A system and method for gale guesstimation

Abstract

The present disclosure discloses a gust (strong wind) estimation system (100) and a method (200) configured to detect, analyze, and predict harmful strong wind and crosswind conditions during vehicle operation. The system (100) includes a first sensing unit (102) that measures a relative apparent wind speed for a moving vehicle and a second sensing unit that determines a vehicle speed vector. An electronic control unit (116) calculates the actual environmental wind speed by vector-analyzing the apparent wind speed and the vehicle motion vector using a vector algebra module (104). A tracking module (106) stores time-series wind speed data in a database (114), and a prediction module (108) predicts future wind conditions using machine learning-based time modeling. A threshold condition module (110) compares the predicted wind conditions with a predefined safety threshold (110a), and an alarm generation module (112) provides a real-time multimodal alarm and transmits wind condition intelligence to vehicle control and advanced driver assistance systems to improve vehicle safety.

Description

Technology Field

[0001] The present invention generally relates to the field of meteorology. More specifically, it relates to a system for estimating strong winds and the solution of related problems. Background Technology

[0002] The following background information is related to the present invention, but does not necessarily imply prior art.

[0003] Sudden extreme winds and cyclones pose significant risks to vehicles, pedestrians, and infrastructure, often leading to fatal road accidents. As these natural phenomena are difficult to predict and can occur without warning, drivers are currently unprepared to respond effectively. Existing wind monitoring systems typically rely on static weather station data or generalized forecasts, but these lack the granularity and real-time precision required to detect localized wind around moving vehicles. Furthermore, current systems fail to adequately handle the dynamic interaction between wind speed, vehicle speed, and direction, and cannot provide drivers with preemptive warnings of potential hazards. These limitations result in delayed or insufficient responses, increasing the likelihood of accidents caused by sudden gusts or extreme weather conditions.

[0004] Therefore, the need for a strong wind estimation system to mitigate the aforementioned disadvantages is raised. The problem to be solved

[0005] Some of the objectives of the present invention satisfied by at least one embodiment of the present invention are as follows.

[0006] The objective of the present invention is to improve one or more problems of the prior art or at least provide a useful alternative.

[0007] The objective of the present invention is to provide a strong wind estimation system and method.

[0008] Another objective of the present invention is to provide a system that improves vehicle safety in harmful wind and crosswind conditions.

[0009] Another objective of the present invention is to provide a system for detecting and predicting potentially dangerous wind conditions along a vehicle route.

[0010] Another objective of the present invention is to provide a system that generates a real-time alarm to warn a driver of harmful wind conditions.

[0011] Another objective of the present invention is to provide a system that recommends corrective measures to improve vehicle stability during adverse wind events.

[0012] Another objective of the present invention is to provide a system for continuously monitoring wind behavior to maintain spatiotemporal and local wind profiles.

[0013] Another objective of the present invention is to provide a system that integrates wind intelligence with a vehicle control system and a driver assistance system.

[0014] Another objective of the present invention is to provide a system that dynamically adjusts a safety threshold based on wind direction and vehicle behavior.

[0015] Another objective of the present invention is to provide a system that reduces the workload of the operator by automating preventive safety measures in hazardous wind conditions.

[0016] Another objective of the present invention is to provide a system that improves the overall safety of passengers without manual intervention by the driver.

[0017] Another objective of the present invention is to provide a system that improves preemptive decision-making under adverse environmental conditions.

[0018] Other objects and advantages of the present invention will become more apparent from the following description, and this is not intended to limit the scope of the invention. means of solving the problem

[0019] The present invention provides a system and a method configured to estimate, analyze, and predict harmful wind and crosswind conditions acting on a vehicle during operation. The system operates continuously during vehicle movement and is configured to enhance the safety of the vehicle under strong winds and gale-grade wind conditions.

[0020] In one embodiment, the system is configured to measure the apparent wind experienced by a moving vehicle and to acquire vehicle behavior data including speed, direction, and yaw. Additionally, the system is configured to determine actual environmental wind conditions, including wind speed magnitude, wind direction, and crosswind components acting on the vehicle, by decomposing the apparent wind speed data and vehicle behavior data using vector-based operations.

[0021] In one embodiment, the system is configured to continuously sample, aggregate, and store wind-related data over time to generate a local temporal wind profile associated with a vehicle path. The stored data enables the identification of wind behavior patterns and variations encountered during vehicle operation.

[0022] In one embodiment, the system is configured to use machine learning-based temporal modeling to predict future wind conditions and identify potential hazardous or strong wind impact points along the vehicle path. The predicted wind conditions are evaluated against preset safety thresholds that are dynamically adjusted based on wind direction and crosswind angles for vehicle behavior.

[0023] In one embodiment, the system is configured to generate real-time multi-mode alerts and recommended correction measures for the driver or to transmit wind condition information to a vehicle control system and an advanced driver assistance system. This configuration enables the preemptive mitigation of wind-induced vehicle instability and improves overall vehicle safety under adverse wind conditions. Effects of the invention

[0024] The invention described in this specification has the following technical advantages in relation to a strong wind estimation system and method.

