which helps to optimize the configuration and management of aircraft power systems.

[0074] S3. Obtain the predicted value of electrical load power demand.

[0075] S3.1. Based on the preprocessed aircraft operation data converted into a time series format, the time series data is learned through the memory units and gate mechanism in the LSTM model to capture the temporal variation pattern of the electrical load power during aircraft operation.

[0076] It should be noted that, first, the historical load power data within each time window is fed into the LSTM model as an input sequence. The memory unit of the LSTM model can store information and selectively update the state through the input gate. The forget gate determines which information should be discarded, and the output gate controls the information output from the unit state. During the training process, the LSTM model gradually learns the patterns and laws of electrical load power changes over time, including short-term fluctuations and long-term trends. This mechanism can effectively capture the complex time series changes of electrical load power during aircraft operation.

[0077] S3.2. Based on the temporal variation of electrical load power during aircraft operation, combined with the weighting coefficients and historical electrical load power values ​​at historical moments, the electrical load power demand is predicted using the following expression:

[0078]

[0079] Among them, P t is the predicted value of the electrical load power demand at time step t, f(i) is the weighting coefficient at the i-th historical moment, and y t,i is the historical electrical load power value at the i-th historical moment from time step t, W is the output weight matrix of the LSTM model, h t is the hidden state of the LSTM model at time step t, b is the bias term, t is the index variable of the time step, i is the index variable of the historical moment, and N is the number of historical moments.

[0080] It should be noted that the historical electrical load power value refers to the amount of electrical power consumed by the aircraft electrical system at a specific point in time;

[0081] The historical electrical load power value is obtained from historical aircraft operation data obtained through real-time measurement by sensors installed on aircraft electrical equipment and recorded.

[0082] S4. Based on the predicted value of the power demand of the electrical load, a time series pair is constructed using the correlation analysis method, and aligned using the dynamic time warping algorithm. The similarity of the time series pair is analyzed to obtain the load coupling effect and the spectrum information based on the predicted value of the power demand of the electrical load. The power density of the electrical load at different frequencies is analyzed using the spectrum analysis method, and the power factor synergy effect is calculated using the cross-power spectrum analysis method.

[0083] S4.1. Obtain the actual value of the electrical load power demand by using the electrical load power data measured and recorded in real time by the aircraft electrical load sensors and utilizing the power monitoring and data recording method.

[0084] It should be noted that special sensors are installed in each electrical system of the aircraft. These sensors can continuously monitor and collect key parameters such as current and voltage of each electrical system. The real-time power consumption value is then calculated using this raw data, and these data points are recorded together with a timestamp to form the actual value of the electrical load power demand.

[0085] S4.2. Based on the actual value of the electrical load power demand and the predicted value of the electrical load power demand, the two time series are selected by a correlation analysis method to construct a time series pair.

[0086] It should be noted that, first, the actual value of the electrical load power demand obtained by real-time measurement and the predicted value of the electrical load power demand obtained by the load power demand prediction model are respectively organized into two independent time series. Then, the correlation analysis technique in statistics is applied, such as calculating the Pearson correlation coefficient or using the mutual information method, to quantify the linear or nonlinear relationship strength between the two time series. According to the analysis results, the corresponding time point data with significant correlation are selected to form a paired time series pair.

[0087] S4.3. Based on the time series pair, the two time series are aligned using the dynamic time warping algorithm to analyze the similarity between the two time series. The expression is:

[0088]

[0089] Among them, D(P t ,Q t ) is the aligned time series pair (P t,Q t ), Q t is the actual value of the electrical load power demand, and T is the number of time steps.

[0090] S4.4, based on the aligned time series pair (P t ,Q t ) and quantify the coupling effect between loads through the mutual information method to obtain the load coupling effect.

