A vehicle repair monitoring system

Abstract

This invention discloses a vehicle maintenance monitoring system, belonging to the field of vehicle maintenance monitoring technology. The system includes a data acquisition module, a data transmission and preprocessing module, a core monitoring platform module, and a maintenance record and traceability module. This vehicle maintenance monitoring system, through multi-source data fusion acquisition, standardized transmission, and intelligent preprocessing, achieves accurate fault diagnosis and dynamic generation of maintenance tasks. Combined with digital twin real-time monitoring and dynamic threshold alarms, it significantly improves maintenance standardization and safety. Simultaneously, the automated report generation and vehicle health record modules construct a full lifecycle traceability system, which not only optimizes personalized maintenance recommendations but also ensures data immutability and efficient access through encrypted storage and optimized querying, ultimately forming a closed-loop management system. This significantly reduces maintenance costs and failure rates, while improving operational efficiency and customer trust.

Description

Technical Field

[0001] This invention relates to the field of vehicle maintenance monitoring technology, specifically a vehicle maintenance monitoring system. Background Technology

[0002] Vehicle maintenance refers to the process of systematically inspecting, diagnosing, replacing or repairing faulty, underperforming, or maintenance-bound vehicles such as cars, trucks, and construction machinery using professional testing equipment and technical means. It covers the entire process from routine maintenance to troubleshooting complex faults, aiming to restore vehicle safety, reliability, and operational efficiency, extend service life, reduce the risk of sudden failures through preventative maintenance, and ensure that vehicles meet road traffic safety standards and environmental emission requirements.

[0003] Traditional maintenance relies on human experience, which is time-consuming and prone to omissions. The lack of standardized process monitoring for hidden faults can easily lead to operational errors. The monitoring system uses digital twin technology to map maintenance operations and combines dynamic threshold comparison to provide real-time warnings for violations, ensuring compliance with maintenance standards. Therefore, we propose a vehicle maintenance monitoring system. Summary of the Invention

[0004] The purpose of this invention is to provide a vehicle maintenance monitoring system to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a vehicle maintenance monitoring system, the maintenance monitoring system comprising a data acquisition module, a data transmission and preprocessing module, a monitoring platform core module, and a maintenance record and traceability module; The data acquisition module includes: Onboard data acquisition submodule: Reads vehicle operating data and ECU logs in real time via the OBD interface; Workstation sensor submodule: Deploy pressure sensors, temperature sensors, and vibration sensors at the maintenance workstation to monitor the maintenance workstation environment and parameters of key components; Video surveillance submodule: Captures maintenance work footage, detects leftover items, and provides early warnings of safety violations using high-definition cameras; The data transmission and preprocessing module includes: Communication protocol management submodule: unifies multi-source data formats, converts them into standard protocols, and uploads them to the cloud; The data cleaning and labeling submodule filters invalid data, fills in missing values, and labels key data. The core modules of the monitoring platform include: Fault diagnosis and task generation submodule: Based on knowledge graph, locate the root cause of the fault, and generate a step-by-step task list by combining maintenance work order and standard process library; Real-time monitoring and alarm submodule: compares actual operation with standard process to detect deviations, and generates alarms based on threshold triggers; The maintenance record and traceability module includes: Automated report generation submodule: Automatically fills in maintenance record templates, associates work order numbers with maintenance personnel IDs, and allows maintenance personnel to sign operation records via terminals; Vehicle Health Record Submodule: Stores all records of the vehicle from its first maintenance to its scrapping, and generates maintenance recommendations based on historical data.

[0006] Preferably, the vehicle data acquisition submodule uses a standard-compliant OBD interface and CAN / LIN bus protocol parsing to ensure connectivity to vehicles of various brands and models.

[0007] Preferably, the workstation sensor submodule deploys pressure sensors, temperature sensors, and vibration sensors at key locations in the maintenance workstation, and uses a wireless sensor network to achieve wireless transmission of sensor data, and performs real-time processing and analysis of the collected sensor data.

[0008] Preferably, the communication protocol management submodule converts the CAN signal of the OBD into an easily processed digital signal through a CAN bus parser. For analog signals from pressure sensors, temperature sensors, and vibration sensors, it uses an ADC analog-to-digital converter to convert them into digital signals. For RTSP streams of video, it uses a video decoder to convert them into frame image data.

[0009] Preferably, the data cleaning and labeling submodule uses median filtering to filter the data and remove noise data. For video data, it uses frame difference method to detect and remove invalid or noise frames. For missing data, it uses linear interpolation to fill in the missing data. For missing video frames, it uses optical flow method to recover them. It uses labeling tools to label pipeline data and uses NLP technology to automatically label and classify text data.

