A power distribution optimization method for an aero-engine power distribution network

Abstract

The present application relates to the field of distributed control of aero-engines, and more particularly to a power distribution optimization method for a power distribution network of an aero-engine. The method comprises the following steps: establishing a mathematical model of an intelligent power distribution network of an aero-engine; solving the mathematical model by a multi-objective optimization algorithm to obtain a Pareto optimal solution set, which contains a series of selectable power distribution schemes; performing real-time detection on the working state of the engine, executing fault diagnosis on the power distribution network, and performing autonomous repair of the power distribution network when a fault occurs; and selecting an optimal power distribution scheme for a specific scenario from the Pareto optimal solution set in combination with the real-time working state of the engine, the fault diagnosis result of the power distribution network, and the autonomous repair scheme. The present application realizes intelligent optimization of the power distribution network of an aero-engine, can effectively improve the reliability, flexibility and long-term operation efficiency of the power distribution network, and is suitable for various operating scenarios of an aero-engine.

Description

Technical Field

[0001] This invention relates to the field of distributed control of aero-engines, and more specifically, to a power distribution network for aero-engines, particularly a power distribution optimization method for a distributed control wireless intelligent power distribution network. Background Technology

[0002] With the continuous advancement of aviation technology, the electrification level of aero engines is gradually increasing, and hybrid power systems have become an important direction for the future development of aero engines. Traditional aero engine power distribution networks mainly rely on centralized control, with a single energy source and fixed power distribution paths, making it difficult to adapt to the complex power distribution needs of multiple drive modes, multiple power sources, multiple electrical devices, and multiple energy conversion and transmission paths.

[0003] Traditional power distribution networks typically employ centralized control, which struggles to adapt to the dynamic demands of distributed power sources and multiple electrical devices, resulting in inefficient energy allocation. Existing power distribution networks lack sufficient fault detection and autonomous repair capabilities, often relying on manual intervention, leading to slow fault response times and low power supply reliability. Furthermore, existing power distribution networks struggle to achieve optimal energy allocation under different scenarios (such as taxiing, takeoff, and cruise). These limitations severely restrict the further development of aero-engine power distribution networks, especially in the context of hybrid power systems, making it difficult to meet complex power distribution requirements.

[0004] With the increasing demand for electricity from aircraft engines, the complexity of power distribution networks has increased significantly, creating an urgent need for an intelligent power distribution network that can flexibly cope with multiple energy sources and electricity demands. Summary of the Invention

[0005] The purpose of this invention is to provide a power distribution optimization method for aero-engine power distribution networks, which solves the problems of low flexibility, difficulty in adapting to the dynamic needs of distributed power sources and multiple electrical devices, slow fault response speed, and low power supply reliability of existing power distribution networks.

[0006] Another objective of this invention is to provide a power distribution optimization method for an aero-engine power distribution network, which solves the problem that existing power distribution networks are unable to achieve optimal energy allocation in different scenarios.

[0007] To achieve the above objectives, the present invention provides a power distribution optimization method for an aircraft engine power distribution network, wherein the aircraft engine power distribution network is a distributed control wireless intelligent power distribution network, comprising the following steps:

[0008] Step S1: Establish a mathematical model of the intelligent power distribution network for aero-engines;

[0009] Step S2: Solve the mathematical model using a multi-objective optimization algorithm to obtain a Pareto optimal solution set, which includes a series of selectable power distribution schemes;

[0010] Step S3: Real-time monitoring of engine operating status, fault diagnosis of power distribution network, and autonomous repair of power distribution network faults when a fault occurs;

[0011] Step S4: Combining the engine's real-time operating status, the power distribution network fault diagnosis results, and the fault self-repair scheme, select the optimal power distribution scheme for the current specific scenario from the Pareto optimal solution set.

[0012] In some embodiments, after step S4, the method further includes:

[0013] Step S5 involves storing, analyzing, and predicting the power distribution quality data during each aero-engine operation to optimize power distribution decisions.

[0014] In some embodiments, step S1 further includes:

[0015] Considering multiple cost objectives and electricity demand in different scenarios, the multiple cost objectives include at least the costs of power generation, energy storage, power scheduling within the engine, and interaction with the aircraft power supply.

[0016] Define design parameters, multi-objective functions, and boundary constraints of distributed power sources, and perform multi-objective optimization iterative solution design.

