Method for monitoring the technical condition of an unmanned aerial vehicle
The method filters and analyzes UAV telemetry data in real-time to generate precise maintenance recommendations, enhancing UAV operation efficiency by predicting failures and extending service life.
Patent Information
- Application Number
- PCT/RU2025/000162
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-07
- Filing Date
- 2025-05-29
- Publication Date
- 2026-11-12
AI Technical Summary
Existing technologies lack the ability to accurately and effectively generate real-time maintenance recommendations for unmanned aerial vehicles (UAVs) based on current telemetry data.
A method involving a processing server that receives real-time UAV telemetry data, filters noise and abnormal values, identifies relevant data blocks for specific UAV nodes, and generates maintenance recommendations using machine learning tools and historical data.
Enables timely and accurate maintenance recommendations, improving UAV operation efficiency by predicting remaining service life and identifying potential emergencies.
Abstract
Description
[0001] METHOD FOR MONITORING THE TECHNICAL CONDITION OF AN UNMANNED AERIAL VEHICLE IN REAL TIME
[0002] FIELD OF TECHNOLOGY TO WHICH THE INVENTION RELATES The present technical solution relates to the processing of telemetry data of an unmanned aerial vehicle (UAV) in the field of information technology, in particular to a method for monitoring the technical condition of a UAV equipped with a telematics module and operated in the coverage area of a wireless communication network, in real time.
[0003] LEVEL OF TECHNOLOGY
[0004] The prior art discloses US 2020 / 0142433 A1, published May 7, 2020, which discloses an automated system and method for controlling a plurality of unmanned aerial vehicles (UAVs). The system may include a receiver, a transmitter, and at least one processor coupled to a memory. The receiver receives first telemetry data from the plurality of UAVs. The transmitter is configured to transmit control data to the plurality of UAVs. The memory stores instructions issued by the processor for: substantially simultaneously determining a plurality of plans for each of the plurality of UAVs and for a predetermined period of time based on at least the first telemetry data; and iteratively revising the plurality of plans.
[0005] Also known in the prior art is the information source RU 2557771 C1, published on 27.07.2015, which discloses methods for technical control and diagnostics of on-board systems (OS) of an unmanned aerial vehicle (UAV), according to which the analysis and processing of data received from the central computer of the complex is carried out by means of an intelligent decision support system, the classification of the values of critical control parameters characterizing the critical components of the OS of the UAV by a qualitative feature is carried out, with the assignment of a qualitative assessment to each parameter for identifying pre-failure states of the OS of the UAV and conducting proactive diagnostics, upon detection of indistinguishable faults, optimal sequences for conducting diagnostics are formed in the form of a first ranked list of precedents and a second ranked list of incident solutions,and also form the final optimal sequence of diagnostics in the form of a third ranked list of precedents and incident solutions, based on the processing of the first and second lists.
[0006] Finally, the prior art discloses US 2019 / 0243390 A1, published on 08 / 08 / 2019, which discloses the control of one or more drones by downloading flight plans to one or more drones from a user interface (UI), receiving real-time telemetry from the drones and displaying the telemetry on the UI, performing real-time telemetry analytics to determine flight conditions in real time and displaying the flight conditions on the UI in a mobile application, and manually controlling the flight path of one or more drones from the UI.
[0007] A common drawback of the known state-of-the-art solutions is the limited ability to assess the technical condition and generate recommendations for the maintenance of UAVs in operation in real time.
[0008] The solutions known in the prior art do not allow for the accurate and effective generation of recommendations for the maintenance of individual components of operational UAVs in real time based on current telemetry data.
[0009] The proposed solution differs from the prior art solutions in that the processing server receives current UAV telemetry data in real time, filters out noise and abnormal values, identifies the corresponding block of current telemetry data related to each specific UAV node, and generates a maintenance recommendation for each UAV node using machine learning tools and historical data.
