6391results about "Aircraft components testing" patented technology

Disclosed in the present invention is a neural network-based aircraft skin gluing quality defect detection method, comprising: data acquisition: using a camera to photograph an aircraft skin to acquire picture data; preprocessing the acquired picture data; annotating the data by means of annotation software to acquire a data set for network training; establishing a feature erasing and boundary refinement-based defect detection network model, wherein the defect detection network model comprises a feature extraction network, a semantically-guided feature erasing module, a multi-scale feature fusion network, and a boundary refinement-based defect prediction network which are connected in sequence; using the data set to train the network model, and storing parameters of the trained model; and using the trained network model to detect a directly acquired skin gluing image, and outputting the detection result. Nondestructive detection of aircraft skin gluing defects can be quickly and accurately achieved, thereby promoting high-quality intelligent manufacturing processes of skins.

The invention discloses an aviation converter fault detection method based on an information fusion algorithm, and the method comprises the steps: collecting the operation data of an aviation converter, and constructing a data set; performing time information extraction and space information extraction on the data in the data set, and performing feature fusion on time features and space features based on a variational auto-encoder to obtain spatio-temporal data; constructing a Bayesian deep learning model, and training and optimizing the Bayesian deep learning model; inputting the spatio-temporal data into the trained and optimized Bayesian deep learning model for processing, outputting a numerical value representing a fault occurrence probability, and taking a variance based on the probability numerical value as uncertainty estimation; presetting a probability threshold, and when the output probability is greater than the threshold, determining that the converter has a fault; otherwise, judging that the operation state is normal; a more accurate and reliable diagnosis result is provided for fault detection, and the method has high adaptability and robustness in practical application.

Examples relate to a battery management system with an enhanced equivalent circuit model (ECM) for electric vehicles, including electric vertical takeoff and landing (eVTOL) aircraft. The system includes a memory to store an equivalent circuit model (ECM) configured to dynamically adjust a series resistance component in real-time based on operational data from a lithium-ion battery. This adjustment models lithium depletion effects under high discharge conditions. At least one processor is configured to continuously refine parameters of the ECM by analyzing discrepancies between predicted and actual battery performance, where the adjustments are based on real-time changes in state of charge, temperature, and current.

A disclosed airborne vehicle includes split-ring resonators (split ring resonators), which may be embedded within a material. Each split ring resonator may be formed from a three-dimensional (3D) monolithic carbonaceous growth and may detect an electromagnetic ping emitted from a user device. Each split ring resonator may generate an electromagnetic return signal in response to the electromagnetic ping. The electromagnetic return signal may indicate a state of the material in a position proximate to a respective split ring resonator. In some aspects, each may resonate at a first frequency in response to the electromagnetic ping when the material is in a first state, and may resonate at a second frequency in response to the electromagnetic ping when the material is in a second state. A resonant frequency of the 3D monolithic carbonaceous growth may be based on physical characteristics of the material.

A method of operation is provided. During this method, a first power system of an aircraft powerplant is operated to provide a first quantity of power and / or torque to drive rotation of a propulsor rotor. A second power system of the aircraft powerplant is tested during the operating of the first power system. The second power system is configured as or otherwise includes an electric machine. The testing of the second power system includes: signaling the second power system to use the electric machine to provide a second quantity of power and / or torque to further drive the rotation of the propulsor rotor; determining an operational parameter of the aircraft powerplant following the signaling; and evaluating operability of the second power system by comparing the operational parameter to a threshold.

The invention belongs to the technical field of aircraft prediction and health management, and particularly relates to a fault association rule mining method for fault data in a flight management and control system, which comprises the following steps: S1, extracting specified different batches of fault historical data from a flight management and control fault database; s2, counting the simultaneous occurrence frequency of a pair of associated faults in different batches, and calculating the occurrence frequency of the pair of associated faults; s3, according to a preset frequency threshold value, label pairs, namely fault pairs, with significant association are screened out; s4, extracting a time difference between the label pairs; s5, performing statistical analysis on the time difference distribution between each pair of labels to evaluate the association strength; s6, comparing the time difference between the label pairs with a time difference threshold to obtain the association strength between the fault pairs; and S7, comparing and analyzing time difference distribution of the fault pairs among different batches, observing distribution characteristics of time differences, and judging whether stable association exists or not.

