Intelligent track correction and playback system based on multi-source data

Abstract

The invention provides an intelligent track correction and playback system based on multi-source data. The intelligent track correction and playback system comprises a system integration module, a data acquisition module, a data processing module, a track correction module, an early warning mechanism module, a track storage module and a track playback module. Through sensor fusion and an artificial intelligence algorithm, the system realizes data acquisition, anomaly detection, track correction and visual analysis, and ensures the operation stability and safety of the vehicle in a complex environment. The modular design supports real-time data interaction, dynamic early warning and historical track query, provides an efficient solution for transportation optimization and management, and significantly improves the intelligence and reliability of the transportation process.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation technology, and in particular to an intelligent track deviation correction and playback system based on multi-source data. Background Art

[0002] With the widespread application of large-scale power equipment in various industries, the safety and accuracy of its transportation process has become the focus of the industry. Since large equipment is usually large in size and heavy in weight, its transportation process needs to deal with complex road environments and changing external factors, which puts extremely high demands on transportation management technology. However, the current technical means still have many shortcomings in the field of large equipment transportation, which limits its further development in efficient and safe transportation.

[0003] Currently, large-scale transportation mainly relies on traditional GPS positioning systems for trajectory monitoring. However, GPS systems are prone to signal interruption or reduced positioning accuracy in signal-shielded areas such as mountainous areas and tunnels. This limitation makes it difficult to achieve real-time and accurate tracking of transportation trajectories. In addition, the existing system lacks comprehensive consideration of external environmental information (such as weather conditions or road conditions), resulting in insufficient reliability and adaptability of monitoring, and is unable to provide effective support for complex transportation scenarios.

[0004] In terms of data collection, commonly used sensors in the transportation process include accelerometers, gyroscopes, and inclinometers. Although these sensors can provide relevant data on the vehicle's operating status, they usually work independently and fail to achieve effective fusion between the data. Therefore, it is difficult for the existing system to fully reflect the dynamic status of the transport vehicle, resulting in information asymmetry and failure to provide comprehensive reference for transportation decisions in a timely manner, thus affecting transportation efficiency and safety.

[0005] In complex road environments, such as sharp bends, narrow sections or ramps, transport vehicles are prone to deviate from the planned trajectory. However, existing trajectory correction technologies usually rely on simple path comparison algorithms, which are difficult to fully consider the vehicle's inertia, external environmental changes (such as slippery roads or crosswinds), and equipment characteristics. This technical limitation leads to unsatisfactory correction effects and low accuracy, which cannot meet actual transportation needs.

[0006] In addition, the existing transportation management system also has obvious deficiencies in the early warning mechanism. Usually, these systems use static early warning strategies based on fixed thresholds to determine whether the vehicle status is abnormal. However, during the transportation of large equipment, environmental factors (such as weather changes, road conditions) and dynamic changes in vehicle loads will significantly affect the operating status, and static thresholds are difficult to adapt to these changes. Therefore, this mechanism is prone to missed reports or false reports, increasing potential risks during transportation.

[0007] In terms of data storage and playback functions, existing transportation monitoring systems focus on real-time monitoring, but lack comprehensive historical data storage and playback functions. Even if the transportation trajectory can be recorded, the displayed content is mostly simple path information, and it is impossible to intuitively present key events in the transportation process, such as deviation points or alarm points. At the same time, the system cannot conduct in-depth analysis based on external environmental information, which limits the possibility of optimizing transportation plans and improving equipment performance afterwards.

[0008] In addition, large-scale transportation is significantly affected by meteorological conditions (such as strong winds and heavy rains), traffic conditions (such as congestion or accidents), and road conditions (such as construction, height and width restrictions). However, existing systems generally fail to effectively integrate these external environmental factors, making them less adaptable and safe in complex transportation scenarios. This further limits their ability to respond to emergencies and optimize transportation routes.

[0009] In summary, the existing technology still has significant deficiencies in real-time monitoring, trajectory correction, early warning mechanism and data analysis capabilities of large-scale power equipment transportation. In order to solve these problems, it is urgent to develop a more intelligent and comprehensive system to improve the safety and efficiency of large-scale equipment transportation and meet the industry's growing technical needs. Summary of the invention

[0010] In order to solve the above problems in the prior art, the present invention proposes an intelligent trajectory correction and playback system based on multi-source data, the trajectory correction and playback system includes a system integration module 101, a data acquisition module 102, a data processing module 103, and a trajectory correction module 104:

[0011] The system integration module 101 is used to communicate with the IoT terminal management platform, receive vehicle terminal data, and realize system data interaction;

[0012] The data acquisition module 102 includes a multi-source sensor for collecting dynamic state information and external environment information of the transport vehicle;

[0013] The data processing module 103 is used to perform fusion analysis on the collected multi-source data, identify abnormal situations and generate correction instructions;

[0014] The trajectory correction module 104 uses path matching technology and intelligent algorithms to generate a correction strategy and perform adjustments based on the deviation between the actual vehicle trajectory and the preset trajectory, combined with vehicle dynamic parameters and external environment information.

[0015] The trajectory correction and playback system also includes an early warning mechanism module 105, a trajectory storage module 106 and a trajectory playback module 107;

[0016] The early warning mechanism module 105 is used to evaluate the vehicle operation status in real time based on multi-source sensor data and trigger an alarm;

[0017] The track storage module 106 is used to store track data, abnormal information and warning records collected during transportation;

[0018] The trajectory playback module 107 is used to display historical trajectories and mark key events.