[0091] It should be noted that, first, the dynamic time warping algorithm is used to ensure that the time series of actual values ​​and predicted values ​​are correctly aligned on the time axis to accurately compare the two. Then, the mutual information of the two aligned time series is calculated. Mutual information is a statistical method to measure the amount of shared information between two variables. It can reveal the nonlinear dependence between different electrical loads and is not limited to linear correlation. A higher mutual information value indicates a stronger coupling effect between the two loads, which means that changes in one load are likely to affect the behavior of another load. By analyzing the mutual information between multiple loads, we can fully understand the complex pattern of interaction between loads in the entire power system, thereby obtaining the load coupling effect.

[0092] S4.5. Perform Fourier transform on the time series of predicted values ​​of electrical load power demand using a Fourier transform method to obtain spectrum information.

[0093] It should be noted that first, a representative time series data of the predicted value of the electrical load power demand is selected, and then the discrete Fourier transform (DFT) or fast Fourier transform (FFT) algorithm is applied to convert the time series from the time domain to the frequency domain. This conversion can decompose the original signal into a combination of a series of sine and cosine waves of different frequencies. In the frequency domain, the amplitude and phase information corresponding to each frequency component can be intuitively seen, that is, the spectrum diagram, which shows the power distribution at different frequencies, thereby obtaining the spectrum information.

[0094] S4.6. Analyze the main frequency components in the spectrum information using a spectrum analysis method to obtain the power density of the electrical load at different frequencies.

[0095] It should be noted that, first, the Fourier transform is used to convert the time series of electrical load power demand forecast values ​​into frequency domain representation to obtain its spectrum diagram. Then, the frequency components with significant amplitudes are identified from the spectrum diagram. These are the main frequency components, which represent the most important periodic fluctuations in the signal. The power density at each frequency point is then calculated. This is usually quantified by the square of the amplitude of each frequency component, reflecting the distribution of power at different frequencies.

[0096] S4.7. Based on the power density of the electrical load at different frequencies, the power factor synergy effect is calculated using the cross-power spectrum analysis method. The expression is:

[0097]

[0098] Among them, C xy (ω) is the power factor synergy effect of signal x and signal y at frequency ω, S xy (ω) is the cross power density of signal x and signal y at frequency ω, S x (ω) is the autopower density of signal x at frequency ω, S y (ω) is the autopower density of signal y at frequency ω, where ω is the frequency component of the signal.

[0099] S5. Use the differential method to analyze the change in electrical load power at each time step, combine the load coupling effect and power factor synergy effect, and optimize the power capacity requirement through a multi-objective optimization algorithm.

[0100] S5.1. Based on historical aircraft operation data, analyze the average and peak electrical load requirements for each flight phase using statistical analysis methods to obtain power capacity requirements.

[0101] It should be noted that, first, historical aircraft operation data covering different flight phases (such as take-off, cruising, and landing) are collected and preprocessed, and then statistical analysis techniques such as mean calculation, peak detection, and trend analysis are applied to identify the typical load pattern and its maximum and average power requirements for each flight phase. Then, combined with the flight plan and operational requirements, the load characteristics of each phase are evaluated to ensure that all possible load conditions are fully considered. Finally, based on the analysis results, the minimum and maximum power capacity required for each flight phase is determined, and the power capacity requirements for the entire flight cycle are summarized.

[0102] S5.2. Based on the preprocessed aircraft operation data, analyze the change in electrical load power at each time step using a differential method to obtain the change in electrical load power.

[0103] It should be noted that the electrical load data extracted from the pre-processed aircraft operation data includes current, voltage and power values ​​calculated therefrom;

[0104] It should also be noted that based on the electrical load data, an electrical load power data sequence is formed by arranging the data in chronological order. Then, for each time point in the sequence, the difference between the power value at that time point and the previous time point is calculated, that is, the power value at the current moment minus the power value at the previous moment. This difference is the change in electrical load power at that time step.