[0010] ESSENCE OF THE INVENTION
[0011] The technical problem that the declared technical solution is aimed at solving is the elimination of the shortcomings of the previous level of technology.
[0012] The technical result achieved by solving the above technical problem is an increase in the efficiency of UAV operation due to the timely generation of accurate recommendations for the maintenance of each UAV unit using filtered telemetry data. In accordance with one embodiment of the invention, a method is proposed for monitoring the technical condition of an unmanned aerial vehicle (UAV) equipped with a telematics module and operated within the coverage area of a wireless communication network, in real time. According to the proposed method: current telemetry data from the UAV's on-board sensors, sent by the telematics module through a wireless communication network channel, are received via an internet connection in a ground data gateway;transmit the received current telemetry data from the ground data gateway to the processing server, where the following is performed: filtering of noise and abnormal values in relation to the received current telemetry data; selecting from the filtered current telemetry data the corresponding block of current telemetry data related to each of the specific UAV nodes; storing each selected corresponding block of current telemetry data in the database to the historical telemetry data for each specific UAV node; based on the historical data and the block of current telemetry data, using machine learning tools, predicting the remaining service life, analyzing the probability of failure and identifying a potential emergency situation for each UAV node; generating a recommendation for technical maintenance for each UAV node based on the predicted remaining service life, analyzing the probability of failure and identifying a potential emergency situation;generate a report with recommendations for UAV maintenance; and send the generated report via a web interface to the user device for display.
[0013] In a particular embodiment of the proposed method, the wireless communication network includes at least one of: a cellular communication network, a satellite communication network, and a radio communication network.
[0014] In a particular embodiment of the proposed method, noise filtering additionally includes compensation for data transmission delays based on the time synchronization of telemetry timestamps with the reference clock of the processing server.
[0015] In a particular embodiment of the proposed method, machine learning tools are pre-trained on a set of historical data, including normal and emergency operating modes of UAV nodes.
[0016] RECORD OF IMPLEMENTATION OF THE INVENTION
[0017] The following detailed description of the invention includes numerous implementation details intended to provide a clear understanding of the present invention. However, one skilled in the art will readily appreciate how the present invention may be utilized with or without these implementation details. In other instances, well-known methods, procedures, and components have not been described in detail to avoid unnecessarily obscuring the features of the present invention.
[0018] Furthermore, it will be clear from the foregoing description that the invention is not limited to the embodiment described. Numerous possible modifications, changes, variations, and substitutions, while preserving the spirit and form of the present invention, will be apparent to those skilled in the art.
[0019] The proposed method for monitoring the technical condition of an unmanned aerial vehicle (UAV) equipped with a telematics module and operated within the coverage area of a wireless communication network is implemented in real time in a distributed system for monitoring, diagnosing and predicting the technical condition of UAV components and assemblies (hereinafter referred to as the system), which ensures the prevention of emergency situations and increased efficiency of maintenance and, as a result, more efficient operation of the UAV.
[0020] The distributed system includes one or more UAVs, each equipped with a telematics module, a wireless communications network in the coverage area of which the UAVs fly, a wired communications network that is connected to the wireless communications network and to which a ground data gateway is connected, and a processing server.
[0021] The UAV according to the present invention is equipped with a telematics module capable of transmitting telemetry data collected from the UAV's onboard sensors to a ground-based data gateway. The onboard sensors are capable of collecting data such as temperature, vibration, engine load, battery voltage, and so on.
[0022] The UAV flies within the coverage area of a wireless communication network and maintains a wireless connection with it (e.g., via a wireless communication channel). The wireless communication network includes at least one of: a cellular communication network, a satellite communication network, and a radio communication network.
[0023] Information exchange between the UAV and the ground-based data gateway is carried out via a wireless radio channel. The UAV is equipped with a miniature onboard navigation and communication equipment (ONCE), which contains a telematics module powered by the UAV's onboard network or independently powered by its own battery. The telematics module comprises one or more of a radio modem for communicating with the radio network, a satellite modem for communicating with the satellite network, and a cellular modem for communicating with the cellular network. In one embodiment, the telematics module combines the functionality of all three communication modules.
