A method, device and electronic equipment for optimizing aircraft energy management strategy

Abstract

The embodiment of the present invention discloses an optimization method, device and electronic device for an aircraft energy management strategy. The method includes: allocating the load demand power of the aircraft according to the state machine energy management strategy, and obtaining the output power of the fuel cell power supply system and the lithium battery power supply system under the non-cruise condition of the aircraft; or, allocating the load demand power of the aircraft according to the improved Q-Learning energy management strategy, and obtaining the output power of the fuel cell power supply system and the lithium battery power supply system under the cruise condition of the aircraft; and then calculating the reference current output by the aircraft's energy management controller to the fuel cell converter and the lithium battery converter. Through the present invention, the technical problems of large amount of calculation and poor real-time performance caused by relying on lithium battery SOC estimation to implement energy management strategies in related technologies are solved, and the technical effects of reducing the amount of calculation, improving the energy utilization rate of the aircraft hybrid power supply system, and ensuring the safe and stable operation of the system are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of management and control of aircraft hybrid power supply systems, and in particular to an optimization method, device and electronic equipment for an aircraft energy management strategy. Background Art

[0002] At present, with the development of transportation electrification technology, electric propulsion aircraft has attracted the attention of academia and industry. Due to its low cost, low noise, low heat radiation and other characteristics, electric propulsion aircraft have begun to achieve good application results in transportation, exploration, security and other aspects. In order to further improve the energy efficiency of electric propulsion aircraft, reduce weight and reduce carbon emissions, clean energy such as hydrogen energy and solar energy have begun to be applied to the power system of electric propulsion aircraft. Among them, proton exchange membrane fuel cells are considered to be ideal power sources for electric propulsion aircraft due to their high efficiency, high energy density and zero emissions. However, proton exchange membrane fuel cells have the disadvantage of slow dynamic characteristics, so they need high power density energy assistance to form a hybrid power supply system. A reasonable design of the energy management strategy of the aircraft hybrid power supply system is the core guarantee to ensure the high-quality power output of the system and the safe operation of the machine.

[0003] At present, the energy management strategies of hybrid power supply systems can be divided into two categories: rule-based and optimization-based. The rule-based ones are easier to apply in practice due to their high stability and low computational burden. However, the current design of rule-based EMS mainly relies on the engineering experience of researchers. On the other hand, in terms of improving the performance of key system parameters, rule-based energy management strategies are usually weaker than optimization-based energy management strategies.

[0004] In order to better optimize the performance of fuel cells in terms of efficiency, life, economy, etc., the energy management strategy (EMS) based on optimization has attracted the attention of researchers. However, the current EMS design based on optimization is not easy to implement online in practical applications due to the complexity of the optimization target model and the high computational burden of the solution algorithm. At the same time, many EMS designs based on optimization only focus on improving the performance of fuel cells and ignore auxiliary energy. However, as an important component of the hybrid power supply system, the auxiliary energy outputs the instantaneous power required by the load, which is the key to the safe operation of the aircraft. Therefore, some studies on hybrid power supply systems are specifically aimed at maintaining the state of charge (SOC) of the auxiliary energy, and the computational burden generated by this is difficult to ignore. If it is directly applied to the design of energy management strategies, it will seriously affect the aircraft's requirements for high real-time performance of the algorithm.

[0005] With regard to the problems of large amount of calculation and poor real-time performance caused by relying on lithium battery SOC estimation to implement energy management strategies in the above-mentioned related technologies, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide an optimization method, device and electronic device for an aircraft energy management strategy, so as to at least solve the technical problems of large amount of calculation and poor real-time performance caused by relying on lithium battery SOC estimation to implement energy management strategy in related technologies.

[0007] According to one aspect of an embodiment of the present invention, there is provided a method for optimizing an aircraft energy management strategy, comprising: determining an operating state of the aircraft, wherein the operating state comprises at least one of the following: a non-cruise condition and a cruise condition; when the operating state is the non-cruise condition, performing load demand power allocation of the aircraft according to a state machine energy management strategy to obtain an output power of a fuel cell power supply system and an output power of a lithium battery power supply system; or, when the operating state is the cruise condition, performing load demand power allocation of the aircraft according to an improved Q-Learning energy management strategy to obtain an output power of the fuel cell power supply system and an output power of the lithium battery power supply system; and determining a reference current outputted by the aircraft's energy management controller to a fuel cell converter and a reference current of a lithium battery converter based on the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

[0008] Optionally, determining the operating state of the aircraft includes: judging whether the flight altitude of the aircraft is within a flight altitude range under a cruising condition; if the flight altitude is not within the flight altitude range, determining that the operating state is the non-cruise condition, wherein the non-cruise condition includes at least one of the following: take-off, climb, descent, landing; if the flight altitude is within the flight altitude range, determining that the operating state is the cruise condition.