[0017] In some embodiments, the design parameters include at least the power supply and the power allocation ratio parameters for each electrical device;

[0018] The multi-objective function The corresponding expression is:

[0019]

[0020] in, Indicates the first A set of objective functions, wherein the objective functions include at least the power generation and energy storage cost, the dispatch interaction cost, and the continuous power supply capability;

[0021] The boundary constraints of the distributed power source include at least the upper and lower limits of output power, the upper and lower limits of output power ratio, and the upper and lower limits of output power change rate.

[0022] In some embodiments, step S2 further includes:

[0023] The Pareto optimal solution set is backed up, and power distribution schemes are selected and switched in specific scenarios.

[0024] In some embodiments, the real-time detection of the engine operating status in step S3 further includes:

[0025] Several fault detection points are set up for the power transmission lines and the power paths of each load device, and relevant power supply parameters are monitored in real time. The relevant power supply parameters include at least voltage, current, power and temperature.

[0026] In some embodiments, performing fault diagnosis on the power distribution network in step S3 further includes:

[0027] Combining star or bus-type distributed control power network topology, and based on the division of intelligent nodes and / or intelligent node areas, fault detection is divided into zones and circuits.

[0028] Inside the engine controller, fault diagnosis logic is executed to complete fault location model calculations and power node fault location.

[0029] Based on the engine's operating status and the health status assessment data of the power system, the model parameters and alarm thresholds are calculated and dynamically adjusted through pre-stored interpolation tables or adaptive models.

[0030] In some embodiments, the power distribution network faults in step S3 include voltage imbalance, current instability, and line area anomalies.

[0031] In some embodiments, the autonomous repair of the power distribution network fault when a fault occurs in step S3 further includes:

[0032] By executing control logic, the wireless intelligent power distribution network can perform fault repair operations to achieve autonomous repair of the power distribution network.

[0033] The fault repair operation includes at least the following: power node voltage and current adjustment, autonomous switching of redundancy power lines, and adjustment of line on / off status.

[0034] The autonomous repair of the power distribution network includes fault node isolation and power distribution network reconfiguration.

[0035] In some embodiments, the fault node isolation in step S3 further includes:

[0036] Based on the fault diagnosis results and the autonomous repair status of the power distribution network, for specific power distribution network fault states, the influence of relevant power supply and consumption modules on the multi-objective function is eliminated, and the multi-objective function and constraints are adjusted and updated in real time.

[0037] In some embodiments, the power distribution network reconfiguration in step S3 further includes:

[0038] Taking into account fault recovery speed, power loss and node voltage deviation, an objective function is constructed by assigning appropriate weights and performing weighted summation.

[0039] Genetic algorithms are used to search and solve historical experimental data to obtain fault recovery schemes, which are then used as training datasets.

[0040] The neural network model is trained using a training dataset to establish a nonlinear mapping relationship between distribution network faults, distribution network topology, and the optimal solution of distribution network reconfiguration schemes.

[0041] During actual engine operation, the neural network model is solved in real time based on the fault status of the power distribution network to obtain and execute a power distribution network reconfiguration scheme.

[0042] In some embodiments, step S4 further includes:

[0043] Based on the engine's current operating status and power demand, the objective function is adjusted according to weighted conditions, and the Pareto optimal solution set is recalculated to select the optimal power distribution scheme for the current specific scenario.

[0044] In some embodiments, step S5 further includes:

[0045] The power distribution quality data is used to generate event messages or non-event messages. The power distribution quality data includes statistical data on power distribution network faults and power supply quality, power supply decision quality, and fault diagnosis quality in each flight cycle.

[0046] After the message is generated, it is transmitted wirelessly from the aircraft to the ground during flight to enable real-time monitoring and management.

[0047] In some embodiments, step S5 further includes:

[0048] Quality management is performed on the power network sensor signals and decision-making, diagnosis, and reconstruction records during the flight cycle using a ground-based database.

[0049] The results of ground-based static algorithms are used to evaluate the quality of airborne dynamic power distribution and reconfiguration decisions, and to conduct power distribution network lifetime management and prediction.