[0019] The system integration module 101 integrates the trajectory correction and playback system with the IoT terminal management platform through the MQTT protocol to achieve data interaction and communication;

[0020] The system integration module 101 is configured as a publish-subscribe mode, in which the IoT terminal management platform acts as a data publisher to push dynamic data of transport vehicles, and the system integration module acts as a subscriber to receive data.

[0021] The data acquisition module 102 is equipped with a plurality of high-precision sensors, including a GPS positioning sensor, an acceleration sensor, a gyroscope sensor, a meteorological sensor and a road condition sensor.

[0022] The data acquisition module 102 accesses external multi-source environmental information, including meteorological data and traffic condition data, through an Internet of Things interface;

[0023] A unified timestamp and high-precision time synchronization protocol are used to time-align sensor data.

[0024] The data processing module 103 receives multi-dimensional data from the data acquisition module through an internal interface; and uses a multi-source data fusion formula to perform comprehensive processing on sensor data from different sources. The fusion formula is:

[0025]

[0026] in, is the fusion estimate, φ(E) is the dynamic environment factor weight adjustment function, represents the trend of data change, α is the adjustment coefficient, {x1,x2,…,x i ,…,x n} is the input sensor data set, {w1,w2,…,w i ,…,w n} is the static weight.

[0027] The static weight w i Calculated by the following formula:

[0028]

[0029] The dynamic environmental factor weight adjustment function φ(E) is:

[0030]

[0031] in, are the uncertainties of the i-th and j-th sensors respectively, E represents the current environmental parameters, E0 is the reference environmental value, and k is the environmental sensitivity coefficient.

[0032] The data processing module 103 has an anomaly detection algorithm embedded therein for identifying potential anomalies in the transportation process in real time;

[0033] The abnormal state probability P a The calculation formula is:

[0034]

[0035] in, represents the difference between the sensor data and the fusion estimate, ψ(E) = exp(-γ·(E-E0) 2 ) is the environmental factor inhibition function, γ is the adjustment coefficient, and β is the adjustment parameter.

[0036] The data processing module 103 uses parallel processing technology to distribute data preprocessing, fusion analysis and anomaly detection to a multi-threaded or multi-core computing architecture; and uses sliding window technology to process only the data in the latest time period.

[0037] The trajectory correction module 104 analyzes the deviation between the actual driving trajectory of the vehicle and the preset trajectory based on high-precision map matching technology; determines the offset and the direction of the offset by calculating the spatial position relationship between the real-time position of the vehicle and the preset trajectory point; the module formulates a correction strategy based on the vehicle dynamic parameters and external environment information; the correction strategy includes adjusting the vehicle's driving speed, direction or path.

[0038] The early warning mechanism module is based on multi-source sensor data fusion technology to evaluate whether the vehicle's operating status exceeds the safety threshold; dynamically adjust the sensor acquisition mode and optimize the early warning threshold according to environmental changes; when overspeeding, excessive tilt angle or severe weather conditions are detected, an alarm is triggered and the driver is notified through the early warning prompt system to take measures;

[0039] The trajectory storage module performs structured storage of the collected trajectory data, abnormal information and warning records; performs long-term data preservation, and provides a convenient query interface to quickly retrieve relevant data according to time, vehicle or task number;

[0040] The trajectory playback module provides a playback function for the historical trajectory of the transportation task, performs trajectory zooming and key event marking, and displays the association with external environment data.

[0041] Beneficial effects:

[0042] The intelligent trajectory correction and playback system for large-scale power equipment transportation based on multi-source data provided by the present invention realizes the whole process management from data collection, processing, monitoring to trajectory correction and optimization through modular design. The system integration module ensures the real-time and stability of data interaction, and can efficiently transmit data even in a complex network environment; the data acquisition module obtains comprehensive and reliable dynamic and environmental information through sensor fusion technology, providing multi-dimensional data support for the system; the data processing module combines artificial intelligence algorithms to accurately identify abnormal conditions during transportation and quickly generate correction instructions. The trajectory correction module uses high-precision map matching technology and intelligent algorithms, combined with dynamic parameters and environmental information, to optimize the vehicle operation path, significantly improving the accuracy and safety of transportation. The early warning mechanism module effectively reduces missed reports and false alarms by dynamically adjusting the collection mode and early warning threshold, thereby improving the reliability of the system. The trajectory storage module realizes structured storage and rapid query of data, which is convenient for subsequent analysis and optimization, while the trajectory playback module provides users with comprehensive transportation evaluation and optimization support through visual display functions. The overall system greatly improves the safety, efficiency and management intelligence level of the transportation process of large-scale power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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:

[0044] Figure 1 A structural schematic diagram of an intelligent trajectory correction and playback system for large-scale power equipment transportation based on multi-source data is shown. DETAILED DESCRIPTION

[0045] 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.

[0046] Figure 1 A structural schematic diagram of an intelligent trajectory correction and playback system for large-scale power equipment transportation based on multi-source data is shown.

[0047] like Figure 1As shown, this embodiment provides an intelligent trajectory correction and playback system for large-scale power equipment transportation based on multi-source data. The system includes a system integration module 101, a data acquisition module 102, a data processing module 103, a trajectory correction module 104, an early warning mechanism module 105, a trajectory storage module 106 and a trajectory playback module 107. The above modules cooperate with each other to complete the entire process from transportation data collection, processing, monitoring to trajectory correction and optimization. The following is a detailed analysis of each module:

[0048] 1) System Integration Module 101

[0049] The system integration module integrates this system with the IoT terminal management platform through the MQTT protocol. Its main function is to receive vehicle terminal data and realize data interaction and communication. Through this module, the system can obtain dynamic information of multiple transport vehicles in real time, including location, speed, acceleration, etc., providing a reliable data input basis for subsequent modules. In addition, this module ensures the stability of data transmission, and can ensure the accuracy and timeliness of data interaction through optimized communication protocols even in weak signal environments.