[0009] Optionally, before determining the operating state of the aircraft, the method further includes: collecting the flight altitude and load power demand of the aircraft, and inputting the flight altitude and the load power demand into an energy management controller.

[0010] Optionally, before determining the operating status of the aircraft, the method further includes: determining the flight altitude range, the system rated cruise load demand power range and the system maximum load demand power of the aircraft under cruise conditions according to the mission profile of the aircraft.

[0011] Optionally, the load demand power of the aircraft is allocated according to the state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: setting the state machine energy management strategy according to the maximum load demand power of the system, wherein the state machine energy management strategy includes different aircraft load power levels and the fuel cell power supply system matching power and lithium battery power supply system matching power associated with each aircraft load power level; determining the aircraft load power level under the load demand power of the aircraft based on the state machine energy management strategy, and using the fuel cell power supply system matching power corresponding to the aircraft load power level as the fuel cell power supply system output power, and using the lithium battery power supply system matching power corresponding to the aircraft load power level as the lithium battery power supply system output power.

[0012] Optionally, the load demand power of the aircraft is allocated according to an improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: setting the improved Q-Learning energy management strategy according to the rated cruise load demand power range of the system, wherein the improved Q-Learning energy management strategy includes a State-Action matrix defined according to the rated cruise load demand power range of the system, a reward matrix vector calculated according to a reward function, and a Q matrix generated by an iteration; based on the Q matrix in the improved Q-Learning energy management strategy, an ε-greedy algorithm is used to determine the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

[0013] Optionally, after obtaining the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, the method further comprises: recording the output power of the lithium battery power supply system into a lithium battery power supply system output power vector.

[0014] Optionally, the reference current output by the energy management controller of the aircraft to the fuel cell converter and the reference current of the lithium battery converter are determined according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: obtaining the system bus voltage; calculating the reference current of the fuel cell converter according to the output power of the fuel cell power supply system and the system bus voltage; calculating the reference current of the lithium battery converter according to the output power of the lithium battery power supply system and the system bus voltage.

[0015] According to another aspect of an embodiment of the present invention, there is also provided an optimization device for an aircraft energy management strategy, comprising: a first determination module, used to determine the operating state of the aircraft, wherein the operating state comprises at least one of the following: non-cruise condition, cruise condition; an optimization module, used to, when the operating state is the non-cruise condition, perform load demand power distribution of the aircraft according to the state machine energy management strategy, and obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; or, when the operating state is the cruise condition, perform load demand power distribution of the aircraft according to the improved energy management strategy, and obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; a second determination module, used to determine the reference current output by the energy management controller of the aircraft to the fuel cell converter and the reference current of the lithium battery converter according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

[0016] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement any one of the method steps described above.

[0017] In an embodiment of the present invention, the operating state of the aircraft is determined, wherein the operating state includes at least one of the following: non-cruise condition, cruise condition; when the operating state is non-cruise condition, the load demand power of the aircraft is allocated according to the state machine energy management strategy, and the output power of the fuel cell power supply system and the output power of the lithium battery power supply system are obtained; or, when the operating state is cruise condition, the load demand power of the aircraft is allocated according to the improved Q-Learning energy management strategy, and the output power of the fuel cell power supply system and the output power of the lithium battery power supply system are obtained; according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, the reference current output to the fuel cell converter by the energy management controller of the aircraft and the reference current of the lithium battery converter are determined. That is to say, the energy management strategy of the embodiment of the present invention realizes the maintenance of the stability of the lithium battery energy storage level without online estimation, so that the fuel cell can always operate in its high efficiency range during the aircraft cruise phase, thereby solving the technical problems of large calculation amount and poor real-time performance caused by relying on lithium battery SOC estimation to realize energy management strategy in related technologies, and achieving the technical effect of reducing the amount of calculation, improving the energy utilization rate of the aircraft hybrid power supply system, and ensuring the safe and stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 A flowchart of a method for optimizing an aircraft energy management strategy provided by an embodiment of the present invention;

[0020] Figure 2 A topological structure diagram of an aircraft proton exchange membrane fuel cell-lithium battery hybrid power supply system provided in an embodiment of the present invention;

[0021] Figure 3 An aircraft mission profile analysis diagram provided by an embodiment of the present invention;

[0022] Figure 4 A flowchart of an improved Q-Learning algorithm power allocation strategy provided by an embodiment of the present invention;

[0023] Figure 5 A surface diagram of an improved State-Action matrix provided by an embodiment of the present invention;

[0024] Figure 6 An efficiency interval analysis diagram of a fuel cell power supply system provided by an embodiment of the present invention;

[0025] Figure 7 A hierarchical energy management strategy structure diagram provided by an embodiment of the present invention;

[0026] Figure 8 A schematic diagram of an optimization device for an aircraft energy management strategy provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second" and the like in the specification, claims and drawings of the present invention are used to distinguish different objects rather than to limit a specific order.