[0050] This invention provides a power distribution optimization method for aero-engine power distribution networks. By establishing a mathematical model of the intelligent power distribution network, multi-objective optimization, real-time fault diagnosis and autonomous repair, and power distribution quality data storage analysis and health management prediction, it realizes intelligent optimization of the aero-engine power distribution network, which can effectively improve the reliability, flexibility and long-term operating efficiency of the power distribution network and is applicable to various operating scenarios of aero-engines. Attached Figure Description

[0051] The above and other features, properties and advantages of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings and embodiments, in which the same reference numerals always denote the same features, wherein:

[0052] Figure 1 A step diagram of a power distribution optimization method for an aero-engine power distribution network according to an embodiment of the present invention is disclosed;

[0053] Figure 2 A flowchart of a power distribution optimization method for an aero-engine power distribution network according to an embodiment of the present invention is disclosed. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0055] This invention proposes a power distribution optimization method for a distributed control wireless intelligent power distribution network for aero-engines. By considering the energy state of the power system and the power demand of each electrical accessory under different operating scenarios, the method rationally designs the power matching between the power system and the electrical accessories, realizes the design, selection and switching of power distribution schemes under specific scenarios, and can detect and autonomously repair faults in real time, ensuring highly reliable intelligent power supply.

[0056] Figure 1 The present invention discloses a step diagram of a power distribution optimization method for an aircraft engine power distribution network according to an embodiment of the present invention. The present invention proposes a power distribution optimization method for an aircraft engine power distribution network, wherein the aircraft engine power distribution network is a distributed control wireless intelligent power distribution network, and includes the following steps:

[0057] Step S1: Establish a mathematical model of the intelligent power distribution network for aero-engines;

[0058] Step S2: Solve the mathematical model using a multi-objective optimization algorithm to obtain a Pareto optimal solution set, which contains a series of selectable power distribution schemes;

[0059] Step S3: Real-time monitoring of engine operating status, fault diagnosis of power distribution network, and autonomous repair of power distribution network faults when a fault occurs;

[0060] Step S4: Combining the engine's real-time operating status, the power distribution network fault diagnosis results, and the fault self-repair status, select the optimal power distribution scheme for the current specific scenario from the Pareto optimal solution set.

[0061] Furthermore, after step S4, the method further includes:

[0062] Step S5 involves storing, analyzing, and predicting the power distribution quality data during each aero-engine operation to optimize power distribution decisions.

[0063] The present invention proposes a power distribution optimization method for aero-engine power distribution networks. The wireless intelligent power distribution network relies on distributed control and high-security wireless data transmission. Based on the mathematical model of aero-engine intelligent power distribution networks, the Pareto optimal solution set is obtained.

[0064] Based on the fault diagnosis results of the power distribution network obtained from various wireless transmission data, a target value for a fault node elimination algorithm is designed to solve for an efficient fault recovery scheme. Combining the detected current engine operating status, power distribution network fault diagnosis results, and the autonomous fault repair status of the power distribution network, and considering the power demand under the current scenario, a power distribution scheme with the optimal characteristics under the current state is comprehensively selected from the obtained Pareto optimal solution set. Furthermore, data storage and health trend analysis are performed on the power distribution quality of this wireless intelligent power distribution network during this engine operation to continuously optimize the power distribution decision algorithm.

[0065] Figure 2 A flowchart of a power distribution optimization method for an aero-engine power distribution network according to an embodiment of the present invention is disclosed below, which will be combined with Figure 1 and Figure 2 These steps are described in detail below. It should be understood that, within the scope of this invention, the above-described technical features of this invention and the technical features specifically described below (such as in the embodiments) can be combined and related to each other to form preferred technical solutions.

[0066] Step S1: Establish a mathematical model of the intelligent power distribution network for aero-engines;

[0067] In this embodiment, step S1 further includes:

[0068] Considering multiple cost objectives and electricity demand in different scenarios, the multiple cost objectives include at least the costs of power generation, energy storage, power scheduling within the engine, and interaction with the aircraft power supply.

[0069] The power requirements of equipment will change in different scenarios (such as takeoff, cruise, landing, etc.). The model needs to dynamically adjust the power distribution strategy according to the scenario.

[0070] Define design parameters, multi-objective functions, and boundary constraints of distributed power sources, and perform multi-objective optimization iterative solution design.