[0025] To accurately assess environmental wind conditions, the apparent wind speed of the vehicle is measured in real time.

[0026] The actual wind speed is calculated by decomposing the apparent wind speed and vehicle behavior vectors using vector algebra.

[0027] Continuously monitor wind conditions and aggregate data to generate temporal and local wind profiles.

[0028] Use machine learning-based temporal modeling to predict future wind conditions and identify potential strong wind impact points.

[0029] Predicted wind conditions are evaluated against dynamically adjustable safety thresholds for early risk detection.

[0030] It generates a real-time multi-mode alarm including visual, auditory, and tactile signals to warn the driver.

[0031] To enhance vehicle safety, corrective measures such as deceleration, route adjustment, or temporary stopping are recommended.

[0032] It transmits wind condition information to vehicle control systems and advanced driver assistance systems for preemptive intervention.

[0033] It is integrated with autonomous or semi-autonomous vehicle systems to automatically adjust vehicle speed, steering, or trajectory.

[0034] To optimize safety response, alarm sensitivity and threshold levels are adapted based on crosswind angle and vehicle behavior.

[0035] By storing wind data in a database to build historical records, prediction accuracy is improved over time.

[0036] It improves overall passenger safety by mitigating risks associated with harmful winds and strong wind conditions. Brief explanation of the drawing

[0037] With respect to a strong wind estimation system and method, the present invention will now be described with reference to the accompanying drawings. FIGS. 1A and FIGS. 1B illustrate an architecture diagram of a strong wind estimation system according to the present invention. FIGS. 2a and 2b illustrate a method for estimating strong winds according to the present invention. FIGS. 3a to 3d illustrate graphs showing wind direction and vehicle movement direction in different directions according to the present invention. Specific details for implementing the invention

[0038] Hereinafter, embodiments of the present invention will be described with reference to the attached drawings.

[0039] The embodiments are provided to convey the scope of the invention in detail and clearly to those skilled in the art. Numerous details regarding specific components and methods are presented to aid in a complete understanding of the embodiments of the invention. However, it will be obvious to those skilled in the art that the details provided in the embodiments of the invention should not be interpreted as limiting the scope of the invention. In some embodiments, known processes, known device structures, and known technologies are not described in detail.

[0040] The terms used in this invention are for the purpose of describing specific embodiments only and are not intended to limit the scope of this invention. As used in this invention, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. The terms “comprising,” “comprising,” “comprising,” and “having” are open-ended connecting phrases that specify the presence of the mentioned features, elements, modules, units, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or groups thereof.

[0041] Where one element is referred to as being "mounted," "connected," or "combined" with another element, it may be directly mounted, connected, or combined with said other element. As used herein, the term "and / or" includes any and all combinations of one or more of the elements enumerated in association.

[0042] Sudden extreme winds, including gales and cyclones, pose significant risks to vehicles, pedestrians, and infrastructure, often leading to fatal road accidents. These phenomena are difficult to predict and can occur without warning, preventing drivers from being prepared to respond effectively. Existing wind monitoring systems typically rely on static weather station data or generalized forecasts, but these lack the resolution and real-time precision required to detect localized wind around moving vehicles. Furthermore, current systems fail to adequately handle the dynamic interaction between wind speed, vehicle speed, and direction, and cannot provide drivers with preemptive warnings of potential hazards. These limitations result in delayed or insufficient responses, increasing the likelihood of accidents caused by sudden gusts or hazardous wind conditions. Therefore, there is a need for a system capable of continuously monitoring, predicting, and warning drivers of environmental wind conditions under variable and extreme wind scenarios to enhance safety and vehicle stability.

[0043] Accordingly, the present invention provides a strong wind estimation system and method (hereinafter referred to as system (100) and method (200)). The present invention will be described with reference to FIGS. 1a to 3d.

[0044] Referring to FIGS. 1a and 1b, the present invention relates to a strong wind estimation system (100) configured to operate in a moving vehicle for real-time detection, estimation, prediction, and mitigation of harmful winds, crosswinds, and strong wind conditions.

[0045] The system (100) includes a first sensing unit (102), a second sensing unit, an electronic control unit (116), a vector algebra module (104), a tracking module (106), a prediction module (108), a critical condition module (110), an alarm generation module (112), and a database (114). The system (100) is configured to interface and interact with existing vehicle subsystems, including but not limited to a speedometer, an inertial measurement unit, a global positioning system (GPS) module, a yaw sensor, and a vehicle control system, thereby enabling the generation of local and vehicle-specific wind condition information during vehicle movement.

[0046] The first sensing unit (102) is configured to measure the apparent wind velocity for a moving vehicle and generate a corresponding first sensing signal. In one embodiment, the first sensing unit (102) operates independently of mechanical rotation by including one or more acoustic anemometers configured to measure wind velocity using ultrasonic signal propagation. This configuration enables accurate wind measurement under turbulent airflow conditions and minimizes sensor degradation due to mechanical wear. The first sensing unit (102) may be positioned along the four corners of the vehicle rooftop or surrounding areas to detect multidirectional wind vectors. The apparent wind velocity measured by the first sensing unit (102) includes both magnitude and direction and represents the combined effect of actual environmental wind conditions and vehicle behavior.

