A vehicle gearbox thermal fault monitoring and processing method and device integrating digital twin

Abstract

The present invention proposes a vehicle gearbox thermal fault monitoring and processing method and device that integrates digital twins, which belongs to the field of vehicle monitoring and maintenance, and solves the problems of gearbox thermal balance monitoring, fault prediction difficulties and automatic adjustment lag in the prior art. By constructing a digital twin model and a fault prediction model, real-time monitoring of the thermal balance state of the gearbox and prediction of potential faults can be achieved. At the same time, under the action of the automatic compensation system, the automatic compensation strategy is continuously optimized according to the actual operating results and accumulated data, and the system response speed and compensation effect are improved, thereby improving the gearbox operation efficiency and reducing the occurrence of faults. The present invention also provides a fault monitoring device, in which real-time data is collected on the CAN bus, and the data is transmitted and stored through the control unit and the network system, and the automatic compensation system performs thermal balance adjustment.

Description

Technical Field

[0001] The present invention belongs to the field of vehicle monitoring and maintenance, and specifically, relates to a vehicle gearbox thermal fault monitoring and processing method and device integrating digital twins. Background Art

[0002] In the field of modern construction machinery, the gearbox is an important part of the vehicle, responsible for transmitting the power of the engine and adjusting the speed and torque of the vehicle. The normal operation of the gearbox is crucial to the overall performance and life of the vehicle. However, the operating environment of the vehicle is usually very harsh, which can easily cause problems such as gearbox overheating, wear, and failure, thus affecting the reliability and production efficiency of the vehicle.

[0003] With the advancement of technology, digital twin technology has gradually been applied in the field of engineering machinery. Digital twin technology can accurately simulate and monitor the state of physical entities by synchronizing physical entities with their virtual models in real time. Using sensors, the Internet of Things and big data analysis, digital twins can obtain and analyze the working status of gearboxes in real time, predict potential failures and provide targeted maintenance advice. This technology can not only improve the operating reliability of gearboxes, but also extend their service life and reduce downtime caused by failures.

[0004] Traditional transmission monitoring methods usually rely on regular maintenance and manual inspections, which have certain lags and limitations. They are unable to detect and adjust the thermal balance state of the transmission in real time, and it is difficult to detect potential problems in a timely manner. The vehicle transmission generates a lot of heat during operation, which may cause the transmission to overheat and affect its performance and life, increasing maintenance costs.

[0005] Therefore, a new solution is needed that can monitor and adjust the thermal balance state of the gearbox in a timely manner. Summary of the invention

[0006] In view of the above-mentioned problems existing in the prior art, the purpose of the present invention is to provide a vehicle gearbox thermal fault monitoring and processing method and device integrating digital twins, which mainly solves the problem of untimely gearbox monitoring and maintenance means in the prior art, can predict potential gearbox failures in advance, and automatically compensate when problems occur, thereby improving the vehicle's operating reliability and efficiency.

[0007] In order to solve the above problems, the technical solution adopted by the present invention is as follows:

[0008] A vehicle gearbox thermal fault monitoring and processing method integrating digital twins, comprising:

[0009] Obtain vehicle transmission operating data in real time;

[0010] Use the actual gearbox geometry data to build a digital twin model of the gearbox, and synchronize the actual gearbox status with the digital twin model in real time;

[0011] Use the digital twin model to simulate and analyze the heat generation and dissipation process of the gearbox, and then compare the simulation analysis results with the real-time operation data to monitor the thermal balance state of the gearbox in real time and detect whether there are thermal anomalies;

[0012] Based on the real-time and historical data output by the digital twin model, a deep learning model is used to predict faults;

[0013] Dynamically adjust the gearbox's operating parameters based on the results of fault prediction to maintain the normal operation of the gearbox;

[0014] The digital twin model is used to simulate and analyze the heat generation and dissipation process of the gearbox. The simulation analysis results are then compared with the real-time operation data to monitor the thermal balance state of the gearbox in real time and detect whether there are thermal anomalies, including:

[0015] Establish a heat generation model for the gearbox, including the distribution of heat sources in each internal component;

[0016] Define heat transfer pathways, including heat transfer mechanisms of conduction, convection, and radiation;

[0017] Establish a heat exchange model between the gearbox and the environment, taking into account the ambient temperature, radiator efficiency and ventilation conditions, and simulate the heat exchange process between the gearbox and the external environment;

[0018] By updating the temperature distribution and heat flow in the digital twin model in real time, the real-time collected temperature data is compared with the simulation results of the digital twin model to identify areas in the digital twin model that do not match the actual temperature data in order to detect whether there are thermal anomalies.

[0019] Furthermore, real-time acquisition of vehicle transmission operation data includes:

[0020] Obtain parameters through sensors installed on the gearbox;

[0021] transmitting the data to a central processing unit via a transmission network;

[0022] Data preprocessing including noise filtering, data smoothing and rectification is performed by the central processing unit;

[0023] The pre-processed data is input into the digital twin model and fault prediction system through the transmission network;

[0024] The data is updated regularly through feedback from the digital twin model and repeatedly collected gearbox operating data.

[0025] Furthermore, the digital twin model of the gearbox is constructed by using the geometric data of the actual gearbox, and the state of the actual gearbox is synchronized with the digital twin model in real time, including:

[0026] Obtain the actual gearbox geometry data, including size, shape and internal structure;

[0027] Use modeling software to create a 3D geometric model of the gearbox and ensure that the geometry of the model is consistent with the actual gearbox;

[0028] Finite element analysis technology is applied to the digital twin model to simulate the heat conduction, convection and radiation processes of the gearbox to calculate its heat generation and dissipation characteristics;

[0029] Establish a data synchronization interface to ensure that the digital twin model can obtain data in real time and perform real-time integration and correction of the model.