[0029] According to one aspect of an embodiment of the present invention, a method for optimizing an aircraft energy management strategy is provided, and the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 A flowchart of a method for optimizing an aircraft energy management strategy provided by an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0031] Step S102, determining the operating state of the aircraft, wherein the operating state includes at least one of the following: non-cruise operating state and cruise operating state;

[0032] The operating state of the above-mentioned aircraft is determined according to the flight altitude of the aircraft, wherein the flight altitude of the aircraft is also called the aircraft altitude. The above-mentioned non-cruise operating conditions include but are not limited to take-off, climb, descent and landing.

[0033] Step S104, when the operating state is a non-cruise condition, the load demand power of the aircraft is allocated according to the state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; or, when the operating state is a cruise condition, the load demand power of the aircraft is allocated according to the improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system;

[0034] In an optional implementation, different energy management strategies are selected according to the operating state of the aircraft, wherein the energy management strategies include but are not limited to state machine energy management strategies, improved Q-Learning energy management strategies, etc. For example, when the aircraft is operating in a non-cruise condition, the load demand power allocation is completed according to the state machine energy management strategy designed according to the system maximum load demand power; when the aircraft is operating in a cruise condition, the load demand power allocation is completed according to the improved Q-Learning energy management strategy designed according to the system rated cruise load demand power range.

[0035] Step S106, determining a reference current outputted from the aircraft's energy management controller to the fuel cell converter and a reference current outputted to the lithium battery converter according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

[0036] In an embodiment of the present invention, the operating state of the aircraft is determined; when the operating state is a non-cruise condition, the load demand power of the aircraft is allocated according to the state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; or, when the operating state is a cruise condition, the load demand power of the aircraft is allocated according to the improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, the reference current output to the fuel cell converter and the reference current of the lithium battery converter by the energy management controller of the aircraft are determined. In other words, the energy management strategy of the embodiment of the present invention realizes the maintenance of the stability of the lithium battery energy storage level without online estimation, so that the fuel cell can always operate in its high efficiency range during the aircraft cruise phase, thereby solving the technical problems of large calculation amount and poor real-time performance caused by relying on lithium battery SOC estimation to realize the energy management strategy in the related technology, and achieving the technical effect of reducing the amount of calculation, improving the energy utilization rate of the aircraft hybrid power supply system, and ensuring the safe and stable operation of the system.

[0037] It should be noted that the application scenarios of the above method include but are not limited to aircraft hybrid power supply systems, wherein the hybrid power supply system includes but is not limited to a fuel cell-lithium battery hybrid power supply system, and the fuel cell includes but is not limited to a proton exchange membrane hydrogen fuel cell, etc.

[0038] In an optional embodiment, determining the operating state of the aircraft includes: judging whether the flight altitude of the aircraft is within the flight altitude range under the cruising condition; if the flight altitude is not within the flight altitude range, determining that the operating state is a non-cruise condition, wherein the non-cruise condition includes at least one of the following: take-off, climb, descent, landing; if the flight altitude is within the flight altitude range, determining that the operating state is a cruise condition.

[0039] The flight altitude of the above aircraft is h, and the flight altitude range is [h cruising -m 1 ,h cruising +m 2 ].

[0040] In the specific implementation process, it is determined whether the flight altitude h of the aircraft is within the flight altitude range [h cruising -m 1 ,h cruising +m 2 ], when the aircraft is in non-cruise condition, that is, When the aircraft is in the cruising state, that is, h∈[h cruising -m 1 ,h cruising +m2 ].

[0041] In the above-mentioned embodiments of the present invention, the flight altitude of the aircraft can be used to quickly determine the operating state of the aircraft, that is, to determine whether the aircraft is in a cruising condition or a non-cruising condition.

[0042] In an optional implementation, before determining the operating state of the aircraft, the method further includes: collecting the flight altitude and load power requirement of the aircraft, and inputting the flight altitude and load power requirement into the energy management controller.

[0043] In the specific implementation process, before determining the operating state of the aircraft, the flight altitude h and the load demand power P of the aircraft in the operating state can be collected. load , the flight altitude h and the load power required P load Enter the energy management controller.

[0044] In an optional embodiment, before determining the operating status of the aircraft, the above method also includes: determining the flight altitude range of the aircraft under cruise conditions, the system rated cruise load demand power range and the system maximum load demand power according to the mission profile of the aircraft.