[0010] Preferably, the fault diagnosis and task generation submodule integrates manufacturer repair manuals, historical work order data, and expert experience to construct a fault code-possible cause-solution triple. It uses Neo4j to store knowledge graphs for rapid reasoning, defines repair process rules, and combines work order data with standard processes to dynamically generate a step-by-step task list through a rule engine.

[0011] Preferably, the real-time monitoring and alarm submodule constructs a digital twin of the maintenance scenario using Unity, maps the real-time mapping tool usage sequence and parameter settings, compares the actual operation data with the standard process in the digital twin model to detect deviations, and sets dynamic thresholds based on historical data.

[0012] Preferably, the automated report generation submodule uses FreeMarker to generate maintenance report templates, automatically fills in the fault phenomena, handling measures and replacement parts list, uses InfluxDB to store vehicle historical maintenance records, and performs cold storage for data that has not been accessed for a long time.

[0013] Preferably, the video monitoring submodule uses YOLOv8 to monitor the hand area and tools of maintenance personnel in real time, locates the tool position by bounding box, uses DeepSORT to track the position of small targets such as screws in the video, records their initial installation position and final state, and uses YOLOv8-Face to detect the face area and crop the image around the eyes.

[0014] Preferably, the vehicle health record submodule predicts the next failure time based on historical failure frequency and component life data. Combining the prediction results with the manufacturer's recommended cycle, it generates personalized maintenance suggestions, indexes high-frequency queries to reduce Neo4j query latency, and associates maintenance personnel ID and tool usage records through work order numbers. Maintenance personnel sign operation records through mobile terminals, and the signature data is encrypted, stored, and timestamped.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention, through its vehicle maintenance monitoring system, achieves precise fault diagnosis and dynamic generation of maintenance tasks by integrating multi-source data collection, standardized transmission, and intelligent preprocessing. Combined with digital twin real-time monitoring and dynamic threshold alarms, it significantly improves maintenance standardization and safety. Simultaneously, the automated report generation and vehicle health record module construct a full lifecycle traceability system. This not only optimizes personalized maintenance recommendations but also ensures data immutability and efficient access through encrypted storage and optimized querying. Ultimately, it forms a closed-loop management system of "prevention-diagnosis-execution-traceability," significantly reducing maintenance costs and failure rates while improving operational efficiency and customer trust. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0017] 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 embodiments of the present invention, and not all embodiments. 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.

[0018] Example: Please refer to Figure 1The present invention provides a technical solution: a vehicle maintenance monitoring system, which includes a data acquisition module, a data transmission and preprocessing module, a monitoring platform core module, and a maintenance record and traceability module; The data acquisition module includes: Onboard data acquisition submodule: Reads vehicle operating data and ECU logs in real time via the OBD interface; Workstation sensor submodule: Deploy pressure sensors, temperature sensors, and vibration sensors at the maintenance workstation to monitor the maintenance workstation environment and parameters of key components; Video surveillance submodule: Captures maintenance work footage, detects leftover items, and provides early warnings of safety violations using high-definition cameras; The data transmission and preprocessing module includes: Communication protocol management submodule: unifies multi-source data formats, converts them into standard protocols, and uploads them to the cloud; The data cleaning and labeling submodule filters invalid data, fills in missing values, and labels key data. The core modules of the monitoring platform include: Fault diagnosis and task generation submodule: Based on knowledge graph, locate the root cause of the fault, and generate a step-by-step task list by combining maintenance work order and standard process library; Real-time monitoring and alarm submodule: compares actual operation with standard process to detect deviations, and generates alarms based on threshold triggers; The maintenance record and traceability module includes: Automated report generation submodule: Automatically fills in maintenance record templates, associates work order numbers with maintenance personnel IDs, and allows maintenance personnel to sign operation records via terminals; Vehicle Health Record Submodule: Stores all records of the vehicle from its first maintenance to its scrapping, and generates maintenance recommendations based on historical data.

[0019] The vehicle data acquisition submodule uses a standard-compliant OBD interface and CAN / LIN bus protocol parsing to ensure connectivity with vehicles of various brands and models.

[0020] The workstation sensor submodule deploys pressure sensors, temperature sensors, and vibration sensors at key locations in the maintenance workstation. It uses a wireless sensor network to achieve wireless transmission of sensor data and performs real-time processing and analysis of the collected sensor data.

[0021] The communication protocol management submodule converts the CAN signals of the OBD into easily processed digital signals through a CAN bus parser. For analog signals from pressure sensors, temperature sensors, and vibration sensors, it uses an ADC analog-to-digital converter to convert them into digital signals. For RTSP video streams, it uses a video decoder to convert them into frame image data.