Disclosed in the present invention is a neural network-based defect detection method for gluing quality on aircraft skin. The method includes: data acquisition: taking photos of aircraft skin by using a camera to acquire image data; preprocessing the acquired image data; annotating the data by using annotation software to acquire a data set for network training; establishing a defect detection network model based on feature erasure and boundary refinement, where the defect detection network model includes a feature extraction network, a semantic-guided feature erasure module, a multi-scale feature fusion network, and a defect prediction network based on boundary refinement, which are sequentially connected, the data set is used for training the network model, and trained model parameters are saved; and detecting a directly collected skin gluing image by using the trained network model and outputting detection results.

A decision tool models emissions for a sustainable aircraft fuel (SAF) for the lifecycle of the fuel. The decision tool includes a controller module configured to receive data related to at least one fuel pathway for the fuel wherein the fuel pathway considers emissions from initial feedstock production to fuel burn during flight and arrival. The decision tool determines at least one fuel pathway for the fuel used to fuel the aircraft during a flight, models an emission score for the at least one fuel pathway, and then outputs the emission score where a user can purchase the fuel or make other decisions based upon the fuel pathway provided by the decision tool.

Aspects of the present disclosure generally relate to systems and methods for flight control of aircrafts driven by electric propulsion systems and in other types of vehicles. In some embodiments, a flight control system of an aircraft is disclosed, configured to receive one or more signals to control movement of the aircraft, determine at least one flight condition of the aircraft, wherein the at least one flight condition includes at least a phase of flight, calculate at least one or more loads associated with the aircraft based on the determined at least one flight condition; determine an optimized flight configuration to alleviate loads on one or more components of the aircraft based on the received one or more signals and the calculated loads, generate one or more effector commands based on the optimized flight configuration; and actuate one or more aircraft effectors based on the one or more effector commands.

A method of using computer implemented neural network for simulation of aerodynamic performance of technical object having geometry, method includes: training neural network using plurality of sets of pre-computed computational fluid dynamics encodings, CFD, outputs, wherein training is generated using inputs including: geometry of at least one training technical object; spatial locations of neural network input nodes as node attributes; relationship between geometry of at least one training technical object and neural network input node locations; associated boundary conditions; operating conditions; and computed outputs including flow fields and aerodynamic performance parameters; training using loss function evaluating error between neural network and pre-computed CFD outputs to produce trained neural network; using trained neural network with new inputs to generate as output predicted aerodynamic performance of technical object, wherein relationship between geometry of at least one training technical object and neural network input node locations includes vector with at least two parameters.

The invention discloses a small-size rotor test bed, a parameter matching method and a control angle resolving method, belongs to the technical field of aviation aerodynamic wind tunnel tests, and aims to solve the problems of an existing small-size rotor test bed. The test bench comprises a main shaft tilting system, the main shaft tilting system comprises a base, a tilting electric cylinder, two rotating shaft seats, a tilting table and a tilt angle sensor, the two rotating shaft seats are arranged on the left side and the right side of the base respectively, shaft heads are arranged on the left side and the right side of the tilting table respectively, and the two coaxial shaft heads are in corresponding rotating fit with the two rotating shaft seats respectively. A rear cylinder cover of the tilting electric cylinder is hinged to the front side of the base, a piston rod of the tilting electric cylinder is arranged upwards and hinged to the front side of the tilting table, and a tilt angle sensor is arranged on the tilting table. The test rotor wing is connected with the power transmission system, the power transmission system is connected with the tilting table, and technical support can be provided for measurement of rotor wing performance, blade surface pressure and blade bending moment load of the small unmanned aerial vehicle.

A disclosed airborne vehicle includes split-ring resonators (split ring resonators), which may be embedded within a material. Each split ring resonator may be formed from a three-dimensional (3D) monolithic carbonaceous growth and may detect an electromagnetic ping emitted from a user device. Each split ring resonator may generate an electromagnetic return signal in response to the electromagnetic ping. The electromagnetic return signal may indicate a state of the material in a position proximate to a respective split ring resonator. In some aspects, each may resonate at a first frequency in response to the electromagnetic ping when the material is in a first state, and may resonate at a second frequency in response to the electromagnetic ping when the material is in a second state. A resonant frequency of the 3D monolithic carbonaceous growth may be based on physical characteristics of the material.