[0045] In the specific implementation process, before determining the operating state of the aircraft, the flight altitude range under the cruise condition can also be determined according to the aircraft mission profile [h cruising -m 1 ,h cruising +m 2 ], the system rated cruise load demand power range [P cruising -n 1 ,P cruising +n 2 ] and the system maximum load power requirement P max-load .

[0046] In an optional embodiment, the load demand power of the aircraft is allocated according to a state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: setting the state machine energy management strategy according to the maximum load demand power of the system, wherein the state machine energy management strategy includes different aircraft load power levels and the fuel cell power supply system matching power and lithium battery power supply system matching power associated with each aircraft load power level; determining the aircraft load power level under the aircraft load demand power based on the state machine energy management strategy, and using the fuel cell power supply system matching power corresponding to the aircraft load power level as the fuel cell power supply system output power, and using the lithium battery power supply system matching power corresponding to the aircraft load power level as the lithium battery power supply system output power.

[0047] In the specific implementation process, the state machine energy management strategy designed according to the system maximum load demand power can be used to complete the load demand power allocation. fc According to the load demand power P load Set to 1 / 5 (P max-load ), 2 / 5(P max-load ), 3 / 5(P max-load ), 4 / 5(P max-load ), P fc-max ; The corresponding lithium battery power supply system matching power P bat Then set it to load -1 / 5(P max-load ), P load -2 / 5(P max-load ), P load -3 / 5(P max-load ), P load -4 / 5(P max-load ), P load -P fc-max Then, the aircraft load power level under the aircraft load demand power is determined according to the state machine energy management strategy, and the fuel cell power supply system matching power corresponding to the aircraft load power level is used as the fuel cell power supply system output power, and the lithium battery power supply system matching power corresponding to the aircraft load power level is used as the lithium battery power supply system output power.

[0048] In the above-mentioned embodiment of the present invention, the output power of the fuel cell power supply system and the output power of the lithium battery power supply system in the non-cruise state of the aircraft can be accurately calculated through the state machine energy management strategy.

[0049] In an optional embodiment, the load demand power of the aircraft is allocated according to an improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: setting an improved Q-Learning energy management strategy according to the system rated cruise load demand power range, wherein the improved Q-Learning energy management strategy includes a State-Action matrix defined according to the system rated cruise load demand power range, a reward matrix vector calculated according to a reward function, and a Q matrix generated in an iterative manner; using an ε-greedy algorithm based on the Q matrix in the improved Q-Learning energy management strategy to determine the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

[0050] In the specific implementation process, the improved Q-Learning energy management strategy designed according to the system rated cruise load demand power range can be used to complete the load demand power allocation.

[0051] Furthermore, the State-Action matrix of Q-Learning is defined according to the system rated cruise load required power range; the reward matrix vector is defined according to the reward function R = f(P load ,P fc ,P bat )+f(P bati ,P bat ) is calculated; the Q matrix is ​​calculated according to NewQ(s,a)←Q(s,a)+α[R+γmax a Q(s′,a)-Q(s,a)] is iteratively generated, and the output power of the fuel cell power supply system and the lithium battery power supply system is determined by the ε-greedy algorithm based on the Q matrix.

[0052] The above-mentioned improved Q-Learning energy management strategy includes a Q-Learning algorithm.

[0053] Furthermore, in the Q-Learning algorithm reward function R,

[0054]

[0055] It is a random sampling of the elements in the output power vector Output_Mode of the lithium battery power supply system. The more Output_Mode elements there are, the more realistic it can reflect the changes in the output power of the lithium battery. In order to reduce the computational burden generated by the algorithm, the present invention randomly samples the elements in the Output_Mode vector to make them participate in the reward matrix calculation.

[0056] In the above-mentioned embodiment of the present invention, the output power of the fuel cell power supply system and the output power of the lithium battery power supply system in the cruising state of the aircraft can be accurately calculated through the improved Q-Learning energy management strategy.

[0057] In an optional implementation, after obtaining the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, the method further includes: recording the output power of the lithium battery power supply system into the output power vector of the lithium battery power supply system.

[0058] During the specific implementation process, if the operating state of the aircraft is a non-cruise condition, the load demand power allocation of the aircraft can be performed according to the state machine energy management strategy, and the output power of the fuel cell power supply system and the output power of the lithium battery power supply system are obtained, and then the output power of the lithium battery power supply system of the aircraft in the non-cruise state is recorded in the output power vector of the lithium battery power supply system; or, if the operating state of the aircraft is a cruise condition, the load demand power allocation of the aircraft can be performed according to the improved Q-Learning energy management strategy, and the output power of the fuel cell power supply system and the output power of the lithium battery power supply system are obtained, and then the output power of the lithium battery power supply system of the aircraft in the cruise state is recorded in the output power vector of the lithium battery power supply system.