[0022] The data cleaning and labeling submodule uses median filtering to filter the data and remove noise. For video data, it uses frame difference to detect and remove invalid or noisy frames. For missing data, it uses linear interpolation to fill in the missing data. For missing video frames, it uses optical flow to recover them. It uses labeling tools to label pipeline data and uses NLP technology to automatically label and classify text data.

[0023] Fault Diagnosis and Task Generation Submodule: Integrates manufacturer repair manuals, historical work order data, and expert experience to construct a triplet of fault code-possible cause-solution. It uses Neo4j to store knowledge graphs for rapid reasoning, defines repair process rules, and combines work order data with standard processes to dynamically generate a step-by-step task list through a rule engine.

[0024] The real-time monitoring and alarm submodule uses Unity to build a digital twin of the maintenance scenario, and uses the real-time mapping tool to compare the actual operation data with the standard process in the digital twin model to detect deviations. It also sets dynamic thresholds based on historical data.

[0025] The automated report generation submodule uses FreeMarker to generate maintenance report templates, automatically filling in fault symptoms, handling measures, and a list of replaced parts. It uses InfluxDB to store vehicle history maintenance records and performs cold storage for data that has not been accessed for a long time.

[0026] The video monitoring submodule uses YOLOv8 to monitor the hand area and tools of maintenance personnel in real time. It locates the position of tools by bounding boxes, uses DeepSORT to track the position of small targets such as screws in the video, records their initial installation position and final state, and uses YOLOv8-Face to detect the face area and crop the image around the eyes.

[0027] The vehicle health record submodule predicts the next failure time based on historical failure frequency and component life data. It combines the prediction results with the manufacturer's recommended cycle to generate personalized maintenance suggestions. It indexes high-frequency queries to reduce Neo4j query latency. It associates maintenance personnel ID and tool usage records with work order numbers. Maintenance personnel sign operation records through mobile terminals. The signature data is encrypted, stored, and timestamped.

[0028] The specific implementation method of this embodiment is as follows: The data acquisition module achieves comprehensive monitoring through multi-source data fusion: the vehicle-mounted data acquisition submodule utilizes a standardized OBD interface and CAN / LIN bus protocol to read vehicle operating parameters (such as speed and fault codes) and ECU logs in real time, compatible with multiple vehicle brands; the workstation sensor submodule deploys pressure, temperature, and vibration sensors at the repair workstation, combined with Zigbee wireless transmission technology to monitor the environment and equipment status in real time, and triggers abnormal alarms through edge computing devices; the video monitoring submodule uses YOLOv8 and DeepSORT algorithms to achieve tool positioning, object detection, and safety violation warnings (such as not wearing safety goggles), and at the same time, recovers missing video frames through optical flow to ensure data integrity; The data transmission and preprocessing module addresses the standardization and cleaning of multi-source data: The communication protocol management submodule unifies the data format, converting CAN signals, analog sensor data, and RTSP video streams into JSON, digital signals, and frame images, respectively, to facilitate cloud transmission. The data cleaning and labeling submodule uses techniques such as median filtering and linear interpolation to process noise and missing values, and classifies and labels text and pipeline data using NLP and manual labeling tools, providing a high-quality data foundation for subsequent analysis. The core modules of the monitoring platform focus on fault diagnosis and real-time monitoring: The fault diagnosis and task generation sub-module integrates manufacturer manuals, historical work orders and expert experience based on Neo4j knowledge graph, and dynamically generates step-by-step maintenance tasks through a rule engine. The real-time monitoring and alarm sub-module uses Unity to build a digital twin model, which maps maintenance operations and standard procedures in real time. It detects deviations through dynamic threshold comparison and triggers alarm notifications to ensure maintenance standardization. The maintenance record and traceability module enables full traceability of the maintenance process: The automated report generation submodule uses FreeMarker templates to automatically fill in fault phenomena, handling measures, and replacement parts lists, and combines InfluxDB to store historical records to reduce the cost of storing cold data. The vehicle health record submodule predicts the next maintenance time based on historical fault frequency and component lifespan, generates personalized suggestions, and optimizes Neo4j query efficiency through indexing. At the same time, it uses encrypted signature and timestamp technology to ensure that maintenance records are tamper-proof, forming a complete closed-loop management.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0030] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A vehicle maintenance monitoring system, characterized in that: The maintenance monitoring system includes a data acquisition module, a data transmission and preprocessing module, a core monitoring platform module, and a maintenance record and traceability module. The data acquisition module includes an on-board data acquisition submodule, a workstation sensor submodule, and a video monitoring submodule. Specifically, the on-board data acquisition submodule reads vehicle operating data and ECU logs in real time through the OBD interface; the workstation sensor submodule deploys pressure sensors, temperature sensors, and vibration sensors at the repair workstation to monitor the workstation environment and parameters of key components; and the video monitoring submodule captures repair work footage, detects leftovers, and provides early warnings of safety violations using a high-definition camera. The data transmission and preprocessing module includes a communication protocol management submodule and a data cleaning and labeling submodule. The communication protocol management submodule unifies the multi-source data format, converts it into a standard protocol, and uploads it to the cloud. The data cleaning and labeling submodule filters invalid data, fills in missing values, and labels key data. The core modules of the monitoring platform include a fault diagnosis and task generation submodule and a real-time monitoring and alarm submodule. The fault diagnosis and task generation submodule uses a knowledge graph to locate the root cause of the fault and generates a step-by-step task list by combining maintenance work orders and standard process libraries. The real-time monitoring and alarm submodule compares the actual operation with the standard process to detect deviations and generates alarms by triggering thresholds. The maintenance record and traceability module includes an automated report generation submodule and a vehicle health record submodule. The automated report generation submodule automatically fills in maintenance record templates, associates work order numbers with maintenance personnel IDs, and allows maintenance personnel to sign operation records via terminals. The vehicle health record submodule stores all records of the vehicle from its first maintenance to its scrapping and generates maintenance recommendations based on historical data.