[0050] 2) Data acquisition module 102

[0051] The data acquisition module is the core data source of the system, including multiple sensors, which are used to collect dynamic status information of transport vehicles in real time, such as speed, acceleration, inclination, position and direction. In order to improve the comprehensiveness and reliability of data, the module uses sensor fusion technology to combine vehicle status data with multi-source environmental information (such as meteorological data, road condition information, and traffic conditions). Through the comprehensive collection of multi-dimensional data, the module provides diversified data support for subsequent analysis and processing.

[0052] 3) Data processing module 103

[0053] The data processing module is responsible for receiving and analyzing multi-source data from the data acquisition module. The module has an embedded artificial intelligence algorithm that comprehensively processes the sensor fusion data to identify possible abnormalities during transportation. For example, when a vehicle deviates from the scheduled route or an abnormal operation occurs, the data processing module can quickly determine the cause of the deviation and send a correction instruction to the trajectory correction module.

[0054] 4) Track correction module 104

[0055] The trajectory correction module uses high-precision map matching technology and intelligent algorithms to compare the actual vehicle trajectory with the preset trajectory and calculate the offset and direction. The module proposes a correction strategy based on the degree of offset, combined with vehicle dynamic parameters (such as acceleration and inclination) and external environmental information (such as weather and road conditions). Specific strategies include adjusting the vehicle speed, direction or running path to ensure that the vehicle can quickly return to the optimal driving path.

[0056] 5) Early warning mechanism module 105

[0057] The early warning mechanism module is based on multi-source sensor data fusion technology to evaluate in real time whether the vehicle's operating status exceeds the safety threshold. The module dynamically adjusts the sensor acquisition mode and optimizes the early warning threshold according to environmental changes (such as meteorological conditions). For example, when overspeeding, excessive tilt angle or severe weather conditions are detected, the module will trigger an alarm and notify the driver to take corresponding measures through the early warning prompt system. The dynamic adjustment function of this module effectively reduces the probability of missed and false alarms.

[0058] 6) Track storage module 106

[0059] The track storage module stores all track data, abnormal information and warning records collected during transportation in a structured manner. The module supports long-term data preservation, which is convenient for subsequent analysis and optimization. In addition, the track storage module also provides a convenient query interface, allowing users to quickly retrieve relevant data based on time, vehicle or task number.

[0060] 7) Track playback module 107

[0061] The track playback module provides users with a comprehensive visual display of historical tracks. Users can replay the historical tracks of transportation tasks through the system interface, supporting zooming, key event marking, and the association of tracks with external environment data. Through the track playback function, users can more intuitively evaluate abnormal events in the transportation process and optimize the transportation plan based on actual conditions.

[0062] The coordinated operation of the above modules constitutes the complete technical chain of the system of the present invention, which effectively realizes the intelligent management and optimization of the whole process of transportation of large power equipment. The specific implementation plan of each module is as follows:

[0063] The system integration module 101 is the core data interaction component of the entire system. It integrates the system with the IoT terminal management platform through the MQTT (Message Queuing Telemetry Transport) protocol to achieve efficient operation of data interaction and communication.

[0064] The function of the system integration module is based on the lightweight MQTT protocol, which is highly efficient, has low latency, and low bandwidth usage, and is very suitable for transmitting real-time data. The module first establishes a stable connection channel with the IoT terminal management platform and configures it in publish-subscribe mode. In this mode, the IoT terminal management platform, as a data publisher, pushes the dynamic data uploaded from the transport vehicle to the system integration module, and the system integration module, as a subscriber, receives the data and distributes it to subsequent modules for processing.

[0065] The system integration module assigns an independent MQTT topic to each transport vehicle, for example, in the form of / vehicle / {vehicle_id} / data. Through this topic division method, the module can accurately identify the data source of each vehicle and parse the key parameters in the data packet, including the vehicle's real-time location, speed, acceleration, etc. The parsed data is stored in the memory in a structured form, which is convenient for subsequent module calls and processing.

[0066] In order to prevent packet loss or delay during data transmission, the system integration module adopts the MQTT QoS (Quality of Service) service quality level mechanism, which is specifically set to QoS2 (Exactly Once). This mechanism ensures that data messages can be delivered completely and without duplication regardless of network conditions, avoiding data loss due to weak signals or interruptions.

[0067] The system integration module has a built-in efficient cache mechanism, which uses a circular queue to temporarily store the received data. Each data message is accompanied by a timestamp and enters the queue in order of arrival time. If the subsequent module does not process the data in time, the cache mechanism will clear the oldest data that exceeds the queue length to maintain the real-time nature of the queue. The fields contained in the queue include timestamp, vehicle identification (vehicle_id), position, speed, acceleration, and inclination parameters. Through this management method, the system can maintain high efficiency in data processing under high-frequency data flow.

[0068] In environments with weak or unstable signals (such as tunnels or mountainous areas), the system integration module introduces a breakpoint-resume transmission mechanism. The module periodically sends heartbeat packets to detect network status and saves unconfirmed message packets when the connection is interrupted. When the network is restored, the module resends the unconfirmed message to ensure data integrity.

[0069] In order to adapt to the situation where multiple transport vehicles transmit data at the same time, the system integration module adopts a multi-threaded architecture for data distribution. The data of each vehicle is processed by an independent thread, and the parsed data is distributed to subsequent components such as the data acquisition module and the data processing module. The threads share the memory pool, but use the Read-Write Lock mechanism to avoid competition and ensure the system's concurrent performance and data consistency.