[0024] The BNSO records telemetry data on the operating parameters and status of UAV components, as well as flight parameters, via connected onboard UAV sensors and transmits this data to the ground data gateway in real time. Information from the BNSO is transmitted initially via a wireless network channel, and then via a wired internet connection to the ground data gateway. The range of wireless data transmission channels is determined by the wireless network coverage. Telemetry data is transmitted from the BNSO to the ground data gateway over the internet via the operator's communication channels (e.g., cellular, satellite, or radio). The ground data gateway receives telemetry data from the BNSO via unified data exchange protocols and records it in the database.
[0025] If there is no connection, data is accumulated in the UAV's buffer storage and transmitted when the connection is restored.
[0026] A ground data gateway is a computing device, such as a computer (usually located in a provider's data center), connected to the Internet with special software installed that receives, processes, and records telemetry data from UAVs into a database.
[0027] The number of BNSOs simultaneously connected and transmitting telemetry data to the ground-based data gateway is up to 10,000 units. The number of BNSOs simultaneously connected to the gateway can be expanded by deploying two, three, or more gateways.
[0028] The data gateway communicates with the data processing and storage server (hereinafter referred to as the processing server) over the internet. The data gateway and the data processing server can be located in the same provider's data center. In this case, data exchange can occur within the local network. The land-based data gateway collects telemetry data, thereby reducing the load on the processing server.
[0029] According to one embodiment, the processing server may be a remote server. The processing server provides the computational operations necessary to implement a method for real-time monitoring of the technical condition of an unmanned aerial vehicle (UAV) equipped with a telematics module and operating within a wireless network coverage area. The processing server may be a cloud-based data storage and processing server, or it may be part of a set of remote servers among which the computational load can be distributed and additional computing resources utilized for data processing and storage.
[0030] The computing resources of the server form software and hardware functional modules that ensure the implementation of specific operations in accordance with the present invention.
[0031] The system, in terms of implementation on the processing server, includes the following modules: central data storage, data pre-processing module, analytics and forecasting module, historical values database, recommendation generation module, notification module, web interface, and analytical reporting module.
[0032] Data from the ground data gateway is sent to the central data storage of the processing server.
[0033] The data preprocessing module then performs the following operations: • Filtering out noise and outliers
[0034] • Normalization of values
[0035] • Bringing data to a unified format
[0036] • Separation of data by UAV, units and assemblies.
[0037] • Historical data is aggregated in a central repository for subsequent analysis. Noise is data distortion caused by electromagnetic interference in the communication channel, sensor quantization errors, or packet transmission failures.
[0038] Anomalous values are data that fall outside the predetermined physically possible ranges for specific parameters.
[0039] Filtering in the data preprocessing module is performed using digital filters and statistical methods, which increases the reliability of the data for subsequent analysis.
[0040] Noise filtering additionally includes compensation for data transmission delays by synchronizing telemetry timestamps with the reference clock of the processing server.
[0041] Value normalization is used to prevent incorrect data from being recorded in the database due to abnormal readings from UAV onboard sensors. Such behavior of UAV onboard sensors can be observed under the influence of external factors, such as onboard power surges, electronic interference, adverse weather conditions, etc.
[0042] The analytics and forecasting module with access to a database of historical values for the analysis and forecasting of the technical condition of UAV components is designed with the ability to:
[0043] • Detection of deviations from the normal state (for example, engine overheating, voltage instability).
[0044] • Predicting the remaining life of parts (for example, the replacement period for bearings) and UAV units
[0045] • Analysis of the probability of failures and identification of potential emergency situations
[0046] • Using machine learning tools (such as LSTM, GRU, XGBoost, and other neural networks) to process historical and current data to improve forecast accuracy. Machine learning tools are pre-trained on a set of historical data that includes both normal and emergency operating modes of UAV nodes.