Aspects of the present disclosure generally relate to systems and methods for flight control of aircrafts driven by electric propulsion systems and in other types of vehicles. In some embodiments, a computer-implemented method for controlling an aircraft is disclosed, comprising: receiving, from a source processor, a first copy of a signal corresponding to an input device; sending a second copy of the signal to all other processors; receiving a number of second copies of the signal from all other processors, the number of second copies being equal to the number of all other processors excluding the source processor; determining a consensus signal based on the first copy and the second copies of the signal; and determining a command signal for an effector of the aircraft based on the consensus signal, and wherein no two processors are configured to receive signals from a same input device.

The invention discloses an AE-GCN-based unmanned aerial vehicle system fault diagnosis method and equipment, belongs to the technical field of unmanned aerial vehicle fault diagnosis, and is used for solving the technical problems that an existing unmanned aerial vehicle fault diagnosis method depends on expert experience and feature engineering and has the defects of low efficiency, poor generalization ability and the like. The method comprises the following steps: constructing a corresponding structure topological graph based on a topological structure of a target unmanned aerial vehicle, and obtaining a topological matrix; performing node feature extraction on the structure topological graph to obtain a node feature vector; inputting the topological matrix and the node feature vector into a graph convolution neural network for graph convolution operation to obtain a node state feature vector; inputting the data into an attention mechanism module to obtain attention features, and mapping the attention features into node state updating parameters; comparing the node state updating parameter with the node state historical parameter, and positioning a fault node and a fault type; and predicting a fault propagation path based on other nodes directly connected with the fault node in the structural topological graph.

The embodiment of the invention provides a multi-configuration relay-oriented aircraft electrical box parameter measurement system and method, and belongs to the field of aircraft electrical box test and diagnosis. According to the hardware level, flexible access of a multi-configuration relay electrical box is achieved based on a universal adapter interface, core parameter measurement is completed in combination with an integrated measurement and control circuit, and synchronous acquisition and processing are conducted on multiple paths of signals through a signal acquisition and processing unit; according to the software level, the pull-in / release time, the rebound time and the voltage parameters are accurately calculated through a parameter calculation module on the basis of waveform feature point recognition and dynamic excitation-response theories, and the functions of fault diagnosis, safety protection and data storage are integrated. According to the method, the crossing from on-off judgment to parameterized precise evaluation is realized, the detection efficiency, the measurement precision and the equipment reliability evaluation capability are remarkably improved, and an integrated solution is provided for external field maintenance and state prediction of the aircraft relay.

A disclosed leaky coaxial resonant sensor system and methods. In use, the system includes at least one split-ring resonator (SRR) embedded within a material of the component. The at least one SRR is formed from a composite material. Additionally, the at least one SRR is configured to resonate at a first frequency in response to an interrogation signal from a leaky coaxial cable antenna. In some aspects, each SRR may resonate at a first frequency in response to an electromagnetic ping when the composite material is in a first state, and may resonate at a second frequency in response to the electromagnetic ping when the composite material is in a second state. A resonant frequency of the composite material may be based on physical characteristics of the composite material.

The invention provides a fault diagnosis method and device for an aircraft, electronic equipment and a storage medium, and relates to the technical field of machine learning, and the method comprises the steps: obtaining the state variable data of the aircraft; inputting the state variable data of the aircraft into the fault diagnosis model to obtain a fault prediction result of the aircraft output by the fault diagnosis model; wherein the fault diagnosis model is obtained by training state variable sample data and fault labels of the aircraft on the basis of a k-nearest neighbor algorithm kNN model. According to the method, the similarity between the samples is analyzed by using the k-nearest neighbor algorithm, and various fault types are effectively identified and classified, so that rapid and accurate fault diagnosis is realized, and the efficiency and reliability of fault identification are improved.

The invention relates to an aircraft nose landing gear taxiing and shimmy simulation test bed. The test bed comprises a test device main body structure, a power execution control mechanism, a vibration excitation mechanism and a vibration detection system. The method solves the problems of determination, contrast evaluation and detection analysis of the shimmy influence factors of the nose landing gear of the aircraft. The torsion steering engine is added, so that the turning condition of a ground plane can be simulated. The height-adjustable supporting cross beam can adapt to undercarriages of different sizes only by replacing the undercarriage clamp instead of replacing the whole frame, so that the use cost is greatly reduced. And more accurate data are provided for the design of the nose landing gear of the aircraft.

