Vehicle weighing intelligent monitoring method and system based on Internet of Things

Abstract

The invention discloses a vehicle weighing intelligent monitoring method and system based on the Internet of Things, and the method comprises the steps: carrying out the bidirectional anonymous authentication through a vehicle-mounted OBU and a wagon balance edge node, verifying the legality of a vehicle, and starting a weighing process of a corresponding trust level; after successful authentication, heterogeneous physical field data are synchronously collected and processed in real time through multiple sensors, and a force-shape-heat-sound coupling verification vector is constructed; based on the collected data, the three-dimensional pose of the vehicle is reconstructed through the UWB positioning technology and the visual SLAM technology, and if the vehicle is unstable, the weighing is automatically cancelled; according to vehicle stability and abnormal judgment of weighing data, trust evaluation is carried out on vehicles through a dynamic trust scoring mechanism, high-trust vehicles enter a fast channel, and low-trust vehicles trigger full-mode monitoring and AI behavior analysis; weighing data, a risk assessment result and a model optimization log are encrypted and uploaded through a block chain technology, and a unique hash value is generated in combination with a timestamp.

Description

Technical Field

[0001] This invention relates to the fields of Internet of Things (IoT) technology, intelligent monitoring technology, data security technology, and vehicle weighing, specifically to an IoT-based intelligent monitoring method and system for vehicle weighing. Background Technology

[0002] In modern logistics, transportation, and mining industries, vehicle weighing is a crucial means of measuring the weight of transported goods and is widely used in the management of various material transportation. However, existing traditional vehicle weighing systems mainly rely on weighbridges and sensor equipment, which typically suffer from a series of problems. First, traditional systems lack effective security protection measures; vehicle identification information and weighing data may be leaked or tampered with during transmission, creating security risks. Second, traditional systems are usually operated manually, making them susceptible to human factors, resulting in lower data accuracy and reliability, and making them prone to data forgery and fraud.

[0003] Furthermore, traditional vehicle weighing systems struggle to monitor and assess vehicle stability in real time. Vehicles may become unstable during weighing (e.g., tilting or uneven tire contact), leading to inaccurate weighing results. However, current technologies often rely on static sensors, making it difficult to capture the vehicle's dynamic state in real time and lacking intelligent analysis mechanisms to identify anomalies. With the increasing demands for efficiency and accuracy in the logistics and transportation industry, improving weighing accuracy and stability has become a pressing issue.

[0004] Furthermore, traditional vehicle weighing systems lack robust data management and auditing mechanisms, making it difficult to ensure the immutability and traceability of weighing data, thus increasing the risk of data forgery. With the development of technologies such as the Internet of Things (IoT), artificial intelligence (AI), and blockchain, leveraging these advanced technologies to achieve intelligent and automated vehicle weighing monitoring while ensuring data security and traceability has become crucial for improving the safety and reliability of weighing systems. Therefore, developing an intelligent, accurate, and secure vehicle weighing monitoring system by combining IoT, AI algorithms, and blockchain technology has become a current direction for technological development. Summary of the Invention

[0005] This invention provides an intelligent monitoring method for vehicle weighing based on the Internet of Things, comprising: S10. Through two-way anonymous authentication between the vehicle-mounted OBU and the edge node of the weighbridge, the legitimacy of the vehicle is verified and the weighing process of the corresponding trust level is initiated to ensure the safety and privacy protection of the weighing process. S20. After successful certification, heterogeneous physical field data are collected and processed in real time through multiple sensors to construct a "force-shape-thermal-acoustic" coupled verification vector, providing a verification basis for data analysis. S30. Based on the collected data, the vehicle's three-dimensional pose is reconstructed using UWB positioning technology and visual SLAM technology to further ensure stability during the weighing process. If the vehicle is unstable, the weighing will be automatically cancelled. S40. Based on the judgment of vehicle stability and abnormal weighing data, a dynamic trust scoring mechanism is used to assess the trust of vehicles. Vehicles with high trust enter the fast lane, while vehicles with low trust trigger full-modal monitoring and AI behavior analysis, further improving the accuracy and safety of the weighing process. S50. By using blockchain technology, weighing data, risk assessment results, and model optimization logs are encrypted and uploaded, and a unique hash value is generated by combining the timestamp, ensuring the immutability and traceability of the weighing process data.

[0006] The above-described IoT-based intelligent vehicle weighing monitoring method verifies the vehicle's legitimacy and initiates the weighing process at the appropriate trust level through two-way anonymous authentication between the vehicle's onboard unit (OBU) and the weighbridge edge node, ensuring the security and privacy protection of the weighing process. Specifically, this includes: The weighbridge edge node sends a one-time authentication challenge to the vehicle-mounted OBU. The vehicle-mounted OBU generates response information based on pre-set anonymous identity credentials without revealing the vehicle's true identity. The vehicle-mounted OBU verifies the digital certificate and deployment location legitimacy of the weighbridge edge node, and completes two-way identity mutual trust. Based on the vehicle's historical interaction records and the results of this authentication, an initial trust level is determined, and the weighing safety policy corresponding to that trust level is loaded.

