Transportation track deviation rectification system based on dynamic deviation rectification parameter adjustment

Abstract

The invention relates to a transportation track deviation rectification system based on dynamic deviation rectification parameter adjustment. The transportation track deviation rectification system comprises a system integration subsystem, a data acquisition subsystem, a data processing subsystem, a track deviation rectification subsystem, an early warning subsystem and an optional track storage and track playback subsystem. The system realizes real-time matching and optimization of vehicle tracks through a high-precision map and a dynamically generated reference track, provides comprehensive input data in combination with a multi-source data fusion technology, and realizes anomaly detection and correction instruction generation by using an artificial intelligence algorithm and a dynamic threshold adjustment mechanism. The track storage subsystem supports historical data storage and rapid retrieval, and the track playback subsystem adjusts and optimizes transportation analysis through visual display and dynamic track. The system is suitable for complex terrains, severe weather and dynamic traffic environments, and safety and efficiency are remarkably improved especially in transportation of large electrical equipment. The modular design enables the system to have expansibility and universality, and meets the requirements of multi-scene transportation.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation management, and in particular to a transportation trajectory correction system based on dynamic correction parameter adjustment, which is particularly suitable for scenarios such as real-time correction of transportation trajectories, abnormal state warnings, and storage and playback analysis of historical trajectory data during the transportation of large power equipment. Background Art

[0002] In the transportation process of large equipment, the accuracy and safety of the transportation trajectory are of great significance to ensure the integrity of the equipment and improve the transportation efficiency. However, the existing transportation management technology still has many problems and shortcomings when facing complex transportation environments, which need further improvement and optimization.

[0003] The current transportation system has obvious limitations in trajectory collection accuracy. Most systems rely mainly on single GPS data or other low-precision positioning technologies to monitor the operation trajectory of transportation vehicles. However, in severe weather conditions or in complex terrain environments where signals are blocked, GPS signals are prone to drift or even loss, resulting in inaccurate trajectory monitoring results, which directly affects the safety and stability of transportation.

[0004] At the same time, the trajectory correction capabilities of existing transportation management systems are also relatively limited. Traditional correction mechanisms usually rely on fixed thresholds or preset parameters and lack the flexibility to adjust according to dynamic environmental changes. This mechanism is often unable to respond effectively to complex changes in the transportation environment (such as temporary construction, traffic control, or emergencies), which may cause vehicles to deviate from the planned path and even cause safety accidents. In addition, static correction methods are difficult to adapt to the needs of real-time changes in complex transportation scenarios, reducing the practicality of the system.

[0005] The existing early warning mechanism also has the problem of poor adaptability. Traditional early warning methods are usually based on fixed rules, such as setting static thresholds for parameters such as speed and inclination. However, such rules are difficult to effectively cope with dynamic changes in the actual transportation environment. For example, in the case of slippery roads, strong winds or other abnormal weather conditions, fixed thresholds may not reflect real-time risks, resulting in inaccurate or delayed early warning signals, further increasing the uncertainty and risk in the transportation process.

[0006] The current transportation trajectory management system is still insufficient in terms of multi-source data integration. Most systems only focus on the vehicle's own status data, and rarely combine other environmental data, such as traffic conditions, weather information or satellite images. The limitation of this single data source makes it difficult to fully understand and analyze the actual situation of the transportation environment, which significantly reduces the system's adaptability in complex situations. In addition, due to the lack of effective data fusion and comprehensive analysis methods, it is difficult for the system to provide accurate operation trajectories and reliable decision support.

[0007] The existing system also has certain deficiencies in terms of data storage and historical trajectory playback. The storage of transportation data usually lacks unified standards, the amount of data is limited and the utilization rate is low. Although some systems support the playback function of historical trajectories, they are usually limited to static display and fail to conduct comprehensive analysis and evaluation in combination with the environmental data at the time. This limitation makes it difficult for historical data to provide strong support for the optimization and improvement of subsequent transportation plans, which weakens the practical application value of the system.

[0008] In addition, the existing system relies heavily on human intervention, which is also a significant shortcoming. Many transportation management processes, including deviation correction and early warning, require the intervention of operators. This not only increases the complexity of operations, but may also cause delayed response or misjudgment due to human factors, thus affecting the efficiency and safety of transportation.

[0009] In general, the current transportation trajectory management system has obvious limitations in terms of data collection accuracy, deviation correction flexibility, early warning mechanism adaptability, multi-source data integration capabilities, and data storage and utilization efficiency. These problems are particularly prominent in complex transportation environments, and a more advanced technical solution is urgently needed to improve transportation efficiency and safety and adapt to dynamically changing complex scenarios. Summary of the invention

[0010] In order to solve the above problems in the prior art, the present invention proposes a transport track correction system based on dynamic correction parameter adjustment, the transport track correction system comprising a system integration subsystem, a data acquisition subsystem, a data processing subsystem, a track correction subsystem and an early warning subsystem;

[0011] The system integration subsystem is used to integrate with the data platform through the communication protocol to realize the interaction and communication of vehicle terminal data;

[0012] The data acquisition subsystem is used to collect vehicle operation status data and environmental data, and perform multi-source information fusion to provide input data required for trajectory analysis;

[0013] The data processing subsystem is used to use data analysis algorithms to combine historical data and real-time data to identify abnormal conditions during transportation and generate correction instructions;

[0014] The trajectory correction subsystem optimizes the vehicle's driving path through trajectory matching and dynamic parameter adjustment to ensure that the vehicle's trajectory meets the set target;

[0015] The early warning subsystem determines whether the vehicle operating status exceeds a set threshold range based on multi-source data fusion and dynamic adjustment mechanism, and triggers an alarm prompt when an abnormal operating status is detected.