[0070] Through the above technical means, the system integration module 101 can realize the efficient reception and distribution of data pushed by the IoT terminal management platform, and ensure the accuracy and stability of data transmission in transportation scenarios with complex network conditions, providing reliable basic support for subsequent data collection and analysis.

[0071] The data acquisition module 102 is a core component for acquiring dynamic information in the system, and mainly collects status data and environmental data of the transport vehicle in real time through a variety of sensors.

[0072] The data acquisition module adopts multi-sensor fusion technology to achieve comprehensive monitoring of transport vehicles and surrounding environment.

[0073] The data acquisition module is equipped with multiple high-precision sensors to collect data of different dimensions to meet the monitoring needs of the vehicle's operating status during transportation. Specific sensors and collected data include:

[0074] GPS positioning sensor: used to collect the vehicle's geographic location, direction and moving speed.

[0075] Acceleration sensor: monitors the acceleration changes of the vehicle in real time to determine whether there are drastic starting, braking or turning behaviors.

[0076] Gyroscope sensor: monitors the vehicle's tilt angle changes and identifies the vehicle's dynamic performance on a slope or in a roll situation.

[0077] Meteorological sensors: collect ambient temperature, humidity, wind speed and direction data.

[0078] Road condition sensor: Vibration and road condition detection sensors installed at the bottom of the vehicle are used to assess the road roughness and impact conditions on the vehicle.

[0079] Traffic condition data interface: Receive real-time traffic data through the IoT interface, including congestion, accident information, and construction sections.

[0080] The module uses a unified timestamp mechanism to synchronize the data collected by multiple sensors. Through high-precision time synchronization protocols (such as NTP or PTP), it ensures that the data of each sensor has a consistent time base for subsequent fusion analysis.

[0081] The data acquisition module uses sensor fusion technology to comprehensively process different types of sensor data. The implementation of fusion technology is based on the Kalman Filter algorithm to reduce the random noise and uncertainty of single sensor data and improve the accuracy and reliability of data. For example:

[0082] GPS positioning data is combined with acceleration sensor data to correct the vehicle's trajectory continuity in weak or interrupted signal environments.

[0083] The gyroscope is combined with the inclination sensor data to measure the vehicle's posture changes with high precision.

[0084] The road condition sensor is combined with the meteorological sensor data to determine the relationship between the external impact on the vehicle and the environmental conditions.

[0085] The module has a built-in data quality detection mechanism to conduct real-time validity judgment and quality assessment of the collected data. For example:

[0086] Determine whether the GPS signal is interfered with. If the signal accuracy is reduced, the acceleration and gyroscope data are combined to compensate the trajectory calculation.

[0087] Monitors the operating status of each sensor (such as low battery or signal loss) and issues an alarm when a failure occurs, prompting the system to switch to a backup sensor or mode.

[0088] The data acquisition module has a built-in cache mechanism to temporarily store the collected raw data in chronological order and transmit it to the system integration module (101) in batches or in real time. Data transmission is achieved through wireless communication protocols (such as Wi-Fi, 4G / 5G), and supports dynamic bandwidth adjustment to adapt to changes in network conditions.

[0089] The data acquisition module also accesses external multi-source environmental information through the Internet of Things interface, including:

[0090] Meteorological data: Obtain real-time weather conditions from public meteorological platforms to assess risks during transportation.

[0091] Traffic conditions: Combined with data from regional traffic monitoring systems, potential congested sections and accident points can be identified in real time.

[0092] Through the above technical means, the data acquisition module 102 can realize comprehensive and accurate monitoring of the transport vehicle and the surrounding environment, and provide high-quality data support for subsequent trajectory correction, early warning mechanism and trajectory analysis. The design of the module ensures the real-time, reliability and comprehensiveness of the data, and is suitable for the transportation management needs of large power equipment in complex transportation scenarios.

[0093] The data processing module 103 is the core functional module in the system for analyzing and processing multi-source data. It mainly performs comprehensive analysis and processing on the multi-dimensional data from the data acquisition module, identifies abnormal situations in the transportation process, and provides decision support.

[0094] The data processing module receives multi-source sensor data from the data acquisition module through an internal interface, including but not limited to vehicle position, speed, acceleration, inclination, road conditions and environmental information. The received raw data is first parsed into a structured format, such as timestamp, sensor identifier and numerical parameters, for subsequent processing.

[0095] The module cleans and preprocesses the received raw data, including the following steps:

[0096] Missing value processing: When some sensor data is missing, interpolation or prediction models are used to fill in the missing values ​​to ensure data integrity.

[0097] Denoising: Use filtering algorithms (such as Kalman filtering or median filtering) to reduce the noise of sensor data (such as acceleration or inclination data) to improve data accuracy.

[0098] Normalization: Normalize data from different sources to make them conform to a unified dimensional standard for subsequent analysis.

[0099] The data processing module uses a dynamic multi-source data fusion formula to comprehensively process data from different sources to improve the accuracy and robustness of the data.

[0100] For multi-source sensor data X = {x1, x2, ..., x i ,…,x n}, the estimated value after fusion It is expressed as:

[0101]

[0102] This formula describes a multi-source sensor data fusion model, which aims to calculate a more accurate fusion estimate based on the uncertainty of sensor data, the influence of environmental factors and the real-time change trend of data.

[0103] The formula consists of two main parts:

[0104] Static weighted average part

[0105] Exploiting the uncertainty of each sensor data Calculate the weight of each sensor data in the fusion estimate (w i ), thus obtaining the uncertainty-weighted average.

[0106] Dynamic trend adjustment section

[0107] Consider the trend of data over time and the dynamic influence of current environmental conditions (φ(E)) to further adjust the fusion results.