[0059] In the above-mentioned embodiment of the present invention, by recording the output power of the lithium battery power supply system into the output power vector of the lithium battery power supply system, it is more convenient for subsequent processing of the output power of the lithium battery power supply system, such as displaying the output power of the lithium battery power supply system or calculating the reference current of the lithium battery converter corresponding to the output power of the lithium battery power supply system.

[0060] In an optional embodiment, the reference current output by the aircraft's energy management controller to the fuel cell converter and the reference current of the lithium battery converter are determined based on the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: obtaining the system bus voltage; calculating the reference current of the fuel cell converter based on the output power of the fuel cell power supply system and the system bus voltage; calculating the reference current of the lithium battery converter based on the output power of the lithium battery power supply system and the system bus voltage.

[0061] In the above-mentioned embodiment of the present invention, the output power of the fuel cell power supply system and the lithium battery power supply system divided by the system bus voltage can be used as the reference current output by the energy management controller to the fuel cell converter and the reference current of the lithium battery converter, thereby being able to achieve stable SOC control without estimating the lithium battery SOC and having good real-time performance. It should be noted that the above-mentioned lithium battery converter includes but is not limited to BOOST converter, BUCK converter, etc.

[0062] An optional embodiment of the present invention is described in detail below by taking a fuel cell-lithium battery hybrid power supply system as an example.

[0063] An energy management strategy for optimizing the efficiency of a fuel cell-lithium battery hybrid power supply system provided by an optional embodiment of the present invention includes the following steps:

[0064] Step 1: According to the mission profile of the aircraft, determine the flight altitude range under the cruise condition [h cruising -m 1 ,hcruising +m 2 ], the system rated cruise load demand power range [P cruising -n 1 ,P cruising +n 2 ] and the system maximum load power requirement P max-load ;

[0065] Step 2: Collect the flight altitude h and load power P of the aircraft under operation status load , the flight altitude h and the load power required P load Enter the energy management controller;

[0066] Step three, determine the aircraft's flight altitude h state.

[0067] When the aircraft is in non-cruise condition, When the aircraft is in the cruise condition, that is, h∈[h cruising -m 1 ,h cruising +m 2 ], proceed to step five.

[0068] Step 4: First, when the aircraft is operating in non-cruise conditions, the system will demand power P according to the maximum load. max-load The designed state machine energy management strategy completes the load demand power allocation. The matching power of the fuel cell power supply system and the corresponding matching power of the lithium battery power supply system are shown in Table 1. The output power of the lithium battery power supply system in the non-cruise state of the aircraft is recorded in the vector Output_Mode, and step six is ​​executed.

[0069] Step 5: When the aircraft is operating in the cruise condition, the system will be rated for cruise load and the required power range [p cruising -n 1 ,p cruising +n 2 ] designed an improved Q-Learning energy management strategy to complete the load demand power allocation. The State-Action matrix of Q-Learning is based on [P cruising -n 1 ,P cruising +n 2 ] definition, the reward matrix vector is defined according to the reward function Calculate, the Q matrix according to NewQ(s,a)←Q(s,a)+α[R+γmax aQ(s′,a)-Q(s,a)] is iterated, and the output power of the fuel cell power supply system and the lithium battery power supply system is determined by the ε-greedy algorithm according to the Q matrix. The output power of the lithium battery power supply system in the cruising state of the aircraft is recorded in the vector Output_Mode, and step six is ​​executed.

[0070] Step 6: Divide the obtained output power of the fuel cell power supply system and the lithium battery power supply system by the system bus voltage U bus , which is the reference current i output by the energy management controller to the fuel cell converter and the lithium battery converter fc andi bat .

[0071] Table 1 State machine energy management strategy

[0072]

[0073]

[0074] Note: P fc-max The maximum rated output power of the fuel cell.

[0075] Figure 2 A topological structure diagram of an aircraft proton exchange membrane fuel cell-lithium battery hybrid power supply system provided by an embodiment of the present invention, such as Figure 2 As shown, the energy source includes H 2 Hydrogen storage tank, power sources include fuel cells and lithium batteries, converters include fuel cell converters, BOOST converters and BUCK converters, and loads include aircraft loads.