[0047] The second sensing unit is configured to provide a vehicle speed vector and generate a second sensing signal indicating the instantaneous motion state of the vehicle. The vehicle speed vector includes vehicle speed, heading, yaw rate, acceleration, and position data derived from one or more onboard systems, including a speedometer, an inertial measurement unit, a GPS module, a yaw sensor, or other vehicle motion sensors. The second sensing signal provides continuously updated information regarding vehicle movement and orientation, which is utilized in subsequent wind vector calculations.

[0048] The electronic control unit (116) is communicably coupled to the first sensing unit (102) and the second sensing unit and is configured to coordinate the operation of the vector algebra module (104), tracking module (106), prediction module (108), critical condition module (110), and alarm generation module (112). The electronic control unit (116) executes programmed commands for processing sensor inputs, performing vector operations, managing data storage in the database (114), executing machine learning inference, evaluating safety thresholds, and generating alarms or vehicle control commands.

[0049] The vector algebra module (104) is configured to calculate the actual environmental wind speed by performing a vector decomposition between the apparent wind speed vector measured by the first sensing unit (102) and the vehicle speed vector provided by the second sensing unit. Through vector subtraction and direction decomposition, the vector algebra module (104) derives the actual wind conditions acting on the vehicle by separating the influence of vehicle behavior from the measured apparent wind speed.

[0050] In one embodiment, the vector algebra module (104) includes a vehicle driving wind speed module (104a), a vehicle actual speed module (104b), and an actual wind speed module (104c). The vehicle driving wind speed module (104a) identifies the apparent wind speed and direction measured by the first sensing unit (102) during vehicle movement. The vehicle actual speed module (104b) determines the vehicle speed vector using a second sensing signal including the vehicle speed and driving direction. The actual wind speed module (104c) calculates the actual wind speed vector by decomposing the apparent wind speed vector with respect to the vehicle speed vector. Through these calculations, the magnitude of the wind speed, the wind direction, and the crosswind component acting on the vehicle can be accurately determined, which are important parameters for evaluating vehicle stability under wind-induced loads.

[0051] The tracking module (106) is configured to continuously monitor, sample, aggregate, and store wind speed vectors calculated over time. In one embodiment, the tracking module (106) collects at least 500 wind speed samples at intervals of approximately 10 seconds. The tracking module (106) stores the collected wind speed data in conjunction with the database (114) and generates historical and temporal wind profiles associated with specific vehicle locations and paths. The stored data forms a continuously evolving dataset that reflects the local wind behavior encountered by the vehicle during operation.

[0052] The prediction module (108) is configured to apply machine learning-based temporal modeling to the processed wind data and the historical time series generated by the tracking module (106) and to predict future wind speed vectors. In one embodiment, the prediction module (108) employs a Long Short-Term Memory (LSTM) neural network trained via time-based backpropagation and optimized using a mean squared error loss function. The LSTM neural network receives sequential wind speed vectors as input, models temporal dependencies and evolving wind patterns, and outputs predicted future wind speed magnitude and direction. Additionally, the prediction module (108) is configured to identify potential strong wind impact points along the vehicle path by correlating the predicted wind conditions with vehicle trajectory and location data.

[0053] The critical condition module (110) is configured to compare the predicted wind speed vector generated by the prediction module (108) with a preset safety threshold (110a). The preset safety threshold (110a) corresponds to a number of wind severity levels, including moderate, strong, severe, and strong wind conditions. The critical condition module (110) dynamically adjusts the preset safety threshold (110a) based on the wind speed magnitude, wind direction, and crosswind angle for the vehicle speed vector. The crosswind angle is defined as the angular difference between the wind direction vector and the vehicle speed vector. If the crosswind angle exceeds a preset vehicle safety risk threshold, the sensitivity of the critical condition module (110) increases, enabling early detection and classification of hazardous wind conditions.

[0054] The alarm generation module (112) is configured to generate a real-time alarm when the predicted wind conditions exceed one or more preset safety thresholds (110a). The alarm generation module (112) provides multi-mode alarms including visual alarms displayed on the vehicle instrument panel or infotainment system, auditory alarms such as warning sounds or voice prompts, and tactile alarms such as vibrations transmitted through the steering wheel or vehicle seat. In one embodiment, the alarm generation module (112) provides recommended corrective measures including vehicle speed reduction, change of driving path, adjustment of yaw or stability control parameters, or temporary stopping of the vehicle until wind conditions improve. The alarm generation module (112) is coupled with the critical condition module (110) so that the alarm is context-aware, timely, and proportional to the assessed risk level.