[0030] Furthermore, based on the real-time data and historical data output by the digital twin model, the deep learning model is used to predict faults, including:

[0031] Preprocess historical operation data, including data cleaning, noise filtering, data normalization and missing value management;

[0032] Analyze pre-processed historical data to identify common failure modes and abnormal characteristics;

[0033] Establishing a deep-learnable fault prediction model based on the common fault modes and abnormal characteristics;

[0034] The data obtained by analyzing the real-time data of the gearbox by the digital twin model is input into the fault prediction model;

[0035] Based on the results given by the fault prediction model, potential fault types are identified and the occurrence time is predicted.

[0036] Furthermore, dynamically adjusting the operating parameters of the gearbox according to the results of the fault prediction to maintain the normal operation of the gearbox includes:

[0037] Adjust the operating parameters of the gearbox based on the results of the thermal balance detection and fault prediction model of the digital twin model, including adjusting the oil pressure, controlling the speed, and optimizing the cooling system;

[0038] Establish a feedback adjustment mechanism, detect the actual operating effect after adjustment, detect the actual temperature change after adjustment, compare the real-time data with the expected effect of feedback adjustment, evaluate the effectiveness of adjustment measures, and optimize the adjustment strategy;

[0039] Based on the actual effect of the optimized plan adjusted by the feedback adjustment mechanism, further optimize the adjustment strategy of the feedback adjustment mechanism;

[0040] Regularly evaluate and update parameter adjustments and feedback regulation mechanism strategies.

[0041] A vehicle transmission thermal fault monitoring and processing device integrating digital twins is used to implement the above-mentioned vehicle transmission thermal fault monitoring and processing method integrating digital twins, including a data acquisition module, a digital twin model module, a thermal balance detection module, a fault prediction module and an automatic compensation module. The modules are electrically connected to each other, and the data acquisition module is arranged on the vehicle chassis.

[0042] Furthermore, the data acquisition module includes a displacement sensor, a vibration sensor, a temperature sensor, a pressure sensor, an oil level sensor and an acceleration sensor. The displacement sensor is arranged between the vehicle's clutch and the gearbox input shaft and the gearbox output shaft. The vibration sensor is arranged on the gearbox housing. The pressure sensor and the oil level sensor are arranged inside the gearbox. There are multiple temperature sensors, which are respectively arranged on the gearbox housing and inside the gearbox. The acceleration sensor is arranged at the bottom or side of the gearbox.

[0043] Further, the digital twin model module includes a geometric model unit, a material property unit and a real-time synchronization unit;

[0044] The thermal balance detection module includes a heat exchange unit and an abnormality detection unit;

[0045] The fault prediction module includes a data processing unit, a model building unit and a fault prediction unit;

[0046] The automatic compensation module includes a parameter adjustment unit and a feedback adjustment unit.

[0047] Furthermore, the monitoring and processing device is externally connected to a communication network system, and the communication network system includes a device layer, a communication layer, a network layer, an application layer and a feedback layer. The detection device is arranged at the device layer, and the device layer is provided with a device gateway. The communication layer includes a mobile network and a satellite network, the network layer includes a server, the application layer includes a receiving client, and the feedback layer includes a fault detection server. The various layers in the communication network system are connected and data is transmitted through signals.

[0048] Compared with the existing inventions, the present invention forms a vehicle gearbox thermal fault monitoring device through the close cooperation of various modules, which can fully realize the monitoring, prediction and compensation functions. This precise and real-time monitoring and adjustment mechanism greatly improves the operating reliability of the gearbox, reduces the risk of unplanned downtime, and can significantly extend the service life of the equipment.

[0049] At the same time, the functions of fault prediction and automatic compensation reduce reliance on manual intervention. The deep learning algorithm makes fault prediction more intelligent, and the adaptive adjustment method is used to optimize the automatic compensation function, which significantly improves the real-time and accuracy of digital twin technology, makes operation more convenient, and significantly improves the overall benefits, effectively reducing the company's operating costs and improving overall operational efficiency.

[0050] And based on the communication network system to which the monitoring device is connected, the operator can monitor the various parameters of the gearbox in real time through the receiving client, receive and process the early warning information generated by the server. When there is a problem with the automatic compensation strategy, the operator can also manually adjust the compensation strategy remotely to ensure that human intervention can be timely to deal with emergencies in an emergency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 The overall framework implementation flow chart of a vehicle gearbox thermal fault monitoring and processing method based on digital twin of the present invention;

[0052] Figure 2 A diagram of the automatic compensation method for forced heat dissipation of a vehicle gearbox according to the present invention;

[0053] Figure 3 It is the equipment installation diagram of the monitoring device using the gearbox thermal fault treatment method;

[0054] Figure 4 It is the construction process and working diagram of each module of the monitoring device;

[0055] Figure 5 The first part of the system diagram of the external communication network for the service monitoring device;

[0056] Figure 6 The second part of the system diagram of the external communication network for the service monitoring device;

[0057] Figure 7 Schematic diagram of the visual control platform for the receiving client. DETAILED DESCRIPTION

[0058] The present invention is further described below in conjunction with specific embodiments.

