Stratospheric airship operation control system, method, equipment, medium and product

Abstract

The invention discloses a stratospheric airship operation control system, method, device, medium and product, and relates to the technical field of stratospheric airship control, the system comprises a multi-source data fusion module, a fault diagnosis and fault tolerance control module, a multi-constraint intelligent planning and decision module and a central processing unit; the multi-source data fusion module fuses original data collected by multiple sensors, and determines an environment state variable estimation value by using an improved particle filtering method based on the fused data; the fault diagnosis and fault-tolerant control module performs fault diagnosis based on the environment state variable estimation value and the system operation data, and generates a fault-tolerant control strategy according to a comprehensive fault diagnosis result; the multi-constraint intelligent planning and decision-making module constructs a multi-system constraint model based on system operation data, and determines an optimal flight path in combination with a fault-tolerant control strategy; and generating an execution control instruction according to the optimal flight path to control the stratospheric airship. According to the invention, highly autonomous flight of the stratospheric airship in a complex environment can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of stratospheric airship control, and in particular to a stratospheric airship operation and control system, method, equipment, medium and product. Background Art

[0002] Stratospheric airships are reusable, powered, and controllable aircraft that do not require a pilot. They play an increasingly important role in fields such as geographic surveying and mapping, disaster monitoring, agricultural plant protection, and logistics distribution. However, traditional stratospheric airships usually require manual supervision and control, which not only increases labor costs, but also limits the working time and scope of the airship. Especially in some complex environments or long-term missions, manual supervision is difficult to meet actual needs.

[0003] For example, when conducting large-scale monitoring, traditional manual control methods cannot guarantee 24-hour uninterrupted monitoring, nor can they respond quickly to emergencies. Another example is that when conducting long-distance, high-risk tasks, manual remote control often faces problems such as communication delays and unstable signals, which seriously affect the efficiency and safety of task execution.

[0004] At present, although there are some autonomous flight systems, most of them have the following problems:

[0005] It is difficult to achieve intelligent planning and decision-making under multiple constraints, and the autonomy is insufficient. When performing flight planning, the existing system often only considers simple factors such as distance or time, and it is difficult to comprehensively consider multiple constraints, resulting in insufficient optimization of planning results and difficulty in adapting to complex and changing mission requirements.

[0006] Therefore, there is an urgent need for a highly autonomous stratospheric airship flight control system to solve the above problems and promote the further development and application of stratospheric airship technology. Summary of the invention

[0007] The purpose of this application is to provide a stratospheric airship operation and control system, method, equipment, medium and product to solve the problem that stratospheric airships cannot achieve highly autonomous flight in complex environments.

[0008] To achieve the above objectives, this application provides the following solutions:

[0009] In a first aspect, the present application provides a stratospheric airship operation and control system, the stratospheric airship operation and control system comprising: a multi-source data fusion module, a fault diagnosis and fault-tolerant control module, a multi-constraint intelligent planning and decision-making module, and a central processing unit;

[0010] The multi-source data fusion module is used to fuse the original data collected by multiple sensors to obtain fused data, and based on the fused data, determine the estimated value of the environmental state variable using an improved particle filtering method; the original data includes the distance, speed, imaging data, position information and attitude information of the stratospheric airship;

[0011] The central processing unit is connected to the multi-source data fusion module and the fault diagnosis and fault-tolerant control module respectively, and the central processing unit is used to receive the estimated value of the environmental state variable, and send the estimated value of the environmental state variable and the acquired stratospheric airship operation data to the fault diagnosis and fault-tolerant control module;

[0012] The fault diagnosis and fault-tolerant control module is used to perform fault diagnosis on the setting components in the stratospheric airship based on the estimated value of the environmental state variable and the stratospheric airship operation data, obtain a comprehensive fault diagnosis result, and generate a corresponding fault-tolerant control strategy according to the comprehensive fault diagnosis result; the fault-tolerant control strategy includes a mission degradation strategy, a control reconstruction strategy and an emergency landing strategy; the setting component includes a first component and a second component;

[0013] The central processing unit is also connected to the fault diagnosis and fault-tolerant control module, and is used to receive the fault-tolerant control strategy, and send the fault-tolerant control strategy and the stratospheric airship operation data to the multi-constraint intelligent planning and decision-making module;

[0014] The multi-constraint intelligent planning and decision module is connected to the central processing unit, and the multi-constraint intelligent planning and decision module is used to build a multi-system constraint model based on the stratospheric airship operation data, and determine the optimal flight trajectory of the stratospheric airship based on the multi-system constraint model and the fault-tolerant control strategy;

[0015] The central processing unit is also used to generate an execution control instruction according to the optimal flight trajectory, and send the execution control instruction to the flight control system of the stratospheric airship to control the stratospheric airship.

[0016] Optionally, the multi-source data fusion module includes:

[0017] A system error correction unit is connected to the multiple sensors and is used to perform system error correction on the raw data collected by the multiple sensors to obtain data after system error correction;

[0018] An installation error correction unit is connected to the system error correction unit and is used to perform installation error correction on the original data after the system error correction to obtain installation error corrected data;

[0019] A time series feature extraction unit, connected to the installation error correction unit, for extracting time series features from the data after the installation error correction to obtain time series features;

[0020] The fusion algorithm unit is connected to the time series feature extraction unit, and is used to obtain fusion data based on the time series features, and determine the estimated value of the environmental state variable based on the fusion data using an improved particle filtering method.