[0055] In one embodiment, the alarm generation module (112) is operably coupled to one or more vehicle output devices configured to deliver alarm information to vehicle occupants. These output devices include, but are not limited to, a vehicle instrument panel display, a head-up display, a center infotainment display, and an auxiliary dashboard indicator for providing visual alarms. Auditory alarms are generated through one or more vehicle audio output devices, including built-in speakers, a warning buzzer, or a voice notification system integrated with the infotainment unit. Tactile alarms are generated by operating a tactile feedback device, including a steering wheel vibration actuator, a seat vibration module, a pedal feedback mechanism, or a seatbelt tensioning device. The alarm generation module (112) ensures that the manner, intensity, and duration of the alarm are suitable for the predicted wind risk level and vehicle operating conditions by selectively activating one or more of these output devices based on the wind speed risk class determined by the critical condition module (110).

[0056] In one embodiment, the system (100) is integrated with an autonomous or semi-autonomous vehicle control system. In this configuration, upon detection or prediction of hazardous wind conditions or strong wind conditions, the system (100) is configured to automatically change vehicle operating parameters, including speed, steering input, lane keeping, or trajectory, without driver intervention. This integration enables the preemptive mitigation of wind-induced vehicle instability, thereby improving overall vehicle safety.

[0057] In one embodiment, when the vehicle is stationary, the ambient wind acting on the vehicle generates measurable force components, including crosswind and drag, despite the absence of vehicle movement. The first sensing unit (102) measures the apparent wind speed, and in this configuration, since the vehicle speed vector is zero, the apparent wind speed corresponds directly to the actual ambient wind conditions. From a physical perspective, the wind generates a quantifiable wind vector by applying a force proportional to its speed and the exposed surface area of ​​the vehicle. This vector can be decomposed to determine the wind speed magnitude, direction, and crosswind components independently of vehicle movement. This principle enables the capture and consideration of ambient wind condition information under stationary conditions and provides consistent and reliable information regarding ambient wind conditions for subsequent analysis, prediction, or integration with vehicle systems without requiring the vehicle to be in motion.

[0058] In one embodiment, the system (100) is configured to transmit wind condition data, predicted wind vectors, threshold evaluation results, and alarm status information to other vehicle systems and advanced driver assistance systems (ADAS) through one or more vehicle communication interfaces. These interfaces include, but are not limited to, a controller area network (CAN) bus, CAN-FD, FlexRay, automotive Ethernet, or other in-vehicle communication protocols. The electronic control unit (116) packages the calculated wind data and predicted risk indicators into standard or dedicated message frames that are transmitted to vehicle subsystems including an electronic stability control system, a traction control system, an adaptive cruise control module, a lane keeping assist system, and an autonomous driving controller.

[0059] In these embodiments, wind data received by the ADAS module is used to change or limit vehicle control strategies. For example, an adaptive cruise control system may reduce the target speed under predicted crosswind conditions, a lane keeping assist system may increase steering correction sensitivity, and an electronic stability control system may preemptively adjust the yaw control threshold in response to increased crosswind risk. In autonomous or semi-autonomous vehicle configurations, the transmitted wind data enables the path planning module to mitigate wind-induced instability by adjusting the vehicle trajectory, lane selection, or routing decisions.

[0060] In another embodiment, the system (100) is configured to share wind condition data with a navigation system and a route planning module. Predicted strong wind impact points identified by the prediction module (108) are transmitted to the navigation system to enable the generation of route-specific safety recommendations, alternative route recommendations, or delay warnings. In a specific configuration, wind condition data may be logged or transmitted to external systems such as a fleet management platform, a cloud-based analytics server, or vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) systems, thereby enabling coordinated awareness of hazardous wind conditions across multiple vehicles or geographical areas.

[0061] FIGS. 2a and 2b illustrate a method for estimating strong winds according to an embodiment of the present invention.

[0062] In step 202, the method (200) includes the step of measuring the apparent wind speed by the first sensing unit (102) and generating a first sensing signal.

[0063] In step 204, the method (200) includes the step of measuring the vehicle speed by the second sensing unit and generating a second sensing signal.

[0064] In step 206, the method (200) includes the step of processing first and second detection signals by an electronic control unit (ECU) (116) and generating a processed signal.

[0065] In step 208, the method (200) includes the step of calculating the actual environmental wind speed by performing vector decomposition between the first and second detection signals by the vector algebra module (104).

[0066] In step 210, the method (200) includes the step of monitoring by a tracking module (106) configured to continuously sample, aggregate, and store a processing signal calculated over time to generate time series data.

[0067] In step 212, the method (200) includes the step of predicting the processed signal and time series data using machine learning-based temporal modeling by the prediction module (108) and generating trained data.

[0068] In step 214, the method (200) includes the step of comparing the learned data, which is dynamically predicted by the critical condition module (110), with a preset safety threshold.

[0069] In step 216, the method (200) includes the step of generating a real-time driver alert by the alarm generation module (112) when the predicted calculation processing signal exceeds a preset safety threshold.

[0070] In step 218, the method (200) is configured to operate continuously to improve vehicle safety under harmful wind, crosswind and strong wind conditions.