[0016] The transport trajectory correction system further includes a trajectory storage subsystem and a trajectory playback subsystem; the trajectory storage subsystem is used to store historical trajectory data, environmental data and warning information during the transportation process; the trajectory playback subsystem is used for users to view historical trajectory data through the system interface, zoom and replay the trajectory, and visualize it in combination with historical environmental data, and optimize trajectory playback using a dynamic trajectory adjustment model.

[0017] The system integration subsystem adopts the MQTT protocol to realize communication with the IoT terminal management platform, receives and classifies vehicle terminal data through the publish-subscribe mode; is equipped with a service quality level (QoS) setting function to ensure that the message arrives at least once, and maintains the communication connection through the heartbeat detection mechanism, and supports automatic reconnection when the network is interrupted; performs integrity check and range verification on the received data, and maps the parsed data to a unified data model for use by subsequent subsystems; enables encrypted communication and identity authentication mechanisms, including transport layer security protocol (TLS) encryption and client certificate verification.

[0018] The data acquisition subsystem collects state parameters of the transport vehicle, including speed, acceleration, inclination, position and direction; and collects multi-source environmental data, including satellite images, real-time traffic information and meteorological information.

[0019] The data processing subsystem comprises:

[0020] Receive and process vehicle status information and environmental data from the data acquisition subsystem; use artificial intelligence adaptive algorithms to jointly analyze historical trajectory data and real-time sensor data to detect abnormal situations; optimize vehicle status data and environmental data through multi-sensor fusion algorithms; identify offsets or abnormal conditions in real time based on a dynamic threshold adjustment mechanism, and send adjustment instructions to the trajectory correction subsystem.

[0021] The trajectory correction subsystem matches the vehicle trajectory data through a high-precision map and a dynamically generated reference trajectory, and adjusts the correction direction and amplitude in real time according to the degree of deviation, environmental complexity and vehicle status through a dynamic correction parameter adjustment module, and dynamically generates adjustable reference trajectory points.

[0022] The formula of the dynamic correction parameter P of the dynamic correction parameter adjustment module is:

[0023]

[0024] in:

[0025] ‖d‖ represents the offset distance between the vehicle’s current position and the reference trajectory point;

[0026] is the second-order derivative of the path curvature;

[0027] θ is the steering angle of the vehicle that is dynamically adjusted;

[0028] α is the speed adjustment factor;

[0029] R is the path curvature radius;

[0030] is the normalized value of the speed adjustment factor. The speed should not exceed the maximum allowable speed v during dynamic adjustment. max ;

[0031] w1, w2, w3: weight parameters, which respectively control the impact of offset distance, path smoothness and speed adjustment on the total cost. The setting of weights depends on the scene requirements;

[0032] Φ(e,C) is the environmental complexity function, which depends on the offset error e and the environmental complexity C and is defined as:

[0033]

[0034] Among them, σ e is the standard deviation of the offset error, and C is the environmental complexity factor, which is calculated by weighting obstacle density, road width, and traffic conditions.

[0035] The early warning subsystem receives vehicle status parameters and environmental data, and processes them through multi-source data fusion technology; dynamically adjusts the safety threshold range, and compares the vehicle's current operating status with the threshold range in real time according to the operating environment; when an abnormal operating status is detected, it triggers an alarm prompt and outputs the abnormality type and adjustment suggestions.

[0036] The transportation described is the transportation of large-scale electric power equipment.

[0037] The transport trajectory correction system based on dynamic correction parameter adjustment of the present invention shows significant advantages in many aspects. The system realizes real-time matching and optimization of vehicle trajectories through high-precision maps, dynamically generated reference trajectories and correction parameter adjustment modules, significantly reduces offset errors, and thus improves the accuracy and reliability of the transport path. The application of multi-source data fusion technology enables the comprehensive combination of vehicle status data and environmental data, providing a reliable data basis for trajectory analysis, anomaly detection and path optimization, and greatly improving the adaptability of the system.

[0038] The system also uses artificial intelligence algorithms combined with a dynamic threshold adjustment mechanism to achieve real-time identification of deviations or abnormal situations, and can quickly generate correction instructions and early warning prompts to effectively ensure the safety of the transportation process. The trajectory storage subsystem supports the long-term preservation and rapid retrieval of historical data, and the trajectory playback subsystem provides important support for transportation optimization and comprehensive analysis through visual display and dynamic trajectory adjustment models. In addition, the system operates efficiently under complex terrain, severe weather and dynamic traffic conditions, which is particularly suitable for the transportation of large power equipment, significantly improving transportation efficiency and safety. The implementation of modular design makes the division of labor of each subsystem clear, with high scalability and versatility, able to adapt to the needs of various transportation scenarios, and easy to upgrade and maintain functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application, but do not constitute an improper limitation of the present invention. In the drawings:

[0040] Figure 1 A structural schematic diagram of a transport trajectory correction system based on dynamic correction parameter adjustment is shown. DETAILED DESCRIPTION

[0041] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0042] In order to better understand the present invention, specific implementation modes are described in detail below with reference to the accompanying drawings.

[0043] like Figure 1 As shown, this embodiment provides a transport track deviation correction system based on dynamic deviation correction parameter adjustment. The system includes a system integration subsystem 101, a data acquisition subsystem 102, a data processing subsystem 103, a track deviation correction subsystem 104, an early warning subsystem 105, a track storage subsystem 106 and a track playback subsystem 107. The above subsystems work together to realize the whole process from transport data collection and processing to real-time deviation correction, abnormal early warning and historical track playback.