[0021] Optionally, the system error correction unit includes:

[0022] The distance error correction subunit of the laser radar is used to obtain the distance data measured by the laser radar and correct the distance data;

[0023] The speed error correction subunit of the millimeter wave radar is used to obtain speed data measured by the millimeter wave radar and correct the speed data;

[0024] An imaging error correction subunit of the optical camera and the infrared sensor, used to correct the imaging data of the optical camera and the infrared sensor;

[0025] The GPS / INS position and attitude error correction subunit is used to obtain the position information collected by the GPS and the attitude information collected by the INS, and perform error correction on the position information and the attitude information.

[0026] Optionally, the fault diagnosis and fault tolerance control module includes:

[0027] A fault feature extraction unit connected to the central processing unit, used to extract a fault feature set from the stratospheric airship operation data; the fault feature set includes a plurality of fault feature parameters;

[0028] A fault diagnosis unit is connected to the fault feature extraction unit and is used to input the fault feature set into a plurality of single fault type diagnosis models respectively to obtain corresponding fault diagnosis result prediction values; wherein the output fault diagnosis result prediction value of a single fault type diagnosis model corresponds to a fault type, and each of the single fault diagnosis models is obtained by training a support vector machine using training samples; the training samples include fault feature parameter sample values ​​and corresponding fault diagnosis result sample values;

[0029] A hybrid voting unit, connected to the fault diagnosis model, is used to obtain a comprehensive fault diagnosis result based on all fault diagnosis result prediction values ​​and corresponding preset weights;

[0030] A fault-tolerant control unit is connected to the hybrid voting unit and is used to generate a fault-tolerant control strategy according to the comprehensive fault diagnosis result.

[0031] Optionally, the fault-tolerant control unit includes:

[0032] a mission degradation strategy generating subunit, connected to the hybrid voting unit, for generating a mission degradation strategy to perform fault-tolerant control on the flight control system when the comprehensive fault diagnosis result indicates that the first component has failed;

[0033] a control reconstruction strategy generating subunit, connected to the hybrid voting unit, for updating the second component and performing fault diagnosis on the updated set component when the comprehensive fault diagnosis result indicates that the second component has a fault, thereby generating a fault-tolerant control strategy to perform fault-tolerant control on the flight control system;

[0034] The emergency landing strategy generating subunit is connected to the hybrid voting unit and is used to start the emergency landing procedure to perform fault-tolerant control on the flight control system when the comprehensive fault diagnosis result shows that the stratospheric airship cannot fly normally.

[0035] Optionally, the multi-constraint intelligent planning and decision-making module includes:

[0036] A constraint model building unit connected to the central processing unit, and used to build a multi-system constraint model based on the system operation data; the multi-system constraint model includes an energy constraint model, a heat constraint model, a time constraint model, a safety constraint model and a task constraint model;

[0037] A random sampling unit, configured to perform sampling in a state space to generate candidate path nodes; the state space is determined based on a state vector of the stratospheric airship and executable maneuvers;

[0038] a trajectory generation unit, connected to the central processing unit and the random sampling unit, respectively, for generating a plurality of candidate flight trajectories by using a fast random tree algorithm, based on the candidate path nodes and the fault-tolerant control strategy, and taking a multi-system constraint model as a constraint condition;

[0039] The evaluation and optimization unit is connected to the trajectory generation unit and is used to optimize multiple candidate flight trajectories using an ant colony algorithm, and evaluate the optimized flight trajectories to determine the optimal flight trajectory.

[0040] In a second aspect, the present application provides a stratospheric airship operation and control method, the stratospheric airship operation and control method is based on the stratospheric airship operation and control system, and the stratospheric airship operation and control method includes:

[0041] The raw data collected by multiple sensors are fused to obtain fused data, and based on the fused data, an estimated value of the environmental state variable is determined using an improved particle filter method; the raw data includes the distance, speed, imaging data, position information and attitude information of the stratospheric airship;

[0042] Based on the estimated value of the environmental state variable and the stratospheric airship operation data, a fault diagnosis is performed on the set component in the stratospheric airship to obtain a comprehensive fault diagnosis result, and a corresponding fault-tolerant control strategy is generated according to the comprehensive fault diagnosis result; the fault-tolerant control strategy includes a mission degradation strategy, a control reconstruction strategy and an emergency landing strategy; the set component includes a set first component and a second component;

[0043] constructing a multi-system constraint model based on the stratospheric airship operation data, and determining an optimal flight trajectory of the stratospheric airship based on the multi-system constraint model and the fault-tolerant control strategy;

[0044] A corresponding execution control instruction is generated according to the optimal flight trajectory, and the execution control instruction is sent to a flight control system so that the flight control system flies according to the execution control instruction.

[0045] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned stratospheric airship operation and control method.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned stratospheric airship operation and control method.

[0047] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the above-mentioned stratospheric airship operation and control method when executed by a processor.

[0048] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0049] The present application discloses a stratospheric airship operation and control system, method, device, medium and product. The stratospheric airship operation and control system includes a multi-source data fusion module, a fault diagnosis and fault-tolerant control module, a multi-constraint intelligent planning and decision-making module and a central processing unit. Among them, by setting up the multi-constraint intelligent planning and decision-making module, the stratospheric airship can achieve highly autonomous flight in a complex environment. Under the condition of considering multiple constraints, the optimal flight trajectory is autonomously generated to adapt to various complex mission requirements, thereby greatly improving the flexibility of mission execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 This is a schematic diagram of the functional modules of a stratospheric airship operation and control system in one embodiment of the present application;

[0052] Figure 2 A schematic diagram of a flow chart of a stratospheric airship operation and control method provided in one embodiment of the present application;

[0053] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.