[0105] S5.3. Based on the load coupling effect, the relationship between different loads is reflected. The power factor synergy effect is used to reveal the interaction between power transmission at different frequencies. The dynamic fluctuation of load demand is reflected by combining the change in electrical load power. The power capacity demand is optimized through a multi-objective optimization algorithm. The expression is:

[0106]

[0107] Among them, F is the optimized power capacity requirement, G PQ is the load coupling effect between time series P and time series Q, ω max is the maximum frequency, K is the target power factor synergy, ΔP t is the electrical load power variation, α1 is the weight coefficient of the load coupling effect, α2 is the weight coefficient of the power factor synergy effect, and α3 is the weight coefficient of the electrical load power variation.

[0108] It should be noted that the target power factor synergy effect analyzes the spectrum information of the predicted value of the electrical load power demand through Fourier transform, identifies the power density at different frequencies, and then uses the cross-power spectrum analysis method based on these spectral components to calculate the actual power factor at each frequency and compare it with the ideal power factor standard (the ideal power factor standard is usually set according to the design specifications of the power system). Finally, an optimization target, namely the target power factor synergy effect, is determined.

[0109] S6. Utilize trend analysis and error feedback mechanisms to identify the electrical load power demand error and the trend of electrical load power demand fluctuations. Combined with the optimized power capacity requirements, analyze through a load matching algorithm to obtain the required power capacity for aircraft operation.

[0110] S6.1. Develop an initial power capacity allocation strategy based on the predicted electrical load power demand, load coupling effects, and power factor synergy effects.

[0111] It should be noted that, first, the load power demand forecast value is used to estimate the power demand in each time period. Then, the mutual influence between different loads is analyzed in combination with the load coupling effect to ensure that the power distribution can adapt to the dynamic interaction between loads. Then, the power factor synergy effect is considered to optimize the power transmission efficiency at different frequencies and ensure the power quality. By combining these three aspects of information, the preliminary distribution plan of each power unit is determined through simulation and optimization algorithms.

[0112] S6.2. Based on the actual value of the electrical load power demand and the predicted value of the electrical load power demand, deviation is identified through an error feedback mechanism to obtain an electrical load power demand error.

[0113] It should be noted that first, the actual value of the electrical load power demand monitored in real time is compared with the power demand value previously predicted by the model. Then, the difference between the two, that is, the error value, is calculated. This can be done through a simple subtraction operation to obtain the error at each time point. In order to comprehensively evaluate the overall error level, more complex measurement methods such as mean square error (MSE) or mean absolute error (MAE) can also be used. These error data are then analyzed to identify any patterns or trends, understand the accuracy of the prediction model and any possible deviations. Through this error feedback mechanism, not only can the prediction performance be evaluated, but potential problems or improvement points can also be discovered, thereby obtaining an accurate electrical load power demand error.

[0114] S6.3. Compare the time series of the predicted values ​​of the electrical load power demand through trend analysis to identify the trend of fluctuations in the electrical load power demand.

[0115] It should be noted that the forecast values ​​of electrical load power demand over a period of time are collected and organized to form time series data, and then these data are smoothed using statistical or mathematical methods (such as moving average, exponential smoothing, etc.) to reduce the impact of short-term fluctuations and highlight long-term patterns. Then, trend analysis techniques, such as linear regression analysis or time series decomposition, are used to focus on identifying and quantifying rising, falling or stable trends in the data, thereby obtaining the fluctuation trend of electrical load power demand.

[0116] S6.4. Based on the electrical load power demand error and the electrical load power demand fluctuation trend, perform fault-tolerant adjustment on the initial allocation strategy of the power capacity.

[0117] It should be noted that, first, the error between the actual value and the predicted value of the electrical load power demand is analyzed, and the pattern and cause of the prediction deviation are identified by calculating statistical indicators such as the mean square error (MSE) and the mean absolute error (MAE). Then, the trend analysis method is used to evaluate the change trend of the electrical load power demand over time, and the rising, falling or stable mode of demand is determined. Then, based on the results of error analysis and trend evaluation, the initial allocation strategy of power capacity is adjusted, redundancy is increased or allocation is optimized to cope with prediction errors and load fluctuations, ensuring that the power system can flexibly respond to actual demand changes.

