An energy management method and system based on a series hybrid electric propulsion system

Abstract

The present invention relates to an energy management method and system based on a series hybrid electric propulsion system, and relates to the field of energy management. The method includes extracting k flight missions from historical flight data as target flight missions; each flight mission is represented by a feature vector composed of feature parameters; using the dynamic programming method to optimize the energy management strategy for each target flight mission respectively, and obtaining the energy management strategy corresponding to each target flight mission; each energy management strategy includes the engine output power, the energy storage battery pack output power, and the energy storage battery pack output current; obtaining the current feature parameters of the aircraft; according to the current feature parameters, matching the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy; and performing energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy. The present invention improves the energy utilization rate, thereby improving the endurance of the aircraft.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and particularly to an energy management method and system based on a series hybrid electric propulsion system. Background Art

[0002] The series hybrid electric propulsion system provides energy for a fixed-wing vertical takeoff and landing aircraft, and the supply of energy is crucial for the fixed-wing vertical takeoff and landing aircraft to perform flight missions. The series hybrid electric energy system includes three major parts: a power generation system, an energy storage battery system, and an energy management system, which provide the energy required for the normal operation of electrical loads such as the power system, on-board loads, and control systems of the fixed-wing vertical takeoff and landing aircraft. Among them, the generator system consists of an engine, a generator, a working condition optimization control module, and a DC / DC power module. The engine does not directly drive the propeller, but only converts the chemical energy of fuel into mechanical energy and transmits it to the generator, and the generator converts the mechanical energy into electrical energy to supply power to electrical equipment. The energy storage battery pack serves as power supplement, and is used to supply power together with the generator during high-power demand stages such as takeoff and landing, and can absorb the excess power generated by the generator through charging when the power demand is small, playing the role of "peak shaving and valley filling".

[0003] However, the current series hybrid electric propulsion system cannot meet the distributed power supply requirements of fixed-wing vertical takeoff and landing aircraft, and the endurance of the aircraft needs to be improved. Summary of the Invention

[0004] The purpose of the present invention is to provide an energy management method and system based on a series hybrid electric propulsion system, which improves the energy utilization rate and thus improves the endurance of the aircraft.

[0005] To achieve the above purpose, the present invention provides the following solution:

[0006] An energy management method based on a series hybrid electric propulsion system includes:

[0007] Obtain a data sample set of the aircraft, where each sample data in the data sample set is historical flight data; the energy system of the aircraft adopts a series hybrid electric propulsion system;

[0008] Extract k flight missions from the historical flight data as target flight missions; each flight mission is represented by a feature vector composed of feature parameters, and the feature parameters are parameters in the historical flight data;

[0009] Optimize the energy management strategies for each of the target flight missions using the dynamic programming method, obtain the energy management strategies corresponding to each of the target flight missions, and store each of the target flight missions and the corresponding energy management strategies in an energy management strategy library; each of the energy management strategies includes the engine output power, the energy storage battery pack output power, and the energy storage battery pack output current;

[0010] Obtain the current characteristic parameters of the aircraft;

[0011] According to the current characteristic parameters, match the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy;

[0012] Perform energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy.

[0013] Optionally, the characteristic parameters include the vertical takeoff height, the fixed-wing climb rate, the cruise flight height, the cruise flight speed, the cruise flight distance, and the vertical descent height.

[0014] Optionally, extracting k flight missions from the historical flight data as the target flight missions specifically includes:

[0015] Adopt the K-means clustering algorithm to extract k flight missions from the historical flight data as the target flight missions.

[0016] Optionally, the adopting the K-means clustering algorithm to extract k flight missions from the historical flight data as the target flight missions specifically includes:

[0017] Randomly select k sample data from the data sample set to initialize k centroids;

[0018] According to the Euclidean distances from each sample data in the data sample set to each of the centroids, divide the data sample set into k clusters;

[0019] Calculate the means of each cluster to update the centroids of each cluster;

[0020] Repeat the steps of "According to the Euclidean distances from each sample data in the data sample set to each of the centroids, divide the data sample set into k clusters; calculate the means of each cluster to update the centroids of each cluster" until each cluster no longer changes, and take the feature vectors formed by the characteristic parameters in the sample data closest to the centroid in each final cluster as the target flight missions to obtain k target flight missions.