[0076] Figure 3 An aircraft mission profile analysis diagram provided by an embodiment of the present invention is as follows: Figure 3 As shown in the figure, the aircraft take-off, climb, descent and landing conditions are defined as non-cruise conditions. The corresponding cruising condition flight altitude is 200±10m, and the load demand power is 600±100W. During the operation of the aircraft, the load power distribution will be realized according to the following method according to the flight altitude:

[0077]

[0078] The output power of the lithium battery power supply system obtained according to the state machine power allocation strategy will be recorded in the lithium battery power supply system output power vector Output_Mode. Figure 4 A flowchart of an improved Q-Learning algorithm power allocation strategy provided by an embodiment of the present invention, such as Figure 4As shown, the output power of the lithium battery power supply system obtained according to the improved Q-Learning algorithm power allocation strategy will also be recorded in the lithium battery power supply system output power vector Output_Mode. Therefore, the elements in the Output_Mode vector will be constructed in the following way,

[0079]

[0080] The improved Q-Learning algorithm process is:

[0081] First, the algorithm needs to define the State-Action matrix, that is,

[0082] PEMFC state =Pcruising-100W:step:Pcruising+100W

[0083] bat state =-50W:step:+50W

[0084] PEMFC action =-100W:step:+100W

[0085] bat action =-50W:step:+50W

[0086] Among them, PEMFC state is the fuel cell output power state matrix, bat state Output power state matrix for lithium battery, PEMFC action is the fuel cell output power action matrix, bat action The output power action matrix of the lithium battery. Therefore, the ±150W system output power variation range can meet the load demand power of 600±100W under the aircraft cruising condition. Figure 5 The surface diagram of an improved State-Action matrix provided by the embodiment of the present invention, the size of the matrix surface defined by the traditional method is as follows Figure 5 As shown in the middle surface, after improvement, it can be reduced to Figure 5 As shown in the shaded part, the computational burden of the algorithm is effectively reduced. Figure 6 An efficiency interval analysis diagram of a fuel cell power supply system provided by an embodiment of the present invention, such as Figure 6 As shown, the above fuel cell output power state matrix can correspond to the high efficiency range of the fuel cell power supply system in the system to improve the energy utilization rate of the aircraft hybrid power supply system.

[0087] Then, the algorithm needs to calculate the reward matrix for each state and action based on the reward function, that is,

[0088]

[0089] Among them, f(P Load ,P fc ,P bat ) is the power matching part, which indicates the value of each state and action for load power matching, that is,

[0090]

[0091] This is the lithium battery energy storage level maintenance part, which shows the impact of each state and action on the lithium battery energy storage level, that is,

[0092]

[0093]

[0094] Among them, α 1 and α 2 is the weight, and in the present invention, α 1 >α 2 The energy storage level can be maintained under the premise of matching the load demand power. 1 and 2 It is a constant to prevent calculation errors caused by a denominator of 0.

[0095] Finally, the algorithm Q matrix is ​​iteratively calculated using the following formula, and the final power allocation method is determined by the Q matrix and the ε-greedy algorithm.

[0096] NewQ(s,a)←Q(s,a)+α[R+γmax a Q(s′,a)-Q(s,a)]

[0097] Combining the above state machine power allocation strategy and the improved Q-Learning algorithm power allocation strategy, a hierarchical energy management strategy for aircraft hybrid power supply system is designed. Figure 7 A hierarchical energy management strategy structure diagram provided by an embodiment of the present invention, such as Figure 7 As shown, the hierarchical energy management strategy includes a first energy management strategy layer and a second energy management strategy layer, wherein energy management strategies at different layers implement load demand power distribution of the aircraft under different operating conditions.

[0098] In the above embodiment of the present invention, through the energy management strategy based on the online optimization of the improved Q-Learning algorithm, not only can the fuel cell always operate in its high efficiency range, but also the function of stabilizing the lithium battery energy storage level without estimating the lithium battery SOC is realized. Therefore, the above energy management strategy, as a system energy storage level maintenance energy management strategy with low computational burden provided by the present invention, can realize the SOC stability control without estimating the lithium battery SOC and has good real-time performance.

[0099] According to another aspect of the embodiments of the present invention, there is also provided an optimization device for an aircraft energy management strategy. Figure 8 A schematic diagram of an optimization device for an aircraft energy management strategy provided by an embodiment of the present invention, such as Figure 8 As shown, the aircraft energy management strategy optimization device includes: a first determination module 82, an optimization module 84, and a second determination module 86. The aircraft energy management strategy optimization device is described in detail below.

[0100] A first determination module 82 is used to determine the operating state of the aircraft, wherein the operating state includes at least one of the following: non-cruise condition and cruise condition; an optimization module 84 is connected to the above-mentioned first determination module 82, and is used to distribute the load demand power of the aircraft according to the state machine energy management strategy when the operating state is a non-cruise condition, and obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; or, when the operating state is a cruise condition, distribute the load demand power of the aircraft according to the improved Q-Learning energy management strategy, and obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; a second determination module 86 is connected to the above-mentioned optimization module 84, and is used to determine the reference current output by the energy management controller of the aircraft to the fuel cell converter and the reference current of the lithium battery converter according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

[0101] It should be noted that the above-mentioned modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above-mentioned modules can be located in the same processor; and / or the above-mentioned modules are located in different processors in any combination.