[0054] Reference numerals:

[0055] Multi-source data fusion module 1, system error correction unit 11, installation error correction unit 12, time series feature extraction unit 13, fusion algorithm unit 14; fault diagnosis and fault-tolerant control module 2, fault feature extraction unit 21, fault diagnosis unit 22, hybrid voting unit 23, fault-tolerant control unit 24; multi-constraint intelligent planning and decision-making module 3 and central processing unit 4, constraint model establishment unit 41, random sampling unit 42, trajectory generation unit 43, evaluation and optimization unit 44. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] At present, the autonomous flight system of the stratospheric airship still has the following problems:

[0058] 1. Insufficient environmental perception capabilities, making it difficult to cope with complex and changing flight environments. Existing systems rely on single or limited sensors to perceive the environment. When faced with changes in lighting, weather, complex terrain, etc., perception errors or blind spots are prone to occur, affecting flight safety.

[0059] 2. Limited fault diagnosis and fault tolerance capabilities, and low system reliability. Most systems lack a comprehensive fault diagnosis mechanism, making it difficult to detect and handle potential system failures in a timely manner. At the same time, when faced with failures, there is a lack of effective fault-tolerant control strategies, which can easily lead to mission interruptions or flight accidents.

[0060] 3. Lack of unified system architecture, low integration of functional modules. Many systems are composed of multiple independent modules, and the coordination ability between modules is insufficient, making it difficult to achieve true intelligence and autonomy.

[0061] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0062] In an exemplary embodiment, Figure 1 As shown, a stratospheric airship operation and control system is provided, comprising: a multi-source data fusion module 1, a fault diagnosis and fault-tolerant control module 2, a multi-constraint intelligent planning and decision-making module 3 and a central processing unit 4.

[0063] The multi-source data fusion module 1 is used to fuse the original data collected by multiple sensors to obtain fused data, and based on the fused data, determine the estimated value of the environmental state variable using an improved particle filtering method; the original data includes the distance, speed, imaging data, position information and attitude information of the stratospheric airship.

[0064] Specifically, the multi-source data fusion module 1 is the "perception center" of the operation and control system, which is used to fuse data from multiple sensors such as lidar, millimeter-wave radar, optical camera, infrared sensor, GPS / INS, etc. to build an accurate flight environment model. Through the data fusion algorithm, this module can build a high-precision and high-robustness flight environment model to provide reliable environmental information for system decision-making and control.

[0065] The central processing unit 4 is connected to the multi-source data fusion module 1 and the fault diagnosis and fault-tolerant control module 2 respectively, and the central processing unit 4 is used to receive the estimated values ​​of the environmental state variables, and send the estimated values ​​of the environmental state variables and the acquired stratospheric airship operation data to the fault diagnosis and fault-tolerant control module 2. As the "general commander" of the operation and control system, the central processing unit 4 is responsible for coordinating the work of the above-mentioned functional modules and executing the overall control logic. It receives information from each module, conducts comprehensive analysis and decision-making, and sends control instructions to each actuator of the aircraft. It adopts a multi-core processor architecture, has powerful parallel processing capabilities, and can process large amounts of data in real time and respond quickly. The main functions of the central processing unit 4 include:

[0066] 1) Task management: Receive and parse task instructions, and break down high-level tasks into specific execution steps.

[0067] 2) Resource scheduling: Rationally allocate computing resources and storage resources based on task requirements and system status.

[0068] 3) Module coordination: Coordinate the work of each functional module to ensure timely interaction and consistency of information.

[0069] 4) Decision execution: Make the final decision based on the output of each module and send instructions to the corresponding executive agency.

[0070] 5) Communication management: responsible for communication with ground stations or other aircraft to realize data transmission and command reception.

[0071] 6) Log recording: record system operation status and key events to provide a basis for subsequent analysis and optimization.

[0072] The fault diagnosis and fault-tolerant control module 2 is used to perform fault diagnosis on the set components in the stratospheric airship based on the estimated value of the environmental state variable and the stratospheric airship operation data, obtain a comprehensive fault diagnosis result, and generate a corresponding fault-tolerant control strategy according to the comprehensive fault diagnosis result; the fault-tolerant control strategy includes a mission degradation strategy, a control reconstruction strategy and an emergency landing strategy; the set components include a first component and a second component. The first component refers to some non-critical components, such as a non-essential sensor; the second component refers to a critical component, such as a motor or a steering gear.

[0073] Specifically, the fault diagnosis and fault-tolerant control module 2 serves as the "health manager" of the operation and control system. It is used to monitor the operating status of each component of the system in real time, identify and process multi-parameter and multi-faults that may occur in the system. Through advanced fault diagnosis algorithms and fault-tolerant control strategies, this module can significantly improve the safety and reliability of the system, ensuring that the aircraft can maintain stable operation in the face of various abnormal situations.

[0074] The central processing unit 4 is also connected to the fault diagnosis and fault-tolerant control module 2 for receiving the fault-tolerant control strategy, and sending the fault-tolerant control strategy and the stratospheric airship operation data to the multi-constraint intelligent planning and decision-making module 3 .