[0059] like Figure 1 As shown, the present invention provides a vehicle gearbox thermal fault monitoring and processing method integrating digital twins. The method is based on digital twin technology, and realizes online monitoring of thermal balance and fault prediction of vehicle gearboxes through real-time data acquisition and virtual model comparison. The method can also continuously self-iterate based on historical detection data and adjustment schemes to realize automatic compensation of the processing method.

[0060] The main steps of this method include:

[0061] Step 1: Obtain the operating data of the vehicle gearbox in real time;

[0062] Step 2: Use the actual gearbox geometry data to build a digital twin model of the gearbox, and synchronize the actual gearbox status with the digital twin model in real time;

[0063] Step 3: Use the digital twin model to simulate and analyze the heat generation and dissipation process of the gearbox, then compare the simulation analysis results with the real-time operation data, monitor the thermal balance state of the gearbox in real time, and detect whether there are thermal anomalies;

[0064] Step 4: Based on the real-time data and historical data output by the digital twin model, use the deep learning model to predict faults;

[0065] Step 5: Dynamically adjust the gearbox operating parameters according to the fault prediction results to maintain the normal operation of the gearbox.

[0066] It can dynamically adjust the operating status of the gearbox, which not only optimizes the performance of the gearbox, but also effectively reduces maintenance costs, improves the overall reliability and service life of the equipment, and ensures the stability and safety of the vehicle under various working conditions.

[0067] Reference Figure 1 As shown, it is a modular integrated operation process of the method, and the implementation of the method specifically includes the following steps:

[0068] Step 101: Acquire the operating data of the vehicle transmission in real time.

[0069] Step 102: Use the geometric data of the actual gearbox to build a digital twin model of the gearbox, and synchronize the state of the actual gearbox with the digital twin model in real time.

[0070] Step 103: Use the digital twin model to simulate and analyze the heat generation and dissipation process of the gearbox, then compare the simulation analysis results with the real-time operation data, monitor the thermal balance state of the gearbox in real time, and detect whether there is thermal anomaly.

[0071] Step 104: Based on the real-time data and historical data output by the digital twin model, a deep learning model is used to predict faults.

[0072] Step 105: Dynamically adjust the operating parameters of the gearbox according to the result of the fault prediction to maintain the normal operation of the gearbox.

[0073] It can be seen that the steps in the actual modular integration operation correspond to the steps of the fault handling method, wherein step one corresponds to step 101 , step two corresponds to step 102 , step three corresponds to step 103 , step four corresponds to step 104 , and step five corresponds to step 105 .

[0074] In step 101, real-time acquisition of operating data can accurately measure and transmit real-time data such as temperature, pressure, vibration and speed, ensuring the accuracy and real-time performance of data acquisition of the gearbox under various working conditions. The collected data is not only used as input for the digital twin model, but also as the basis for subsequent fault prediction and thermal balance analysis.

[0075] Through in-depth analysis of this data, the device can promptly identify potential problems, predict possible failures, and automatically adjust the operating parameters of the transmission when necessary, thereby optimizing performance and enhancing the overall reliability of the equipment.

[0076] The specific process is:

[0077] Obtain parameters through sensors installed on the gearbox;

[0078] transmitting the data to a central processing unit via a transmission network;

[0079] Data preprocessing including noise filtering, data smoothing and rectification is performed by the central processing unit;

[0080] The pre-processed data is input into the digital twin model and fault prediction system through the transmission network;

[0081] The data is updated regularly through feedback from the digital twin model and repeatedly collected gearbox operating data.

[0082] In the actual implementation process, step 101 can be specifically implemented according to the following steps:

[0083] Step 1011: Install and configure multiple high-precision sensors at key locations of the gearbox. These sensors are used to monitor parameters such as temperature, pressure, vibration, and speed in real time. Ensure that the arrangement of sensors can fully cover the operating status of the gearbox.

[0084] Step 1012: Establish a data acquisition system to transmit the data collected by the sensor to the central processing unit in real time via a wireless or wired network. These data will be recorded at a high frequency to ensure that the instantaneous changes in the operation of the gearbox can be captured.

[0085] Step 1013: Perform data preprocessing, including noise filtering, data smoothing and correction, etc., to ensure that the acquired data has high accuracy and stability.

[0086] Step 1014: The preprocessed data is transmitted to the digital twin model and fault prediction system in real time to provide support for subsequent thermal balance analysis and fault prediction.

[0087] Step 1015: Regularly inspect and maintain sensors and data acquisition systems to ensure long-term stability of the equipment and continued accuracy of data acquisition.

[0088] Through the above implementation steps, the accuracy and reliability of the data acquired in real time can be ensured, thereby providing a solid data foundation for the accuracy of the digital twin model, the effectiveness of thermal balance monitoring, and the accuracy of fault prediction.

[0089] In step 102, the operating data is used to construct a digital twin model of the gearbox. By creating a three-dimensional model that is highly consistent with the actual gearbox geometry and combining finite element analysis technology, the heat conduction, convection and radiation characteristics of the gearbox are accurately simulated.

[0090] Then the dynamic characteristics of the model include the synchronization of real-time operating data to ensure that the digital twin model can accurately reflect the state changes of the gearbox under various working conditions and be updated in real time.

[0091] This dynamic update capability not only improves the accuracy of the model, but also provides immediate feedback when the gearbox is abnormal, thus providing detailed and real-time data support for subsequent thermal balance analysis and fault prediction. The synchronization mechanism ensures a close connection between the model and the actual equipment, allowing the system to quickly adapt to changes and make effective adjustments and compensations.