A fixed-wing unmanned aerial vehicle large-attack-angle longitudinal aerodynamic characteristic test device and a test method relate to the technical field of aircraft aerodynamic characteristic test, and mainly comprise a wind tunnel simulation device, an unmanned aerial vehicle bearing and motion simulation device, a sensor arranged on an unmanned aerial vehicle or a model, a data acquisition system and the like. The simulation module is used for simulating longitudinal motion states and attitudes of the unmanned aerial vehicle in various pneumatic environments; the device is used for experiments, nonlinear longitudinal aerodynamic characteristics of the unmanned aerial vehicle under various attack angles are obtained, a phase diagram reflecting the attack angle-pitch angle speed change relation of the system state is obtained, a balance point under the normal working condition and the limit working condition is determined, and a basis is provided for flight control of the unmanned aerial vehicle under the large attack angle limit working condition.

The invention provides a turbine cooler fault diagnosis method and device under a variable rotating speed, and belongs to the field of aviation electromechanics. The method provided by the invention comprises the steps that a monitored fault signal is determined based on historical faults of the turbine cooler under the variable rotating speed, and the fault signal changes in each historical fault; determining a critical value of the fault signal based on the historical fault, wherein the critical value is a value of the fault signal when the historical fault is generated; calculating a first relationship between the rotating speed of the turbine cooler and a historical fault judgment threshold value based on the critical value; correcting the first relation based on the rotating speed change rate of the turbine cooler to obtain a second relation; real-time information of the turbine cooler under the variable rotating speed is obtained; a fault of the turbine cooler is identified based on the real-time information and a second relationship. According to the fault diagnosis method and device for the turbine cooler under the variable rotating speed, rapid fault positioning of the turbine cooler can be supported under the complex variable rotating speed working condition.

A method of using a computer implemented neural network for a simulation of aerodynamic performance of a technical object having a geometry, the method comprising: Training the neural network using a plurality of sets of encodings of pre-computed computational fluid dynamics, CFD, outputs, wherein the training is generated using inputs comprising: a geometry of at least one training technical object; spatial locations of input nodes of the neural network as node attributes; a relationship between the geometry of the at least one training technical object and the neural network input node locations; associated boundary conditions; operating conditions; and computed outputs comprising flow fields and aerodynamic performance parameters; the training using a loss function that evaluates an error between a neural network output and the pre-computed CFD outputs to produce a trained neural network; using the trained neural network with new inputs to generate as output a predicted aerodynamic performance of the technical object, wherein the relationship between the geometry of the at least one training technical object and the neural network input node locations comprises a vector with at least two parameters.

The invention discloses an evtol tilt rotor aerodynamic noise wind tunnel test method, and belongs to the technical field of wind tunnel tests. In order to establish an evtol tilt rotor aerodynamic noise wind tunnel test method, the method comprises the following steps: carrying out a hovering empty propeller hub background noise test: rotating a rotor table, enabling the axis of a rotor to be perpendicular to the axis of a wind tunnel, carrying out an empty propeller hub aerodynamic and noise test, and then carrying out aerodynamic data acquisition and noise data acquisition at each rotating speed to obtain hovering empty propeller hub background noise data; performing a tilt rotor hovering noise test: installing blades, setting a rotor axis to be perpendicular to a wind tunnel axis, then performing pneumatic data acquisition and noise data acquisition at each total pitch and rotating speed, and correcting the obtained tilt rotor hovering noise data by using hovering empty propeller hub background noise data to obtain a tilt rotor hovering noise test result; obtaining static tension and static power under each total pitch and rotating speed of tilt rotor hovering; carrying out a transition state and axial flow forward flight empty propeller hub noise characteristic test; and carrying out a transition state and axial flow forward flight tilt rotor noise characteristic test.

Methods and scan systems for analyzing an object. The methods include obtaining a local operation dataset that includes a plurality of operation data points obtained from an object and a corresponding location, within the operation coordinate system, for each operation data point of the plurality of operation data points. The methods also include mapping the plurality of operation data points from the operation coordinate system to a global coordinate system for the object. The mapping includes mapping to generate a global operation dataset that includes the plurality of operation data points and a corresponding global location, within the global coordinate system, for each operation data point. The scan systems include a robot that performs a plurality of operations on an object within an operation coordinate system and a computing device that maps the plurality of operation data points from the operation coordinate system to a global coordinate system.