[0007] The above-described IoT-based intelligent vehicle weighing monitoring method involves simultaneously collecting and processing heterogeneous physical field data from multiple sensors in real time to construct a coupled verification vector of "force-shape-thermal-acoustic" to provide verification basis for data analysis. Specifically, this includes: The pressure sensor array, structural strain sensor, infrared thermal imaging module and acoustic microphone array are synchronously triggered to collect vehicle load distribution, frame deformation, tire contact surface temperature rise and chassis vibration noise signals, respectively. Time synchronization and feature extraction are performed on the collected multi-source heterogeneous physical field signals; The extracted force field features, deformation features, thermal field features, and acoustic features are fused to form a unified "force-shape-thermal-sound" coupled verification vector, which is used for subsequent consistency verification.

[0008] The above-described IoT-based intelligent vehicle weighing monitoring method includes the following steps in constructing a coupled verification vector of "force-shape-thermal-sound": The moment the vehicle enters the weighbridge platform, the pressure sensor array, chassis strain gauge, infrared thermal imager and acoustic microphone array are activated simultaneously to capture the load distribution pattern, structural micro-deformation response, temperature rise dynamics of the tire-ground contact area, and acoustic signature characteristics generated by chassis mechanical vibration. Millisecond-level time alignment was performed on four types of physical field signals, and their key behavioral features were extracted. Based on the spatiotemporal consistency relationship between multi-physics field characteristics, it is possible to determine whether there is human intervention or abnormal load state, thereby identifying hidden violations such as skipping the scale, pressing the edge, partial occlusion, or counterweight cheating.

[0009] The above-described IoT-based intelligent vehicle weighing monitoring method reconstructs the vehicle's three-dimensional pose using UWB positioning technology and visual SLAM technology based on collected data, further ensuring stability during the weighing process. If the vehicle is unstable, the weighing is automatically invalidated. Specifically, this includes: High-precision ranging is achieved by using multiple UWB anchor points deployed in the weighbridge area and vehicle-mounted UWB tags, while continuous image frames of the vehicle are acquired through a vision acquisition device above the weighbridge. Based on UWB ranging data and visual image frames, a joint localization and mapping algorithm is used to reconstruct the three-dimensional spatial pose of the vehicle on the weighbridge. The vehicle is judged to be completely stopped and all wheelsets are within the effective weighing area based on the reconstructed three-dimensional pose. If there is any deviation, tilt or instability, the weighing is automatically invalidated.

[0010] The above-described IoT-based intelligent vehicle weighing monitoring method, based on vehicle stability and anomaly detection in weighing data, uses a dynamic trust scoring mechanism to assess vehicle trust. High-trust vehicles enter the fast lane, while low-trust vehicles trigger full-modal monitoring and AI behavior analysis, further improving the accuracy and safety of the weighing process. Specifically, this includes: By combining the consistency of the coupled verification vectors, the stability of the vehicle's 3D pose, and historical behavior records, the current trust assessment result of the vehicle is generated. For vehicles with high trust assessment results, a simplified weighing process is enabled, performing only weight reading and basic verification. For vehicles with low trust assessment results, activate the full-modal data review mechanism and call the artificial intelligence behavior analysis model to identify potential abnormal weighing behavior.

[0011] The above-described IoT-based intelligent monitoring method for vehicle weighing encrypts and uploads weighing data, risk assessment results, and model optimization logs using blockchain technology, and generates a unique hash value by combining it with a timestamp, ensuring the immutability and traceability of the weighing process data. Specifically, it includes: The raw weight data, coupled verification vector, pose stability judgment results, trust assessment results, and artificial intelligence analysis logs generated during this weighing process are encapsulated into a structured data package; The structured data packet is encrypted and a timestamp issued by a trusted time source is appended. Encrypted and timestamped data packets are uploaded to the blockchain network to generate globally unique hash identifiers, enabling tamper-proof storage and cross-institutional traceability auditing of weighing data throughout the entire process.

[0012] This invention also provides an Internet of Things-based intelligent monitoring system for vehicle weighing, comprising: The vehicle-mounted unit module has a built-in security chip that supports anonymous authentication and a UWB communication module, which is used to perform two-way anonymous authentication with the edge node of the weighbridge to ensure the privacy protection and trust assessment of the vehicle's identity. The weighbridge edge node module integrates a pressure sensing pad, structural strain gauge, infrared thermal imager, acoustic microphone array, UWB anchor point, and high-definition visual acquisition device to synchronously acquire multimodal physical field data of vehicles and provide high-precision spatial positioning and vehicle image data. The edge intelligence processing unit module is used to perform multimodal data fusion, 3D pose reconstruction and AI behavior analysis, analyze vehicle stability, load status and other parameters in real time, and generate trust assessment results. The dynamic trust assessment module generates a vehicle trust score based on collected vehicle data, historical interaction records, and current trust level. It schedules and optimizes the weighing process to ensure that high-trust vehicles enter the fast lane and low-trust vehicles trigger full-modal monitoring and AI behavior analysis. The blockchain evidence storage interface module connects to a consortium blockchain jointly maintained by regulatory agencies, logistics platforms, and third-party notaries. It is used to encrypt and upload weighing data, risk assessment results, model optimization logs, etc., and generate a unique hash value by combining the timestamp, so as to realize tamper-proof evidence storage and cross-institutional traceability audit of the entire weighing process data.