[0044] The system integration subsystem is integrated with the IoT terminal management platform through the MQTT protocol to receive data from vehicle terminals and achieve efficient data interaction and communication. This subsystem is responsible for transmitting the collected vehicle status information, location data and other environmental information to the system, providing basic support for subsequent data processing and analysis.

[0045] The data acquisition subsystem is used to collect the speed, acceleration, inclination, position and direction of the transport vehicle in real time, and integrate multi-source environmental data such as satellite images, real-time traffic information and meteorological information through sensor fusion technology. The subsystem uses high-precision sensors and data fusion algorithms to ensure the real-time, comprehensive and reliable data, and provide accurate basic data for trajectory analysis in complex environments.

[0046] The data processing subsystem processes the vehicle status information and environmental data from the data acquisition subsystem in real time. By introducing an adaptive algorithm based on artificial intelligence, the subsystem comprehensively analyzes historical trajectory data and real-time sensor data, identifies abnormal conditions during transportation (such as path deviation or speed abnormality), and triggers the trajectory correction subsystem to make adjustments. In addition, the subsystem optimizes and integrates multi-source data in complex environments to improve the accuracy and efficiency of data analysis.

[0047] The trajectory correction subsystem is one of the core functional subsystems of the system. This subsystem matches and analyzes the vehicle trajectory data through high-precision maps and dynamically generated reference trajectories, and adjusts the correction direction and amplitude in real time according to the degree of deviation, environmental complexity and vehicle status. Through the dynamic correction parameter adjustment module, the subsystem can dynamically generate optimized reference trajectory points to adapt to special transportation environments such as areas without clear road signs or complex construction areas.

[0048] The early warning subsystem determines whether the vehicle's operating status exceeds the set early warning threshold range based on multi-source data fusion and dynamic adjustment mechanisms. The subsystem can dynamically adjust the early warning threshold according to real-time traffic conditions, weather changes and vehicle operating status. When the vehicle is detected to be speeding, tilting too much or in other abnormal operating conditions, the early warning subsystem immediately triggers an alarm to ensure transportation safety.

[0049] The track storage subsystem is used to store historical track data, environmental data, and warning information during transportation. The stored data supports long-term preservation and can be used for subsequent analysis and optimization of transportation plans. Through efficient database management technology, the subsystem can quickly retrieve historical data to provide a basis for track playback and transportation plan improvement.

[0050] The trajectory playback subsystem allows users to view historical trajectory data through the system interface and visualize it in combination with the environmental data at the time. The subsystem also introduces a dynamic trajectory adjustment model to optimize the replayed trajectory, reproduce the transportation path in a complex environment, support comprehensive trajectory evaluation and analysis, and provide strong support for future transportation decisions.

[0051] Each subsystem works together through software and hardware integration to form a complete transportation track correction and management system. This system can significantly improve the track monitoring accuracy, abnormality recognition ability and safety during the transportation of large equipment. The specific implementation plans of each subsystem are as follows:

[0052] The system integration subsystem 101 is integrated with the IoT terminal management platform through the MQTT protocol and is the core part for realizing data interaction and communication.

[0053] The system integration subsystem first adopts the MQTT protocol, which supports a lightweight publish-subscribe model and can efficiently handle the communication needs of large-scale vehicle terminal data. The subsystem implements data classification by defining message topics. For example, independent topic names are defined for vehicle parameters such as speed, position, and inclination, so as to facilitate accurate subscription and processing of data. At the same time, the quality of service level (QoS) of message transmission is set to ensure that the message arrives at least once, ensuring that the reliability of data transmission can be guaranteed even in the case of network fluctuations. In order to maintain the stability of the connection, the system has designed a heartbeat detection mechanism, setting a reasonable time interval to ensure continuous communication between the client and the server, and automatically reconnecting when the connection is interrupted.

[0054] In terms of receiving data, the system integration subsystem subscribes to multiple message topics pushed by the IoT terminal management platform. After receiving the data, the system will parse and verify the message. The data is usually in a structured format, such as a hierarchical key-value pair. During the parsing process, the system first checks the integrity of the data to ensure that all key fields have been transmitted; then verifies the value range, such as the speed must be within a reasonable range, and the location parameters (longitude and latitude) must meet the standards of geographic coordinates. The parsed data is mapped to a unified data model within the system to ensure that subsequent subsystems can use it efficiently.

[0055] In order to achieve efficient data transmission, the system integration subsystem uses internal message queue technology to send the parsed data to the data processing subsystem or other subsystems for further analysis. The message queue can support asynchronous transmission to ensure the stability of the system under high-load scenarios. All transmitted data uses a standardized format to facilitate cross-module use and reduce the performance overhead caused by format conversion.

[0056] In terms of system reliability, the system integration subsystem is designed with multiple fault-tolerant mechanisms. The disconnection reconnection function can detect the disconnection of the connection and automatically recover, and adopts a gradually increasing reconnection interval strategy to avoid increasing the system load due to frequent connection attempts. At the same time, the system will temporarily store the unsent data in the local cache during the disconnection period, and give priority to sending this data after the connection is restored to reduce the possibility of data loss.

[0057] To ensure the security of data communication, the system integration subsystem enables encrypted communication and encrypts data through the Transport Layer Security Protocol (TLS) to prevent interception or tampering during communication. In addition, the system also supports a security mechanism based on identity authentication, which ensures the legitimacy of data interaction through two-way verification of username, password and client certificate. For different terminal devices and message topics, the system is configured with refined permission control to ensure that each device can only access data topics related to its permissions, further improving the security of the system and the privacy protection of data.