[0075] The multi-constraint intelligent planning and decision module 3 is connected to the central processing unit 4, and the multi-constraint intelligent planning and decision module 3 is used to build a multi-system constraint model based on the stratospheric airship operation data, and determine the optimal flight trajectory of the stratospheric airship based on the multi-system constraint model and the fault-tolerant control strategy.

[0076] Specifically, the multi-constraint intelligent planning and decision module 3 is the "decision center" of the operation and control system, which is used to realize the intelligent path planning and mission decision of the airship under the multi-system constraint conditions. Through the optimization algorithm, this module can generate the optimal flight trajectory and mission execution plan for the airship.

[0077] The central processing unit 4 is further used to generate an execution control instruction according to the optimal flight trajectory, and send the execution control instruction to the flight control system of the stratospheric airship to control the stratospheric airship.

[0078] As an optional implementation, the multi-source data fusion module 1 adopts a Bayesian network framework, and the multi-source data fusion module 1 includes:

[0079] The system error correction unit is connected to the multiple sensors and is used to perform system error correction on the raw data collected by the multiple sensors to obtain data after system error correction. The system error correction unit defines data models from different sensors, including probability distribution characteristics of various sensor data.

[0080] The installation error correction unit 12 is connected to the system error correction unit and is used to perform installation error correction on the original data after the system error correction to obtain the installation error corrected data. The installation error correction unit 12 provides the prior distribution of the model parameters, such as the installation error distribution of the sensor, the prior knowledge of the system noise level, and the parameter distribution of the influence of environmental factors (such as temperature and humidity) on the sensor performance.

[0081] The time series feature extraction unit 13 is connected to the installation error correction unit 12, and is used to extract the time series features of the data after the installation error correction to obtain the time series features. The time series features extracted by the time series feature extraction unit 13 reflect the time evolution law of the environmental state, including but not limited to: 1) target motion model: describing the motion characteristics of dynamic targets in the environment; 2) weather change model: simulating the impact of weather conditions on sensor performance; 3) environmental dynamic change model: describing the change law of other elements in the environment (such as vegetation, buildings, etc.).

[0082] The fusion algorithm unit 14 is connected to the time series feature extraction unit 13, and is used to obtain fusion data based on the time series features, and based on the fusion data, use the improved particle filtering method to determine the estimated value of the environmental state variable. The fusion algorithm unit 14 uses an improved particle filtering method to realize the automatic calibration, association and optimization combination of heterogeneous sensor data, and finally obtains the estimated value of the environmental state variable. The improved particle filtering algorithm can effectively handle the complex situations of nonlinear and non-Gaussian distribution by maintaining a set of weighted particles to represent the posterior probability distribution of the system state; the algorithm also introduces an adaptive resampling strategy to effectively solve the particle degradation problem and improve the accuracy and stability of the estimation. Finally, the fusion algorithm unit 14 outputs high-precision and high-reliability estimated values ​​of the environmental state variables, providing a solid foundation for the decision-making and control of the operation and control system. The specific steps are as follows:

[0083] a) Particle initialization: Initialize a set of weighted particles based on prior knowledge, where each particle represents a possible system state.

[0084] b) Prediction: Predict the state of each particle and simulate the state evolution of the system.

[0085] c) Update:

[0086] 1) Calculate the likelihood probability of each particle.

[0087] 2) Update particle weights according to likelihood probability.

[0088] 3) Normalize particle weights.

[0089] d) Resampling: Introduce an adaptive resampling strategy to solve the problem of particle degradation. When the number of valid particles is less than the threshold, resampling is performed.

[0090] e) State estimation: The a posteriori estimate of the system state is calculated based on the weighted average of the particles, that is, the estimated value of the environmental state variable is obtained.

[0091] f) Return to step b) for the next iteration.

[0092] As an optional implementation, the system error correction unit includes:

[0093] The distance error correction subunit of the laser radar is used to obtain the distance data measured by the laser radar and correct the distance data.

[0094] The speed error correction subunit of the millimeter wave radar is used to obtain speed data measured by the millimeter wave radar and correct the speed data.

[0095] The imaging error correction subunit of the optical camera and the infrared sensor is used to correct the imaging data of the optical camera and the infrared sensor.

[0096] The GPS / INS position and attitude error correction subunit is used to obtain the position information collected by the GPS and the attitude information collected by the INS, and perform error correction on the position information and the attitude information.

[0097] As an optional implementation, the fault diagnosis and fault tolerance control module 2 includes:

[0098] The fault feature extraction unit 21 is connected to the central processing unit 4 and is used to extract a fault feature set from the stratospheric airship operation data; the fault feature set includes multiple fault feature parameters; the fault feature parameters include vibration features (i.e., vibration spectrum), temperature features (i.e., temperature change trend), current features (i.e., motor current waveform) and communication quality indicators, etc. Fault feature extraction uses methods such as wavelet transform and principal component analysis to improve the distinguishability and anti-noise ability of fault features.

[0099] The fault diagnosis unit 22 is connected to the fault feature extraction unit 21, and is used to input the fault feature set into multiple single fault type diagnosis models respectively to obtain corresponding fault diagnosis result prediction values; wherein, the output fault diagnosis result prediction value of a single fault type diagnosis model corresponds to a fault type, and each of the single fault diagnosis models is obtained by training a support vector machine with training samples; the training samples include fault feature parameter sample values ​​and corresponding fault diagnosis result sample values.