[0092] The specific process includes:

[0093] Obtain the actual gearbox geometry data, including size, shape and internal structure;

[0094] Use modeling software to create a 3D geometric model of the gearbox and ensure that the geometry of the model is consistent with the actual gearbox;

[0095] Finite element analysis technology is applied to the digital twin model to simulate the heat conduction, convection and radiation processes of the gearbox to calculate its heat generation and dissipation characteristics;

[0096] Establish a data synchronization interface to ensure that the digital twin model can obtain data in real time and perform real-time integration and correction of the model.

[0097] In the actual implementation process, step 102 can be specifically implemented according to the following steps:

[0098] Step 1021: First, obtain detailed geometric data from the actual gearbox, including its size, shape and internal structure.

[0099] Step 1022: Use 3D modeling software to create a digital twin model of the gearbox, ensuring that the geometry of the model is highly consistent with the actual gearbox. The model should include all key components and their relationships to accurately reflect the actual structure of the gearbox.

[0100] Step 1023: Apply finite element analysis technology to the digital twin model to calculate the heat generation and dissipation characteristics of the gearbox by simulating the heat conduction, convection and radiation processes of the gearbox. This includes defining parameters such as material properties, boundary conditions and heat sources to ensure the accuracy of thermal analysis.

[0101] Step 1024: Establish a data synchronization interface to transmit real-time operation data to the digital twin model through the data acquisition system. This requires the development of a data interface that is compatible with the actual transmission sensor data format and enables real-time data update and synchronization.

[0102] Step 1025: Design and implement a data fusion algorithm to integrate real-time data with the digital twin model to ensure that the model can be dynamically adjusted according to the actual gearbox operating status. This includes real-time correction of model parameters so that it accurately reflects the gearbox status under current operating conditions.

[0103] Step 1026: Regularly verify and update the model to ensure that it remains accurate in the long run. By comparing the actual operation data with the model prediction results, possible deviations can be identified and corrected to maintain the high accuracy and reliability of the model.

[0104] In step 103, the digital twin model is used to simulate and analyze the heat generation and dissipation process of the gearbox, monitor the thermal balance state of the gearbox in real time, and detect whether there is thermal anomaly. Specifically, it simulates the heat source and heat transfer path inside the gearbox, as well as the heat exchange between the gearbox and the environment.

[0105] The specific process is:

[0106] Establish a heat generation model for the gearbox, including the distribution of heat sources in each internal component;

[0107] Define heat transfer pathways, including heat transfer mechanisms of conduction, convection, and radiation;

[0108] Establish a heat exchange model between the gearbox and the environment, taking into account the ambient temperature, radiator efficiency and ventilation conditions, and simulate the heat exchange process between the gearbox and the external environment;

[0109] By updating the temperature distribution and heat flow in the digital twin model in real time, the real-time collected temperature data is compared with the simulation results of the digital twin model to identify areas in the digital twin model that do not match the actual temperature data in order to detect whether there are thermal anomalies.

[0110] By comparing the temperature data collected in real time with the digital twin model constructed in step 102, the system can accurately identify thermal balance anomalies, such as local overheating or insufficient heat dissipation, and promptly issue an alarm when an anomaly is found, providing detailed analysis results for troubleshooting or adjusting the operating parameters of the gearbox.

[0111] In the actual implementation process, step 103 can be specifically implemented according to the following steps:

[0112] Step 1031: Based on step 102, a heat generation model of the gearbox is further established, including the heat source distribution of each internal component, such as friction heat, transmission heat, etc. Each heat source is modeled to determine its heat output under different working conditions.

[0113] Step 1032: Define the heat transfer path, including heat transfer mechanisms such as heat conduction, convection and radiation. Use finite element analysis to calculate the heat distribution inside the gearbox and simulate the heat transfer process between different components.

[0114] Step 1033: Establish a heat exchange model between the gearbox and the environment, taking into account factors such as ambient temperature, radiator efficiency, and ventilation conditions, and simulate the heat exchange process between the gearbox and the external environment.

[0115] Step 1034: By comparing the temperature distribution and heat flow in the digital twin model that are updated in real time, the real-time collected temperature data is compared with the simulation results of the digital twin model to identify areas in the digital twin model that do not match the actual temperature data to detect whether there are thermal anomalies.

[0116] Through the above implementation steps, the digital twin model can be used to accurately monitor the thermal balance state of the gearbox, identify thermal balance anomalies in a timely manner, improve the efficiency of thermal anomaly detection, and ensure the reliable operation of the gearbox under various working conditions.

[0117] In step 104, a deep learning model is used to predict faults and identify possible fault types and their occurrence times. Specifically, the historical operation data is preprocessed to improve data quality, the preprocessed historical data is analyzed to identify common fault modes, and a fault prediction model is established. The real-time data is input into the fault prediction model, and the current state of the gearbox is judged by the model, and the possibility and time of potential faults are predicted. When the real-time data matches the output of the model, the system generates an early warning signal to prompt the operator to take preventive measures or perform maintenance to avoid major failures.

[0118] This predictive capability allows maintenance work to be performed before a failure occurs, thus avoiding unexpected downtime and production interruptions. Accurate fault prediction not only improves the reliability and service life of the gearbox, but also optimizes the allocation of maintenance resources, reduces unnecessary maintenance and operating costs, and significantly improves the overall operating efficiency and economy of the system.

[0119] The specific process includes:

[0120] Preprocess historical operation data, including data cleaning, noise filtering, data normalization and missing value management;

[0121] Analyze pre-processed historical data to identify common failure modes and abnormal characteristics;

[0122] Establishing a deep-learnable fault prediction model based on the common fault modes and abnormal characteristics;

[0123] The data obtained by analyzing the real-time data of the gearbox by the digital twin model is input into the fault prediction model;

[0124] Based on the results given by the fault prediction model, potential fault types are identified and the occurrence time is predicted.