[0021] Optionally, the dividing the data sample set into k clusters according to the Euclidean distances from each sample data in the data sample set to each of the centroids specifically includes:

[0022] For the nth sample data, calculate the Euclidean distance from the nth sample data to each of the centroids, and use the cluster of the centroid corresponding to the minimum Euclidean distance as the cluster of the nth sample data.

[0023] Optionally, the method of using dynamic programming to optimize the energy management strategy for each of the target flight missions respectively, obtain the energy management strategy corresponding to each of the target flight missions, and store the energy management strategy corresponding to each of the target flight missions in the energy management strategy library specifically includes:

[0024] For the lth target flight mission, divide the entire flight process of the lth target flight mission into N stages with a set step size according to time sequence;

[0025] Construct the minimum fuel consumption function from each stage to the end of the flight process of the lth target flight mission;

[0026] According to the minimum fuel consumption function from each stage to the end of the flight process of the lth target flight mission, with the minimum total fuel consumption of the entire flight process of the lth target flight mission as the optimization goal, determine the energy management strategy of the entire flight process of the lth target flight mission.

[0027] Optionally, the minimum fuel consumption function from each stage to the end of the flight process of the lth target flight mission is expressed as:

[0028]

[0029] f N+1 (x(N + 1)) = 0;

[0030] where, f i (x(i)) represents the minimum fuel consumption function from the state variable x(i) in the ith stage to the end of the flight process, f i+1 (x(i + 1)) represents the minimum fuel consumption function from the state variable x(i + 1) in the (i + 1)th stage to the end of the flight process, d i (x(i), u i (i)) represents the engine fuel consumption in the ith stage, u i (i) represents the output current of the energy storage battery pack;

[0031] d i (x(i), u(i)) = (P ICE (i) BSFC(P ICE (i))) ts;

[0032] P ICE (i) = (P req (i) - P batt (i)) ηgen ;

[0033] P ICE (i) represents the engine output power, P batt (i) represents the output power of the energy storage battery pack, ts represents the single-stage time step, η gen represents the generator efficiency.

[0034] Optionally, matching the energy management strategy corresponding to the current flight mission from the energy management strategy library according to the current characteristic parameters as the current energy management strategy specifically includes:

[0035] Obtaining the current feature vector composed of the current characteristic parameters;

[0036] Calculating the Euclidean distances between the current feature vector and the feature vectors corresponding to each target flight mission respectively, and taking the energy management strategy corresponding to the target flight mission with the minimum Euclidean distance as the current energy management strategy.

[0037] Optionally, performing energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy specifically includes:

[0038] Obtaining the motion condition data of the current aircraft; the motion condition data includes speed command, climb rate command and flight altitude;

[0039] Calculating the real-time required power of the aircraft according to the motion condition data;

[0040] Obtaining the energy storage battery pack data of the current aircraft;

[0041] Based on the energy management strategy, allocating the real-time required power to the generator and the energy storage battery pack according to the real-time required power and the energy storage battery pack data;

[0042] Determining the torque command and speed command of the engine according to the output power allocated to the generator.

[0043] The present invention also discloses an energy management system based on a series hybrid electric propulsion system, including:

[0044] A data sample set acquisition module, configured to acquire a data sample set of the aircraft, and each sample data in the data sample set is historical flight data; the energy system of the aircraft adopts a series hybrid electric propulsion system;

[0045] A target flight mission determination module, configured to extract k flight missions from the historical flight data as target flight missions; each flight mission is represented by a feature vector composed of characteristic parameters, and the characteristic parameters are parameters in the historical flight data;

[0046] An energy management strategy optimization module, which is used to optimize the energy management strategies for each of the target flight missions respectively by using the dynamic programming method, obtain the energy management strategies corresponding to each of the target flight missions, and store each of the target flight missions and the corresponding energy management strategies into an energy management strategy library; each of the energy management strategies includes the engine output power and the energy storage battery pack output power;

[0047] A current characteristic parameter acquisition module, which is used to acquire the current characteristic parameters of the aircraft;

[0048] A current energy management strategy matching module, which is used to match, according to the current characteristic parameters, the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy;

[0049] An energy management strategy application module, which is used to perform energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy.