[0100] Specifically, a single fault diagnosis model is constructed for each possible fault type (such as motor failure, sensor failure, communication failure, etc.), and the fault diagnosis unit 22 adopts deep learning, support vector machine and other algorithms, and is pre-trained using a large amount of historical data and simulation data, so that it can identify various common faults and rare faults, thereby improving the accuracy and real-time performance of fault diagnosis.

[0101] Assume a fault feature set P i ={p i1 ,…,p ia ,…,p ik} with a fault f i is related, θ i is the fault characteristic parameter p i The threshold value of the fault characteristic parameter p ia Define a fault signal δ ia (p ia The expected output and actual output are d ia ,y ia ):

[0102]

[0103] Considering the mutual influence between fault characteristic parameters, the fault f i The necessary condition for occurrence Ci is defined as:

[0104]

[0105] Among them, || || represents the norm. p i1 Indicates P iThe first fault characteristic parameter in ia Indicates P i The ath fault characteristic parameter in ik Indicates P i The kth fault characteristic parameter in .

[0106] By using the support vector machine to establish multiple single fault diagnosis models for the historical data of the fault feature set of the stratospheric airship (i.e., the fault feature parameter sample values ​​and the corresponding fault diagnosis result sample values), each single fault diagnosis model is used to make category judgments on the newly acquired historical data of the airship, and the judgment results of each single fault diagnosis model on the category to which the new data belongs are combined to obtain higher fault identification performance. Different single fault diagnosis models have different contribution rates to the final fault judgment, so it is necessary to set the weight of each single fault diagnosis model:

[0107] Assume a single fault diagnosis model M i The classification error rate is q i , then the weight value w of the single fault diagnosis model i Calculated using the following formula:

[0108]

[0109] The SVM algorithm is mainly divided into two stages, namely, fault feature parameter extraction and model training. Fault feature parameter extraction is to determine the correlation between the fault and the fault feature set. Assume that the fault f i , whose fault feature set is P j , single fault diagnosis model M i Only using the fault signature set P i data to train, so as to reduce the interference of irrelevant parameters on model building.

[0110] The mixed voting unit 23 is connected to the fault diagnosis model establishment unit and is used to obtain a comprehensive fault diagnosis result based on all fault diagnosis result prediction values ​​and corresponding preset weights. The fault diagnosis result prediction values ​​of each single fault diagnosis model are combined, and the corresponding preset weights are determined by weighted voting, fuzzy reasoning and other methods to obtain the final comprehensive fault diagnosis result.

[0111] Specifically, the hybrid voting unit 23 adopts the Dempster-Shafer evidence theory, which can effectively deal with the uncertainty and conflict of the outputs of different diagnosis models and improve the reliability of the overall diagnosis.

[0112] The fault-tolerant control unit 24 is connected to the hybrid voting unit 23 and is used to generate a fault-tolerant control strategy according to the comprehensive fault diagnosis result to ensure the safe and reliable operation of the operation control system.

[0113] As an optional implementation manner, the fault-tolerant control unit 24 includes:

[0114] The mission degradation strategy generation subunit is connected to the hybrid voting unit 23 and is used to generate a mission degradation strategy to perform fault-tolerant control on the flight control system when the comprehensive fault diagnosis result is that the first component fails.

[0115] Specifically, when a failure of the first component, i.e., a non-critical component, is detected, the operation control system will automatically reduce the mission requirements to ensure that the core mission can be completed safely. The specific implementation includes: reducing the flight speed and maneuverability requirements, reducing the mission coverage, and simplifying the data collection and processing process.

[0116] For example, if a non-essential sensor fails, the operation and control system may reduce the accuracy requirements of environmental perception while still ensuring basic obstacle avoidance capabilities.

[0117] The control reconstruction strategy generation subunit is connected to the hybrid voting unit 23 and is used to update the second component when the comprehensive fault diagnosis result is that the second component has a fault, and to perform fault diagnosis on the updated set component, thereby generating a fault-tolerant control strategy to perform fault-tolerant control on the flight control system.

[0118] Specifically, when the second component, i.e., the key executive component (such as a motor or a steering gear), fails, the operation control system will reallocate the power and control strategy of the remaining executive components to maintain flight stability. The implementation methods include: dynamically adjusting the control allocation matrix, modifying the control law parameters, and enabling the backup control mode.

[0119] For example, when a motor failure is detected, the operation and control system will reallocate the power of the remaining motors and adjust the flight attitude to maintain balance.

[0120] The emergency landing strategy generation subunit is connected to the hybrid voting unit 23 and is used to start the emergency landing procedure when the comprehensive fault diagnosis result shows that the stratospheric airship cannot fly normally, so as to perform fault-tolerant control on the flight control system.

[0121] Specifically, the steps include:

[0122] 1) Quickly assess the surrounding environment and select the best landing point.

[0123] 2) Plan the safest descent trajectory.

[0124] 3) Adjust the flight attitude to minimize the impact.

[0125] 4) Continuously monitor and adjust during the landing process to deal with possible risks.

[0126] As an optional implementation, the multi-constraint intelligent planning and decision-making module 3 includes:

[0127] The constraint model building unit 41 is connected to the central processing unit 4 and is used to build a multi-system constraint model based on the system operation data; the multi-system constraint model includes an energy constraint model, a heat constraint model, a time constraint model, a safety constraint model and a task constraint model, and comprehensively builds constraints such as energy consumption, heat balance, flight time, safe flight, and task priority. Among them, the energy constraint model is established, taking into account factors such as battery capacity, solar charging efficiency, and power consumption; the heat constraint model is established, taking into account the heat dissipation characteristics of each component and the change of ambient temperature; the time constraint model is established to meet the time requirements for task completion; the safety constraint model is established, taking into account no-fly zones, obstacles, etc.; the task constraint model is established to meet the coverage, sampling density, and other requirements of specific tasks.