[0125] In the actual implementation process, step 104 can be specifically implemented according to the following steps:

[0126] Step 1041: Preprocess the historical operation data, including data cleaning, noise filtering, data normalization, and missing value processing, to improve the quality and reliability of the data and provide a clean and consistent data set for the training of the deep learning model.

[0127] Step 1042: Analyze the pre-processed historical data to identify common failure modes and abnormal features. This step uses statistical analysis and pattern recognition techniques to extract key features and trends that are helpful for failure prediction from historical data.

[0128] Step 1043: Establish a deep learning fault prediction model. Select an appropriate deep learning algorithm, such as a long short-term memory network model LSTM, and train the model to learn the ability to identify potential faults from data based on the identified fault modes and features.

[0129] Step 1044: Input the real-time data into the trained fault prediction model. The real-time data is analyzed by the model to determine the current state of the gearbox and assess the possibility of its fault.

[0130] Step 1045: Based on the prediction results output by the model, identify potential fault types and occurrence times. The system will generate a fault prediction report including the probability of fault occurrence, expected time, and possible impact.

[0131] The deep learning model can accurately predict possible gearbox failures and when they will occur, providing effective early warnings and maintenance advice. This predictive capability enables the system to take preventive measures before failures occur, reducing equipment downtime and improving operational efficiency and safety.

[0132] In step 105, according to the results of thermal balance monitoring and fault prediction, the working parameters of the gearbox are dynamically adjusted to maintain its normal operation. It includes a parameter adjustment unit and a feedback adjustment unit. The parameter adjustment unit is responsible for adjusting the oil pressure, controlling the speed and optimizing the cooling system; the feedback adjustment unit continuously optimizes the automatic compensation strategy according to the actual operation effect and accumulated data, improves the system response speed and compensation effect, thereby improving the gearbox operation efficiency and reducing the occurrence of faults.

[0133] The specific process includes:

[0134] Adjust the operating parameters of the gearbox based on the results of the thermal balance detection and fault prediction model of the digital twin model, including adjusting the oil pressure, controlling the speed, and optimizing the cooling system;

[0135] Establish a feedback adjustment mechanism, detect the actual operating effect after adjustment, detect the actual temperature change after adjustment, compare the real-time data with the expected effect of feedback adjustment, evaluate the effectiveness of adjustment measures, and optimize the adjustment strategy;

[0136] Based on the actual effect of the optimized plan adjusted by the feedback adjustment mechanism, further optimize the adjustment strategy of the feedback adjustment mechanism;

[0137] Regularly evaluate and update parameter adjustments and feedback regulation mechanism strategies.

[0138] In the actual implementation process, step 105 can be specifically implemented according to the following steps:

[0139] Step 1051: Based on the results of thermal balance monitoring and fault prediction, the parameter adjustment unit automatically adjusts the real-time parameters of the gearbox according to the identified adjustment requirements, optimizes the operation of the cooling system, responds to changes in the working state of the gearbox in real time, and ensures that it operates within a normal thermal balance range.

[0140] Step 1052: Establish a feedback adjustment mechanism to monitor the actual operating effect after parameter adjustment. The feedback adjustment unit compares the real-time data with the expected effect after adjustment, evaluates the effectiveness of the adjustment measures, and optimizes the adjustment strategy.

[0141] Step 1053: Based on the analysis results of the feedback adjustment unit, further optimize the automatic compensation strategy, regularly evaluate and update the parameter adjustment and feedback adjustment strategy. Combined with historical operation data and actual operation results, continuously improve the adjustment and compensation strategy to adapt to the long-term use of the gearbox and changes in different operating environments.

[0142] The data flow of the monitoring system actively intervening to adjust the gearbox is as follows Figure 2 As shown. When it is detected that the temperature of the gearbox exceeds the preset safety threshold, the system automatically starts the forced cooling mechanism. First, the fan is started, the radiator coolant flow rate is adjusted, and the oil pump rate is adjusted to quickly increase the working intensity to reduce the temperature of the gearbox. At the same time, the system evaluates the cooling effect based on real-time data and makes dynamic adjustments as needed to ensure the effectiveness of the cooling process. If the temperature drops below the safety threshold, the forced cooling measures are stopped; if insufficient cooling is found or the temperature continues to be abnormal, the system will trigger continuous forced cooling and stimulate the automatic compensation mechanism to prevent failures caused by overheating by adjusting working parameters or executing emergency protection measures to ensure the normal operation of the gearbox.

[0143] The system can dynamically adjust the gearbox's operating parameters based on real-time monitoring and prediction, effectively optimizing its operating efficiency. This automatic compensation method based on the feedback mechanism not only reduces the frequency of failures, but also improves the overall performance and reliability of the gearbox and extends the service life of the equipment.

[0144] In summary, the vehicle gearbox thermal fault monitoring and processing method based on digital twin provided by the present invention can effectively improve the operating efficiency and safety of the vehicle gearbox. By real-time monitoring and analyzing the operating status of the gearbox, the system can promptly detect and prevent potential faults and avoid downtime caused by sudden damage.

[0145] In addition, the fault monitoring and processing method that can automatically compensate allows the gearbox to dynamically adjust according to actual working conditions, ensuring that it maintains optimal performance in various environments.