[0013] The beneficial effects achieved by this invention are as follows: By combining IoT, AI, and blockchain technologies, this invention helps improve the safety, accuracy, and intelligence of the vehicle weighing monitoring process. Through two-way anonymous authentication between the vehicle's OBU and the weighbridge edge node, the privacy of vehicle identity and data security are ensured. Multi-sensor synchronous acquisition of vehicle data and the construction of a coupled "force-shape-thermal-sound" verification vector enable a high-precision and stable weighing process. UWB positioning and visual SLAM technologies allow for real-time reconstruction of the vehicle's three-dimensional pose, automatically assessing vehicle stability and optimizing the weighing process. Finally, blockchain technology ensures the immutability and traceability of data, improving the efficiency and trustworthiness of the entire system, and possesses significant practical application value. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0015] Figure 1 This is a flowchart of an IoT-based intelligent monitoring method for vehicle weighing provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of an IoT-based intelligent vehicle weighing monitoring system provided in Embodiment 2 of this application. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1 like Figure 1 As shown, Embodiment 1 of this application provides a vehicle weighing intelligent monitoring method based on the Internet of Things, including the following steps: S10. Through two-way anonymous authentication between the vehicle-mounted OBU and the edge node of the weighbridge, the legitimacy of the vehicle is verified and the weighing process of the corresponding trust level is initiated to ensure the safety and privacy protection of the weighing process. This process ensures the security, privacy, and intelligence of the weighing process through two-way anonymous authentication and dynamic trust assessment mechanisms. Specifically, it includes the following steps: S101, the weighbridge edge node sends a one-time authentication challenge to the vehicle-mounted OBU, and the vehicle-mounted OBU generates response information based on the pre-set anonymous identity credentials without revealing the vehicle's true identity; After a vehicle enters the weighing area, the weighbridge edge node initiates an authentication process, sending a one-time authentication challenge to the vehicle's Onboard Unit (OBU). This challenge message includes the following parts: randomly generated authentication challenge data, a timestamp, the weighbridge node's identifier, and challenge verification information based on the AES encryption algorithm. The challenge data is transmitted through an encrypted channel to ensure the security and eavesdropping prevention of the communication process. Upon receiving the challenge, the onboard OBU uses its built-in anonymous identity credentials and a preset key to generate a response, and then generates corresponding response data using an encryption algorithm. This response data includes encrypted challenge verification information, ensuring that even if the communication process is intercepted, the vehicle's identity information cannot be exposed.

[0018] S102. The vehicle-mounted OBU verifies the digital certificate and deployment location of the weighbridge edge node to establish two-way identity trust. After completing the challenge response, the vehicle-mounted OBU will proceed to verify the legitimacy of the weighbridge edge node. First, the vehicle-mounted OBU will verify the legitimacy of the digital certificate provided by the weighbridge edge node. This verification process includes using Public Key Infrastructure (PKI) to verify the certificate, ensuring it was issued by a trusted Certificate Authority (CA) and has not expired or been revoked. Next, the vehicle-mounted OBU will obtain the location information of the weighbridge edge node through its integrated positioning module and verify the validity of its geographic coordinates. By comparing this coordinates with the geographic boundaries of a pre-defined legal area, the vehicle-mounted OBU ensures that the weighbridge edge node is located within the designated weighbridge weighing area, thereby preventing the deployment of forged or malicious nodes.

[0019] S103. Based on the vehicle's historical interaction records and the results of this authentication, determine the initial trust level and load the weighing safety policy corresponding to that trust level.

[0020] After identity and location verification are completed, the onboard unit (OBU) determines the vehicle's initial trust level based on the vehicle's historical interaction records and the current authentication result. The vehicle's historical interaction records include previous weighing behavior, trust scores, historical abnormal event records (such as scale skipping, wheels hanging off the ground, etc.), and the vehicle's typical behavior patterns. The system combines this data with the current authentication result, using a machine learning model to dynamically evaluate the vehicle and generate a comprehensive trust score. Vehicles with higher trust scores are automatically classified as "high trust" and enter a simplified weighing process, while vehicles with lower trust scores are marked as "low trust" and require more stringent monitoring and review procedures.

[0021] S20. After successful certification, heterogeneous physical field data are collected and processed in real time through multiple sensors to construct a "force-shape-thermal-acoustic" coupled verification vector, providing a verification basis for data analysis. By synchronously collecting pressure, deformation, thermal field, and acoustic data in real time, the system can comprehensively monitor physical changes during the weighing process and promptly identify potential abnormal behaviors. Specifically, it includes the following steps: S201, synchronously triggered pressure sensor array, structural strain sensor, infrared thermal imaging module and acoustic microphone array, respectively collect vehicle load distribution, frame deformation, tire contact surface temperature rise and chassis vibration noise signals; After the vehicle enters the weighbridge platform and comes to a complete stop, the system simultaneously activates multiple sensor arrays to collect data. The pressure sensor array senses the contact area between the vehicle's tires and the weighbridge platform in real time, accurately capturing the load distribution of each wheel assembly. The frame strain sensor monitors minute deformations of the frame to reflect the vehicle's deformation state under stress. The infrared thermal imaging module tracks the dynamic temperature rise of the tire-ground contact area in real time, helping to identify heat changes caused by friction or uneven stress. Simultaneously, the acoustic microphone array captures the acoustic signature generated by chassis vibrations, reflecting the vehicle's stress and motion state through the vibration frequency and amplitude.