[0058] Through the above design and implementation, the system integration subsystem can efficiently and reliably receive vehicle terminal data and communicate with the IoT terminal management platform, providing basic support for the operation of the entire transportation trajectory correction system.

[0059] The data acquisition subsystem 102 is used to collect various status parameters of the transport vehicle in real time, including speed, acceleration, inclination, position and direction, and integrate multi-source environmental data, such as satellite images, real-time traffic information and weather information.

[0060] The data acquisition subsystem first completes the real-time acquisition of vehicle status parameters through high-precision sensors. The speed and acceleration data are acquired in real time by the high-precision inertial measurement unit (IMU) installed on the vehicle. The IMU can record the dynamic state changes of the vehicle at a high sampling rate. The inclination data is measured by the inclination sensor, which is installed at the center of the vehicle to ensure accurate perception of the overall tilt state of the vehicle. The position and direction data are acquired through the differential global positioning system (DGPS) in conjunction with the geomagnetic sensor. DGPS significantly improves positioning accuracy through differential technology and is suitable for high-precision position monitoring under complex terrain conditions; the geomagnetic sensor is used to provide vehicle orientation information, which is especially important in scenes without clear reference objects.

[0061] The collection of multi-source environmental data is achieved through sensor fusion technology. Satellite image data is obtained by accessing the remote satellite image service interface, which regularly provides updated surface images with a resolution of up to sub-meter level, suitable for macro-monitoring of the transportation area environment. Real-time traffic information is obtained through the Internet of Things traffic data platform, including road conditions, traffic control information, etc., to ensure dynamic optimization of vehicle driving paths. Meteorological information is collected in real time by sensors connected to the meteorological service platform. The data includes key environmental parameters such as wind speed, rainfall, and temperature to support safety assessment under complex weather conditions.

[0062] In order to ensure the comprehensiveness and real-time nature of data collection, the data collection subsystem adopts a distributed data collection architecture. All sensors and external data sources are connected to the central data processing node through wireless communication protocols (such as LoRa or 5G) to achieve seamless data transmission. After preliminary timestamp alignment and error correction, the collected data are uniformly stored in the data buffer of the central node.

[0063] Sensor fusion technology is the key to the data acquisition subsystem. The fusion algorithm is used to achieve the fusion of multi-source data to improve the accuracy and stability of the data. For example, for the measurement data of vehicle position and speed, by fusing the absolute position data of DGPS with the dynamic speed data of IMU, it is possible to maintain a high positioning accuracy when the DGPS signal is weak or interrupted. The state prediction model of the fusion algorithm combines the dynamic characteristics of the vehicle with the measured values ​​to provide more reliable data results.

[0064] To improve the applicability of the system, the data acquisition subsystem supports environmental adaptability parameter adjustment. For example, during transportation, the system can dynamically adjust the sampling frequency and fusion strategy of the sensor according to the complexity of the environment. When the system detects that the resolution of satellite image data is reduced, it will increase the sampling frequency of ground sensors (such as IMU or tilt sensors) to compensate for the loss of accuracy.

[0065] The design of the data acquisition subsystem also focuses on reliability and redundancy. When a sensor fails, the system uses a redundant sensor mechanism to compensate for the data. For example, when the main DGPS module fails temporarily due to signal shielding, the system can call on the backup low-precision GPS module to jointly provide position data with the IMU.

[0066] Through the above technical means, the data acquisition subsystem 102 can collect the state parameters and environmental data of the transport vehicle in real time and comprehensively, and ensure the high accuracy and reliability of the data. These collected data provide a reliable basic support for subsequent trajectory analysis, anomaly detection and deviation correction operations.

[0067] The data processing subsystem 103 is used to process the vehicle status information and environmental data from the data acquisition subsystem in real time, and combines the adaptive algorithm of artificial intelligence to achieve comprehensive analysis and abnormality identification, providing a basis for trajectory correction.

[0068] The core function of the data processing subsystem is to receive, process and analyze vehicle status information and multi-source environmental data. The received data includes speed, acceleration, inclination, position, direction, as well as environmental data such as meteorological information, real-time traffic information and satellite images. The subsystem is connected to the data acquisition subsystem through a unified interface protocol to ensure seamless data transmission. In the data receiving stage, the subsystem first pre-processes the input data, including timestamp synchronization, data format unification and noise filtering, to ensure data integrity and consistency.

[0069] During the data analysis process, the data processing subsystem uses an adaptive algorithm based on artificial intelligence to achieve joint analysis of historical trajectory data and real-time sensor data. The algorithm uses neural networks and probabilistic models to predict the vehicle's expected trajectory and compare it with the real-time collected trajectory to detect deviations or anomalies. For example, for path deviation detection, the algorithm analyzes the deviation between the reference path generated by the historical trajectory and the real-time vehicle position, and dynamically adjusts the deviation tolerance range in combination with factors such as road structure and environmental obstacles to accurately identify anomalies.

[0070] For speed anomaly detection, the subsystem introduces a dynamic threshold adjustment mechanism. According to the traffic conditions and the current operating environment of the vehicle, the algorithm adjusts the upper and lower thresholds of the speed limit in real time. For example, on an open road, the upper speed limit is higher, while in narrow or complex terrain conditions, the threshold is dynamically lowered. The detection algorithm combines parameters such as vehicle acceleration changes, road slope and wind speed to determine whether the speed exceeds the safe range, and triggers the trajectory correction subsystem in abnormal situations.