[0071] The design parameters include at least the power supply capacity and the power allocation ratio parameters for each electrical device:

[0072] The power supply refers to the power provided by each power source (such as engine generator, energy storage system, etc.);

[0073] The power allocation ratio of each electrical device refers to the power allocation ratio required by different electrical devices at a given time.

[0074] The multi-objective function The corresponding expression is:

[0075]

[0076] in, Indicates the first One objective function;

[0077] The objective function includes at least the power generation and energy storage cost, dispatch interaction cost, and continuous power supply capability.

[0078] The power generation and energy storage cost refers to the operating cost of the power generation and energy storage system.

[0079] The scheduling interaction cost refers to the cost of power scheduling and interaction with other power systems of the aircraft.

[0080] The continuous power supply capability refers to the ability of the power distribution network to continuously supply power under different scenarios.

[0081] The boundary constraints of the distributed power source include at least the upper and lower limits of output power, the upper and lower limits of output power ratio, and the upper and lower limits of output power change rate.

[0082] Output power upper and lower limit constraints are used to limit the output power range of distributed power sources to ensure that they operate between minimum and maximum power.

[0083] Output power ratio upper and lower limit constraints are used to limit the ratio range of distributed power supply output power to meet the needs of different electrical devices.

[0084] Upper and lower limits of output power change rate constraints are used to limit the rate of change of output power of distributed power sources and avoid the impact of power fluctuations on the stability of the power distribution network.

[0085] The aforementioned boundary constraints work together to ensure that distributed power sources operate within a safe and stable range, while also meeting the optimization requirements of the power distribution network.

[0086] Step S1 establishes a mathematical model of the intelligent power distribution network for aero-engines, defining multiple cost objectives, power demand scenarios, design parameters, objective functions, and constraints. This provides a theoretical framework and mathematical foundation for the optimization of the power distribution network, ensuring that the network can operate efficiently and reliably under different scenarios, and providing support for subsequent optimization, fault diagnosis, and power distribution scheme selection.

[0087] Step S2: Solve the mathematical model using a multi-objective optimization algorithm to obtain a Pareto optimal solution set, which contains a series of selectable power distribution schemes;

[0088] A multi-objective optimization algorithm is used to solve the mathematical model based on boundary constraints in order to obtain the Pareto optimal solution set.

[0089] Multi-objective optimization algorithms (such as NSGA-II, MOEA / D, etc.) are used to solve the mathematical model. These algorithms can optimize multiple objective functions simultaneously and generate a series of Pareto optimal solutions.

[0090] NSGA-II (Non-dominated sorting genetic algorithm II) is a multi-objective optimization algorithm based on genetic algorithms, while MOEA / D (decomposition-based multi-objective evolutionary algorithm) is a multi-objective optimization algorithm based on decomposition.

[0091] The Pareto optimal solution set contains a series of optimization schemes that weigh multiple objective functions, providing diverse options for power distribution networks. The corresponding expression is:

[0092]

[0093] in, Let be a q-dimensional design parameter vector. It is a multi-objective function.

[0094] After defining the design parameters, objective function, and constraints in step S1, a multi-objective optimization algorithm is used for iterative solution to obtain a series of Pareto optimal solutions, corresponding to the following expression:

[0095]

[0096] Each solution in the Pareto optimal solution set corresponds to a specific power distribution scheme, which can adapt to the power demand of the engine under different operating scenarios.

[0097] Step S2 further includes:

[0098] The Pareto optimal solution set is backed up, and power distribution schemes are selected and switched in specific scenarios.

[0099] By backing up the Pareto optimal solution set, the system can quickly select or switch power distribution schemes in specific scenarios, ensuring the flexibility and adaptability of the power distribution network.

[0100] In specific scenarios, the most suitable power distribution scheme is selected from the Pareto optimal solution set based on the engine's real-time operating status and power demand, and is dynamically switched when needed.

[0101] The purpose of step S2 is to provide multiple power distribution schemes for the power distribution network, ensure the optimal overall performance of the power distribution network, and provide support for subsequent power distribution scheme selection and switching.

[0102] Step S3: Real-time monitoring of engine operating status, fault diagnosis of power distribution network, and autonomous repair of power distribution network faults when a fault occurs;

[0103] Fault detection, diagnosis, and autonomous repair can significantly improve the reliability of the power distribution network and reduce the impact of faults on engine operation.