[0108] The specific parameters are described as follows:

[0109] Input data set X = {x1, x2, ..., x i ,…,x n}:

[0110] x i : Represents the data of the i-th sensor.

[0111] n: indicates the total number of sensors.

[0112] Static weight w i :

[0113]

[0114] Represents the static weight of the i-th sensor data.

[0115] represents the uncertainty of the i-th sensor data (i.e., the variance of the noise); represents the uncertainty of the j-th sensor data (i.e., the variance of the noise).

[0116] The smaller it is, the more reliable the data is, and the weight w of the sensor is i The sum of all weights is 1 to achieve weighted average.

[0117] Dynamic environmental factor weight adjustment function φ(E):

[0118]

[0119] E: Current environmental parameters, such as humidity, wind speed, and other factors that may affect sensor performance.

[0120] E0: Reference environmental value, which indicates the reference value of environmental parameters when the sensor is under normal working conditions.

[0121] k: Environmental sensitivity coefficient, used to control the response of φ(E) to changes in environmental parameters.

[0122] The value range of φ(E) is between 0 and 1, and is used to dynamically adjust the influence of the trend term. When E is close to E0, φ(E) is close to 0.5 or higher, indicating that the environmental changes have little impact on the sensor; when E deviates from E0, φ(E) will significantly adjust the weight.

[0123] Data change trend Indicates the rate of change of sensor data relative to time. It is used to capture real-time change trends, such as sudden acceleration, position drift and other dynamic features.

[0124] Adjustment factor α:

[0125] Used to balance the impact of static weight averaging and dynamic trend adjustment. The value range is generally a positive number. The larger the value, the more significant the impact of dynamic trend adjustment. Dynamically adjust the weight ratio of the static weight part and the dynamic trend part in the fusion estimate.

[0126] The formula combines the reliability of the sensor (uncertainty ) is used for basic fusion, and the influence of environmental conditions and real-time changing trends is introduced through the dynamic trend adjustment part, so that the fused estimate can not only reflect the reliability of the current sensor data, but also dynamically adapt to the complex external environmental conditions and real-time changes of sensor data.

[0127] The module embeds artificial intelligence algorithms, which combine the above fusion formula to analyze sensor data in real time and identify abnormal situations during transportation. The anomaly detection formula is as follows:

[0128] Abnormal state probability P a Calculation:

[0129]

[0130] in:

[0131] Represents the difference between the sensor data and the fused estimate.

[0132] w i is the static weight in the fusion formula.

[0133] ψ(E)=exp(-γ·(E-E0) 2 ) is the environmental factor suppression function, and γ is the adjustment coefficient, which is used to reduce the interference of drastic environmental changes on anomaly detection.

[0134] β is an adjustment parameter used to balance the effects of variance and environmental factors.

[0135] When P a When the set threshold is exceeded, the module determines that the current state is abnormal and triggers the corresponding processing mechanism according to the type of abnormality.

[0136] The data processing module generates corresponding control instructions based on the analysis results and sends the instructions to the trajectory correction module. For example:

[0137] When the vehicle deviates from the predetermined route, the module sends correction parameters (including offset distance, direction and recommended path) to the trajectory correction module.

[0138] When abnormal dynamic behavior is identified, the module sends recommendations for slowing down or adjusting direction.

[0139] To ensure the efficient operation of the module in a real-time environment, the data processing module uses parallel processing technology to distribute data preprocessing, fusion analysis and anomaly detection to a multi-threaded or multi-core computing architecture. In addition, the module uses sliding window technology to process only the data in the latest time period, thereby reducing the system's computing burden and improving response speed.

[0140] Through the above-mentioned fusion formula and anomaly detection formula, the data processing module 103 can more accurately and dynamically identify potential abnormal situations in the transport vehicle and the external environment, significantly improving the adaptability and reliability of the system in complex transportation scenarios.

[0141] The track correction module 104 is an important functional component in the system for correcting the deviation of the transport vehicle from the preset track. Based on high-precision map matching technology and intelligent algorithms, the module analyzes the deviation between the actual driving track of the vehicle and the preset track, calculates the deviation amount and direction, and formulates appropriate correction strategies to ensure the path accuracy of the vehicle in complex transportation scenarios.

[0142] The track deviation correction module first uses high-precision map matching technology to compare and analyze the real-time location data of the vehicle with the pre-loaded high-precision map. By comparing the spatial position relationship between the actual track point and the preset track point, the module can accurately calculate the offset (including the offset distance and offset direction). The calculation formula of the offset can be expressed as:

[0143]

[0144] Among them, (x r ,y r ) represents the real-time position coordinates of the vehicle, (x p ,y p ) represents the coordinates of the preset trajectory point, and Δd is the offset distance. The offset direction is calculated by the angle between the direction vector of the real-time trajectory and the direction vector of the preset trajectory.

[0145] Based on the offset and direction, the trajectory correction module further combines the vehicle's dynamic parameters (such as speed, acceleration, and inclination) and external environmental information (such as real-time weather and road conditions) for comprehensive analysis. For example:

[0146] If a large offset is detected and the vehicle is at a high speed, the module will give priority to adopting a correction strategy of gradually adjusting the direction to avoid instability of the transport equipment due to sudden turns.

[0147] If the detected offset is small, but the road is slippery or the wind speed is high, the module will use the inclination data to determine the risk of roll, and achieve safe correction through a comprehensive strategy of reducing speed and adjusting direction.

[0148] The correction strategy is formulated by the module's built-in intelligent algorithm, which comprehensively considers the degree of deviation, vehicle status and environmental conditions and generates the optimal correction instructions. Specific strategies include:

[0149] The module dynamically adjusts the vehicle's speed based on the degree of deviation and current environmental conditions. For example, in sharp bends or ramps, the module will prioritize reducing the vehicle's speed to more stably correct the deviation.