[0022] S202. Perform time synchronization and feature extraction on the collected multi-source heterogeneous physical field signals; All physical field data collected by sensors are synchronized at the millisecond level via the system's time synchronization module, ensuring that the physical changes corresponding to various signals are consistent at the same point in time. After synchronization, the system extracts features from pressure, deformation, thermal field, and acoustic signals. Specifically, pressure signals will extract key features of load distribution, deformation signals will extract minute deformation data of the chassis, thermal imaging signals will extract key points of temperature changes, and acoustic signals will extract the frequency and amplitude features of chassis vibration. Through feature extraction, the system transforms data from different physical fields into standardized feature vectors, laying the foundation for subsequent data analysis, model training, and anomaly identification.

[0023] S203. The extracted force field features, deformation features, thermal field features and acoustic features are fused to form a unified "force-shape-thermal-sound" coupled verification vector for subsequent consistency verification.

[0024] After feature extraction, the system fuses the feature data from the four physical fields to form a unified "force-shape-thermal-acoustic" coupled verification vector. This verification vector integrates key features from pressure, deformation, thermal field, and acoustic signals, comprehensively reflecting the physical state of the vehicle during the weighing process. By fusing these features, the system can perform consistency verification on multi-physical field signals, determining whether there are deviations or inconsistencies between the signals. If an anomaly is found, the system will issue an alarm, indicating potential data problems and ensuring the accuracy and reliability of the data during the weighing process.

[0025] In constructing the "force-shape-thermal-acoustic" coupled verification vector, the system performs the following key steps: The moment the vehicle enters the weighbridge platform, the pressure sensor array, chassis strain gauge, infrared thermal imager and acoustic microphone array are activated simultaneously to capture the load distribution pattern, structural micro-deformation response, temperature rise dynamics of the tire-ground contact area, and acoustic signature characteristics generated by chassis mechanical vibration. Millisecond-level time alignment was performed on four types of physical field signals, and their key behavioral features were extracted. Based on the spatiotemporal consistency relationship between multi-physics field characteristics, the system determines whether there is human intervention or abnormal load conditions, thereby identifying covert violations such as load skipping, edge pressing, partial obstruction, or counterweight cheating. For example, if the pressure sensor array detects uneven load distribution, but the acoustic microphone array does not reflect the corresponding chassis vibration changes, or the thermal imaging module detects abnormal temperature fluctuations but the deformation sensor does not detect the corresponding deformation, the system will identify possible abnormal load conditions such as load skipping (vehicle not completely stopped), edge pressing (vehicle tires not properly contacting the ground), partial obstruction (such as an object blocking the sensor under the vehicle body), or counterweight cheating (increasing weight by increasing the local load on the wheels).

[0026] S30. Based on the collected data, the vehicle's three-dimensional pose is reconstructed using UWB positioning technology and visual SLAM technology to further ensure stability during the weighing process. If the vehicle is unstable, the weighing will be automatically cancelled. By precisely tracking the vehicle's position and attitude, the system can determine whether the vehicle has come to a complete stop and ensure that all wheelsets are within the valid weighing area. If the vehicle deviates, tilts, or is not completely stopped, the system will automatically invalidate the weighing, ensuring the accuracy and reliability of the weighing results. The specific steps include the following: S301. High-precision ranging is achieved by using multiple UWB anchor points deployed in the weighbridge area and vehicle-mounted UWB tags, while continuous image frames of the vehicle are acquired through a visual acquisition device above the weighbridge. After the vehicle enters the weighbridge area, the system utilizes multiple UWB anchor points deployed within the weighbridge area to perform high-precision ranging with the vehicle's onboard UWB tag. This high-precision ranging between the UWB anchor points and the onboard tag provides centimeter-level positioning accuracy, determining the vehicle's position on the platform in real time. Simultaneously, the vision acquisition device above the weighbridge platform begins operation, capturing continuous image frames of the vehicle. This image data helps the system acquire the vehicle's external features and provides detailed information about its motion. The combination of UWB and visual image data provides a rich source of information for pose reconstruction, enhancing the system's ability to accurately estimate the vehicle's position and attitude.