[0146] Overall, the system not only extends the service life of the gearbox and reduces maintenance costs, but also greatly improves the overall operating efficiency and reliability of the vehicle, bringing significant economic benefits and technical advantages to industrial applications.

[0147] Based on this invention concept, Figure 3An installation layout of a vehicle chassis gearbox thermal fault monitoring and processing device applicable to the method is proposed. The device mainly includes a data acquisition module, a digital twin model module, a thermal balance detection module, a fault prediction module and an automatic compensation module, and each module is electrically connected to each other, wherein the data acquisition module is arranged on the vehicle chassis to ensure effective monitoring of the thermal balance state of the gearbox. The data acquisition module includes a displacement sensor, a vibration sensor, a temperature sensor, a pressure sensor, an oil level sensor and an acceleration sensor. The displacement sensor is arranged between the vehicle's clutch and the gearbox input shaft and the gearbox output shaft, the vibration sensor is arranged on the gearbox housing, the pressure sensor and the oil level sensor are arranged inside the gearbox, and a plurality of temperature sensors are arranged on the gearbox housing and the gearbox interior, respectively, and the acceleration sensor is arranged at the bottom or side of the gearbox. These data are transmitted to the central processing unit through the control module for real-time analysis and fault prediction, thereby realizing comprehensive monitoring and management of the gearbox operation status.

[0148] The functions of each module of the monitoring device are as follows:

[0149] A data acquisition module is used to obtain the operating data of the vehicle gearbox in real time;

[0150] A digital twin model module, which uses the operating data to construct a digital twin model of the gearbox and synchronizes the state of the actual gearbox with the digital twin model in real time;

[0151] The thermal balance monitoring module uses the digital twin model to simulate and analyze the heat generation and dissipation process of the gearbox, monitor the thermal balance state of the gearbox in real time, and detect whether there are thermal anomalies;

[0152] The fault prediction module uses deep learning models to predict faults based on real-time and historical data, identifying possible fault types and their occurrence times;

[0153] The automatic compensation module dynamically adjusts the working parameters of the gearbox according to the results of thermal balance monitoring and fault prediction to maintain its normal operation.

[0154] The functions of each module of the monitoring device correspond to each step in the automatic compensation method for thermal fault monitoring and processing, wherein the data acquisition module corresponds to step 101, the digital twin module corresponds to step 102, the thermal balance detection module corresponds to step 103, the fault prediction module corresponds to step 104, and the automatic compensation module corresponds to step 105. The effects and usage scenarios achieved by each module and the corresponding steps are the same, but are not limited to the contents disclosed in the above method.

[0155] The construction process and work units of each module are as follows: Figure 4 shown.

[0156] The data acquisition module can accurately measure and transmit real-time temperature, pressure, vibration and speed data, ensuring the accuracy and real-time performance of data acquisition of the gearbox under various working conditions. The collected data is not only used as input for the digital twin model, but also as the basis for subsequent fault prediction and thermal balance analysis, ensuring that the system can make accurate judgments and adjustments based on high-quality data.

[0157] The digital twin model module is used to construct a digital twin model. The digital twin model constructed in this device is a three-dimensional geometric model that is highly consistent with the actual gearbox. The model further combines the thermodynamic characteristics of the gearbox and accurately simulates its heat conduction, convection and radiation characteristics through simulation technologies such as finite element analysis. The dynamic characteristics of the model also include the synchronization of real-time operating data to ensure that the digital twin model is consistent with the operating status of the actual gearbox and can accurately reflect the state changes of the gearbox under different working conditions.

[0158] The model is constructed by including geometric model unit, material property unit and real-time synchronization unit, and its specific functions are as follows:

[0159] The geometric model unit builds the three-dimensional geometric model of the gearbox;

[0160] Material properties unit, which defines the material properties and thermal characteristics of the gearbox;

[0161] The real-time synchronization unit inputs the actually collected operating data into the digital twin model, and synchronizes the model with the actual gearbox status in real time through the data interface.

[0162] The thermal balance detection module is mainly used to simulate the heat generation and dissipation process of the gearbox. The internal specific working units include a heat exchange unit and an abnormality detection unit. Its specific functions are:

[0163] The heat exchange unit simulates the heat source and heat transfer path inside the gearbox, as well as the heat exchange between the outside of the gearbox and the environment.

[0164] The abnormality detection unit compares the real-time collected temperature data, and the system can accurately identify abnormal thermal balance, such as local overheating or insufficient heat dissipation. When the thermal balance is abnormal, the system can issue an alarm and provide further analysis results to the fault monitoring module to guide fault handling or adjust the operating parameters of the gearbox to avoid more serious faults.

[0165] The fault monitoring module mainly analyzes the historical operating data and real-time collected data of the gearbox, identifies potential fault modes and trends through deep learning algorithms, and continuously learns and updates the model to adapt to changes in gearbox operating conditions and continuously improve the accuracy and reliability of fault prediction. The specific working units include data processing units, model building units and fault prediction units, and their specific functions are:

[0166] The data processing unit pre-processes the collected historical operation data, including data cleaning, noise reduction and standardization, to remove noise and outliers in the data and improve the quality and consistency of the data;

[0167] The model building unit analyzes the pre-processed historical data to identify common failure modes, including overheating, abnormal vibration, abnormal pressure, and abnormal speed, and builds a failure prediction model based on this;

[0168] The fault prediction unit inputs the collected current real-time operation data into the fault prediction model, determines the current state of the gearbox through the fault prediction model and real-time data analysis, and predicts the possibility and time of its potential fault.