[0050] According to the specific embodiments provided by the present invention, the following technical effects are disclosed by the present invention:

[0051] The present invention extracts target flight missions from historical flight data, obtains an energy management strategy library through offline optimization, and uses the energy management strategy library for online energy management; through the methods of characteristic parameter identification and matching, online invocation of energy management strategies, and engine operating condition optimization, online optimization management of energy is realized, which can not only meet the power requirements of electrical equipment in real time, but also effectively improve the overall efficiency of the energy system, thereby enhancing the endurance of the aircraft and better completing flight missions. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0053] Figure 1 Schematic diagram of the process of an energy management method based on a series hybrid electric propulsion system of the present invention Figure 1 ;

[0054] Figure 2 Schematic diagram of the process of an energy management method based on a series hybrid electric propulsion system of the present invention Figure 2 ;

[0055] Figure 3 Schematic diagram of the structure of the series hybrid electric propulsion system of the present invention;

[0056] Figure 4 Schematic diagram of the energy management process of the present invention;

[0057] Figure 5 Schematic diagram of the structure of an energy management system based on a series hybrid electric propulsion system of the present invention. Specific embodiments

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0059] The purpose of the present invention is to provide an energy management method and system based on a series hybrid electric propulsion system, which improves the energy utilization rate and thus improves the flight endurance of the aircraft.

[0060] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0061] Figure 1 Schematic diagram of the process of an energy management method based on a series hybrid electric propulsion system of the present invention Figure 1 ; Figure 2 Schematic diagram of the process of an energy management method based on a series hybrid electric propulsion system of the present invention Figure 2 , such as Figure 1 - Figure 2 shown, an energy management method based on a series hybrid electric propulsion system includes the following steps:

[0062] Step 101: Obtain a data sample set of the aircraft, and each sample data in the data sample set is historical flight data; the energy system of the aircraft adopts a series hybrid electric propulsion system.

[0063] The series hybrid electric propulsion system is as Figure 3As shown in the figure. The series hybrid electric propulsion system (aircraft energy system) includes a power generation system, an energy storage system, and an energy management system. The series hybrid electric propulsion system provides the energy required for the normal operation of electrical loads such as the aircraft platform power system, control system, and on-board payloads. Among them, the power generation system includes an engine, a generator, and a DC / DC module. The engine converts the chemical energy of the fuel into mechanical energy, and the engine shaft is only connected to the generator and not to components such as the propeller. The generator converts the mechanical energy output by the engine into electrical energy to supply power to electrical equipment; the energy storage system includes an energy storage battery pack and a BMS module (battery management system), providing the functions of energy storage and energy supply; the energy management system includes a power calculation module, an energy storage calculation module, an energy management module, and an engine optimization module, responsible for energy management and control. By reasonably adjusting the power output of the power generation system and the energy storage battery pack, the energy system can further improve the overall system efficiency while meeting the aircraft's power requirements. When the power demand is large, the power generation system and the energy storage battery system output power simultaneously to provide energy for electrical equipment; when the power demand is small, only the power generation system can provide energy, and at the same time, it can charge the energy storage battery pack; the charging battery pack can smooth the power fluctuations, enabling the power generation system to always operate in the high-efficiency area; in the case of very small power demand or special situations such as engine failure during gliding, the energy storage battery pack can also supply power alone.

[0064] Step 102: Extract k flight missions from the historical flight data as target flight missions; each flight mission is represented by a feature vector composed of feature parameters, and the feature parameters are parameters in the historical flight data.

[0065] The aircraft is a fixed-wing vertical takeoff and landing aircraft, and the feature parameters are selected according to the fixed-wing vertical takeoff and landing aircraft. The feature parameters include vertical takeoff height, fixed-wing climb rate, cruise flight height, cruise flight speed, cruise flight distance, and vertical descent height.