[0027] S302. Based on UWB ranging data and visual image frames, a joint positioning and mapping algorithm is used to reconstruct the three-dimensional spatial pose of the vehicle on the weighbridge. By combining UWB ranging data and visual image frames, the system runs a Localization and Mapping Algorithm (SLAM) to accurately reconstruct the vehicle's 3D spatial pose on the weighbridge platform. UWB technology provides precise positional information for the vehicle, while visual data provides external viewpoint features through image processing techniques. This information, combined with the SLAM algorithm, enables the system to accurately estimate the vehicle's position, attitude, and trajectory in 3D space. The reconstructed 3D pose reflects the vehicle's stationary state in real time, ensuring precise control at every stage of the weighing process.

[0028] S303. Based on the reconstructed three-dimensional pose, determine whether the vehicle has come to a complete stop and whether all wheelsets are within the effective weighing area. If there is any deviation, tilt, or instability, the weighing will be automatically invalidated.

[0029] Based on the reconstructed 3D pose data, the system can determine whether the vehicle has come to a complete stop and ensure that all wheelsets are within the valid weighing area. The system analyzes the vehicle's position and tilt to determine if there is any vehicle deviation or uneven force distribution. If the vehicle deviates, causing some wheelsets to be outside the weighing area, or if the vehicle tilts, resulting in uneven force distribution on some wheelsets, the system will immediately detect this anomaly and invalidate the weighing attempt. Furthermore, if the vehicle still experiences slight vibrations or is not completely stopped, the system will also trigger an invalidation mechanism to ensure the stability of the weighing process and the accuracy of the data.

[0030] S40. Based on the judgment of vehicle stability and abnormal weighing data, a dynamic trust scoring mechanism is used to assess the trust of vehicles. Vehicles with high trust enter the fast lane, while vehicles with low trust trigger full-modal monitoring and AI behavior analysis, further improving the accuracy and safety of the weighing process. Based on the vehicle trust assessment results, the system intelligently adjusts the weighing process, simplifying the weighing steps for high-trust vehicles and subjecting low-trust vehicles to more stringent monitoring and analysis to prevent abnormal behavior or cheating. Specifically, this includes the following steps: S401, by combining the consistency of the integrated coupled verification vectors, the stability of the vehicle's three-dimensional pose, and historical behavior records, the current trust assessment result of the vehicle is generated. The system first conducts a comprehensive trust assessment based on the consistency of the coupled verification vectors (force-shape-thermal-acoustic), the stability of the vehicle's 3D pose, and the vehicle's historical behavior records. Specifically, the system analyzes the consistency of various physical signals within the coupled verification vectors to determine the vehicle's stability during the weighing process. It also examines the vehicle's 3D pose data to assess whether there is any deviation, tilting, or incomplete stopping. Simultaneously, the system combines historical behavior data with previous weighing records, abnormal events, and trust scores to comprehensively determine the vehicle's trust level. Finally, the system generates a trust assessment result for the current vehicle based on this information, quantifying the vehicle's trust score.

[0031] S402. For vehicles with high trust assessment results, a simplified weighing process is enabled, performing only weight reading and basic verification. For vehicles with high trust assessment results, the system will implement a simplified weighing process. Vehicles with high trust assessment results typically show no record of abnormal weighing behavior and behave consistently during the current weighing process. In this case, the system only needs to perform basic weight reading and basic verification, without requiring additional comprehensive review. This simplified process reduces unnecessary monitoring and data processing time, while ensuring that the weighing process is not delayed due to unnecessary checks.

[0032] S403. For vehicles with low trust assessment results, activate the full-modal data review mechanism and call the artificial intelligence behavior analysis model to identify potential abnormal weighing behavior.

[0033] For vehicles with low trust assessment results, the system activates a full-modal data review mechanism for more stringent monitoring. Vehicles with low trust assessment results may exhibit abnormal behavior or pose a risk of weighing fraud; therefore, the system enhances monitoring through more comprehensive data reviews. These reviews include reanalyzing data from multiple sensors to check for patterns inconsistent with normal behavior. Simultaneously, the system utilizes artificial intelligence behavioral analysis models to identify potential abnormal weighing behaviors, such as skipping the weighbridge, pressing the edge of the scale, and counterweight fraud. By identifying these potential problems, the system can promptly detect and prevent abnormal weighing, ensuring the accuracy of weighing data and the security of the system.

[0034] S50. Weighing data, risk assessment results, and model optimization logs are encrypted and uploaded using blockchain technology, and a unique hash value is generated by combining it with a timestamp, ensuring the immutability and traceability of the weighing process data. Specifically, this includes the following steps: S501. Encapsulate the raw weight data, coupled verification vector, pose stability judgment result, trust assessment result and artificial intelligence analysis log generated during this weighing process into a structured data package. After the weighing process is completed, the system encapsulates the relevant key data into a structured data package. This data package includes the original weight data from the weighing process, the coupling verification vector, the pose stability determination result, the trust assessment result, and the artificial intelligence analysis log. This data represents the core content of the weighing process, covering the entire process from data acquisition and verification to risk assessment and artificial intelligence analysis.

[0035] S502. Encrypt the structured data packet and append a timestamp issued by a trusted time source; To ensure data security and privacy protection, the system encrypts the encapsulated structured data packets. During encryption, encryption algorithms conforming to national standards are used to ensure data security during storage and transmission. Simultaneously, the system attaches a timestamp issued by a trusted time source to each data packet, providing precise time stamping, effectively preventing data tampering and forgery, and ensuring the time validity and authenticity of the data.