[0118] S6.5. Based on the adjusted power capacity allocation strategy, the electrical load demand in each time period is dynamically evaluated by combining the flight plan, flight phase, and real-time electrical load data through time series analysis methods to ultimately obtain the required power capacity during aircraft operation.

[0119] It should be noted that, first, time series analysis technology is used to conduct in-depth analysis of historical electrical load data to identify typical load patterns and trends in different flight phases (such as takeoff, cruising, and landing). Then, based on a detailed flight plan, including range, estimated flight time, and specific operational requirements, the expected load requirements for each flight phase are planned in advance to ensure that all possible load conditions are fully considered. Then, during the flight, electrical load data is collected and monitored in real time to identify any deviations or anomalies, and the power distribution strategy is adjusted immediately to cope with unexpected demand. At the same time, through continuous monitoring and feedback mechanisms, the power capacity configuration is dynamically optimized and fine-tuned to ensure that the actual electrical load requirements can be accurately met during each flight period. Finally, the above analysis results and real-time adjustment measures are combined to summarize the power requirements of each flight phase, and the total power capacity requirements for the entire flight cycle are calculated, thereby obtaining the precise power capacity required by the aircraft during the entire operation.

[0120] This embodiment also provides a device for aircraft electrical load statistics and power supply capacity analysis, comprising: a data collection module, a model building and prediction module, a load effect analysis module, a power supply capacity optimization module, and a power supply capacity analysis module;

[0121] A data collection module is used to collect and pre-process aircraft operation data;

[0122] The model building and prediction module is used to convert the time series format through the sliding window method, build a load power demand prediction model based on the long short-term memory network model, and obtain the predicted value of electrical load power demand;

[0123] The load effect analysis module is used to construct time series pairs based on the predicted value of electrical load power demand using the correlation analysis method, align them using the dynamic time warping algorithm, analyze the similarity of the time series pairs, obtain load coupling effects, and obtain spectrum information based on the predicted value of electrical load power demand using the Fourier transform method. The power density of the electrical load at different frequencies is analyzed using the spectrum analysis method, and the power factor synergy effect is calculated using the cross-power spectrum analysis method.

[0124] The power capacity optimization module is used to analyze the change in electrical load power at each time step using the differential method, combining the load coupling effect and the power factor synergy effect, and optimizing the power capacity requirements through a multi-objective optimization algorithm;

[0125] The power capacity analysis module is used to identify the electrical load power demand error and the trend of electrical load power demand fluctuation by using trend analysis and error feedback mechanism. Combined with the optimized power capacity demand, it is analyzed through load matching algorithm to obtain the required power capacity during aircraft operation.

[0126] This embodiment also provides a computer device suitable for the method of aircraft electrical load statistics and power supply capacity analysis, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method of aircraft electrical load statistics and power supply capacity analysis proposed in the above embodiment.