[0104] The real-time detection of the engine operating status in step S3 further includes:

[0105] Several fault detection points are set up for the power transmission lines and the power paths of each load device to monitor relevant power supply parameters in real time, so as to facilitate the design of power-on and periodic BIT (built-in self-test).

[0106] The relevant power supply parameters include at least voltage, current, power, and temperature, thereby enabling real-time monitoring of these parameters, and further including:

[0107] Check if the voltage is stable and if there is any voltage imbalance;

[0108] Check if the current is within the normal range and whether there is current instability;

[0109] Check whether the power supply meets the load requirements;

[0110] Check whether the temperature of the circuits and equipment is within a safe range.

[0111] In this embodiment, the monitored power supply parameters are sent to the engine controller in real time through a distributed control high-security wireless communication network, providing data support for fault diagnosis.

[0112] Step S3, which involves performing fault diagnosis on the power distribution network, further includes:

[0113] Step S311: Combining the star or bus type distributed control power network topology, based on the division of intelligent nodes and / or intelligent node areas, fault detection is divided into zones and circuits, which can quickly locate the area where the fault occurs.

[0114] Step S312: Inside the engine controller, execute the fault diagnosis logic to complete the fault location model calculation and power node fault location.

[0115] Step S313: Based on the engine's operating status and the health status assessment data of the power system, the model parameters and alarm thresholds are calculated and dynamically adjusted using a pre-stored interpolation table or adaptive model to ensure the accuracy and adaptability of fault diagnosis.

[0116] Among them, distribution network faults include voltage imbalance, current instability, and line area anomalies.

[0117] In step S311, in a star topology, all intelligent nodes (such as power supply nodes and electrical equipment nodes) are directly connected to a central controller (such as an engine controller). In a bus topology, all intelligent nodes are connected through a shared communication bus.

[0118] Based on a star or bus topology, the power distribution network is divided into multiple zones (such as power supply zones, equipment zones, etc.), with each zone having an independent fault detection point. This zoned and circuit-based design allows for rapid location of faults, reducing troubleshooting time.

[0119] In step S312, fault diagnosis logic is executed within the engine controller, and fault information is analyzed and calculated using a fault location model. The fault location model, based on the power distribution network topology, node states, and fault characteristics, can accurately locate the power node where the fault occurred.

[0120] In step S313, model parameters and alarm thresholds are calculated using a pre-stored interpolation table or adaptive model.

[0121] The pre-stored interpolation table, based on historical data and / or experimental data, pre-stores parameters and thresholds under different operating conditions for real-time retrieval.

[0122] The adaptive model dynamically adjusts parameters and thresholds based on real-time data to adapt to changes in the power distribution network.

[0123] In this embodiment, the autonomous repair of the power distribution network fault in step S3 when a fault occurs further includes:

[0124] By executing control logic, the wireless intelligent power distribution network can perform fault repair operations to achieve autonomous repair of the power distribution network.

[0125] The fault repair operation includes at least the following:

[0126] Power node voltage and current regulation refers to adjusting the voltage and current of the power node to restore them to normal.

[0127] Redundant power line autonomous switching means switching to the backup power line to ensure power supply continuity;

[0128] Adjusting the continuity of a line means disconnecting the faulty line to prevent the fault from spreading.

[0129] In this embodiment, the autonomous repair of the power distribution network includes fault node isolation and power distribution network reconfiguration.

[0130] In this embodiment, the fault node isolation in step S3 further includes:

[0131] Based on the fault diagnosis results and the autonomous repair status of the power distribution network, for specific power distribution network fault states, the influence of relevant power supply and consumption modules on the multi-objective function is eliminated, and the multi-objective function and constraints are adjusted and updated in real time to ensure the effectiveness of the optimization algorithm.

[0132] For example, if a power node fails and is isolated, the power supply capacity constraint of that node is removed from the optimization model.

[0133] The power distribution network reconfiguration in step S3 further includes:

[0134] Taking into account fault recovery speed, power loss and node voltage deviation, an objective function is constructed by assigning appropriate weights and performing weighted summation.

[0135] Genetic algorithms are used to search and solve historical experimental data to obtain fault recovery schemes, and the obtained fault recovery schemes are used as training datasets.