[0036] S503. Upload the encrypted and timestamped data packet to the blockchain network to generate a globally unique hash identifier, thereby achieving tamper-proof storage and cross-institutional traceability auditing of the entire weighing process data.

[0037] Encrypted and timestamped data packets are uploaded to the blockchain network via a secure communication channel. On the blockchain, the data generates a globally unique hash value, serving as a digital credential for the weighing event. The immutability of blockchain technology ensures data security and allows all weighing data to be traced back to its original source. Through the decentralized storage and consensus mechanism of the blockchain, the system can achieve tamper-proof data storage throughout the weighing process and support cross-institutional traceability auditing. Any query and verification of the data will be controlled by blockchain smart contracts, ensuring that only authorized users can access the data, while also ensuring the transparency and compliance of the data access process.

[0038] Example 2 like Figure 2 As shown, Embodiment 2 of this application provides an IoT-based intelligent vehicle weighing monitoring system, comprising: Vehicle-mounted unit module 21 is the core module of the system responsible for communication, identity authentication, and trust assessment with the edge nodes of the weighbridge. Its main task is to ensure the protection of vehicle identity privacy and trust level assessment during the weighing process. Specific functions include two-way anonymous authentication and trust level determination. (Includes:) Anonymous Identity Authentication Submodule 211: This submodule is responsible for sending authentication requests from the vehicle's OBU to the weighbridge edge node and performing identity verification. Through an AES-based encryption-based authentication challenge and response mechanism, it ensures the protection of vehicle identity privacy while verifying the legitimacy of the weighbridge edge node.

[0039] Secure Communication Submodule 212: Responsible for data encryption and secure communication between the vehicle-mounted OBU and the weighbridge edge node. It employs a high-strength encryption algorithm to prevent interception or tampering of communication data, ensuring the confidentiality and integrity of the communication process.

[0040] Trust Level Assessment Submodule 213: Based on the vehicle's historical interaction records and authentication results, the system dynamically assesses the vehicle's trust level. The vehicle's trust score affects the processing method of subsequent weighing procedures. Vehicles with higher trust levels can have their processes simplified, while vehicles with lower trust levels require additional verification and monitoring.

[0041] The weighbridge edge node module 22 is responsible for collecting data from multiple sensors and providing accurate vehicle status and position through high-precision positioning and image acquisition technology. The core task of this module is to ensure the accuracy of data acquisition and vehicle positioning during the weighing process. It includes: Sensor acquisition submodule 221 integrates multiple sensors, including pressure sensing pads, structural strain gauges, infrared thermal imagers, and acoustic microphone arrays, to collect real-time information on vehicle load distribution, frame deformation, tire contact surface temperature rise, and chassis vibration. This submodule provides data support for subsequent physical field verification and anomaly detection.

[0042] UWB positioning and image acquisition submodule 222: This submodule performs high-precision ranging using multiple UWB anchor points deployed in the weighbridge area and vehicle-mounted UWB tags, while simultaneously acquiring continuous image frames of the vehicle using a high-definition visual acquisition device above the weighbridge. This submodule provides accurate vehicle position and attitude information by combining UWB positioning and visual information.

[0043] Data Synchronization and Calibration Submodule 223: This submodule is responsible for time synchronization and data calibration of various types of collected sensor data, ensuring that data from different sensors can be processed uniformly within the same time period.

[0044] Edge intelligent processing unit module 23 is responsible for fusing and processing the collected sensor data, and for performing real-time analysis of vehicle stability, load status, etc., based on AI algorithms to generate trust assessment results. The core task of this module is to perform intelligent analysis and monitoring of the weighing process. This includes: Data fusion submodule 231: This submodule is responsible for fusing signals from multiple sensors, including pressure sensors, deformation sensors, infrared thermal imagers, and acoustic microphone arrays. By integrating multi-source data, the system can comprehensively understand the physical state of the vehicle during the weighing process, ensuring data consistency and integrity.

[0045] 3D Pose Reconstruction Submodule 232: This submodule reconstructs the 3D pose of the vehicle on the weighbridge platform using UWB ranging data and visual image frames, employing a SLAM algorithm. Through high-precision positioning and mapping algorithms, this submodule accurately reflects the vehicle's position and attitude, ensuring vehicle stability and remaining within the effective weighing area.

[0046] AI Behavior Analysis Submodule 233: This submodule uses an artificial intelligence model to analyze abnormal vehicle behavior during the weighing process, identifying potential abnormal weighing behaviors such as skipping the scale, pressing the edge, and counterweight cheating. Through real-time behavior analysis, this submodule can promptly identify abnormal weighing and take appropriate measures.

[0047] The dynamic trust assessment module 24 scores vehicle trust based on multi-source data and intelligently adjusts the weighing process. This module analyzes historical vehicle behavior, real-time stability, and sensor data to ensure high-trust vehicles pass quickly, while low-trust vehicles trigger a rigorous review process. This includes: Trust Score Calculation Submodule 241: Based on factors such as the consistency of the "force-shape-thermal-acoustic" coupled verification vector, the vehicle's three-dimensional pose stability, and historical behavior records, this submodule calculates and generates a comprehensive trust score for the vehicle. Vehicles with high trust scores will enter a simplified weighing process, while vehicles with low trust scores will trigger additional monitoring and inspections.