[0150] By calculating the required steering angle of the vehicle, the module sends a direction adjustment command to the vehicle control system. The adjustment is mainly based on gradual correction to ensure the smoothness and safety of the vehicle during the correction process.

[0151] When the deviation cannot be corrected by simply adjusting the speed or direction, the module will re-plan the temporary path to ensure that the vehicle can return to the preset trajectory in the shortest distance while avoiding possible obstacles or dangerous sections.

[0152] In order to adapt to the dynamically changing transportation environment, the trajectory correction module also works with the data processing module to optimize the correction strategy by acquiring environmental information (such as wind speed, temperature, humidity) and dynamic traffic data in real time. For example, under high wind speed conditions, the module may prioritize deceleration and adjust the direction angle to enhance the stability of the vehicle.

[0153] In addition, to ensure the accurate execution of the correction instructions, the module has a built-in feedback mechanism to monitor the vehicle status after correction in real time. If the correction effect does not meet expectations, the module will recalculate the offset and adjust the strategy until the vehicle returns to the optimal driving path.

[0154] Through the above-mentioned technical means, the trajectory correction module 104 can achieve high-precision correction of the vehicle trajectory, and ensure that the vehicle travels along the optimal path even under complex road conditions and harsh environments, thereby significantly improving the safety and efficiency of the transportation process.

[0155] The early warning mechanism module 105 is an important component in the system for monitoring and evaluating the vehicle's operating status and triggering early warnings. It is based on multi-source sensor data fusion technology, and through real-time analysis of the vehicle's dynamic state and external environmental conditions, determines whether the vehicle exceeds the safety threshold, and triggers an alarm when necessary, thereby ensuring the safety and stability of the transportation process. The following is a detailed description of the module's functions and technical details:

[0156] The early warning mechanism module first uses data from multi-source sensors (including speed, acceleration, inclination, position, weather conditions, etc.) combined with the fusion results provided by the data processing module to conduct a real-time assessment of the vehicle's current operating status. The module has an embedded dynamic threshold adjustment mechanism that can optimize the safety threshold according to changes in environmental conditions, thereby enhancing the ability to adapt to complex scenarios. For example:

[0157] In adverse weather conditions with slippery roads or low visibility, the module dynamically reduces the safety thresholds for speed and inclination to adapt to higher risk environments.

[0158] On flat roads and in good weather conditions, the module can appropriately relax the threshold range to reduce unnecessary alarm triggering and optimize system response efficiency.

[0159] The module has a built-in sensor dynamic acquisition mode adjustment mechanism that automatically adjusts the data acquisition frequency and range according to changes in environmental factors. For example:

[0160] When a high vehicle speed is detected, the module increases the data sampling frequency of the acceleration and inclination sensors to respond more quickly to possible emergency situations.

[0161] Under complex road conditions (such as steep slopes or sharp turns), the module will focus on collecting inclination and road impact data, while reducing the frequency of updating meteorological data to save computing resources and focus on key parameters.

[0162] The early warning mechanism module is based on a multi-factor fusion judgment method, which determines whether to trigger an alarm by analyzing the combined state of multiple sensor data. For example:

[0163] When it is detected that the real-time speed of the vehicle exceeds the dynamic safety speed allowed by the environment, the module triggers an overspeed alarm.

[0164] When the vehicle's tilt angle continues to exceed the set safety threshold (such as a roll angle of more than 15 degrees and lasts for more than 2 seconds), the module triggers a roll risk alarm.

[0165] When the external environment detects strong winds (such as wind speeds greater than 20m / s) or heavy rain, the module triggers an alarm for severe weather conditions and recommends slowing down or stopping the vehicle.

[0166] Once the warning is triggered, the module will send real-time warning information to the driver through the system interface or vehicle control terminal. The prompt content includes:

[0167] Specific abnormality type (such as speeding, roll, slippery road, etc.).

[0168] Recommended operating measures (such as slowing down, adjusting direction, stopping and waiting, etc.).

[0169] In addition, the module can issue multimodal warning prompts to the driver through sound, vision or vibration to ensure that the driver can pay attention to potential risks in time.

[0170] In order to reduce the probability of missed alarms and false alarms that may occur during the early warning process, the module adopts the following optimization strategies:

[0171] Dynamic threshold adjustment: Dynamically adjust security thresholds based on real-time environmental data to avoid false alarms caused by environmental changes.

[0172] Multi-sensor data cross-validation: By analyzing the consistency of multiple sensor data, possible abnormal values ​​of a single sensor can be filtered out. For example, when judging the risk of rollover, the inclination data and gyroscope data are combined for verification to avoid the alarm being triggered by abnormal single-point data.

[0173] Time window filtering: Perform time window smoothing on burst data within a short period of time, and trigger an alarm only when the abnormal state persists for a certain period of time to prevent false alarms caused by instantaneous fluctuations.

[0174] The early warning mechanism module uses parallel computing and sliding window algorithms to ensure that data analysis and early warning triggering can be completed within milliseconds. Even in complex scenarios with multiple tasks running in parallel, the module can still maintain high response speed and stability.

[0175] Through the above-mentioned technical means, the early warning mechanism module 105 can monitor the dynamic state of the vehicle in real time in a complex transportation environment, accurately identify potential risks, and notify the driver to take necessary measures in an efficient manner, thereby significantly improving the safety and reliability of the transportation process of large power equipment.