[0127] The computer device may be a terminal, comprising 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 comprises 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 may 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 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 button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0128] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for implementing aircraft electrical load statistics and power supply capacity analysis as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0129] In summary, this invention combines a long short-term memory network model with a dynamic time warping algorithm and spectrum analysis methods to accurately predict aircraft electrical load power requirements and analyze load coupling and power factor synergy effects, thereby providing accurate and dynamic input for optimizing power capacity requirements. By optimizing power capacity through a multi-objective optimization algorithm and achieving precise power capacity allocation through a load matching algorithm, the system effectively improves aircraft operating efficiency and safety, ensures that power configuration can be flexibly adjusted based on actual flight data, and enhances overall energy utilization and system adaptability.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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. A method for aircraft electrical load statistics and power supply capacity analysis, characterized by: include: Collect aircraft operation data and pre-process the aircraft operation data; The time series format is converted by the sliding window method, and a load power demand forecasting model is constructed based on the long short-term memory network model to obtain the predicted value of electrical load power demand; The time series format is converted by the sliding window method, and a load power demand prediction model is constructed based on the long short-term memory network model. The specific steps are as follows: The pre-processed historical aircraft operation data are converted into time series format using a sliding window method; The model is based on the long short-term memory network model; The input layer receives pre-processed historical aircraft operation data converted into time series format; The LSTM layer uses memory cells and gate mechanisms to selectively remember and forget information, capturing long-term dependencies in time series. The fully connected layer extracts features and reduces the dimension based on the output of the LSTM layer and maps it to the output layer; Output the prediction results through the output layer; Finally, a load power demand prediction model is constructed; Based on the predicted power demand value of the electrical load, a correlation analysis method is used to construct a time series pair. These are then aligned using a dynamic time warping algorithm. The similarity of the time series pairs is analyzed to obtain the load coupling effect. Based on the predicted power demand value of the electrical load, a Fourier transform method is used to obtain spectrum information. The power density of the electrical load at different frequencies is analyzed using a spectrum analysis method. The power factor synergy effect is calculated using a cross-power spectrum analysis method. The specific steps are as follows: The actual value of electrical load power demand is obtained by using electrical load power data measured and recorded in real time by aircraft electrical load sensors and using power monitoring and data recording methods; Based on the actual value of electrical load power demand and the predicted value of electrical load power demand, the two time series are selected through the correlation analysis method to construct a time series pair; Based on the time series pair, the two time series are aligned using the dynamic time warping algorithm to analyze the similarity between the two time series. The expression is: Among them, D(P t , Q t ) is the aligned time series pair (P t , Q t ), Q t is the actual value of the electrical load power demand, T is the number of time steps; Based on the aligned time series pairs (P t , Q t ) and quantify the coupling effect between loads through the mutual information method to obtain the load coupling effect; The Fourier transform method is used to perform Fourier transform on the time series of electrical load power demand forecast values ​​to obtain spectrum information; By using the spectrum analysis method, the main frequency components in the spectrum information are analyzed to obtain the power density of the electrical load at different frequencies; Based on the power density of electrical loads at different frequencies, the power factor synergy effect is calculated using the cross-power spectrum analysis method. The expression is: Among them, C xy (ω) is the power factor synergy effect of signal x and signal y at frequency ω, S xy (ω) is the cross power density of signal x and signal y at frequency ω, S x (ω) is the autopower density of signal x at frequency ω, S y (ω) is the autopower density of signal y at frequency ω, where ω is the frequency component of the signal; The difference method is used to analyze the change in electrical load power at each time step, combining the load coupling effect and power factor synergy effect, and optimizing the power capacity demand through a multi-objective optimization algorithm; The trend analysis method and error feedback mechanism are used to identify the error in electrical load power demand and the trend of electrical load power demand fluctuation. Combined with the optimized power capacity requirement, the load matching algorithm is used for analysis to obtain the required power capacity during aircraft operation.

2. The method for aircraft electrical load statistics and power supply capacity analysis according to claim 1, wherein: The aircraft operation data includes flight control data, environmental sensor data, and electrical load data; The pre-processing of the aircraft operation data includes standardization, removal of noise data and removal of abnormal values.

3. The method for aircraft electrical load statistics and power supply capacity analysis according to claim 1, wherein: The specific steps of obtaining the predicted value of electrical load power demand are as follows: Based on the pre-processed aircraft operation data converted into a time series format, the memory unit and gate mechanism in the LSTM model are used to learn the time series data to capture the temporal variation pattern of the electrical load power during aircraft operation. Based on the temporal variation of electrical load power during aircraft operation, combined with the weighted coefficients and historical electrical load power values ​​at historical moments, the electrical load power demand is predicted. The expression is: Among them, P t is the predicted value of the electrical load power demand at time step t, f(i) is the weighting coefficient at the i-th historical moment, and y t，i is the historical electrical load power value at the i-th historical moment from time step t, W is the output weight matrix of the LSTM model, h t is the hidden state of the LSTM model at time step t, b is the bias term, t is the index variable of the time step, i is the index variable of the historical moment, and N is the number of historical moments.