[0071] The optimized fusion of multi-source data is another key function of the data processing subsystem. The subsystem uses a multi-sensor fusion algorithm to weightedly integrate vehicle status data with environmental data. Specifically, the system dynamically adjusts data weights based on the signal quality of the sensors (such as GPS signal strength and IMU noise level). For example, when the GPS signal is weak, the system will rely more on IMU data; when the satellite image quality is high, image data is used first to update the vehicle's location information. Through the weighted fusion of multi-source data, the subsystem can maintain high analysis accuracy and stability in complex environments.

[0072] The data processing subsystem also has the ability to identify and provide feedback on abnormal situations in real time. Once an abnormal situation is identified, such as path deviation or speed exceeding the limit, the subsystem will immediately send an adjustment instruction to the trajectory correction subsystem. The instruction includes the type of abnormality, correction suggestions, and current vehicle status parameters. This real-time feedback mechanism can significantly improve the system's response speed to emergencies and reduce the impact of abnormalities on the transportation process.

[0073] In addition, to improve the efficiency of data processing, the subsystem introduces a distributed computing architecture. In the case of high data traffic, the subsystem can distribute processing tasks to multiple computing nodes and use parallel computing to quickly complete complex data analysis. The data processing results are stored in a temporary cache in a unified format to facilitate subsequent subsystem calls.

[0074] Through the above-mentioned technical means, the data processing subsystem 103 can efficiently and accurately analyze vehicle status information and environmental data, identify abnormal conditions during transportation, and realize real-time adjustment of the vehicle's running trajectory by triggering the trajectory correction subsystem, thereby improving the safety and reliability of the transportation system.

[0075] The trajectory correction subsystem 104 is one of the core functional subsystems of the system. Its main function is to match and analyze the vehicle trajectory data through the high-precision map and the dynamically generated reference trajectory, and adjust the correction direction and amplitude in real time according to the degree of deviation, environmental complexity and vehicle status. The technical realization, implementation details and creative formula of this subsystem are described in detail below.

[0076] The trajectory correction subsystem receives real-time trajectory data, environmental data, and vehicle status parameters from the data acquisition subsystem and the data processing subsystem. The current trajectory of the vehicle is compared with the preset reference trajectory through the high-precision map. The key information of the matching trajectory includes position coordinates, curvature radius, and direction vector. The road information stored in the high-precision map is recorded in the Geographic Information System (GIS) format, supporting sub-meter positioning accuracy.

[0077] The subsystem matches and corrects the vehicle's real-time position data. The system determines the direction and magnitude of the trajectory deviation by measuring the shortest distance between the vehicle's current position and the reference trajectory point, and calculates the required adjustment parameters in real time. When the deviation is small, the trajectory adjustment only involves a small steering correction; when the deviation is large or the environment becomes more complex, the dynamic correction parameter adjustment module will optimize the correction scheme in real time to ensure the safety and stability of the correction effect.

[0078] The dynamic correction parameter adjustment module is the core part of this system, which mainly generates optimized reference trajectory points according to the degree of deviation, environmental complexity and vehicle status. Its core formula is:

[0079] Assume the current position of the vehicle is (x, y) and the reference trajectory point is (x r ,y r ), the offset vector is d=(xx r ,yy r ). The dynamic correction parameter P includes the steering angle θ, the speed adjustment factor α and the path curvature radius R. The formula is specifically expressed as follows:

[0080]

[0081] in:

[0082] ‖d‖ represents the offset distance between the vehicle’s current position and the reference trajectory point;

[0083] is the second-order derivative of the path curvature, which is used to measure the smoothness of the trajectory; s represents the arc length on the reference trajectory, which is the cumulative distance along the path from the starting point of the path to the current position.

[0084] The normalized value of the speed adjustment factor α ensures that the speed does not exceed the maximum allowable speed v during dynamic adjustment. max ;

[0085] Φ(e,C) is the environmental complexity function, which depends on the offset error e and the environmental complexity C and is defined as:

[0086]

[0087] Among them, σ e is the standard deviation of the offset error, and C is the environmental complexity factor, which is calculated by weighting obstacle density, road width, and traffic conditions.

[0088] The above formula describes a dynamic correction parameter optimization model, which dynamically adjusts the vehicle's steering angle (θ), speed adjustment factor (α) and path curvature radius (R) by minimizing the vehicle's comprehensive cost function to achieve accurate following of the reference trajectory.

[0089] The optimization goal is to minimize the following three costs:

[0090] Offset distance cost (‖d‖ 2 ).

[0091] Path smoothness cost

[0092] Speed ​​adjustment cost

[0093] Finally, (θ, α, R) is found so that the vehicle follows the reference trajectory in an optimal way.

[0094] w1,w2,w3: weight parameters, which respectively control the impact of offset distance, path smoothness and speed adjustment on the total cost. The weight setting depends on the scene requirements, for example:

[0095] If path accuracy is a priority, w1 can be increased;

[0096] If vehicle stability is a priority, w2 can be increased;

[0097] If the environment is complex and the speed needs to be strictly limited, w3 can be added.

[0098] Input: vehicle current position (x, y), reference trajectory point (x r ,y r ), environmental complexity C.

[0099] Output: optimal dynamic correction parameters P = (θ, α, r).