[0071] FIG. 3a shows that the vehicle is moving at a normal, stable speed through the vehicle's direction of travel (153). The recent synthetic wind (151) represents the current wind acting on the vehicle, while the future synthetic wind (152) represents the wind direction predicted based on temporal modeling. The future synthetic wind (152) is only slightly different from the recent synthetic wind (151), showing that the influence of crosswinds is minimal. The magnitude of the wind speed of the predicted wind (152) is approximately 43.47 m / s, which is below the hazardous threshold. Overall, the graph shows normal wind conditions, and the recent and future wind vectors (151, 152) are aligned closely with the vehicle's direction of travel (153), showing that lateral forces are low and no corrective measures are required.

[0072] FIG. 3b shows the path of a vehicle traveling downward along a straight path in the direction of vehicle movement (153). The recent composite wind (151) represents the current wind directed laterally toward the direction of vehicle movement (153), which implies the presence of a crosswind component. The future composite wind (152) is predicted to deviate further from the recent wind (151) and form a larger angle with the direction of vehicle movement (153). This graph illustrates a potential instability scenario requiring caution, where the crosswind effect is intensified and lateral aerodynamic forces increase.

[0073] FIG. 3c shows that the vehicle is moving in a straight upward direction through the vehicle's direction of travel (153). Recently, the composite wind (151) exhibits a significant right crosswind with respect to the vehicle's direction of travel (153). The future composite wind (152) is further to the right of (151) and increases the angular deviation, showing intensifying crosswind conditions. This graph demonstrates that the magnitude of the wind speed and the lateral influence increase over time, indicating that the potential impact on vehicle stability is growing, and thus suggesting that monitoring or corrective measures are required.

[0074] FIG. 3d shows that the recent composite wind (151) and the future composite wind (152) are aligned on nearly the same path with minimal angular deviation. The direction of vehicle movement (153) is aligned with the two wind vectors. This graph shows that the wind influence is mainly longitudinal and the influence of crosswinds is negligible. This reflects stable wind conditions, low lateral forces, and normal operating conditions that require no correction measures.

[0075] The present invention provides a strong wind estimation system and method, and presents the following examples to explain the function and actual application cases.

[0076] In another exemplary embodiment, the vehicle encounters a crosswind acting perpendicular to its direction of motion. The system (100) detects changes in wind direction and wind speed magnitude through a first sensing unit (102) and processes this in a vector algebra module (104) to determine the composite wind for the vehicle. A prediction module (108) predicts increasing lateral wind, and a critical condition module (110) dynamically adjusts a safety threshold (110a) based on the crosswind angle. An alarm generation module (112) provides real-time visual, auditory, and tactile warnings to recommend to the user to reduce speed, adjust steering, or increase attention.

[0077] In an additional exemplary embodiment, the vehicle faces a tailwind or gust from the rear. The system (100) monitors the apparent wind speed (102) and the vehicle motion vector, and the vector algebra module (104) calculates the composite wind. The prediction module (108) predicts the intensification of the wind along the path, and when it approaches a threshold (110a), the alarm generation module (112) notifies the user to control acceleration or maintain a safe distance between vehicles.

[0078] In another scenario, under strong wind conditions where the wind direction fluctuates, the tracking module (106) collects high-frequency wind data, and the prediction module (108) predicts severe gusts and sudden changes in wind direction. The critical condition module (110) identifies hazardous conditions related to vehicle stability, and the alarm generation module (112) issues an emergency multi-mode alarm and ensures preemptive mitigation of wind risks by reducing speed or changing trajectory in conjunction with the vehicle control system.

[0079] In another exemplary embodiment including an open road or bridge crossing scenario, the first sensing unit (102) detects a lateral change in apparent wind direction indicating the occurrence of a crosswind. The prediction module (108) predicts an increase in crosswind magnitude using a temporal wind profile. The critical condition module (110) dynamically evaluates the predicted wind against an adjusted safety threshold (110a), and if an increased risk is identified, the alarm generation module (112) issues a real-time warning to the user to guide them to reduce speed and increase steering attention.

[0080] In an additional exemplary embodiment involving a stormy or mountainous region, the tracking module (106) identifies rapidly increasing wind intensity over a series of samples. The prediction module (108) predicts strong wind conditions along the vehicle path. When the critical condition module (110) confirms that the predicted wind conditions exceed a safety threshold (110a), the alarm generation module (112) generates an emergency multi-mode alarm and initiates a correction response in conjunction with the vehicle control system in a specific configuration.

[0081] The present invention provides a strong wind estimation system and method, and presents the following examples to explain the function and actual application cases.

[0082] In one exemplary embodiment, a user is driving on a coastal highway when a sudden strong crosswind occurs due to a storm. A first sensing unit (102) detects the apparent wind speed, and a second sensing unit provides the vehicle's speed vector. An electronic control unit (116) calculates the actual wind speed and crosswind component acting on the vehicle through a vector algebra module (104). A tracking module (106) stores wind data in a database (114), and a prediction module (108) predicts that the crosswind may intensify over the next few kilometers. A critical condition module (110) identifies that the predicted wind exceeds a preset safety threshold (110a), and an alarm generation module (112) issues a visual and tactile alarm to induce the user to reduce speed and maintain lane stability.