[0048] Trust Process Scheduling Submodule 242: Based on the vehicle's trust level, the system intelligently schedules the weighing process through this submodule. Vehicles with higher trust scores will enter the fast lane, while vehicles with lower trust scores will trigger a full-modal monitoring mechanism and undergo AI behavior analysis.

[0049] Anomaly Monitoring Submodule 243: This submodule is responsible for additional detection and verification of abnormal load distribution, frame deformation, etc., in full-modal monitoring triggered by low-trust vehicles. Combined with AI models, the system can identify whether a vehicle is engaging in illegal activities and take appropriate countermeasures.

[0050] Blockchain Evidence Storage Interface Module 25 ensures the immutability of weighing data and provides cross-institutional traceability. Through blockchain technology, the system can encrypt and upload weighing data and risk assessment results, and use smart contracts to achieve tamper-proof data preservation.

[0051] Data Encryption Submodule 251: This submodule is responsible for encrypting critical data during the weighing process (such as raw weight data, coupling verification vectors, trust assessment results, etc.). Data encryption ensures security during storage and transmission, preventing unauthorized access or tampering of data.

[0052] Timestamp and Hash Generation Submodule 252: This submodule is responsible for appending a timestamp issued by a trusted time source to the encrypted data packet and generating a unique hash value. The timestamp provides a precise time stamp, ensuring the time sequence accuracy of the data, while the hash value generates a unique digital credential for each weighing.

[0053] Blockchain Upload and Evidence Preservation Submodule 253: Encrypted data packets are uploaded to the blockchain network through a secure communication channel. This submodule is responsible for data preservation and smart contract execution. The smart contract verifies the integrity and legality of the data packets, ensures the immutability of the data, and sets access permissions for the data, guaranteeing the transparency and compliance of the system.

[0054] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor for running one or more program instructions to execute an Internet of Things-based intelligent monitoring method for vehicle weighing.

[0055] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are executed by a processor to provide an Internet of Things-based intelligent monitoring method for vehicle weighing.

[0056] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions. When the computer program instructions are executed on a computer, the computer performs the above-described intelligent monitoring method for vehicle weighing based on the Internet of Things.

[0057] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0058] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0059] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0060] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0061] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0062] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0063] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0064] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart monitoring method for vehicle weighing based on the Internet of Things, characterized in that, Includes the following steps: S10. Through two-way anonymous authentication between the vehicle-mounted OBU and the edge node of the weighbridge, the legitimacy of the vehicle is verified and the weighing process of the corresponding trust level is initiated to ensure the safety and privacy protection of the weighing process. S20. After successful certification, heterogeneous physical field data are collected and processed in real time through multiple sensors to construct a "force-shape-thermal-acoustic" coupled verification vector, providing a verification basis for data analysis. S30. Based on the collected data, the vehicle's three-dimensional pose is reconstructed using UWB positioning technology and visual SLAM technology to further ensure stability during the weighing process. If the vehicle is unstable, the weighing will be automatically cancelled. S40. Based on the judgment of vehicle stability and abnormal weighing data, a dynamic trust scoring mechanism is used to assess the trust of vehicles. Vehicles with high trust enter the fast lane, while vehicles with low trust trigger full-modal monitoring and AI behavior analysis, further improving the accuracy and safety of the weighing process. S50. By using blockchain technology, weighing data, risk assessment results, and model optimization logs are encrypted and uploaded, and a unique hash value is generated by combining the timestamp, ensuring the immutability and traceability of the weighing process data.

2. The intelligent vehicle weighing monitoring method based on the Internet of Things as described in claim 1, characterized in that, By performing two-way anonymous authentication between the vehicle-mounted OBU and the weighbridge edge node, the legitimacy of the vehicle is verified and the weighing process of the corresponding trust level is initiated, ensuring the security and privacy protection of the weighing process. The specific steps include the following: The weighbridge edge node sends a one-time authentication challenge to the vehicle-mounted OBU. The vehicle-mounted OBU generates response information based on pre-set anonymous identity credentials without revealing the vehicle's true identity. The vehicle-mounted OBU verifies the digital certificate and deployment location legitimacy of the weighbridge edge node, and completes two-way identity mutual trust. Based on the vehicle's historical interaction records and the results of this authentication, an initial trust level is determined, and the weighing safety policy corresponding to that trust level is loaded.

3. The intelligent vehicle weighing monitoring method based on the Internet of Things as described in claim 1, characterized in that, After successful certification, heterogeneous physical field data are collected and processed in real time using multiple sensors to construct a coupled verification vector of "force-shape-thermal-acoustic" to provide verification basis for data analysis. The specific steps include the following: The pressure sensor array, structural strain sensor, infrared thermal imaging module and acoustic microphone array are synchronously triggered to collect vehicle load distribution, frame deformation, tire contact surface temperature rise and chassis vibration noise signals, respectively. Time synchronization and feature extraction are performed on the collected multi-source heterogeneous physical field signals; The extracted force field features, deformation features, thermal field features and acoustic features are fused to form a unified "force-shape-thermal-sound" coupled verification vector for subsequent consistency verification.