[0100] By comprehensively optimizing the offset distance, path smoothness, and speed adjustment cost, the vehicle is ensured to smoothly and safely follow the reference trajectory. The environmental complexity function Φ(e,C) provides dynamic response capabilities to complex factors such as obstacle density and road width. This formula can be applied to path planning and real-time control in autonomous driving systems, and is suitable for scenarios such as highways, urban traffic, and unmanned vehicle navigation.

[0101] The dynamic correction parameter adjustment module can ensure the smoothness of the trajectory while comprehensively considering the impact of environmental complexity on the correction strategy.

[0102] When performing dynamic correction, the trajectory correction subsystem calculates the adjusted steering angle, speed and path curvature in real time and sends the optimized reference trajectory points to the vehicle control module. This module is responsible for performing steering, acceleration or deceleration operations to ensure that the vehicle gradually returns to the reference trajectory.

[0103] In areas without clear road signs or complex construction areas, the trajectory correction subsystem uses satellite images and lidar point clouds to generate virtual reference trajectories. The virtual trajectories are dynamically generated based on local environmental features, and their parameters are optimized using the above formula to meet the needs of complex scenarios.

[0104] Through the above technical means, the track correction subsystem 104 can efficiently and accurately complete track matching and correction operations, and realize intelligent and highly reliable track adjustment in various complex transportation environments. The system significantly improves transportation safety and operation efficiency, and provides comprehensive technical support for the transportation of large equipment.

[0105] The early warning subsystem 105 comprehensively monitors the vehicle operation status based on multi-source data fusion and dynamic adjustment mechanism, and determines whether it exceeds the set early warning threshold range. Through comprehensive analysis of real-time traffic conditions, weather changes and vehicle operation status, the subsystem can dynamically adjust the early warning threshold and trigger an alarm prompt in time when an abnormal operation status is detected to ensure the safety and efficiency of the transportation process.

[0106] The early warning subsystem receives real-time data from the data acquisition subsystem, including state parameters such as vehicle speed, acceleration, inclination, position and direction, as well as environmental data such as real-time traffic information and weather information. To ensure the accuracy of the early warning, the subsystem uses multi-source data fusion technology to weight and integrate different data sources, and dynamically adjusts the weights according to the real-time and reliability of the data. For example, in rainy and snowy weather conditions, the system increases the weight of meteorological data in order to make more sensitive judgments on landslide risks or slippery road conditions.

[0107] In the process of judging the operating status, the early warning subsystem first standardizes the input data to ensure that data of different dimensions have a unified analysis scale. Then, the subsystem compares the current operating status of the vehicle with the set safety threshold range. The safety threshold range includes but is not limited to:

[0108] Speed ​​Thresholds: Dynamically adjust upper and lower speed limits based on road type, current traffic flow, and weather conditions. For example, set a higher speed limit on highways and a lower speed limit in narrow or construction zones.

[0109] Tilt angle threshold: The maximum permissible tilt angle is set based on the vehicle's load and road slope. When the vehicle's tilt angle approaches or exceeds the threshold, the system identifies the risk of rollover and triggers an early warning.

[0110] Acceleration threshold: monitors the acceleration or deceleration process of the vehicle and dynamically adjusts the safe range of acceleration, especially when the vehicle is driving on complex roads or in emergency braking situations, to accurately identify abnormal changes in acceleration.

[0111] The dynamic adjustment mechanism of the warning subsystem can automatically optimize the threshold setting according to the complexity of the environment. For example, when the road is slippery and the traffic is dense, the system will reduce the warning thresholds for speed and acceleration to increase the sensitivity of the system; while when the road is flat and the traffic conditions are good, the system will appropriately relax the threshold range to reduce unnecessary alarms.

[0112] When an abnormal operating state is detected, the early warning subsystem immediately triggers an alarm prompt and sends an alarm to the driver and the monitoring center through sound and light alarms, vehicle display prompts or remote notifications. The alarm content includes the type of abnormality (such as speeding, excessive tilt, etc.), the vehicle's current state parameters and recommended adjustment measures. The system also supports a graded alarm mechanism to adjust the alarm intensity according to the severity of the abnormal situation. For example, for minor speeding behaviors, the driver is only prompted to adjust the speed through the display; for situations with a higher risk of overturning, a high-intensity sound and light alarm is used to remind and notify the monitoring center to intervene.

[0113] In addition, the early warning subsystem continuously optimizes the early warning strategy through an adaptive learning model. By analyzing historical operating data, the system can identify common abnormal patterns and improve the accuracy of early warnings in similar scenarios. For example, under specific road conditions, the system can dynamically adjust the threshold based on previous accident data to reduce the occurrence of false alarms and missed alarms.

[0114] Through the above technical means, the early warning subsystem 105 can monitor the vehicle operation status in real time, and provide accurate early warning information by combining multi-source data and dynamic adjustment mechanisms to ensure safety during transportation and flexibility in dealing with complex environments.

[0115] The track storage subsystem 106 is used to store historical track data, environmental data and warning information during the transportation process, and provides reliable basic support for subsequent track playback, transportation plan optimization and safety analysis. Through efficient database management technology, the subsystem can ensure long-term storage and rapid retrieval of data while ensuring data integrity and consistency.

[0116] This subsystem receives real-time data from the data acquisition subsystem and the early warning subsystem, and archives the data through a unified storage interface. The types of data stored include but are not limited to:

[0117] Historical trajectory data: records all the location points and timestamps that the vehicle passes during transportation, covering key information such as location coordinates, direction, and speed.

[0118] Environmental data: includes multi-source environmental information related to transportation, such as weather conditions, road conditions and traffic information, to facilitate analysis of the impact of environmental factors on transportation efficiency and safety.