A method for data processing, a computer, and a storage medium are provided. A service processing request text sent by a first service object is obtained on an intelligent conversation page, and the service processing request text is parsed to obtain service semantic information and intention requirement information. A service database associated with the first service object is determined. A first target type indicated by the service semantic information is obtained, and a first service data set of the first target type is obtained from classified data corresponding to N service types in the service database respectively. Information retrieval is performed in the first service data set to obtain retrieval content associated with the first target component, a service result for the service processing request text is generated based on the intention requirement information and the retrieval content, and the service result is displayed on the intelligent conversation page.

A system for detecting a state of a mechanism includes processing circuitry. The mechanism includes multiple components, at least some of which are capable of moving relative to each other. At least one state is specified for the mechanism, based on the alignment of the mechanism components. The processing circuitry identifies, within image data of the mechanism, reference points on at least two of the components. Based on respective locations of the reference points, it determines whether the components of mechanism are in one of the specified alignments (i.e. states), and outputs an indicator.

The invention provides a helicopter transmission system coaxiality detection and adjustment device and method, the device comprises a main controller 10, a laser emitter 20 and a laser receiver CCD 30, the main controller 10 comprises a computer 11 and a control box 12, after a control instruction on the computer 11 is sent, the control instruction is directly transmitted to the control box 12 through a USB interface; the laser transmitter 20 comprises a first laser transmitter 21 and a second laser transmitter 22, the first laser transmitter 21 comprises a first laser transmitter 211, a first adjusting flange 212 and a positioning cylinder 213, and the second laser transmitter 22 comprises a second laser transmitter 221, a second adjusting flange 222 and a positioning cylinder 223; the laser transmitter 20 is installed on a simulation output shaft flange plate of an engine or a main speed reducer, and the positioning cylinder 223 and the output end of the engine or the main speed reducer are installed in a positioning fit mode.

The present invention belongs to the field of drones, and provides a drone testing system, including a testing device and a processing module, wherein the testing device includes a test bench, on which a torque testing module is installed, and the torque testing module is used to test the torque when the drone turns, and a tension testing module is installed on the torque testing module, and the tension testing module is used to test the vertical tension and tilt tension of the drone. The present invention sets a tension sensor, an angle sensor, a winding drum, a pull rope, and a second motor, and when testing the tilt tension of the drone, the drone is tilted to fly, and the drone tilts and pulls the pull rope, the tension sensor can measure the vertical tension of the pull rope, the angle sensor can detect the tilt angle of the pull rope, and then the tension of the pull rope and its horizontal tension component can be calculated, and the system can comprehensively and accurately test the tension parameters of the drone when it is tilted.

A smart landing platform system includes a flat and rigid platform for landing a drone and having a geometrical center, a center of gravity and a weight, a digital scale disposed beneath the platform for providing measurements of a weight distribution of the platform and the drone, and a control unit connected to the digital scale for instantaneous data collection and storing logic including a statistical inference algorithm based on a nonlinear least squares model to perform automated pre-flight safety check for the drone.

The invention relates to the technical field of electromagnetic environment effect, and discloses a high-intensity radiation field complete machine low-level scanning field extrapolation verification system and verification method, and the verification method comprises the following steps: building a complete machine HIRF high-level scanning field test system under the same test site requirement of a complete machine HIRF-LLSF test, the whole machine HIRF high-level scanning field test system adopts an HPM system to simulate a narrow-band high-level HIRF radiation source, the distance between a transmitting antenna and a test object is kept to be the same as that of a whole machine HIRF-LLSF test, and the placing position of a receiving antenna or a field intensity probe is the same as that of the whole machine HIRF-LLSF test; according to the invention, the technical problems of calibration of the HIRF high-level scanning field of the whole machine and accurate and synchronous measurement of the cabin coupling field and the problem of to-be-verified extrapolation accuracy of the test result of the HIRF-LLSF test of the whole machine can be solved, and a test means is provided for protection design and safety evaluation of the HIRF of the airplane.

The subject matter described herein includes methods, systems, and computer program products for AI tagging of airline fault codes. According to one method, a transformer-based natural language processing (NLP) artificial intelligence (AI) model trained on a dataset is provided. The training dataset includes a plurality of text strings tagged with at least one associated air transport association (ATA) code. The trained AI model then receives an untagged text string as input and automatically tags the text string with an ATA code.