[0066] The historical flight data is specifically the flight data of the entire flight process of the fixed-wing vertical takeoff and landing aircraft from takeoff to landing.

[0067] Among them, Step 102 specifically includes:

[0068] Adopt the K-means clustering algorithm to extract k flight missions from the historical flight data as target flight missions (typical flight missions).

[0069] The adoption of the K-means clustering algorithm to extract k flight missions from the historical flight data as target flight missions specifically includes:

[0070] Randomly select k sample data from the data sample set to initialize k centroids, specifically including: using the K-means clustering algorithm to divide the power curve segments into k clusters. One cluster corresponds to one centroid.

[0071] Divide the data sample set into k clusters according to the Euclidean distances from each sample data in the data sample set to each of the centroids.

[0072] Calculate the mean of each cluster to update the centroid of each cluster.

[0073] Repeat the steps of "divide the data sample set into k clusters according to the Euclidean distances from each sample data in the data sample set to each of the centroids; calculate the mean of each cluster to update the centroid of each cluster" until each cluster no longer changes. Take the feature vector composed of the feature parameters in the sample data closest to the centroid in each final cluster as the target flight mission, and obtain k target flight missions.

[0074] The step of dividing the data sample set into k clusters according to the Euclidean distances from each sample data in the data sample set to each of the centroids specifically includes:

[0075] For the nth sample data, calculate the Euclidean distances from the nth sample data to each of the centroids, and take the cluster of the centroid corresponding to the minimum Euclidean distance as the cluster of the nth sample data. It is expressed by the formula:

[0076] mind=min||a·(x - μ j )||2(j=1,2...,k);

[0077] a=[a1,a2,a3,a4,a5,a6]

[0078] where d represents the minimum Euclidean distance, a represents the weight coefficient vector, a1 - a6 are the weight coefficients corresponding to 6 feature parameters (vertical takeoff height, fixed-wing climb rate, cruise flight height, cruise flight speed, cruise flight distance, and vertical descent height) respectively, μ j represents the feature vector of the jth centroid, x represents the feature vector of the sample data, and k represents the number of centroids.

[0079] Step 103: Use the dynamic programming method to optimize the energy management strategy for each of the target flight missions respectively, obtain the energy management strategy corresponding to each of the target flight missions, and store each of the target flight missions and the corresponding energy management strategy in the energy management strategy library; each of the energy management strategies includes the engine output power, the output power of the energy storage battery pack, and the output current of the energy storage battery pack.

[0080] The present invention uses the dynamic programming method to perform offline optimization on k flight missions respectively, extracts the energy rules according to the optimization results, and obtains a rule-based energy management strategy.

[0081] Among them, step 103 specifically includes:

[0082] For the l-th target flight mission, the entire flight process of the l-th target flight mission is divided into N stages with a set step size according to time sequence;

[0083] Construct the minimum fuel consumption function from each stage to the end of the flight process of the l-th target flight mission;

[0084] According to the minimum fuel consumption function from each stage to the end of the flight process of the l-th target flight mission, with the minimum total fuel consumption of the entire flight process of the l-th target flight mission as the optimization goal, determine the energy management strategy of the entire flight process of the l-th target flight mission.

[0085] The minimum fuel consumption function from each stage to the end of the flight process of the l-th target flight mission is expressed as:

[0086]

[0087] f N+1 (x(N + 1)) = 0;

[0088] Among them, f i (x(i)) represents the minimum fuel consumption function from the state variable x(i) to the end of the flight process in the i-th stage, f i+1 (x(i + 1)) represents the minimum fuel consumption function from the state variable x(i + 1) to the end of the flight process in the i + 1-th stage, d i (x(i), u i (i)) represents the engine fuel consumption in the i-th stage, u i (i) represents the output current of the energy storage battery pack; f N+1 (x(N + 1)) = 0 means that the fuel consumption is 0 when i is N, and the state variable is specifically the SOC (State of Charge) of the energy storage battery pack.