[0136] The neural network model is trained using a training dataset to establish a nonlinear mapping relationship between distribution network faults, distribution network topology, and the optimal solution of distribution network reconfiguration schemes.

[0137] During actual engine operation, the neural network model is solved in real time based on the fault status of the power distribution network to obtain and execute the optimal reconfiguration scheme for the power distribution network.

[0138] By employing the above steps and utilizing neural network models and genetic algorithms, efficient reconstruction schemes can be generated in a short time, meeting real-time requirements. Pre-training the model reduces computational complexity during actual operation and improves the system's response speed.

[0139] Step S3 ensures the high reliability and intelligent operation of the aero-engine power distribution network through real-time detection, fault diagnosis, and autonomous repair. Through fault detection, diagnosis, and autonomous repair, the reliability of the power distribution network can be significantly improved, and the impact of faults on engine operation can be reduced.

[0140] Step S4: Combining the engine's real-time operating status, the power distribution network fault diagnosis results, and the fault autonomous repair status, select the optimal power distribution scheme for the current specific scenario from the Pareto optimal solution set.

[0141] Step S4 further includes:

[0142] Based on the engine's current operating status and power demand, the objective function is adjusted according to weighted conditions, and the Pareto optimal solution set is recalculated to select the optimal power distribution scheme for the current specific scenario.

[0143] In this embodiment, the current power demand is obtained by combining the engine's operating status (such as taxiing, takeoff, climb, cruise, descent, etc.) obtained through real-time monitoring.

[0144] The power demand and requirements of the power distribution network vary depending on the engine's operating conditions.

[0145] For example, engines have high power supply requirements during takeoff and climb, so high power output needs to be prioritized.

[0146] When the engine is in cruise mode, the requirements for dispatching costs and energy consumption are high, and the costs of power generation and energy storage need to be optimized.

[0147] When the engine is descending or coasting, the power supply requirement is lower, and the power output can be appropriately reduced.

[0148] The multi-objective function is weighted and adjusted according to the power demand of the engine under the current operating conditions.

[0149] For example, the engine's power supply capability objective function is given a higher weight during takeoff and climb.

[0150] When the engine is in cruise mode, higher weights are assigned to the objective functions of scheduling cost and energy consumption.

[0151] The weighted objective function expression is as follows:

[0152] minf = ∝1f1 + ... + ∝ k f k

[0153] Among them, ∝ k The weights of the k-th objective function are f. k It is the kth objective function.

[0154] Based on the weighted adjusted objective function, the Pareto optimal solution set is recalculated to generate an optimized power distribution scheme suitable for the current scenario.

[0155] For different engine operating conditions (such as taxiing, takeoff, climb, cruise, and descent), an optimized power distribution scheme suitable for the current scenario is selected by comprehensively considering the requirements of power supply capacity, scheduling costs, energy consumption, and other objectives.

[0156] For example, during takeoff and climb, the power distribution scheme with the strongest power supply capacity is selected. During cruise, the power distribution scheme with the lowest scheduling cost and energy consumption is selected. Based on changes in operating conditions, the most suitable power distribution scheme is dynamically selected from the Pareto optimal solution set, and a switching operation is performed to ensure that the power distribution network can adapt to the engine's power demand under different operating conditions.

[0157] Step S5 involves storing, analyzing, and predicting the power distribution quality data during each aero-engine operation to optimize power distribution decisions.

[0158] Step S5 further includes:

[0159] Power distribution quality data will be used to generate event messages (such as when a fault occurs) or non-event messages (such as periodic statistical reports);

[0160] After the message is generated, it is transmitted wirelessly from the aircraft to the ground during flight to enable real-time monitoring and management.

[0161] The power distribution quality data includes power distribution network fault data, power supply quality data for each flight cycle, power supply decision quality data for each flight cycle, and fault diagnosis quality statistics for each flight cycle.

[0162] The message content includes the operating status of the power distribution network, fault information, power quality statistics, etc.

[0163] During flight, messages are wirelessly transmitted to the ground for real-time monitoring and management. Outside of flight, messages can be automatically transmitted either triggered by an event or after the flight cycle ends.

[0164] Step S5 further includes:

[0165] Quality management is performed on the power network sensor signals and decision-making, diagnosis, and reconstruction records during the flight cycle using a ground-based database.