[0169] When real-time data matches the output of the fault prediction model, the system generates an early warning signal, prompting operators to take preventive measures or perform maintenance to avoid major gearbox failure.

[0170] The automatic compensation module is mainly responsible for intervening according to the results of the thermal balance detection box fault prediction, dynamically adjusting the various data of the gearbox, and collecting the data of the entire system operation, and comparing the various parameters with the historical data. When the parameters are detected to be deviated or a fault occurs, the automatic compensation module automatically adjusts the relevant parameters according to the preset compensation strategy or model to maintain the stable operation of the system. The specific working units include the automatic compensation module, the parameter adjustment unit and the feedback adjustment unit, and their specific functions are:

[0171] The parameter adjustment unit dynamically adjusts the working parameters of the gearbox according to the results of thermal balance monitoring and fault prediction, including adjusting oil pressure, controlling speed, and optimizing the cooling system;

[0172] The feedback adjustment unit continuously optimizes the automatic compensation strategy based on actual operating results and accumulated data to improve the system's response speed and compensation effect, thereby improving the operating efficiency of the gearbox and reducing the occurrence of faults.

[0173] This automatic compensation mechanism is particularly suitable for scenarios where environmental conditions change frequently or system load fluctuates greatly, and helps to improve the overall reliability and accuracy of the system.

[0174] Through the coordination of various modules, real-time monitoring, prediction and dynamic adjustment of the vehicle gearbox are realized, which significantly improves the reliability and safety of the gearbox.

[0175] Based on this gearbox monitoring device, in order to better perform remote detection and fault prediction, a dedicated external communication network system is added, such as Figure 5 and Figure 6 shown.

[0176] The communication network system includes a device layer, a communication layer, a network layer, an application layer and a feedback layer. The detection device is arranged at the device layer. The device layer is provided with a device gateway. The communication layer includes a mobile network and a satellite network. The network layer includes a server. The application layer includes a receiving client. The feedback layer includes a fault detection server. Each layer in the communication network system is connected and data is transmitted through signals.

[0177] Sensor nodes are distributed in various key parts of the gearbox to collect data in real time. The data is collected through the CAN bus and reaches the ECU control unit for analysis and processing. The ECU control unit can not only perform local fault diagnosis and display real-time data and fault diagnosis on the display, but also transmit and store data through the wireless communication network, and finally reach the client for fault monitoring and automatic compensation. The network system facilitates technicians to conduct remote monitoring and fault prediction, and realizes all-round and real-time monitoring and management of the vehicle gearbox status.

[0178] In order to facilitate the operator to perform remote control, the application layer of the external communication network can be used as follows Figure 7 A visual control platform is shown.

[0179] The visual control platform is the receiving client in the communication network system. The receiving client includes a control module and a display module. The control module is used to receive data transmitted by the network layer and send user operation instructions, and the display module is used to provide visual data information in real time.

[0180] The control module receives system operation information and user operation instructions, and performs function adjustments and setting modifications. The display module provides system status monitoring and early warning information to operators in real time. In addition, the control module can also receive adjustment compensation strategies from the user end.

[0181] The platform not only allows operators to monitor various parameters of the gearbox in real time, but also allows them to receive and process warning information generated by the system and promptly understand the possibility of potential failures. At the same time, the platform also supports manual adjustment of compensation strategies to ensure that operators can respond to emergencies in emergency situations.

[0182] The user interface supports remote access and operation, allowing users to monitor and control the system through a mobile device or computer, thereby improving the flexibility and ease of operation of the device to ensure stable operation and timely maintenance of the vehicle transmission.

[0183] The visual control platform enhances the system's predictability and adaptability, ensuring efficient and stable operation of the vehicle's gearbox under various working conditions. The remote operation function further enhances the system's flexibility, meets the operational requirements in different scenarios, and provides users with great convenience and safety.

[0184] The present invention proposes a vehicle gearbox thermal fault monitoring and processing method and device that integrates digital twins, which significantly improves the operating stability and reliability of the gearbox. Through the organic combination of precise simulation, real-time monitoring, fault prediction and automatic adjustment, the thermal balance state of the vehicle gearbox can be accurately controlled, potential faults can be effectively prevented, and the continuous and stable operation of the equipment under long-term and high-intensity working conditions can be ensured. This not only extends the service life of the equipment, but also reduces maintenance costs, and ensures the efficient and safe operation of the vehicle under various complex working conditions, bringing significant technical and economic advantages to the industrial field.