[0089] x(i) represents the state in the i-th stage, and the decision variable is represented by the output current of the battery pack u i (i).

[0090] The state transition equation can be written as:

[0091]

[0092] Among them, ts represents the set step size, and Q represents the total capacity of the battery pack.

[0093] The cost of each set step size is the engine fuel consumption, denoted by d i (x(i), u i (i)).

[0094] d i (x(i), u(i)) = (P ICE (i) BSFC(P ICE (i))) ts;

[0095] P ICE (i) = (P req (i) - P batt (i)) η gen ;

[0096] P batt (i) = u(i) U(x(i));

[0097] P ICE (i) represents the engine output power, P batt (i) represents the output power of the energy storage battery pack, ts represents the single-stage time step, η gen represents the generator efficiency, u(i) represents the output current of the energy storage battery pack, and U(x(i)) represents the output voltage of the energy storage battery pack, which is a function of the battery pack SOC. A set of decision variables that minimize the total fuel consumption, that is, the battery pack output current sequence, can be obtained through programming calculation, and then the corresponding engine power output sequence can be obtained. Analyze the optimization results, observe the change curves of the engine, battery pack power output, battery pack SOC, and the optimal working curve of the engine, and extract the energy management strategy in the form of:

[0098] Rule1: When P req belongs to [a, b] and SOC ∈ [c, d], P ice = xx,

[0099] Rule2:.....

[0100] For example: The optimization results show that during the climbing stage, the power demand is between 180 - 220 kW, the engine output power is 240 kW, and the remaining power is used to charge the battery pack until the battery pack SOC reaches 0.8 and then stops charging. After that, the engine output power is 200 kW. Both 240 kW and 200 kW are the efficient working points of the engine. Then the energy management rules can be extracted as follows:

[0101] Rule1: When P req ∈ [180, 220] kW and SOC ∈ [0, 0.8], P ice = 240 kW;

[0102] Rule2: When P reqWhen ∈[180,220]kW and SOC ∈[0.8,1], P ice = 200kW;

[0103] The energy storage battery pack makes power compensation, smooths the peak power and power oscillation, and absorbs the excess power. It is expressed by the formula P batt (i) = P req (i) - P ice (i)·η gen where P batt (i) is positive for discharging and P batt (i) is negative for charging.

[0104] After the aircraft takes off, this invention obtains the characteristic parameters once every 10 seconds. The flight characteristic parameters obtained each time are matched with the preset typical flight missions. After successful matching, it switches to the energy management strategy corresponding to the typical flight mission.

[0105] Step 104: Obtain the current characteristic parameters of the aircraft.

[0106] Step 105: According to the current characteristic parameters, match the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy.

[0107] Among them, step 105 specifically includes:

[0108] Obtain the current characteristic vector composed of the current characteristic parameters;

[0109] Calculate the Euclidean distances between the current characteristic vector and the characteristic vectors corresponding to each target flight mission respectively. Take the energy management strategy corresponding to the target flight mission with the minimum Euclidean distance as the current energy management strategy. It is expressed by the formula:

[0110]

[0111] where d′ represents the minimum Euclidean distance between the current characteristic vector and the characteristic vectors corresponding to each target flight mission, x′ represents the current characteristic vector, and v i is the characteristic vector of the i-th typical flight mission.

[0112] Step 106: Conduct energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy.

[0113] Among them, step 106 specifically includes:

[0114] As Figure 4 shown, obtain the motion condition data of the current aircraft; the motion condition data includes speed command, climb rate command, and flight altitude.

[0115] Calculate the real-time required power of the aircraft according to the motion condition data.

[0116] Obtain the data of the energy storage battery pack of the aircraft currently.

[0117] According to the real-time required power and the data of the energy storage battery pack, distribute the real-time required power to the generator and the energy storage battery pack based on the energy management strategy, specifically including: taking the engine output power in the energy management strategy as the output power of the current generator, and taking the output power of the energy storage battery pack as the supplementary power of the real-time required power.