2. The vehicle maintenance monitoring system according to claim 1, characterized in that: The vehicle data acquisition submodule selects a standard-compliant OBD interface and uses CAN / LIN bus protocol parsing to ensure connectivity to vehicles of various brands and models.

3. The vehicle maintenance monitoring system according to claim 1, characterized in that: The workstation sensor submodule deploys pressure sensors, temperature sensors, and vibration sensors at key locations in the maintenance workstation. It uses a wireless sensor network to achieve wireless transmission of sensor data and performs real-time processing and analysis of the collected sensor data.

4. The vehicle maintenance monitoring system according to claim 1, characterized in that: The communication protocol management submodule converts the CAN signals of the OBD into easily processed digital signals through a CAN bus parser. For analog signals from pressure sensors, temperature sensors, and vibration sensors, it uses an ADC analog-to-digital converter to convert them into digital signals. For RTSP streams of video, it uses a video decoder to convert them into frame image data.

5. A vehicle maintenance monitoring system according to claim 1, characterized in that: The data cleaning and labeling submodule uses median filtering to filter the data and remove noise. For video data, it uses frame difference to detect and remove invalid or noisy frames. For missing data, it uses linear interpolation to fill in the missing data. For missing video frames, it uses optical flow to recover them. It uses labeling tools to label pipeline data and uses NLP technology to automatically label and classify text data.

6. A vehicle maintenance monitoring system according to claim 1, characterized in that: The fault diagnosis and task generation submodule integrates manufacturer repair manuals, historical work order data, and expert experience to construct a triplet of fault code-possible cause-solution. It uses Neo4j to store knowledge graphs for rapid reasoning, defines repair process rules, and combines work order data with standard processes to dynamically generate a step-by-step task list through a rule engine.

7. A vehicle maintenance monitoring system according to claim 1, characterized in that: The real-time monitoring and alarm submodule uses Unity to build a digital twin of the maintenance scenario, and uses the real-time mapping tool to compare the actual operation data with the standard process in the digital twin model to detect deviations, and sets dynamic thresholds based on historical data.

8. A vehicle maintenance monitoring system according to claim 1, characterized in that: The automated report generation submodule uses FreeMarker to generate maintenance report templates, automatically fills in fault symptoms, handling measures and replacement parts list, and uses InfluxDB to store vehicle historical maintenance records, and performs cold storage for data that has not been accessed for a long time.

9. A vehicle maintenance monitoring system according to claim 1, characterized in that: The video monitoring submodule uses YOLOv8 to monitor the hand area and tools of maintenance personnel in real time. It locates the tool position by bounding box, uses DeepSORT to track the position of small targets such as screws in the video, records their initial installation position and final state, and uses YOLOv8-Face to detect the face area and crop the image around the eyes.

10. A vehicle maintenance monitoring system according to claim 1, characterized in that: The vehicle health record submodule predicts the next failure time based on historical failure frequency and component life data. Combining the prediction results with the manufacturer's recommended cycle, it generates personalized maintenance suggestions, indexes high-frequency queries to reduce Neo4j query latency, and associates maintenance personnel ID and tool usage records through work order numbers. Maintenance personnel sign operation records through mobile terminals, and the signature data is encrypted, stored, and timestamped.

Images