[0128] Specifically, the energy constraint model is: E sy =E sc -E xh , where E sy is the remaining energy, E sc To generate energy, E xh The remaining energy E is consumed sy Minimum value requirements should be met.

[0129] The heat constraint model is: R sy =R sc -R xh , where R sy is the residual heat, R sc To generate heat, R xh To consume heat, the remaining heat R sy Should not exceed the maximum requirement.

[0130] The time constraint model is: t xh >t jh , where t xh The time consumed by the whole process should be less than the required time t jh .

[0131] The safety constraint model is: Φ xj <Φ gh , where Φ xj is the actual position, Φ gh A safe position within the constraints.

[0132] The task constraint model is: sj <Π rw , where Π sj is the actual task execution situation, rw For task constraints.

[0133] The random sampling unit 42 is used to perform sampling in the state space to generate candidate path nodes; the state space is determined based on the state vector of the stratospheric airship and the executable maneuvering operations; and the sampling efficiency is improved by performing intelligent random sampling in the state space. Specifically, as follows:

[0134] State space definition:

[0135] Define the state vector of the airship, including position, velocity, attitude, energy level, etc.

[0136] Define the action space, including the maneuvers the airship can perform.

[0137] Random Sampling:

[0138] Intelligent random sampling is performed in the state space to generate candidate nodes.

[0139] An adaptive sampling strategy is adopted to dynamically adjust the sampling density according to the complexity of the environment and task requirements.

[0140] Leverage heuristic information to guide sampling, such as avoiding obstacles using potential field methods.

[0141] The trajectory generation unit 43 is connected to the central processing unit 4 and the random sampling unit 42 respectively, and is used to generate multiple candidate flight trajectories based on the candidate path nodes and the fault-tolerant control strategy using a fast random tree algorithm and a multi-system constraint model as a constraint condition.

[0142] The specific steps include:

[0143] Starting from the starting state, the random tree is expanded step by step.

[0144] For each newly sampled node, try to connect to it from the nearest existing node.

[0145] Use spline curves to connect the nodes to ensure that the generated flight trajectory meets the dynamic constraints of the airship.

[0146] Apply trajectory smoothing technology to reduce unnecessary energy loss.

[0147] Constraint Check:

[0148] Constraint checks are performed on the generated trajectory segments, including:

[0149] Energy constraint: Ensure that the airship has enough energy throughout the flight trajectory.

[0150] Thermal constraints: Verify that the temperature of each component is within a safe range.

[0151] Time constraint: Check whether the flight trajectory meets the mission time requirement.

[0152] Safety constraints: Ensure that the flight trajectory avoids no-fly zones and obstacles.

[0153] Mission constraints: Verify that the flight trajectory meets the coverage and sampling density requirements.

[0154] Cost calculation:

[0155] The cost is calculated for the flight trajectory segment that satisfies the constraints, taking into account factors such as energy consumption, mission completion, safety margin, and time efficiency.

[0156] Tree expansion:

[0157] If the newly generated flight trajectory segment satisfies all constraints, it is added to the random tree.

[0158] Stop tree expansion if a preset number of nodes or computation time limit is reached.

[0159] The evaluation and optimization unit 44 is connected to the trajectory generation unit 43 and is used to optimize multiple candidate flight trajectories using an ant colony algorithm, and evaluate the optimized flight trajectories to determine the optimal flight trajectory, that is, to perform multi-objective evaluation on multiple candidate trajectories and select the optimal solution through a heuristic algorithm.

[0160] The steps of optimizing multiple candidate flight trajectories using the ant colony algorithm are as follows:

[0161] 1) Search for a feasible path from the starting point to the goal in the random tree.

[0162] 2) Use the improved ant colony algorithm to optimize the feasible path:

[0163] 3) Initialize multiple "ants" (candidate solutions).

[0164] 4) Each ant moves on the path and chooses the next step based on the heuristic information and pheromone concentration.

[0165] 5) Update the pheromone concentration on the path.

[0166] Repeat steps 4)-5) until convergence or the upper limit of iteration number is reached.

[0167] Trajectory Assessment:

[0168] Perform a final evaluation of the optimized flight trajectory to ensure that all constraints are met.

[0169] Calculate the comprehensive performance indicators of the flight trajectory, including energy efficiency, mission completion, safety, etc.

[0170] Result output:

[0171] Output the optimal flight trajectory, including:

[0172] Time series position, velocity, and attitude data.

[0173] Energy state and estimated temperature at key points.

[0174] Expected task completion.

[0175] Generate trajectory execution instructions and pass them to the flight control system.

[0176] Real-time adjustments:

[0177] During the flight execution, the deviation between the actual situation and the planned flight trajectory is continuously monitored.

[0178] If the deviation exceeds the threshold, the flight trajectory replanning process is triggered to re-determine the optimal flight trajectory.

[0179] Beneficial effects of this application:

[0180] 1. Through multi-source data fusion technology, the operation control system's ability to perceive complex environments has been significantly improved. The operation control system can comprehensively utilize the advantages of multiple sensors, overcome the limitations of a single sensor, and achieve all-weather and all-terrain environmental perception. This provides a reliable data basis for autonomous decision-making and greatly improves the adaptability and safety of the operation control system in complex environments.