[0119] Warning information: Detailed storage of warning events triggered during transportation, including abnormality type (such as overspeed or tilt), warning time, event location and corresponding adjustment suggestions, providing a complete record for subsequent safety assessment.

[0120] During the data storage process, the trajectory storage subsystem adopts a hierarchical storage structure to allocate different types of data to corresponding storage levels:

[0121] Real-time storage layer: used to temporarily save the latest collected real-time data and support high-frequency read and write operations.

[0122] Historical storage layer: Archive the completed transportation task data and use compression storage technology to reduce storage space occupancy.

[0123] Analysis storage layer: A dedicated data area is reserved for trajectory playback and optimized analysis, supporting fast query and batch data analysis.

[0124] To improve storage efficiency and retrieval performance, the subsystem uses efficient database management technologies, including index optimization, data partitioning, and parallel query processing. Trajectory data is stored in a spatial index format, such as a geospatial index structure based on an R-tree or quadtree, which can significantly speed up the query of location-related data. For example, when a user needs to retrieve trajectory data within a specific time period, the system can quickly locate the target data through the index, improving retrieval efficiency.

[0125] At the same time, the trace storage subsystem supports data integrity verification and automatic backup functions. Each time data is written, the system verifies the integrity of the data through a hash verification algorithm and regularly performs data snapshots to prevent accidental data loss. In addition, the system provides a multi-copy storage mechanism to synchronize data to multiple storage nodes to improve data reliability and disaster recovery capabilities.

[0126] In terms of long-term data preservation, the trajectory storage subsystem supports a variety of compression algorithms (such as differential compression and time series compression) to reduce the storage space occupied by historical data. For example, for continuous trajectory points, the system only stores key position change points and reconstructs the complete trajectory through interpolation algorithms, thereby significantly reducing storage requirements while ensuring trajectory accuracy.

[0127] The trajectory storage subsystem also provides a flexible query and analysis interface that allows users to quickly retrieve required data based on a variety of conditions. For example, users can query historical records by time range, geographic area, or specific warning type. The subsystem's interface supports standardized query languages ​​(such as SQL) and visual data query tools, making it easy for technicians and managers to directly obtain the required information.

[0128] Through the above technical means, the trajectory storage subsystem 106 not only realizes the efficient storage and management of data during transportation, but also provides strong data support for trajectory playback, solution optimization and safety analysis, thereby improving the practicality and reliability of the system.

[0129] The trajectory playback subsystem 107 is designed to provide users with a comprehensive and intuitive historical trajectory data playback function, support visualization combined with the environmental data at the time, reproduce the transportation path under complex environment, and provide important support for future transportation decisions. Through the dynamic trajectory adjustment model, the subsystem can not only optimize the trajectory playback effect, but also conduct a comprehensive evaluation and analysis of the historical transportation path.

[0130] The trajectory playback subsystem receives historical trajectory data and related environmental data provided by the trajectory storage subsystem, and supports users to flexibly view the transportation path within a specific time period through an interactive interface. The core functions of the subsystem include trajectory playback, visualization, dynamic adjustment, and comprehensive evaluation and analysis.

[0131] In terms of the trajectory playback function, the system gradually presents the historical driving path of the vehicle in chronological order, and combines the environmental data of each time node (such as weather conditions, traffic flow, road conditions, etc.) to achieve a true reproduction of the historical transportation process. Users can flexibly adjust the playback process by controlling the playback speed, pausing, fast forward or rewinding, so as to focus on certain key time periods or locations. In addition, the system supports zooming in and out of the trajectory, and users can choose different perspectives to view the overall picture of the transportation path or the details of a specific area.

[0132] The visualization function of the trajectory playback subsystem is realized by integrating the geographic information system (GIS). The system superimposes trajectory data, environmental data and warning information on a high-precision map and displays them in a multi-layer manner. Different layers display information such as trajectory paths, warning point markers, weather conditions and road conditions. Users can choose to turn on or off specific layers according to their needs to focus on the content of interest. For example, users can only display the speeding or tilt alarm points of the vehicle to analyze the distribution of a specific abnormal type.

[0133] The dynamic trajectory adjustment model is one of the core innovations of the trajectory replay subsystem. The model adjusts historical trajectories through optimization algorithms to correct trajectory deviations caused by sensor errors or data loss, and dynamically generates more reasonable transportation paths based on changes in environmental data. For example, in areas with poor road conditions, the model recalculates the trajectory based on road width and obstacle distribution to reproduce a more realistic transportation path. The goal of dynamic trajectory adjustment is to make the replayed trajectory closer to the actual driving path of the vehicle during transportation, thereby improving the accuracy and reliability of the analysis.

[0134] In terms of comprehensive trajectory evaluation and analysis functions, the trajectory playback subsystem provides a series of tools based on data analysis. The system can automatically generate a transportation efficiency analysis report based on the time range and area selected by the user, including indicators such as transportation time, average speed, and energy consumption level. Users can also perform statistical analysis on the frequency and spatial distribution of warning events to identify common risk points and improve transportation plans. For example, the system can generate an accident risk heat map that shows the probability of abnormal occurrence under specific road sections or conditions, providing intuitive support for future transportation decisions.

[0135] To enhance the user experience, the trajectory playback subsystem also supports multiple playback modes, including normal mode, quick analysis mode, and environmental focus mode. In the quick analysis mode, the system prioritizes the key nodes of the trajectory and skips the playback process of smooth sections to save time. In the environmental focus mode, the system displays the trajectory in conjunction with specific environmental data (such as traffic flow or weather conditions) to highlight the impact of environmental factors on the transportation process.