[0166] The results of ground-based static algorithms are used to evaluate the quality of airborne dynamic power distribution and reconfiguration decisions, and to conduct power distribution network lifetime management and prediction.

[0167] Among them, the ground database refers to the system that stores and manages the operation data of the aircraft engine power distribution network in a ground computing environment;

[0168] Ground-based static algorithms are algorithms that run in a ground-based computing environment and are based on historical data and predefined rules. These algorithms are typically used to analyze, evaluate, and optimize operational data of aircraft engine power distribution networks. Unlike airborne dynamic algorithms, ground-based static algorithms do not rely on real-time data but rather process stored data offline after flight or periodically.

[0169] More specifically, based on historical and real-time data, predictive analysis is performed on the health status of the power distribution network. The predictions include:

[0170] Fault trends in power distribution networks;

[0171] The remaining lifespan of critical components (such as power nodes and lines);

[0172] Future trends in power quality.

[0173] The lifespan management and prediction further includes:

[0174] Based on the health management forecast results, develop a maintenance and replacement plan for the power distribution network;

[0175] Lifetime management extends the lifespan of power distribution networks and reduces maintenance costs.

[0176] Step S5 optimizes power distribution decisions and improves the reliability and intelligence of the power distribution network by storing, analyzing, and predicting the health of power distribution quality data.

[0177] This invention proposes a power distribution optimization method for an aero-engine power distribution network, which specifically has the following features:

[0178] Beneficial effects:

[0179] 1) A mathematical model of a smart power distribution network for aero-engines is built based on a distributed control high-security wireless communication network to ensure the security and reliability of data transmission in the power distribution network;

[0180] 2) Taking into account multiple cost objectives and electricity demand under different scenarios, we define the boundary constraints of distributed power sources, carry out iterative solution design of multi-objective optimization algorithms, solve the Pareto optimal solution set, and further solve the optimal solution under the weighted conditions of specific scenarios, so as to reduce the steps of manual participation in power distribution selection and improve the automation level of power distribution decision-making.

[0181] 3) Backup the optimal solution centralized power distribution scheme, select and switch power distribution schemes in specific scenarios, improve adaptability to various power supply scenarios, and enhance the flexibility and economy of the power distribution network;

[0182] 4) By detecting power supply-related parameters through a wireless communication network, when a fault occurs, it automatically performs repair operations such as voltage and current adjustment, autonomous line switching, and fault node isolation, thereby improving fault detection efficiency and flexibility and reducing the impact of faults on engine operation.

[0183] 5) Establish a data management system for distributed control power supply quality and power supply decision quality to ensure highly reliable intelligent power supply and continuously optimize power distribution decisions.

[0184] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0185] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include plural forms. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0186] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more, unless explicitly defined otherwise.

[0187] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0188] The above embodiments are provided for those skilled in the art to implement or use the present invention. Those skilled in the art can make various modifications or changes to the above embodiments without departing from the inventive concept of the present invention. Therefore, the protection scope of the present invention is not limited to the above embodiments, but should be the maximum scope that conforms to the innovative features mentioned in the claims.

Claims

1. A power distribution optimization method for an aircraft engine power distribution network, wherein the aircraft engine power distribution network is a distributed control wireless intelligent power distribution network, characterized in that, Includes the following steps: Step S1: Establish a mathematical model of the intelligent power distribution network for aero-engines; Step S2: Solve the mathematical model using a multi-objective optimization algorithm to obtain a Pareto optimal solution set, which includes a series of selectable power distribution schemes; Step S3: Real-time monitoring of engine operating status, fault diagnosis of power distribution network, and autonomous repair of power distribution network faults when a fault occurs; Step S4: Combining the engine's real-time operating status, the power distribution network fault diagnosis results, and the fault self-repair status, select the optimal power distribution scheme for the current specific scenario from the Pareto optimal solution set.

2. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, Following step S4, the following further steps are included: Step S5 involves storing, analyzing, and predicting the power distribution quality data during each aero-engine operation to optimize power distribution decisions.

3. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, Step S1 further includes: Considering multiple cost objectives and electricity demand in different scenarios, the multiple cost objectives include at least the costs of power generation, energy storage, power scheduling within the engine, and interaction with the aircraft power supply. Define design parameters, multi-objective functions, and boundary constraints of distributed power sources, and perform multi-objective optimization iterative solution design.