[0118] As a specific implementation manner, it further includes: judging the flight mode according to the aircraft speed command v and the climb rate command h:

[0119] h > 0 & v = 0, vertical takeoff and landing mode;

[0120] h > 0 & v > 0, climb and descent mode;

[0121] h = 0 & v > 0, cruise and level flight mode.

[0122] Calculate the real-time required power P of the aircraft by using the dynamic model established under each flight mode req .

[0123] Obtain the output current data of the energy storage battery pack, and calculate the state of charge (SOC) of the energy storage battery pack by the energy storage calculation module. The ampere-hour integration method is adopted, and the calculation formula is as follows:

[0124]

[0125] SOC(t) is the SOC of the battery pack at the current moment, SOC(0) is the SOC of the battery pack at the initial moment, Q b is the maximum charge capacity of the battery, that is, the rated capacity (Ah), and ΔQ represents the charge change amount, which can be calculated by the following formula:

[0126]

[0127] I b is the battery output current, positive for discharging and negative for charging. η b represents the charge and discharge efficiency of the battery, which can be measured by experiments. The voltage U of the energy storage battery pack oc is a function of the SOC and temperature T of the battery pack, and can be calculated by the following formula:

[0128] U oc = f(SOC, T);

[0129] The function U of the SOC and temperature T of the battery pack oc , through the battery discharge experiment, and interpolation fitting of the experimental data, the function expression can be obtained.

[0130] The obtained required power P req and the SOC of the energy storage battery pack are transmitted to the energy management module, and the energy management module determines the output power P of the engine according to the management rules under the current energy management mode ICE , which is expressed as follows:

[0131] P ICE = f EMS (P req , SOC);

[0132] The energy storage battery pack serves as power supplement, smooths the peak power and power oscillation and absorbs the excess power. f EMS (P req , SOC) indicates that the output power of the engine is calculated by the energy management module according to the required power P req and the value of the SOC of the energy storage battery pack, in combination with the energy management rules.

[0133] According to the output power allocated to the generator, determine the torque command and speed command of the engine to achieve online management of energy, specifically including:

[0134] Transmit the output power P allocated to the engine ice to the engine operating condition optimization module, and the preset ideal operating line function converts the power value into the optimal speed and torque, so that the specific fuel consumption of the engine is the smallest and the efficiency is the highest at this output power value.

[0135] The ideal operating line is obtained based on the engine universal characteristic curve. Take multiple power points within the engine operating range. For each power point, find the operating point with the smallest BSFC in the universal characteristic diagram, record the corresponding torque and speed. For example, at the 15 kW point, the BSFC is the smallest at a speed of 7000 and a torque of 20.46 Nm. A look-up table function can be established. After determining the output power allocated to the engine, the speed and torque of the best operating point at this power can be calculated.

[0136] Transmit the speed and torque signals to the control module, and the control module adjusts the engine throttle opening and generator torque to adjust the engine speed and torque to achieve online management of energy.

[0137] The series hybrid electric propulsion system of the fixed-wing vertical takeoff and landing aircraft of the present invention provides an energy source for the aircraft, which is crucial for the aircraft to successfully execute flight missions. The present invention extracts typical flight missions from historical flight data, obtains an energy management strategy library through offline optimization for online energy management; through the methods of working condition identification and matching, online invocation of energy management rules, and engine working condition optimization, realizes online optimization management of energy, can not only meet the power demand of electrical equipment in real time, but also effectively improve the overall efficiency of the energy system, thereby enhancing the endurance of the aircraft and better completing flight missions.

[0138] Figure 5 FIG. is a schematic structural diagram of an energy management system based on a series hybrid electric propulsion system of the present invention. As Figure 5 shown, an energy management system based on a series hybrid electric propulsion system includes:

[0139] A data sample set acquisition module 201, configured to acquire a data sample set of the aircraft, and each sample data in the data sample set is historical flight data; the energy system of the aircraft adopts a series hybrid electric propulsion system;

[0140] A target flight mission determination module 202, configured to extract k flight missions from the historical flight data as target flight missions; each flight mission is represented by a feature vector composed of feature parameters, and the feature parameters are parameters in the historical flight data;

[0141] An energy management strategy optimization module 203, configured to respectively optimize the energy management strategies for each of the target flight missions by using a dynamic programming method, obtain the energy management strategies corresponding to each of the target flight missions, and store each of the target flight missions and the corresponding energy management strategies in an energy management strategy library; each of the energy management strategies includes the engine output power and the energy storage battery pack output power;

[0142] A current feature parameter acquisition module 204, configured to acquire the current feature parameters of the aircraft;

[0143] A current energy management strategy matching module 205, configured to match, according to the current feature parameters, the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy;

[0144] An energy management strategy application module 206, configured to perform energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy.