[0176] The trajectory storage module 106 is the core component of the system for storing and managing transportation process data. Its main function is to perform structured storage of trajectory data, abnormal information and warning records collected during the transportation process, and to support rapid retrieval and query of data, so as to provide a reliable data basis for subsequent analysis and optimization.

[0177] The trajectory storage module receives data from the data acquisition module and the warning mechanism module, including but not limited to the vehicle's real-time trajectory points, speed, acceleration, inclination, abnormal event time points, and warning types. In order to ensure the organization and efficiency of data, the module uses relational database and distributed storage technology to structure the data.

[0178] The module stores the collected data in a structured manner according to the following logic:

[0179] Trajectory data table: stores the real-time position, speed, acceleration and inclination data of the vehicle. The fields include timestamp, vehicle identifier (vehicle_id), latitude and longitude coordinates, speed value, acceleration value, inclination value, etc.

[0180] Abnormal information table: records all abnormal events that occur during transportation. The fields include abnormal time, abnormal type (such as speeding, excessive tilt), abnormal location, associated vehicle identifier and environmental parameters.

[0181] Warning record table: stores all events that trigger warnings. The fields include warning time, warning level, warning type (such as weather warning, roll warning), associated vehicles and recommended operations.

[0182] The above data tables are associated with each other through foreign keys so that users can quickly retrieve and analyze multi-dimensional information related to a specific vehicle or task.

[0183] In order to meet the needs of retrospective analysis of transportation tasks, the module supports long-term data storage. A distributed storage system is used to achieve efficient management of massive data, and data compression algorithms are used to reduce storage space usage. For example, differential encoding is used to compress the position coordinates in the trajectory data to significantly reduce the amount of redundant data.

[0184] In addition, the module has a built-in tiered storage mechanism that stores frequently used data in high-performance storage devices (such as SSDs), while historical data is transferred to low-cost archive storage (such as HDDs or cloud storage), thereby reducing storage costs while ensuring access efficiency.

[0185] The trajectory storage module provides a convenient query interface, allowing users to quickly retrieve relevant data in multiple dimensions:

[0186] Query by time: The user enters a time range, and the system returns the trajectory data and event records within the corresponding time period.

[0187] Query by vehicle: The user enters the vehicle identifier (vehicle_id), and the system returns all the tracks and warning information related to the vehicle.

[0188] Query by task number: The user enters the transport task number, and the system returns all data records related to the task, including comprehensive information in the multi-vehicle collaborative transport scenario.

[0189] The module supports fuzzy query and complex condition query. For example, users can specify the combination of time range, vehicle identifier and abnormal type, and the system will return detailed data records that meet the conditions.

[0190] To ensure data security and integrity, the module uses a multi-copy storage mechanism to prevent data loss through regular backup and off-site storage strategies. Encryption technology is used for data transmission and storage to prevent unauthorized access and tampering.

[0191] The trajectory storage module provides support for the trajectory playback module, extracting trajectory points and related event data through the query interface to generate a visual display of the trajectory path. For example, during the trajectory playback process, warning events will be marked with different colors on the trajectory path to help users intuitively analyze the distribution and impact of key events.

[0192] Through the above technical means, the trajectory storage module 106 can efficiently save and manage the trajectory and event data during the transportation process, and support subsequent analysis and optimization with flexible query and visualization functions, effectively improving the data utilization efficiency and decision support capabilities of the system.

[0193] The track playback module 107 is an important functional component in the system for displaying and analyzing the historical track of the transportation task. This module intuitively displays the driving track and key events of the vehicle during the transportation process in a comprehensive and visual way, supports multiple operation functions and data association display, and provides users with an efficient evaluation tool. The functions and technical details of the module are described in detail below:

[0194] The trajectory playback module receives data from the trajectory storage module, including historical trajectory points, abnormal event records and related environmental data. Based on the map, the module draws the trajectory points as continuous path lines and dynamically displays the vehicle's driving process in the form of a time series. Users can view the vehicle's position, speed, acceleration, inclination and other parameters at different time nodes in real time through the system interface.

[0195] Key events, such as speeding, excessive roll or warning trigger points, are marked on the trajectory path. These events are marked with different colors and symbols (for example, red marks indicate warning trigger points, and yellow marks indicate abnormal events), making it easy for users to quickly identify important nodes in the transportation process.

[0196] The trajectory playback module provides the following core functions:

[0197] Users can zoom in and out of the track through the interface to view the overall path or focus on a specific area. At the same time, the track map supports panning, which is convenient for users to navigate and view in a large area.

[0198] The module provides users with timeline operation tools. Users can quickly jump to a specified time point by dragging the timeline, or dynamically replay the track in play mode. The play speed can be adjusted as needed, such as setting it to normal speed, speeding up, or viewing frame by frame.

[0199] Users can filter key points on the trajectory according to event type, for example, only display warning trigger points or specific abnormal types (such as speeding or rollover events). This function can help users focus on the analysis of certain specific events.

[0200] The trajectory playback module supports the display of trajectory data in association with external environment data. For example:

[0201] Weather information (such as wind speed and rainfall) is superimposed on the trajectory path to show how environmental conditions affect the vehicle's operating status.

[0202] Overlay traffic information on the map to show how congestion or accident areas affect transportation trajectories.

[0203] Through the data association display function, users can fully understand the impact of the external environment on the transportation process and optimize the transportation plan accordingly.

[0204] The trajectory playback module provides analysis support for abnormal events in historical trajectories. When the user clicks on a key event marker on the trajectory path, the module will pop up a detailed information window to display relevant data of the event, such as:

[0205] Abnormal type (such as overspeed, excessive tilt).

[0206] Time and location of occurrence.

[0207] Associated environmental data (such as humidity, wind speed).