[0047] The analytics and forecasting module is capable of modeling the behavior and wear of UAV components and assemblies based on historical data (large data sets) and current operating conditions. The recommendation generation module is capable of automatically generating personalized recommendations for each UAV in relation to each of its components, taking into account their current state.
[0048] Examples of generated recommendations:
[0049] • “It is recommended to replace the battery after 5 charging cycles.”
[0050] • “Engine behavior is unstable and diagnostics are required.”
[0051] • “The gearbox temperature is above normal - wear is possible”
[0052] The recommendation generation module is designed with the ability to generate reports with recommendations for maintenance.
[0053] In case of critical failures, the notification module sends emergency notifications to operators (users).
[0054] The analytical reporting module generates historical graphs of UAV unit operating parameters, diagnostic reports and forecasts, and status maps of the entire UAV fleet, which are available to users or operators via a web interface or mobile application for display.
[0055] Based on the data received, operators make decisions about repairing or replacing UAV components.
[0056] Preferred embodiment of the invention
[0057] The present invention is implemented as a method for monitoring the technical condition of an unmanned aerial vehicle (UAV) equipped with a telematics module and operated in a wireless communication network coverage area, in real time.
[0058] The UAV telematics module transmits real-time telemetry data from the UAV's onboard sensors via a wireless network channel that provides an internet connection to a ground-based data gateway. The wireless network includes at least one of the following: a cellular network, a satellite network, and a radio network.
[0059] The ground data gateway receives current telemetry data from the UAV's onboard sensors and transmits it to the processing server. The ground data gateway can simultaneously receive telemetry data from 1 to 10,000 UAVs. Telemetry data from each UAV is transmitted jointly to all UAV nodes.
[0060] The processing server filters noise and anomalies from received live telemetry data. Noise filtering may include compensation for data transmission delays based on the synchronization of telemetry timestamps with the processing server's reference clock.
[0061] The processing server extracts from the filtered current telemetry data the corresponding block of current telemetry data related to each of the specific UAV nodes.
[0062] The processing server saves each selected corresponding block of current telemetry data into the database of historical telemetry data for each specific UAV node.
[0063] Based on historical data and a block of current telemetry data, using machine learning tools, the processing server predicts the remaining service life, analyzes the probability of failure, and identifies a potential emergency situation for each UAV node.
[0064] Based on the remaining life forecast, failure probability analysis, and potential emergency situation identification, the processing server generates a maintenance recommendation for each UAV node, generates a report with UAV maintenance recommendations, and sends the generated report via the web interface to the user device for display.
[0065] In an additional embodiment, the machine learning tools are pre-trained on a set of historical data including normal and emergency operating modes of the UAV nodes.
[0066] The distributed system for monitoring, diagnosing and predicting the technical condition of UAV units and assemblies proposed in accordance with the present invention provides the user with the ability to log into the system's personal account by entering a login and password through the authorization interface.
[0067] The proposed technical solution enables real-time assessment of the technical condition and generation of maintenance recommendations for operational UAVs. The accuracy and effectiveness of recommendations are achieved by filtering received current telemetry data and using trained machine learning tools that analyze current telemetry data in conjunction with accumulated historical telemetry data. The generated recommendations enable timely UAV maintenance, improving operational efficiency and extending the UAV's service life.
[0068] The proposed technical solution can be used in the areas of logistics, agriculture, construction, and energy, where UAVs are used.
[0069] The proposed system automates maintenance planning and execution processes, predicts parts replacement, and can be integrated with platforms for the timely provision of UAV components.
[0070] A server in the context of the present invention is an electronic computing device for processing and storing data on which software is installed and operates and which is designed to exchange data with other electronic computing devices via a data transmission network.
[0071] An electronic computing device, including a user computing device, is any known electronic computing device, including a user electronic device, a laptop computer, a desktop computer, a tablet computer, a smartphone, etc., designed with the ability to execute user applications, as well as communicate via a data transmission network with a server.