[0102] In an embodiment of the present invention, the optimization device of the aircraft energy management strategy adopts determining the operating state of the aircraft; when the operating state is a non-cruise condition, the load demand power of the aircraft is distributed according to the state machine energy management strategy, and the output power of the fuel cell power supply system and the output power of the lithium battery power supply system are obtained; or, when the operating state is a cruise condition, the load demand power of the aircraft is distributed according to the improved Q-Learning energy management strategy, and the output power of the fuel cell power supply system and the output power of the lithium battery power supply system are obtained; according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, the reference current output to the fuel cell converter and the reference current of the lithium battery converter by the energy management controller of the aircraft are determined. That is to say, the energy management strategy of the embodiment of the present invention realizes the maintenance of the stability of the lithium battery energy storage level without online estimation, so that the fuel cell can always operate in its high efficiency range during the aircraft cruise phase, thereby solving the technical problems of large calculation amount and poor real-time performance caused by relying on lithium battery SOC estimation to realize the energy management strategy in the related technology, and achieving the technical effect of reducing the calculation amount, improving the energy utilization rate of the aircraft hybrid power supply system, and ensuring the safe and stable operation of the system.

[0103] It should be noted here that the above-mentioned first determination module 82, optimization module 84 and second determination module 86 correspond to steps S102 to S106 in the method embodiment, and the examples and application scenarios implemented by the above-mentioned modules are the same as those of the corresponding steps, but are not limited to the contents disclosed in the above-mentioned method embodiment.

[0104] Optionally, the first determination module 82 includes: a judgment unit, used to judge whether the flight altitude of the aircraft is within the flight altitude range under the cruise condition; a first determination unit, used to determine that the operating state is a non-cruise condition if the flight altitude is not within the flight altitude range, wherein the non-cruise condition includes at least one of the following: take-off, climb, descent, landing; and a second determination unit, used to determine that the operating state is a cruise condition if the flight altitude is within the flight altitude range.

[0105] Optionally, the above-mentioned device also includes: a collection module, which is used to collect the flight altitude and load demand power of the aircraft before determining the operating status of the aircraft, and input the flight altitude and load demand power into the energy management controller.

[0106] Optionally, the above-mentioned device also includes: a third determination module, which is used to determine the flight altitude range of the aircraft under cruise conditions, the system rated cruise load demand power range and the system maximum load demand power according to the mission profile of the aircraft before determining the operating status of the aircraft.

[0107] Optionally, the above-mentioned optimization module 84 includes: a first setting unit, used to set the state machine energy management strategy according to the maximum load demand power of the system, wherein the state machine energy management strategy includes different aircraft load power levels and the fuel cell power supply system matching power and lithium battery power supply system matching power associated with each aircraft load power level; a first processing unit, used to determine the aircraft load power level under the aircraft load demand power based on the state machine energy management strategy, and use the fuel cell power supply system matching power corresponding to the aircraft load power level as the fuel cell power supply system output power, and use the lithium battery power supply system matching power corresponding to the aircraft load power level as the lithium battery power supply system output power.

[0108] Optionally, the above-mentioned optimization module 84 includes: a second setting unit, used to set an improved Q-Learning energy management strategy according to the system rated cruise load demand power range, wherein the improved Q-Learning energy management strategy includes a State-Action matrix defined according to the system rated cruise load demand power range, a reward matrix vector calculated according to the reward function, and a Q matrix generated by iteration; a second processing unit, used to determine the output power of the fuel cell power supply system and the output power of the lithium battery power supply system based on the Q matrix in the improved Q-Learning energy management strategy using an ε-greedy algorithm.

[0109] Optionally, the above device also includes: a recording module, which is used to record the output power of the lithium battery power system into the output power vector of the lithium battery power system after obtaining the output power of the fuel cell power system and the output power of the lithium battery power system.

[0110] Optionally, the second determination module 86 includes: an acquisition unit for acquiring the system bus voltage; a first calculation unit for calculating the reference current of the fuel cell converter based on the output power of the fuel cell power supply system and the system bus voltage; and a second calculation unit for calculating the reference current of the lithium battery converter based on the output power of the lithium battery power supply system and the system bus voltage.

[0111] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement any one of the above method steps.