4. The power distribution optimization method for the aero-engine power distribution network according to claim 3, characterized in that, The design parameters include at least the power supply and the power allocation ratio parameters for each electrical device. The multi-objective function The corresponding expression is: in, Indicates the first A set of objective functions, wherein the objective functions include at least the power generation and energy storage cost, the dispatch interaction cost, and the continuous power supply capability; The boundary constraints of the distributed power source include at least the upper and lower limits of output power, the upper and lower limits of output power ratio, and the upper and lower limits of output power change rate.

5. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, Step S2 further includes: The Pareto optimal solution set is backed up, and power distribution schemes are selected and switched in specific scenarios.

6. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, The real-time detection of the engine operating status in step S3 further includes: Several fault detection points are set up for the power transmission lines and the power paths of each load device, and relevant power supply parameters are monitored in real time. The relevant power supply parameters include at least voltage, current, power and temperature.

7. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, Step S3, which involves performing fault diagnosis on the power distribution network, further includes: Combining star or bus-type distributed control power network topology, and based on the division of intelligent nodes and / or intelligent node areas, fault detection is divided into zones and circuits. Inside the engine controller, fault diagnosis logic is executed to complete fault location model calculations and power node fault location. Based on the engine's operating status and the health status assessment data of the power system, the model parameters and alarm thresholds are calculated and dynamically adjusted through pre-stored interpolation tables or adaptive models.

8. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, The power distribution network faults in step S3 include voltage imbalance, current instability, and line area anomalies.

9. The power distribution optimization method for an aero-engine power distribution network according to claim 3, characterized in that, Step S3, which involves autonomously repairing the power distribution network fault when a fault occurs, further includes: By executing control logic, the wireless intelligent power distribution network can perform fault repair operations to achieve autonomous repair of the power distribution network. The fault repair operation includes at least the following: power node voltage and current adjustment, autonomous switching of redundancy power lines, and adjustment of line on / off status. The autonomous repair of the power distribution network includes fault node isolation and power distribution network reconfiguration.

10. The power distribution optimization method for an aero-engine power distribution network according to claim 9, characterized in that, The fault node isolation in step S3 further includes: Based on the fault diagnosis results and the autonomous repair status of the power distribution network, for specific power distribution network fault states, the influence of relevant power supply and consumption modules on the multi-objective function is eliminated, and the multi-objective function and constraints are adjusted and updated in real time.

11. The power distribution optimization method for an aero-engine power distribution network according to claim 9, characterized in that, The power distribution network reconfiguration in step S3 further includes: Taking into account fault recovery speed, power loss and node voltage deviation, an objective function is constructed by assigning appropriate weights and performing weighted summation. A genetic algorithm is used to search and solve historical experimental data to obtain fault recovery schemes, and these schemes are used as training datasets. The neural network model is trained using a training dataset to establish a nonlinear mapping relationship between distribution network faults, distribution network topology, and the optimal solution of distribution network reconfiguration schemes. During actual engine operation, the neural network model is solved in real time based on the fault status of the power distribution network to obtain and execute a power distribution network reconfiguration scheme.

12. The power distribution optimization method for an aero-engine power distribution network according to claim 1, characterized in that, Step S4 further includes: Based on the engine's current operating status and power demand, the objective function is adjusted according to weighted conditions, and the Pareto optimal solution set is recalculated to select the optimal power distribution scheme for the current specific scenario.

13. The power distribution optimization method for an aero-engine power distribution network according to claim 2, characterized in that, Step S5 further includes: The power distribution quality data is used to generate event messages or non-event messages. The power distribution quality data includes statistical data on power distribution network faults and power supply quality, power supply decision quality, and fault diagnosis quality in each flight cycle. After the message is generated, it is transmitted wirelessly from the aircraft to the ground during flight to enable real-time monitoring and management.

14. The power distribution optimization method for an aero-engine power distribution network according to claim 2, characterized in that, Step S5 further includes: Quality management is performed on the power network sensor signals and decision-making, diagnosis, and reconstruction records during the flight cycle using a ground-based database. The results of ground-based static algorithms are used to evaluate the quality of airborne dynamic power distribution and reconfiguration decisions, and to conduct power distribution network lifetime management and prediction.

Images