[0145] In the present specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts among the embodiments can be referred to each other. For the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method section.

[0146] In this article, specific examples are used to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on the present invention.

Claims

1. An energy management method based on a series hybrid electric propulsion system, characterized in that, Including: Obtain a data sample set of the aircraft, where each sample data in the data sample set is historical flight data; the energy system of the aircraft adopts a series hybrid-electric propulsion system; Extract k flight missions from the historical flight data as target flight missions; each flight mission is represented by a feature vector composed of feature parameters, and the feature parameters are the parameters in the historical flight data; k ​ Use the dynamic programming method to optimize the energy management strategy for each of the target flight missions respectively, obtain the energy management strategy corresponding to each target flight mission, and store each target flight mission and the corresponding energy management strategy in the energy management strategy library; each energy management strategy includes the engine output power, the energy storage battery pack output power, and the energy storage battery pack output current; Obtain the current characteristic parameters of the aircraft; According to the current characteristic parameters, match the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy; Manage the energy of the series hybrid-electric propulsion system of the aircraft according to the current energy management strategy; The characteristic parameters include vertical takeoff height, fixed-wing climb rate, cruise flight height, cruise flight speed, cruise flight distance, and vertical descent height; The step of using the dynamic programming method to optimize the energy management strategy for each of the target flight missions respectively, obtain the energy management strategy corresponding to each target flight mission, and store the energy management strategy corresponding to each target flight mission in the energy management strategy library specifically includes: For the l th target flight mission, divide the entire flight process of the l th target flight mission into N phases with a set step size according to the time sequence; Construct the minimum fuel consumption function from each stage to the end of the flight process of the l th target flight mission; According to the minimum fuel consumption function at the end of the flight process of each stage to the l th target flight mission, with the minimum total fuel consumption during the entire flight process of the l th target flight mission as the optimization goal, determine the energy management strategy for the entire flight process of the l th target flight mission; The minimum fuel consumption function for the end of the flight process of each stage to the l th target flight mission is expressed as: ； ； Among them, represents the minimum fuel consumption function from the state variable i at the x ( i ) to the end of the flight process, represents the minimum fuel consumption function from the state variable i at the x ( i + 1) to the end of the flight process, represents the engine fuel consumption at the i stage, u i ( i ) represents the output current of the energy storage battery pack; ； ； P ICE ( i ) represents the engine output power, P batt ( i ) represents the output power of the energy storage battery pack, ts represents the single-stage time step, represents the generator efficiency.

2. The energy management method based on a series hybrid electric propulsion system according to claim 1, wherein The extraction from the historical flight data yields k flight missions as target flight missions, specifically including: Using the K-means clustering algorithm, extract k flight missions from the historical flight data as target flight missions.

3. The energy management method based on a series hybrid electric propulsion system according to claim 2, characterized in that The K-means clustering algorithm is adopted to extract k flight missions from the historical flight data as target flight missions, specifically including: Randomly select k sample data from the data sample set to initialize k centroids; According to the Euclidean distances from each sample data in the data sample set to each of the centroids, the data sample set is divided into k clusters; Calculate the mean of each cluster to update the centroid of each cluster; Repeat the steps of "dividing the data sample set into k clusters according to the Euclidean distances from each sample data in the data sample set to each of the centroids; calculating the means of each cluster to update the centroids of each cluster" until each cluster no longer changes, and taking the feature vectors formed by the characteristic parameters in the sample data closest to the centroid in each final cluster as the target flight missions, obtaining k target flight missions.