[0181] 2. The use of advanced fault diagnosis and fault-tolerant control technology has significantly improved the safety and reliability of the operation and control system. The operation and control system can detect potential faults in a timely manner and take corresponding fault-tolerant measures to minimize the impact of faults on flight missions. This not only improves the reliability of the operation and control system, but also extends the service life of the aircraft and reduces maintenance costs.

[0182] 3. Based on the multi-constraint intelligent planning and decision-making module 3, highly autonomous flight in complex environments is achieved. The operation and control system can autonomously generate the optimal flight plan under the consideration of multiple constraints to adapt to various complex mission requirements. This greatly improves the efficiency and flexibility of mission execution and expands the application scope of unmanned aerial vehicles.

[0183] 4. The overall design realizes unmanned intelligent flight, greatly reducing labor costs and expanding application scenarios. The operation and control system can operate autonomously for a long time without continuous manual monitoring, which not only reduces the workload of operators, but also makes it possible to perform tasks in some dangerous or difficult-to-reach environments.

[0184] 5. Modular design improves the scalability and maintainability of the system. The interfaces between the functional modules are standardized, which facilitates the upgrade and maintenance of the operation and control system. At the same time, the modular design also allows the operation and control system to be flexibly configured according to different application requirements, improving the applicability of the operation and control system. During the application process, the control engineer can give the airship any desired position or any desired attitude angle according to the situation, and directly transmit the control quantity calculated by this method to the actuator to realize the position or attitude control of the stratospheric airship.

[0185] Based on the same inventive concept, the embodiment of the present application further provides a stratospheric airship operation and control method based on the above-mentioned stratospheric airship operation and control system, and the stratospheric airship operation and control method comprises the following steps:

[0186] S1: fusing raw data collected by multiple sensors to obtain fused data, and determining an estimated value of an environmental state variable based on the fused data using an improved particle filtering method; the raw data includes a distance, speed, imaging data, position information, and attitude information of a stratospheric airship.

[0187] S2: Performing fault diagnosis on set components in the stratospheric airship based on the estimated values ​​of the environmental state variables and the stratospheric airship operation data to obtain a comprehensive fault diagnosis result, and generating a corresponding fault-tolerant control strategy according to the comprehensive fault diagnosis result; the fault-tolerant control strategy includes a mission degradation strategy, a control reconstruction strategy and an emergency landing strategy; the set component includes a set first component and a second component.

[0188] S3: constructing a multi-system constraint model based on the stratospheric airship operation data, and determining the optimal flight trajectory of the stratospheric airship based on the multi-system constraint model and the fault-tolerant control strategy.

[0189] S4: Generate corresponding execution control instructions according to the optimal flight trajectory, and send the execution control instructions to the flight control system, so that the flight control system flies according to the execution control instructions.

[0190] In an exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a stratospheric airship operation and control method.

[0191] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for controlling a stratospheric airship is implemented.

[0192] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements a stratospheric airship operation and control method when executed by a processor.

[0193] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a stratospheric airship operation and control system and method are implemented.

[0194] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0195] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0196] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0197] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0198] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0199] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A stratospheric airship operation and control system, characterized in that: The stratospheric airship operation and control system includes: a multi-source data fusion module, a fault diagnosis and fault-tolerant control module, a multi-constraint intelligent planning and decision-making module and a central processing unit; The multi-source data fusion module is used to fuse the original data collected by multiple sensors to obtain fused data, and based on the fused data, determine the estimated value of the environmental state variable using an improved particle filtering method; the original data includes the distance, speed, imaging data, position information and attitude information of the stratospheric airship; The central processing unit is connected to the multi-source data fusion module and the fault diagnosis and fault-tolerant control module respectively, and the central processing unit is used to receive the estimated value of the environmental state variable, and send the estimated value of the environmental state variable and the acquired stratospheric airship operation data to the fault diagnosis and fault-tolerant control module; The fault diagnosis and fault-tolerant control module is used to perform fault diagnosis on the setting components in the stratospheric airship based on the estimated value of the environmental state variable and the stratospheric airship operation data, obtain a comprehensive fault diagnosis result, and generate a corresponding fault-tolerant control strategy according to the comprehensive fault diagnosis result; the fault-tolerant control strategy includes a mission degradation strategy, a control reconstruction strategy and an emergency landing strategy; the setting component includes a first component and a second component; The central processing unit is also connected to the fault diagnosis and fault-tolerant control module, and is used to receive the fault-tolerant control strategy, and send the fault-tolerant control strategy and the stratospheric airship operation data to the multi-constraint intelligent planning and decision-making module; The multi-constraint intelligent planning and decision module is connected to the central processing unit, and the multi-constraint intelligent planning and decision module is used to build a multi-system constraint model based on the stratospheric airship operation data, and determine the optimal flight trajectory of the stratospheric airship based on the multi-system constraint model and the fault-tolerant control strategy; The central processing unit is also used to generate an execution control instruction according to the optimal flight trajectory, and send the execution control instruction to the flight control system of the stratospheric airship to control the stratospheric airship.