[0083] In one exemplary embodiment, a user is driving on an open highway on a windy afternoon. A first sensing unit (102) detects a gust pattern, and a second sensing unit tracks the vehicle's speed and heading. An electronic control unit (116) continuously updates the actual wind vector through a vector algebra module (104). A prediction module (108) predicts a series of gusts along a future path, and a critical condition module (110) compares the predicted data with safety limits. An alarm generation module (112) provides an audible warning and recommends a temporary speed reduction, while simultaneously transmitting wind condition information to the vehicle's stability control system to adjust traction and yaw control, thereby helping the user maintain safe handling.

[0084] In an exemplary embodiment, a user is driving a semi-autonomous vehicle on a mountain road where wind conditions change significantly due to the terrain. A first sensing unit (102) and a second sensing unit continuously provide real-time data to an electronic control unit (116). A vector algebra module (104) calculates the actual wind speed, and a tracking module (106) updates the historical wind profile stored in the database (114). A prediction module (108) identifies a strong wind zone ahead, and a critical condition module (110) generates a signal when the wind speed magnitude and crosswind angle exceed safety limits. An alarm generation module (112) outputs visual, auditory, and tactile warnings while simultaneously transmitting wind condition information to the semi-autonomous control system to automatically adjust the speed and lane position.

[0085] In one embodiment, while a user is driving a delivery vehicle along an urban route, sudden wind tunnels form between high-rise buildings. A first sensing unit (102) detects sudden fluctuations in apparent wind speed, and a second sensing unit tracks the acceleration and yaw of the vehicle. An electronic control unit (116) uses a vector algebra module (104) to decompose these vectors to determine the actual wind speed magnitude and the effect of crosswinds. A prediction module (108) predicts intermittent gusts that may affect vehicle stability. A critical condition module (110) detects that the wind exceeds a preset threshold (110a), activates an alarm generation module (112), provides tactile feedback through the steering wheel, and recommends corrective measures. Additionally, wind data is transmitted to a driver assistance module to automatically adjust braking and steering.

[0086] In one exemplary embodiment, a user is driving a long-distance truck on a flat highway where sudden strong winds occur. A first sensing unit (102) continuously measures the apparent wind speed, and a second sensing unit tracks the vehicle's speed and heading. An electronic control unit (116) calculates the actual environmental wind condition vector through a vector algebra module (104). A tracking module (106) updates the database (114), and a prediction module (108) predicts a high crosswind zone ahead. A critical condition module (110) identifies winds exceeding safety limits, thereby prompting an alarm generation module (112) to issue a multi-mode warning and recommend measures such as speed reduction and maintaining distance between vehicles. The wind condition information is transmitted to the truck's automatic stability and lane keeping system to respond to trailer sway, thereby ensuring the safety of the driver and cargo.

[0087] In a single operational configuration, the strong wind estimation system (100) is configured to operate continuously on a moving vehicle to evaluate and predict wind conditions in real time. The system (100) receives apparent wind speed measurements from a first sensing unit (102) and vehicle motion data from a second sensing unit, which are processed by an electronic control unit (116). A vector algebra module (104) decomposes the apparent wind speed data and the vehicle speed vector to calculate the actual environmental wind conditions acting on the vehicle. The calculated wind vectors are continuously sampled and aggregated by a tracking module (106) and stored in a database (114) to form a temporal wind profile. A prediction module (108) processes the stored and real-time wind data to predict future wind speed magnitude and direction. A critical condition module (110) evaluates the predicted wind conditions against a preset safety threshold (110a) that considers the wind speed magnitude and direction according to vehicle motion. When the predicted wind conditions exceed a defined threshold, the alarm generation module (112) generates a real-time notification to the driver, thereby enabling early recognition and response to harmful winds, crosswinds, and strong wind conditions while driving.

[0088] Advantageously, this system continuously monitors, calculates, and predicts wind conditions acting on moving vehicles in real time. In this operational configuration, apparent wind speed data and vehicle behavior data are processed together to determine the actual environmental wind conditions acting on the vehicle, thereby enabling an accurate assessment of both wind speed magnitude and direction. Furthermore, the system has the advantage of enabling predictive modeling to forecast future wind behavior before hazardous conditions occur by maintaining continuous sampling and temporal aggregation of wind data. By dynamically evaluating predicted wind conditions against safety thresholds that consider vehicle direction and crosswind influences, the system enables timely and preemptive driver alerts. This operational and integrated approach overcomes the limitations of static or generalized weather monitoring systems by providing early indications of potentially dangerous wind and gale conditions, thereby improving vehicle safety perception, reducing driver response times, and enhancing overall safety.

[0089] The functions described herein may be implemented in hardware, executed by a processor, or implemented by firmware or any combination thereof. Other examples and implementations fall within the scope and spirit of the invention and the appended claims. The invention may be implemented by a processor, hardware, firmware, hardwiring, or any combination thereof. Additionally, features implementing functions may be physically located at various locations, including distributed such that parts of the functions are implemented at different physical locations.