[0136] Through the above technical design, the trajectory playback subsystem 107 can not only truly restore the historical transportation process, but also provide in-depth analysis and evaluation, providing strong support for optimizing future transportation decisions, and further improving the intelligence level and practical value of the transportation system.

[0137] The above description is only a preferred embodiment of the present invention, so all equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A transport track correction system based on dynamic correction parameter adjustment, characterized in that: The transport track deviation correction system includes a system integration subsystem, a data acquisition subsystem, a data processing subsystem, a track deviation correction subsystem and an early warning subsystem; The system integration subsystem is used to integrate with the data platform through the communication protocol to realize the interaction and communication of vehicle terminal data; The data acquisition subsystem is used to collect vehicle operation status data and environmental data, and perform multi-source information fusion to provide input data required for trajectory analysis; The data processing subsystem is used to use data analysis algorithms to combine historical data and real-time data to identify abnormal conditions during transportation and generate correction instructions; The trajectory correction subsystem optimizes the vehicle's driving path through trajectory matching and dynamic parameter adjustment to ensure that the vehicle's trajectory meets the set target; The early warning subsystem determines whether the vehicle operating status exceeds a set threshold range based on multi-source data fusion and dynamic adjustment mechanism, and triggers an alarm prompt when an abnormal operating status is detected.

2. A transport track deviation correction system based on dynamic deviation correction parameter adjustment as claimed in claim 1, characterized in that: The transport trajectory correction system further includes a trajectory storage subsystem and a trajectory playback subsystem; the trajectory storage subsystem is used to store historical trajectory data, environmental data and warning information during the transportation process; the trajectory playback subsystem is used for users to view historical trajectory data through the system interface, zoom and replay the trajectory, and visualize it in combination with historical environmental data, and optimize trajectory playback using a dynamic trajectory adjustment model.

3. A transport track deviation correction system based on dynamic deviation correction parameter adjustment as claimed in claim 1, characterized in that: The system integration subsystem adopts the MQTT protocol to realize communication with the IoT terminal management platform, receives and classifies vehicle terminal data through the publish-subscribe mode; is equipped with a service quality level setting function to ensure that the message arrives at least once, and maintains the communication connection through the heartbeat detection mechanism, and supports automatic reconnection when the network is interrupted; performs integrity check and range verification on the received data, and maps the parsed data to a unified data model for use by subsequent subsystems; enables encrypted communication and identity authentication mechanisms, including transport layer security protocol encryption and client certificate verification.

4. A transport track deviation correction system based on dynamic deviation correction parameter adjustment as claimed in claim 1, characterized in that: The data acquisition subsystem collects state parameters of the transport vehicle, including speed, acceleration, inclination, position and direction; and collects multi-source environmental data, including satellite images, real-time traffic information and meteorological information.

5. A transport track deviation correction system based on dynamic deviation correction parameter adjustment as claimed in claim 1, characterized in that: The data processing subsystem comprises: Receive and process vehicle status information and environmental data from the data acquisition subsystem; use artificial intelligence adaptive algorithms to jointly analyze historical trajectory data and real-time sensor data to detect abnormal situations; optimize vehicle status data and environmental data through multi-sensor fusion algorithms; identify offsets or abnormal conditions in real time based on a dynamic threshold adjustment mechanism, and send adjustment instructions to the trajectory correction subsystem.

6. A transport track deviation correction system based on dynamic deviation correction parameter adjustment as claimed in claim 1, characterized in that: The trajectory correction subsystem matches the vehicle trajectory data through a high-precision map and a dynamically generated reference trajectory, and adjusts the correction direction and amplitude in real time according to the degree of deviation, environmental complexity and vehicle status through a dynamic correction parameter adjustment module, and dynamically generates adjustable reference trajectory points.

7. A transport track deviation correction system based on dynamic deviation correction parameter adjustment as claimed in claim 6, characterized in that: The formula of the dynamic correction parameter P of the dynamic correction parameter adjustment module is: in: ‖d‖ represents the offset distance between the vehicle’s current position and the reference trajectory point; is the second-order derivative of the path curvature; s represents the arc length on the reference trajectory, which is the cumulative distance along the path from the starting point of the path to the current position; θ is the steering angle of the vehicle that is dynamically adjusted; α is the speed adjustment factor; R is the path curvature radius; is the normalized value of the speed adjustment factor. The speed should not exceed the maximum allowable speed v during dynamic adjustment. max ; w1, w2, w3: weight parameters, which respectively control the impact of offset distance, path smoothness and speed adjustment on the total cost. The setting of weights depends on the scene requirements; Φ(e,C) is the environmental complexity function, which depends on the offset error e and the environmental complexity C and is defined as: Among them, σ e is the standard deviation of the offset error, and C is the environmental complexity factor, which is calculated by weighting obstacle density, road width, and traffic conditions.

8. The transport track deviation correction system based on dynamic deviation correction parameter adjustment according to claim 1, characterized in that: The early warning subsystem receives vehicle status parameters and environmental data, and processes them through multi-source data fusion technology; dynamically adjusts the safety threshold range, and compares the vehicle's current operating status with the threshold range in real time according to the operating environment; when an abnormal operating status is detected, it triggers an alarm prompt and outputs the abnormality type and adjustment suggestions.

9. A transport track deviation correction system based on dynamic deviation correction parameter adjustment according to any one of claims 1 to 8, characterized in that: The transportation is the transportation of large-scale electric equipment.

Images