4. The intelligent vehicle weighing monitoring method based on the Internet of Things as described in claim 3, characterized in that, The process of constructing the "force-shape-thermal-acoustic" coupled verification vector includes the following sub-steps: The moment the vehicle enters the weighbridge platform, the pressure sensor array, chassis strain gauge, infrared thermal imager and acoustic microphone array are activated simultaneously to capture the load distribution pattern, structural micro-deformation response, temperature rise dynamics of the tire-ground contact area, and acoustic signature characteristics generated by chassis mechanical vibration. Millisecond-level time alignment was performed on four types of physical field signals, and their key behavioral features were extracted. Based on the spatiotemporal consistency relationship between multi-physics field characteristics, it is possible to determine whether there is human intervention or abnormal load state, thereby identifying hidden violations such as skipping the scale, pressing the edge, partial occlusion, or counterweight cheating.

5. The intelligent vehicle weighing monitoring method based on the Internet of Things as described in claim 1, characterized in that, Based on the collected data, the vehicle's three-dimensional pose is reconstructed using UWB positioning technology and visual SLAM technology to further ensure stability during the weighing process. If the vehicle is unstable, the weighing is automatically invalidated. The specific steps include the following: High-precision ranging is achieved by using multiple UWB anchor points deployed in the weighbridge area and vehicle-mounted UWB tags, while continuous image frames of the vehicle are acquired through a vision acquisition device above the weighbridge. Based on UWB ranging data and visual image frames, a joint localization and mapping algorithm is used to reconstruct the three-dimensional spatial pose of the vehicle on the weighbridge. The vehicle is judged to be completely stopped and all wheelsets are within the effective weighing area based on the reconstructed three-dimensional pose. If there is any deviation, tilt or instability, the weighing is automatically invalidated.

6. The intelligent vehicle weighing monitoring method based on the Internet of Things as described in claim 1, characterized in that, Based on anomalies in vehicle stability and weighing data, a dynamic trust scoring mechanism is used to assess vehicle trust. High-trust vehicles enter the fast lane, while low-trust vehicles trigger full-modal monitoring and AI behavior analysis, further improving the accuracy and safety of the weighing process. This includes the following sub-steps: By combining the consistency of the coupled verification vectors, the stability of the vehicle's 3D pose, and historical behavior records, the current trust assessment result of the vehicle is generated. For vehicles with high trust assessment results, a simplified weighing process is enabled, performing only weight reading and basic verification. For vehicles with low trust assessment results, activate the full-modal data review mechanism and call the artificial intelligence behavior analysis model to identify potential abnormal weighing behavior.

7. The intelligent vehicle weighing monitoring method based on the Internet of Things as described in claim 1, characterized in that, The weighing data, risk assessment results, and model optimization logs are encrypted and uploaded using blockchain technology, and a unique hash value is generated by combining the timestamps to ensure the immutability and traceability of the weighing process data. This process includes the following sub-steps: The raw weight data, coupled verification vector, pose stability judgment results, trust assessment results, and artificial intelligence analysis logs generated during this weighing process are encapsulated into a structured data package; The structured data packet is encrypted and a timestamp issued by a trusted time source is appended. Encrypted and timestamped data packets are uploaded to the blockchain network to generate globally unique hash identifiers, enabling tamper-proof storage and cross-institutional traceability auditing of weighing data throughout the entire process.

8. A vehicle weighing intelligent monitoring system based on the Internet of Things, characterized in that, include: The vehicle-mounted unit module has a built-in security chip that supports anonymous authentication and a UWB communication module, which is used to perform two-way anonymous authentication with the edge node of the weighbridge to ensure the privacy protection and trust assessment of the vehicle's identity. The weighbridge edge node module integrates a pressure sensing pad, structural strain gauge, infrared thermal imager, acoustic microphone array, UWB anchor point, and high-definition visual acquisition device to synchronously acquire multimodal physical field data of vehicles and provide high-precision spatial positioning and vehicle image data. The edge intelligence processing unit module is used to perform multimodal data fusion, 3D pose reconstruction and AI behavior analysis, analyze vehicle stability, load status and other parameters in real time, and generate trust assessment results. The dynamic trust assessment module generates a vehicle trust score based on collected vehicle data, historical interaction records, and current trust level. It schedules and optimizes the weighing process to ensure that high-trust vehicles enter the fast lane and low-trust vehicles trigger full-modal monitoring and AI behavior analysis. The blockchain evidence storage interface module connects to a consortium blockchain jointly maintained by regulatory agencies, logistics platforms, and third-party notaries. It is used to encrypt and upload weighing data, risk assessment results, model optimization logs, etc., and generate a unique hash value by combining the timestamp, so as to realize tamper-proof evidence storage and cross-institutional traceability audit of the entire weighing process data.

Images