4. The energy management method based on a series hybrid electric propulsion system according to claim 3, characterized in that, Dividing the data sample set into k clusters according to the Euclidean distances from each sample data in the data sample set to each of the centroids, specifically including: For the n th sample data, calculate the Euclidean distance from the n th sample data to each of the centroids, and take the cluster of the centroid corresponding to the minimum Euclidean distance as the cluster of the n th sample data.

5. The energy management method based on a series hybrid electric propulsion system according to claim 1, wherein The step of, according to the current characteristic parameters, matching the energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy specifically includes: Obtain the current feature vector composed of the current characteristic parameters; Calculate the Euclidean distance between the current feature vector and the feature vectors corresponding to each target flight mission respectively, and use the energy management strategy corresponding to the target flight mission with the smallest Euclidean distance as the current energy management strategy.

6. The energy management method based on a series hybrid electric propulsion system according to claim 1, wherein The step of managing the energy of the series hybrid-electric propulsion system of the aircraft according to the current energy management strategy specifically includes: Obtain the motion condition data of the current aircraft; the motion condition data includes speed command, climb rate command, and flight height; Calculate the real-time required power of the aircraft according to the motion condition data; Obtain the energy storage battery pack data of the current aircraft; Based on the energy management strategy, distribute the real-time required power to the generator and the energy storage battery pack according to the real-time required power and the energy storage battery pack data; Determine the torque command and speed command of the engine according to the output power allocated to the generator.

7. An energy management system based on a series hybrid electric propulsion system, characterized in that, Including: A data sample set acquisition module, configured to obtain a data sample set of the aircraft, where each sample data in the data sample set is historical flight data; the energy system of the aircraft adopts a series hybrid-electric propulsion system; A target flight mission determination module, configured to extract k flight missions from the historical flight data as target flight missions; each flight mission is represented by a feature vector composed of feature parameters, and the feature parameters are parameters in the historical flight data; An energy management strategy optimization module, configured to use the dynamic programming method to optimize the energy management strategy for each of the target flight missions respectively, obtain the energy management strategy corresponding to each target flight mission, and store each target flight mission and the corresponding energy management strategy in the energy management strategy library; each energy management strategy includes the engine output power and the energy storage battery pack output power; The current feature parameter acquisition module is used to acquire the current feature parameters of the aircraft; The current energy management strategy matching module is used to match, according to the current feature parameters, an energy management strategy corresponding to the current flight mission from the energy management strategy library as the current energy management strategy; The energy management strategy application module is used to perform energy management on the series hybrid electric propulsion system of the aircraft according to the current energy management strategy; The feature parameters include the vertical takeoff height, the fixed-wing climb rate, the cruise flight height, the cruise flight speed, the cruise flight distance, and the vertical descent height; Using the dynamic programming method to optimize the energy management strategy for each of the target flight missions respectively, obtaining the energy management strategy corresponding to each of the target flight missions, and storing the energy management strategy corresponding to each of the target flight missions into the energy management strategy library, specifically including: For the l th target flight mission, divide the entire flight process of the l th target flight mission into N phases with a set step size according to time sequence; Construct the minimum fuel consumption function from each stage to the end of the flight process of the l th target flight mission; According to the minimum fuel consumption function at the end of the flight process of each stage to the l th target flight mission, with the minimum total fuel consumption during the entire flight process of the l th target flight mission as the optimization objective, determine the energy management strategy for the entire flight process of the l th target flight mission; The minimum fuel consumption function for each stage until the end of the l flight mission of the th target flight mission is expressed as: ； ； Among them, represents the minimum fuel consumption function from the state variable i at the x ( i ) to the end of the flight process, represents the minimum fuel consumption function from the state variable i at the x ( i + 1) to the end of the flight process, represents the engine fuel consumption at the i stage, u i ( i ) represents the output current of the energy storage battery pack; ； ； P ICE ( i ) represents the engine output power, P batt ( i ) represents the output power of the energy storage battery pack, ts represents the single-stage time step, represents the generator efficiency.

Images