2. The stratospheric airship operation and control system according to claim 1, characterized in that: The multi-source data fusion module includes: A system error correction unit is connected to the multiple sensors and is used to perform system error correction on the raw data collected by the multiple sensors to obtain data after system error correction; An installation error correction unit is connected to the system error correction unit and is used to perform installation error correction on the original data after the system error correction to obtain installation error corrected data; A time series feature extraction unit, connected to the installation error correction unit, for extracting time series features from the data after the installation error correction to obtain time series features; The fusion algorithm unit is connected to the time series feature extraction unit, and is used to obtain fusion data based on the time series features, and determine the estimated value of the environmental state variable based on the fusion data using an improved particle filtering method.

3. The stratospheric airship operation and control system according to claim 2, characterized in that: The system error correction unit comprises: The distance error correction subunit of the laser radar is used to obtain the distance data measured by the laser radar and correct the distance data; The speed error correction subunit of the millimeter wave radar is used to obtain speed data measured by the millimeter wave radar and correct the speed data; An imaging error correction subunit of the optical camera and the infrared sensor, used to correct the imaging data of the optical camera and the infrared sensor; The GPS / INS position and attitude error correction subunit is used to obtain the position information collected by the GPS and the attitude information collected by the INS, and perform error correction on the position information and the attitude information.

4. The stratospheric airship operation and control system according to claim 1, characterized in that: The fault diagnosis and fault tolerance control module includes: A fault feature extraction unit connected to the central processing unit, used to extract multiple fault feature sets from the stratospheric airship operation data; each fault feature set includes multiple fault feature parameters; and one fault feature set corresponds to one fault type; A fault diagnosis unit is connected to the fault feature extraction unit and is used to input each fault feature set into a corresponding single fault type diagnosis model to obtain a corresponding fault diagnosis result prediction value; wherein the output fault diagnosis result prediction value of a single fault type diagnosis model corresponds to a fault type, and each of the single fault diagnosis models is obtained by training a support vector machine using training samples; the training samples include fault feature parameter sample values ​​and corresponding fault diagnosis result sample values; A hybrid voting unit, connected to the fault diagnosis model, is used to obtain a comprehensive fault diagnosis result based on all fault diagnosis result prediction values ​​and corresponding preset weights; A fault-tolerant control unit is connected to the hybrid voting unit and is used to generate a fault-tolerant control strategy according to the comprehensive fault diagnosis result.

5. The stratospheric airship operation and control system according to claim 4, characterized in that: The fault-tolerant control unit comprises: a mission degradation strategy generating subunit, connected to the hybrid voting unit, for generating a mission degradation strategy to perform fault-tolerant control on the flight control system when the comprehensive fault diagnosis result indicates that the first component has failed; a control reconstruction strategy generating subunit, connected to the hybrid voting unit, for updating the second component and performing fault diagnosis on the updated set component when the comprehensive fault diagnosis result indicates that the second component has a fault, thereby generating a fault-tolerant control strategy to perform fault-tolerant control on the flight control system; The emergency landing strategy generating subunit is connected to the hybrid voting unit and is used to start the emergency landing procedure to perform fault-tolerant control on the flight control system when the comprehensive fault diagnosis result shows that the stratospheric airship cannot fly normally.

6. The stratospheric airship operation and control system according to claim 1, characterized in that: The multi-constraint intelligent planning and decision-making module includes: A constraint model building unit connected to the central processing unit, and used to build a multi-system constraint model based on the system operation data; the multi-system constraint model includes an energy constraint model, a heat constraint model, a time constraint model, a safety constraint model and a task constraint model; A random sampling unit, configured to perform sampling in a state space to generate candidate path nodes; the state space is determined based on a state vector of the stratospheric airship and executable maneuvers; a trajectory generation unit, connected to the central processing unit and the random sampling unit, respectively, for generating a plurality of candidate flight trajectories by using a fast random tree algorithm, based on the candidate path nodes and the fault-tolerant control strategy, and taking a multi-system constraint model as a constraint condition; The evaluation and optimization unit is connected to the trajectory generation unit and is used to optimize multiple candidate flight trajectories using an ant colony algorithm, and evaluate the optimized flight trajectories to determine the optimal flight trajectory.

7. A method for controlling a stratospheric airship, characterized in that: The stratospheric airship operation and control method is based on the stratospheric airship operation and control system according to any one of claims 1 to 6, and the stratospheric airship operation and control method comprises: The raw data collected by multiple sensors are fused to obtain fused data, and based on the fused data, an estimated value of the environmental state variable is determined using an improved particle filter method; the raw data includes the distance, speed, imaging data, position information and attitude information of the stratospheric airship; Based on the estimated value of the environmental state variable and the stratospheric airship operation data, a fault diagnosis is performed on the set component in the stratospheric airship to obtain a comprehensive fault diagnosis result, and a corresponding fault-tolerant control strategy is generated according to the comprehensive fault diagnosis result; the fault-tolerant control strategy includes a mission degradation strategy, a control reconstruction strategy and an emergency landing strategy; the set component includes a set first component and a second component; constructing a multi-system constraint model based on the stratospheric airship operation data, and determining an optimal flight trajectory of the stratospheric airship based on the multi-system constraint model and the fault-tolerant control strategy; A corresponding execution control instruction is generated according to the optimal flight trajectory, and the execution control instruction is sent to a flight control system so that the flight control system flies according to the execution control instruction.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the unmanned airborne operation and control method for a stratospheric airship as described in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the unmanned airborne operation control method for a stratospheric airship as claimed in claim 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the unmanned airborne operation control method for a stratospheric airship as claimed in claim 7 is implemented.

Images