[0090] The description of the foregoing embodiments is provided for illustrative purposes only and is not intended to limit the scope of the invention. The individual components of a particular embodiment are generally not limited to that embodiment and are interchangeable. Such modifications are not deemed to be outside the scope of the invention, and all such modifications are considered to be included within the scope of the invention.

[0091] Technological advancement

[0092] The invention described in this specification has the following technical advantages with respect to a strong wind estimation system and method, but is not limited thereto.

[0093] To accurately assess environmental wind conditions, the apparent wind speed of the vehicle is measured in real time.

[0094] The actual wind speed is calculated by decomposing the apparent wind speed and vehicle behavior vectors using vector algebra.

[0095] Continuously monitor wind conditions and aggregate data to generate temporal and local wind profiles.

[0096] Use machine learning-based temporal modeling to predict future wind conditions and identify potential strong wind impact points.

[0097] Predicted wind conditions are evaluated against dynamically adjustable safety thresholds for early risk detection.

[0098] It generates a real-time multi-mode alarm including visual, auditory, and tactile signals to warn the driver.

[0099] To enhance vehicle safety, corrective measures such as deceleration, route adjustment, or temporary stopping are recommended.

[0100] It transmits wind condition information to vehicle control systems and advanced driver assistance systems for preemptive intervention.

[0101] It is integrated with autonomous or semi-autonomous vehicle systems to automatically adjust vehicle speed, steering, or trajectory.

[0102] To optimize safety response, alarm sensitivity and threshold levels are adapted based on crosswind angle and vehicle behavior.

[0103] By storing wind data in a database to build historical records, prediction accuracy is improved over time.

[0104] It improves overall passenger safety by mitigating risks associated with harmful winds and strong wind conditions.

[0105] The foregoing invention has been described with reference to embodiments that do not limit the scope and range of the invention. The detailed description provided herein is purely for illustrative and illustrative purposes.

[0106] The embodiments of this specification, their various features, and advantageous details are described below with reference to non-limiting embodiments. Descriptions of known components and processing techniques are omitted so as not to unnecessarily obscure the embodiments of the invention. The examples used in this specification are merely intended to aid in understanding how the embodiments may be practiced and to enable those skilled in the art to practice them. Accordingly, these examples should not be construed as limiting the scope of the embodiments of this specification.

[0107] As the foregoing description of specific embodiments sufficiently discloses the general characteristics of the invention, others may easily modify and / or adapt these specific embodiments to various applications by applying current knowledge without departing from the general concept, and such adaptation and modification should be understood and intended to be included within the equivalent scope of the disclosed embodiments. It should be understood that phrases or terms adopted herein are for illustrative purposes only and not for limiting purposes. Accordingly, although embodiments of the invention have been described in terms of preferred embodiments, those skilled in the art will recognize that modifications may be made within the spirit and scope of the embodiments described herein.

[0108] Any discussion regarding devices, articles, etc. included in this specification is intended solely to provide context for the present invention. It should not be construed that any part or all of this content constitutes part of the prior art or was general knowledge known in the field related to the present invention prior to the priority date of this application.

[0109] Although substantial emphasis has been placed on the components and parts of the preferred embodiments in this specification, it should be understood that many embodiments are possible and many modifications can be made to the preferred embodiments without departing from the principles of the invention. Such modifications in the preferred and other embodiments of the invention will be apparent to those skilled in the art from this specification, and therefore it should be clearly understood that the foregoing description is merely illustrative and not limiting of the invention. Explanation of the symbols

[0110] 100 System 102 1st detection unit 104 Vector algebra module 104a Wind speed module while driving 104b Vehicle actual speed module 104c Actual wind speed module 106 Tracking module 108 Prediction module 110 Critical condition module 110a threshold 112 Alarm generation module 114 database 116 Electronic Control Unit (ECU) 151 Recently, synthetic wind 152 Future synthetic wind direction 153 Vehicle movement direction 200-218 Method and Steps