4. The method for aircraft electrical load statistics and power supply capacity analysis according to claim 1, wherein: The difference method is used to analyze the change in electrical load power at each time step, combined with the load coupling effect and the power factor synergy effect, and the power capacity requirement is optimized through a multi-objective optimization algorithm. The specific steps are as follows: Based on historical aircraft operation data, statistical analysis methods are used to analyze the average and peak electrical load requirements in each flight phase to obtain power capacity requirements; Based on the pre-processed aircraft operation data, the change in electrical load power at each time step is analyzed by the difference method to obtain the change in electrical load power; The load coupling effect reflects the relationship between different loads, the power factor synergy effect is used to reveal the interaction of power transmission at different frequencies, and the dynamic fluctuation of load demand is reflected by combining the change in electrical load power. The power capacity demand is optimized through a multi-objective optimization algorithm. The expression is: Among them, F is the optimized power capacity requirement, G PQ is the load coupling effect between time series P and time series Q, ω max is the maximum frequency, K is the target power factor synergy, ΔP t is the electrical load power variation, α1 is the weight coefficient of the load coupling effect, α2 is the weight coefficient of the power factor synergy effect, and α3 is the weight coefficient of the electrical load power variation.

5. The method for aircraft electrical load statistics and power supply capacity analysis according to claim 1, wherein: The trend analysis method and error feedback mechanism are used to identify the electrical load power demand error and the electrical load power demand fluctuation trend. Combined with the optimized power capacity requirement, the load matching algorithm is used for analysis to obtain the required power capacity during aircraft operation. The specific steps are as follows: Formulate an initial power capacity allocation strategy based on the predicted electrical load power demand, load coupling effects, and power factor synergy effects; Based on the actual value of the electrical load power demand and the predicted value of the electrical load power demand, the deviation is identified through the error feedback mechanism to obtain the electrical load power demand error; By comparing the time series of the predicted values ​​of the electrical load power demand through trend analysis, the trend of fluctuation of the electrical load power demand can be identified; Based on the error in the power demand of the electrical load and the trend of the fluctuation of the power demand of the electrical load, the initial allocation strategy of the power capacity is adjusted for fault tolerance; Based on the adjusted power capacity allocation strategy, the electrical load demand in each time period is dynamically evaluated through time series analysis combined with flight plans, flight phases, and real-time electrical load data, ultimately obtaining the required power capacity during aircraft operation.

6. A device for aircraft electrical load statistics and power supply capacity analysis, based on the method for aircraft electrical load statistics and power supply capacity analysis according to any one of claims 1 to 5, characterized in that: include: Data collection module, model building and prediction module, load effect analysis module, power capacity optimization module and power capacity analysis module; A data collection module is used to collect and pre-process aircraft operation data; The model building and prediction module is used to convert the time series format through the sliding window method, build a load power demand prediction model based on the long short-term memory network model, and obtain the predicted value of electrical load power demand; The load effect analysis module is used to construct time series pairs based on the predicted value of electrical load power demand using the correlation analysis method, align them using the dynamic time warping algorithm, analyze the similarity of the time series pairs, obtain load coupling effects, and obtain spectrum information based on the predicted value of electrical load power demand using the Fourier transform method. The power density of the electrical load at different frequencies is analyzed using the spectrum analysis method, and the power factor synergy effect is calculated using the cross-power spectrum analysis method. The power capacity optimization module is used to analyze the change in electrical load power at each time step using the differential method, combining the load coupling effect and the power factor synergy effect, and optimizing the power capacity requirements through a multi-objective optimization algorithm; The power capacity analysis module is used to identify the electrical load power demand error and the trend of electrical load power demand fluctuation by using trend analysis and error feedback mechanism. Combined with the optimized power capacity demand, it is analyzed through load matching algorithm to obtain the required power capacity during aircraft operation.

7. 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 method for aircraft electrical load statistics and power supply capacity analysis according to any one of claims 1 to 5 are implemented.

8. 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 method for aircraft electrical load statistics and power supply capacity analysis according to any one of claims 1 to 5 are implemented.

Images