Claims

1. A vehicle gearbox thermal fault monitoring and processing method integrating digital twin, characterized in that: include: Obtain vehicle transmission operating data in real time; Use the actual gearbox geometry data to build a digital twin model of the gearbox, and synchronize the actual gearbox status with the digital twin model in real time; Use the digital twin model to simulate and analyze the heat generation and dissipation process of the gearbox, and then compare the simulation analysis results with the real-time operation data to monitor the thermal balance state of the gearbox in real time and detect whether there are thermal anomalies; Based on the real-time and historical data output by the digital twin model, a deep learning model is used to predict faults; Dynamically adjust the gearbox's operating parameters based on the results of fault prediction to maintain normal operation of the gearbox; The digital twin model is used to simulate and analyze the heat generation and dissipation process of the gearbox, and then the simulation analysis results are compared with the real-time operation data to monitor the thermal balance state of the gearbox in real time and detect whether there are thermal anomalies, including: Establish a heat generation model for the gearbox, including the distribution of heat sources in each internal component; Define heat transfer pathways, including heat transfer mechanisms of conduction, convection, and radiation; Establish a heat exchange model between the gearbox and the environment, taking into account the ambient temperature, radiator efficiency and ventilation conditions, to simulate the heat exchange process between the gearbox and the external environment; By comparing the temperature distribution and heat flow in the digital twin model, the real-time collected temperature data is compared with the simulation results of the digital twin model to identify areas in the digital twin model that do not match the actual temperature data, in order to detect whether there are thermal anomalies. Real-time acquisition of vehicle transmission operating data includes: Obtain parameters through sensors installed on the gearbox; transmitting the data to a central processing unit via a transmission network; Data preprocessing including noise filtering, data smoothing and rectification is performed by the central processing unit; The pre-processed data is input into the digital twin model and fault prediction system through the transmission network; The data is updated regularly through the feedback of the digital twin model and the repeatedly collected gearbox operation data; Using the actual gearbox geometry data, a digital twin model of the gearbox is constructed, and the state of the actual gearbox is synchronized with the digital twin model in real time, including: Obtain the geometric data of the actual gearbox, including size, shape and internal structure; Use modeling software to create a 3D geometric model of the gearbox and ensure that the geometry of the model is consistent with the actual gearbox; Finite element analysis technology is applied to the digital twin model to simulate the heat conduction, convection and radiation processes of the gearbox to calculate its heat generation and dissipation characteristics; Establish a data synchronization interface to ensure that the digital twin model can obtain data in real time and perform real-time integration and correction of the model; Based on the real-time and historical data output by the digital twin model, fault prediction using deep learning models includes: Preprocess historical operation data, including data cleaning, noise filtering, data normalization and missing value management; Analyze pre-processed historical data to identify common failure modes and abnormal characteristics; Establishing a deep-learnable fault prediction model based on the common fault modes and abnormal characteristics; The data obtained by analyzing the real-time data of the gearbox by the digital twin model is input into the fault prediction model; Identify potential fault types and predict the occurrence time based on the results given by the fault prediction model; Dynamically adjust the gearbox operating parameters according to the results of fault prediction to maintain the normal operation of the gearbox, including: Adjust the operating parameters of the gearbox based on the results of the thermal balance detection and fault prediction model of the digital twin model, including adjusting the oil pressure, controlling the speed, and optimizing the cooling system; Establish a feedback adjustment mechanism, detect the actual operating effect after adjustment, detect the actual temperature change after adjustment, compare the real-time data with the expected effect of feedback adjustment, evaluate the effectiveness of adjustment measures, and optimize the adjustment strategy; Based on the actual effect of the optimized plan adjusted by the feedback adjustment mechanism, further optimize the adjustment strategy of the feedback adjustment mechanism; Regularly evaluate and update parameter adjustments and feedback regulation mechanism strategies; Based on the results of thermal balance monitoring and fault prediction, the parameter adjustment unit automatically adjusts the real-time parameters of the gearbox according to the identified adjustment needs, optimizes the operation of the cooling system, and responds to changes in the working state of the gearbox in real time to ensure that it operates within the normal thermal balance range; Establish a feedback adjustment mechanism to monitor the actual operating effect after parameter adjustment. The feedback adjustment unit compares the real-time data with the expected effect after adjustment, evaluates the effectiveness of the adjustment measures, and optimizes the adjustment strategy; Based on the analysis results of the feedback adjustment unit, the automatic compensation strategy is further optimized, the parameter adjustment and feedback adjustment strategy are regularly evaluated and updated, and the adjustment and compensation strategy is continuously improved in combination with historical operating data and actual operating results to adapt to the long-term use of the gearbox and changes in different operating environments.

2. A vehicle gearbox thermal fault monitoring and processing device integrating digital twin, used to implement a vehicle gearbox thermal fault monitoring and processing method integrating digital twin as claimed in claim 1, characterized in that: It includes a data acquisition module, a digital twin model module, a thermal balance detection module, a fault prediction module and an automatic compensation module. The modules are electrically connected to each other, and the data acquisition module is arranged on the vehicle chassis.

3. The vehicle transmission thermal fault monitoring and processing device integrating digital twin according to claim 2 is characterized in that: The data acquisition module includes a displacement sensor, a vibration sensor, a temperature sensor, a pressure sensor, an oil level sensor and an acceleration sensor. The displacement sensor is arranged between the vehicle's clutch and the gearbox input shaft and the gearbox output shaft. The vibration sensor is arranged on the gearbox housing. The pressure sensor and the oil level sensor are arranged inside the gearbox. There are multiple temperature sensors, which are respectively arranged on the gearbox housing and inside the gearbox. The acceleration sensor is arranged at the bottom or side of the gearbox.

4. The vehicle transmission thermal fault monitoring and processing device integrating digital twin according to claim 3 is characterized in that: The digital twin model module includes a geometric model unit, a material property unit and a real-time synchronization unit; The thermal balance detection module includes a heat exchange unit and an abnormality detection unit; The fault prediction module includes a data processing unit, a model building unit and a fault prediction unit; The automatic compensation module includes a parameter adjustment unit and a feedback adjustment unit.

5. The vehicle transmission thermal fault monitoring and processing device integrating digital twin according to claim 4 is characterized in that: The monitoring and processing device is externally connected to a communication network system, which includes a device layer, a communication layer, a network layer, an application layer and a feedback layer. The detection device is arranged at the device layer, and the device layer is provided with a device gateway. The communication layer includes a mobile network and a satellite network, the network layer includes a server, the application layer includes a receiving client, and the feedback layer includes a fault detection server. The various layers in the communication network system are connected and data is transmitted through signals.

Images