[0208] The system recommends countermeasures.

[0209] Through this analysis function, users can gain in-depth understanding of the causes and impacts of abnormal events, thereby optimizing the planning and execution of subsequent transportation tasks.

[0210] The trajectory playback module provides data interaction and export functions, and users can export analysis results in the form of charts or reports. The report includes a trajectory path map, a list of key events, and environmental data analysis, which is convenient for users to conduct post-event review and reporting.

[0211] To improve user experience, the track playback module supports multi-terminal compatibility, including desktop systems, tablets and mobile devices. The module adopts an adaptive interface design to ensure smooth operation and viewing on different devices.

[0212] Through the above technical means, the trajectory playback module 107 can comprehensively and intuitively display the historical trajectory of the transportation task and its related data, support a variety of interactive operations and analysis functions, and provide strong technical support for users to evaluate abnormal events in the transportation process and optimize transportation plans.

[0213] 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. An intelligent trajectory correction and playback system based on multi-source data, characterized by: The track deviation correction and playback system comprises a system integration module (101), a data acquisition module (102), a data processing module (103), and a track deviation correction module (104): The system integration module (101) is used to communicate with the IoT terminal management platform, receive vehicle terminal data, and realize system data interaction; The data acquisition module (102) includes a multi-source sensor for collecting dynamic state information and external environment information of the transport vehicle; The data processing module (103) is used to perform fusion analysis on the collected multi-source data, identify abnormal situations and generate correction instructions; The trajectory correction module (104) uses path matching technology and intelligent algorithms to generate a correction strategy and perform adjustments based on the deviation between the actual trajectory of the vehicle and the preset trajectory, combined with vehicle dynamic parameters and external environment information.

2. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 1, characterized in that: The trajectory correction and playback system also includes an early warning mechanism module (105), a trajectory storage module (106) and a trajectory playback module (107); The early warning mechanism module (105) is used to evaluate the vehicle operation status in real time based on multi-source sensor data and trigger an alarm; The track storage module (106) is used to store track data, abnormal information and warning records collected during the transportation process; The track playback module (107) is used to display the historical track and mark key events.

3. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 1, characterized in that: The system integration module (101) integrates the trajectory correction and playback system with the IoT terminal management platform through the MQTT protocol to achieve data interaction and communication; The system integration module (101) is configured in a publish-subscribe mode, wherein the IoT terminal management platform acts as a data publisher to push dynamic data of transport vehicles, and the system integration module acts as a subscriber to receive data.

4. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 1, characterized in that: The data acquisition module (102) is equipped with a plurality of high-precision sensors, including a GPS positioning sensor, an acceleration sensor, a gyroscope sensor, a meteorological sensor and a road condition sensor. The data acquisition module (102) accesses external multi-source environmental information, including meteorological data and traffic condition data, through an Internet of Things interface; A unified timestamp and high-precision time synchronization protocol are used to time-align sensor data.

5. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 1, characterized in that: The data processing module (103) receives multi-dimensional data from the data acquisition module through an internal interface; and uses a multi-source data fusion formula to perform comprehensive processing on sensor data from different sources, wherein the fusion formula is: in, is the fusion estimate, φ(E) is the dynamic environment factor weight adjustment function, represents the trend of data change, α is the adjustment coefficient, {x1,x2,…,x i ,…x n } is the input sensor data set, {w1,w2,…,w i ,…w n } is the static weight, and n is the total number of sensors.

6. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 5, characterized in that: The static weight w i Calculated by the following formula: The dynamic environmental factor weight adjustment function φ(E) is: in, are the uncertainties of the i-th and j-th sensors respectively, E represents the current environmental parameters, E0 is the reference environmental value, and k is the environmental sensitivity coefficient.

7. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 6, characterized in that: The data processing module (103) has an embedded anomaly detection algorithm for identifying potential anomalies in the transportation process in real time; The abnormal state probability P a The calculation formula is: in, represents the difference between the sensor data and the fusion estimate, ψ(E) = exp(-γ·(E-E0) 2 ) is the environmental factor inhibition function, γ is the adjustment coefficient, and β is the adjustment parameter.

8. An intelligent trajectory correction and playback system based on multi-source data as claimed in any one of claims 5, 6 and 7, characterized in that: The data processing module (103) adopts parallel processing technology to distribute data preprocessing, fusion analysis and anomaly detection to a multi-threaded or multi-core computing architecture; and adopts sliding window technology to process only the data in the latest time period.

9. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 1, characterized in that: The trajectory correction module (104) analyzes the deviation between the actual driving trajectory of the vehicle and the preset trajectory based on high-precision map matching technology; determines the offset and the direction of the offset by calculating the spatial position relationship between the real-time position of the vehicle and the preset trajectory point; the module formulates a correction strategy in combination with the vehicle dynamic parameters and external environment information; the correction strategy includes adjusting the vehicle driving speed, direction or path.

10. The intelligent trajectory correction and playback system based on multi-source data as claimed in claim 2, characterized in that: The early warning mechanism module evaluates whether the vehicle operation status exceeds the safety threshold based on multi-source sensor data fusion technology; Dynamically adjust sensor acquisition modes and optimize warning thresholds based on environmental changes; When overspeed, excessive bank angle or bad weather conditions are detected, an alarm is triggered and the driver is notified through the early warning system to take action; The trajectory storage module performs structured storage of the collected trajectory data, abnormal information and warning records; performs long-term data preservation, and provides a convenient query interface to quickly retrieve relevant data according to time, vehicle or task number; The trajectory playback module provides a playback function for the historical trajectory of the transportation task, performs trajectory zooming and key event marking, and displays the association with external environment data.

Images