[0112] The above one or more computer instructions can be run in a processor as a computer program, or can also be stored in a memory (or computer-readable medium), which includes permanent and non-permanent, removable and non-removable media. Information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0113] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for optimizing an aircraft energy management strategy, characterized in that: include: Determining an operating state of the aircraft, wherein the operating state includes at least one of the following: a non-cruise operating state and a cruise operating state; When the operating state is the non-cruise condition, the load demand power of the aircraft is allocated according to the state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; or, when the operating state is the cruise condition, the load demand power of the aircraft is allocated according to the improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; The load demand power of the aircraft is distributed according to the state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: The state machine energy management strategy is set according to the maximum load demand power of the system, wherein the state machine energy management strategy includes different aircraft load power levels and the fuel cell power supply system matching power and lithium battery power supply system matching power associated with each aircraft load power level; Determine the aircraft load power level under the aircraft load demand power based on the state machine energy management strategy, and use the fuel cell power supply system matching power corresponding to the aircraft load power level as the fuel cell power supply system output power, and use the lithium battery power supply system matching power corresponding to the aircraft load power level as the lithium battery power supply system output power; The load demand power of the aircraft is distributed according to the improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: The improved Q-Learning energy management strategy is set according to the system rated cruise load demand power range, wherein the improved Q-Learning energy management strategy includes a State-Action matrix defined according to the system rated cruise load demand power range, a reward matrix vector calculated according to a reward function, and a Q matrix generated by iteration; Based on the Q matrix in the improved Q-Learning energy management strategy, an ε-greedy algorithm is used to determine the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; The reference current outputted to the fuel cell converter and the reference current of the lithium battery converter by the energy management controller of the aircraft are determined according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

2. The method according to claim 1, characterized in that Determine the operational status of the aircraft, including: Determining whether the flight altitude of the aircraft is within the flight altitude range under the cruising condition; If the flight altitude is not within the flight altitude range, determining that the operating state is the non-cruise operating condition, wherein the non-cruise operating condition includes at least one of the following: take-off, climb, descent, and landing; If the flight altitude is within the flight altitude range, it is determined that the operating state is the cruise condition.

3. The method according to claim 2, characterized in that Before determining the operating state of the aircraft, the method further includes: The flight altitude and load power requirement of the aircraft are collected, and the flight altitude and load power requirement are input into an energy management controller.

4. The method according to claim 2, characterized in that: Before determining the operating state of the aircraft, the method further includes: According to the mission profile of the aircraft, the flight altitude range of the aircraft under the cruise condition, the system rated cruise load required power range and the system maximum load required power are determined.

5. The method according to claim 1, characterized in that After obtaining the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, the method further includes: The output power of the lithium battery power supply system is recorded in the lithium battery power supply system output power vector.

6. The method according to any one of claims 1 to 5, characterized in that Determining a reference current outputted from the energy management controller of the aircraft to the fuel cell converter and a reference current of the lithium battery converter according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, comprising: Get the system bus voltage; Calculating a reference current of the fuel cell converter according to the output power of the fuel cell power supply system and the system bus voltage; The reference current of the lithium battery converter is calculated based on the output power of the lithium battery power supply system and the system bus voltage.

7. An optimization device for an aircraft energy management strategy, characterized in that: include: A first determination module is used to determine the operating state of the aircraft, wherein the operating state includes at least one of the following: a non-cruise operating state and a cruise operating state; An optimization module is used to distribute the load demand power of the aircraft according to the state machine energy management strategy when the operating state is the non-cruise condition, and obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; or, when the operating state is the cruise condition, distribute the load demand power of the aircraft according to the improved Q-Learning energy management strategy, and obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; The load demand power of the aircraft is distributed according to the state machine energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: The state machine energy management strategy is set according to the maximum load demand power of the system, wherein the state machine energy management strategy includes different aircraft load power levels and the fuel cell power supply system matching power and lithium battery power supply system matching power associated with each aircraft load power level; Determine the aircraft load power level under the aircraft load demand power based on the state machine energy management strategy, and use the fuel cell power supply system matching power corresponding to the aircraft load power level as the fuel cell power supply system output power, and use the lithium battery power supply system matching power corresponding to the aircraft load power level as the lithium battery power supply system output power; The load demand power of the aircraft is distributed according to the improved Q-Learning energy management strategy to obtain the output power of the fuel cell power supply system and the output power of the lithium battery power supply system, including: The improved Q-Learning energy management strategy is set according to the system rated cruise load demand power range, wherein the improved Q-Learning energy management strategy includes a State-Action matrix defined according to the system rated cruise load demand power range, a reward matrix vector calculated according to a reward function, and a Q matrix generated by iteration; Based on the Q matrix in the improved Q-Learning energy management strategy, an ε-greedy algorithm is used to determine the output power of the fuel cell power supply system and the output power of the lithium battery power supply system; The second determination module is used to determine the reference current output by the energy management controller of the aircraft to the fuel cell converter and the reference current of the lithium battery converter according to the output power of the fuel cell power supply system and the output power of the lithium battery power supply system.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1 to 6.

Images