Claims

Claim 1 As a vehicle wind estimation system (100), the system (100) comprises: a first sensing unit (102) configured to generate a first sensing signal by measuring apparent wind velocity; a second sensing unit configured to provide vehicle speed and generate a second sensing signal; an electronic control unit (ECU) (116) configured to process the first and second sensing signals and generate a processed signal - the ECU (116) comprises: a vector algebra module (104) configured to calculate the actual environmental wind speed by performing vector decomposition between the first and second sensing signals; a tracking module (106) configured to continuously sample, aggregate, and store the wind speed calculated over time to generate time series data; a prediction module (108) configured to predict the processed signal and the time series data using machine learning-based temporal modeling and generate trained data; and a threshold condition module (110) configured to compare the dynamically predicted trained data with a preset safety threshold -; and the predicted calculated processing signal is the The system (100) includes an alarm generation module (112) configured to generate a real-time driver alarm when a preset safety threshold is exceeded, and the system (100) is configured to operate continuously to improve vehicle safety under harmful wind, crosswind and strong wind conditions. Claim 2 In claim 1, the system (100) comprises a first sensing unit (102) configured to measure the first sensing signal independently of mechanical rotation. Claim 3 In claim 1, the first sensing unit (102) is distributed on the vehicle rooftop or periphery to detect multi-directional wind vectors, in a system (100). Claim 4 In claim 1, the system (100) wherein the first detection signal includes magnitude and direction and is relative to a moving vehicle. Claim 5 A system (100) according to claim 1, wherein the second detection signal includes speed, heading, yaw, and position data, and the data is derived from at least one of a speedometer, an inertial measurement unit (IMU), and a GPS. Claim 6 In claim 1, the vector algebra module (104) comprises a wind speed module (104a) while the vehicle is driving; a vehicle actual speed module (104b); and an actual wind speed module (104c), in a system (100). Claim 7 In claim 6, the system (100) is configured such that the wind speed module (104a) during vehicle driving identifies the first detection signal measured during vehicle movement. Claim 8 In claim 6, the actual speed module (104b) of the vehicle is configured to determine the second detection signal including the speed and direction of the vehicle, in a system (100). Claim 9 In claim 6, the actual wind speed module (104c) is configured to decompose the first and second detection signals and calculate the processed signal, the system (100). Claim 10 In claim 1, the system (100) comprises a processed signal that includes an actual wind speed vector that enables the determination of the wind speed magnitude, wind direction, and crosswind components acting on the vehicle. Claim 11 In claim 1, the system (100) comprises a processed signal that includes an actual vehicle speed vector that enables the determination of the vehicle speed, i.e., magnitude and vehicle direction. Claim 12 In claim 1, the system (100) is configured such that the tracking module (106) collects at least 500 of the first detection signal samples at intervals of approximately 10 seconds. Claim 13 In paragraph 12, the system (100) is configured such that the tracking module (106) stores the sample in a database (114) to establish a past wind speed profile. Claim 14 In claim 1, the prediction module (108) is configured to use a Long Short-Term Memory (LSTM) neural network, the system (100). Claim 15 In claim 14, the system (100) comprises an input layer configured to receive the processed signal through the vector algebra module (104); one or more LSTM layers configured to model temporal dependencies; a dense fully connected layer; and an output layer configured to output learned data including magnitude and direction. Claim 16 In claim 14, the system (100), wherein the LSTM neural network is trained using time-based backpropagation (BPTT) and optimized using a mean squared error (MSE) loss function. Claim 17 In claim 1, the prediction module (108) is configured to identify strong wind impact points along the vehicle path, the system (100). Claim 18 In claim 1, the above-mentioned preset safety threshold (110a) is based on the wind speed magnitude, direction, and relative crosswind angle for vehicle movement, in a system (100). Claim 19 In claim 1, the critical condition module (110) comprises a plurality of critical value (110a) levels corresponding to normal wind, strong wind, very strong wind and strong wind conditions, in a system (100). Claim 20 In paragraph 18, the above threshold level (110a) is dynamically adjusted based on the crosswind angle defined as the angle difference between the wind vector direction and the vehicle speed vector, in a system (100). Claim 21 In claim 18, a system (100) in which alarm sensitivity increases when the crosswind angle exceeds a preset stability risk threshold. Claim 22 In claim 1, the alarm generation module (112) is configured to generate visual, auditory, and tactile alarms, the system (100). Claim 23 In claim 1, the alarm generating module (112) is configured to provide recommended correction measures including speed reduction, route change, yaw control adjustment, or temporary stopping of the vehicle, in a system (100). Claim 24 In claim 1, the system (100) is integrated with an autonomous or semi-autonomous vehicle control system to automatically change the vehicle speed or trajectory. Claim 25 As a method for estimating strong winds for a vehicle (200), the method (200) comprises the steps of: generating a first detection signal by measuring the apparent wind speed by a first detection unit (102); generating a second detection signal by measuring the vehicle speed by a second detection unit; generating a processed signal by processing the first and second detection signals by an electronic control unit (ECU) (116); calculating the actual environmental wind speed by performing vector decomposition between the first and second detection signals by a vector algebra module (104); monitoring by continuously sampling, aggregating, and storing the calculated processed signal over time to generate time series data by a tracking module (106); predicting the processed signal and the time series data using machine learning-based temporal modeling by a prediction module (108) and generating learned data; comparing the dynamically predicted learned data with a preset safety threshold by a threshold condition module (110); and to an alarm generation module (112). The method (200) includes the step of generating a real-time driver alert when a predicted calculation processing signal exceeds the preset safety threshold, wherein the method (200) is configured to operate continuously to improve vehicle safety under harmful wind, crosswind and strong wind conditions. Claim 26 In claim 25, the machine learning-based temporal modeling comprises an LSTM neural network, method (200). Claim 27 In paragraph 25, the threshold value is dynamically changed based on the predicted wind direction for the vehicle's heading, method (200). Claim 28 In paragraph 25, the predicted strong wind impact point is conveyed as a path-specific safety recommendation, method (200). Claim 29 In paragraph 25, the alarm is generated in a multi-mode form including visual, auditory, and tactile feedback, method (200).

Images