[0072] An electronic computing device that provides the data processing necessary for the implementation of the claimed solution generally contains the following components: one or more processors, at least one memory, a data storage means, input / output interfaces, an input means, and, if necessary, network interaction means.
[0073] When executing machine-readable instructions contained in the RAM, the processor of the device is configured to perform the basic computing operations necessary for the operation of the device or the functionality of one or more of its components.
[0074] Memory is typically implemented as RAM, where the necessary software logic is loaded to provide the required functionality. When implementing the proposed solution, the memory required for its implementation is allocated.
[0075] ioData storage can be implemented as an HDD, SSD, RAID array, network storage, flash memory, etc. The storage medium enables long-term storage of various types of information, such as the aforementioned files with user data sets, databases containing records of time intervals measured for each user, user IDs, etc.
[0076] Interfaces are standard means for connecting and operating peripherals and other devices, such as USB, RS232, RJ45, COM, HDMI, PS / 2, Lightning, etc.
[0077] The choice of interfaces depends on the specific design of the device, which may be a personal computer, mainframe, server cluster, thin client, laptop, etc.
[0078] A keyboard may be used as a data input device in any embodiment of the system implementing the described method. The keyboard hardware may be any known device: it could be a built-in keyboard used on a laptop or netbook, or a separate device connected to a desktop computer, server, or other computing device. The connection may be either wired, in which the keyboard cable is connected to a PS / 2 or USB port located on the desktop computer's system unit, or wireless, in which the keyboard communicates wirelessly, such as via radio, with a base station, which is in turn directly connected to the system unit, such as via a USB port.In addition to the keyboard, data input devices may also include: a joystick, display (touch screen), projector, touchpad, mouse, trackball, light pen, speakers, microphone, camera, etc.
[0079] Network communication tools are selected from a device that provides network data reception and transmission, such as an Ethernet card, WLAN / Wi-Fi module, Bluetooth module, BLE module, NFC module, IrDA, RFID module, GSM modem, etc. These tools facilitate data exchange via a wired or wireless data transmission channel, such as WAN, PAN, LAN, Intranet, Internet, WLAN, WMAN, or GSM.
[0080] The device components are connected via a common data bus.
[0081] liThe present application materials presented a preferred disclosure of the implementation of the claimed technical solution, which should not be used as limiting other, particular embodiments of its implementation that do not go beyond the scope of the requested scope of legal protection and are obvious to specialists in the relevant field of technology.
Claims
CLAUSES OF THE INVENTION 1. A method for monitoring the technical condition of an unmanned aerial vehicle (UAV) equipped with a telematics module and operated in a wireless communications network coverage area, in real time, comprising the following steps: - receive current telemetry data from the UAV's on-board sensors, sent by the telematics module via a wireless network channel, via an Internet connection in the ground data gateway; - transmit received current telemetry data from the ground data gateway to the processing server, on which: -- filter noise and abnormal values in relation to received current telemetry data; -- select from the filtered current telemetry data the corresponding block of current telemetry data related to each of the specific UAV nodes; - save each selected corresponding block of current telemetry data in the database to the historical telemetry data for each specific UAV node; -- based on historical data and a block of current telemetry data, using machine learning tools, they predict the remaining resource, analyze the probability of failure and identify a potential emergency situation for each UAV node; -- generate recommendations for technical maintenance for each UAV component based on the forecast of the remaining service life, analysis of the probability of failure and identification of a potential emergency situation; - generate a report with recommendations for UAV maintenance; and send the generated report via the web interface to the user device for display.
2. The method of claim 1, wherein the wireless communication network includes at least one of: a cellular communication network, a satellite communication network, and a radio communication network.
3. The method according to claim 1, in which the noise filtering further includes compensation for data transmission delays based on the time synchronization of telemetry timestamps with the reference clock of the processing server.
4. The method according to claim 1, in which the machine learning means are pre-trained on a set of historical data including normal and emergency operating modes of the UAV nodes.
