Vehicle fault diagnosis method and system based on digital twinning

Abstract

The invention provides a vehicle fault diagnosis method and system based on digital twinning. The vehicle fault diagnosis method comprises the following steps: (S1) collecting vehicle data of a vehicle; (S2) storing the collected vehicle data in association with the corresponding generation timestamps and sensor identification codes; (S3) according to the collected vehicle sensor data, preliminarily diagnosing whether the vehicle has a fault or not; (S4) when the preliminary diagnosis result indicates that the vehicle has a fault, carrying out digital twinborn diagnosis on the vehicle fault; and S5) generating visual display of the fault. Compared with a traditional diagnosis method, the vehicle fault diagnosis method based on the vehicle real-time digital twin model can provide more efficient, accurate and comprehensive fault detection.

Description

Technical Field

[0001] The present invention relates to automated fault diagnosis of vehicles, and more particularly to a vehicle fault diagnosis method and system based on digital twins. Background Art

[0002] Digital twin technology, or digital twin technology, is a technology that creates virtual copies of physical entities to mirror the state and behavior of actual physical objects for real-time monitoring and analysis. In the field of vehicle fault diagnosis, digital twin technology allows engineers and technicians to detect and predict faults without touching the actual vehicle by creating a virtual copy of the vehicle. This technology uses sensor data, operating history, and real-time performance information to build a dynamic vehicle model that can simulate real-world conditions in a virtual environment to predict and diagnose potential problems. The application of digital twin technology in vehicle fault diagnosis not only improves the accuracy and efficiency of diagnosis, but also contributes to the continuous operation and performance optimization of the vehicle.

[0003] Existing vehicle diagnostics based on digital twin technology mainly rely on data collected by in-vehicle sensors, such as key indicators such as engine temperature, oil pressure, and battery status. Although this information is crucial to understanding the inner workings of the vehicle, it does not fully reveal how the vehicle performs in the real world. In order to obtain more comprehensive data, it is necessary to combine the driver's operating information and vehicle external information, such as weather conditions, road types, and traffic conditions, which are important factors affecting vehicle performance. In addition, another challenge of digital twin models is the iteration and update of the model. As vehicle information is continuously collected, the model needs to be continuously updated to reflect the latest data. This process requires powerful computing power to quickly process large amounts of data and implement complex algorithms and simulations in the model. This not only increases the demand for hardware resources, but also means that the simulation process may take a long time before the model reaches sufficient accuracy. Summary of the invention

[0004] The first aspect of the present disclosure provides a vehicle fault diagnosis method based on digital twins. In some embodiments, the method may include: (S1) collecting vehicle data of a vehicle, the vehicle data including vehicle sensor data, user operation behavior data and vehicle surrounding environment data, wherein the vehicle has an initial digital twin model M1 of the vehicle; (S2) storing the collected vehicle data in association with the corresponding generation timestamp and sensor identification code in a first database DB1 and a second database DB2; (S3) performing a preliminary diagnosis on whether the vehicle has a fault according to the collected vehicle sensor data to obtain a preliminary diagnosis result; (S4) when the preliminary diagnosis result indicates that the vehicle has a fault, performing a digital twin diagnosis of the vehicle fault; and (S5) generating a visual display of the fault. In some instances, processing (S4) may further include: (S41) determining a real-time digital twin model M2 of the vehicle corresponding to the time T of occurrence of the fault and indicating the actual condition of the vehicle; and (S42) determining the location and fault level of the fault component according to the initial digital twin model M1 of the vehicle, the time T of occurrence of the fault and the real-time digital twin model M2 of the vehicle.

[0005] In some embodiments, processing S2 may include: storing the collected vehicle data in the first database DB1 with the generation timestamp as the primary key and the sensor identification code as the secondary key; and storing the collected vehicle data in the second database DB2 with the sensor identification code as the primary key and the generation timestamp as the secondary key.

[0006] In some embodiments, processing S41 may include: (S411) reading the collected vehicle data within a predetermined time period before time T from the first database DB1; (S412) inputting the collected vehicle data read in (S411) as input data into the vehicle initial digital twin model M1 in timestamp order for simulation to generate sensor simulation data; and (S413) comparing the sensor simulation data with the collected vehicle data, thereby iteratively optimizing the vehicle initial digital twin model M1 to obtain the vehicle real-time digital twin model M2. The difference between the model parameter values ​​of the vehicle real-time digital twin model M2 and the vehicle initial digital twin model M1 indicates the location and fault level of the faulty component.

[0007] In some embodiments, processing S412 may include:

[0008] (S4121) Define the state transition equation as shown in formula (1) to generate the current sensor estimation data based on the previous vehicle data:

[0009] x(t|t-1)=f(y(t-1),u(t-1),s(t-1)) (1)

[0010] Wherein, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, wherein y(t-1) is the vehicle sensor data at time t-1, u(t-1) is the user operation behavior data at time t-1, s(t-1) is the vehicle surrounding environment data at time t-1, and f(·) is the associated characteristic equation; and

[0011] (S4122) Define the update equation as shown in formula (2):

[0012] x(t)=x(t|t-1)+x' (t-1)*Ts (2)

[0013] Wherein, x(t) is the sensor simulation data at time t, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, x'(t-1) is the derivative of the sensor simulation data at time t-1, and Ts is the time step. Ts is less than the collection interval of the vehicle data.

[0014] In some embodiments, processing S413 may include:

[0015] (S4131) Define the objective function of the iterative optimization as shown in formula (3):

[0016] min{|y(t)-x(t)|}(3)

[0017] Wherein, y(t) is the vehicle data collected at time t; and

[0018] (S4132) Using the objective function of the iterative optimization, determine the vehicle real-time digital twin model M2 corresponding to the occurrence time T of the vehicle failure and indicating the actual condition of the vehicle.

[0019] In some embodiments, processing S42 may include: when the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a first empirical threshold, it is determined that the one or more components have a general fault; when the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a second empirical threshold, it is determined that the one or more components have a moderate fault; and when the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a third empirical threshold, it is determined that the one or more components have a serious fault. The third empirical threshold may be greater than the second empirical threshold. The second empirical threshold may be greater than the first empirical threshold.

[0020] In some embodiments, processing S5 may include: reading the vehicle data at the time T when the fault occurs from the second database DB2, displaying the vehicle real-time digital twin model M2, and highlighting the model component in the vehicle real-time digital twin model M2 corresponding to the faulty component.

[0021] In some embodiments, process S5 may include: when the terminal user clicks or touches a component in the vehicle real-time digital twin model M2, further displaying detailed model detail information of the component.

[0022] Another aspect of the present disclosure provides a vehicle fault diagnosis system based on digital twins. In some embodiments, the vehicle fault diagnosis system may include: an initial digital twin model M1 of the vehicle; a vehicle data collection unit configured to collect vehicle data of the vehicle, the vehicle data including vehicle sensor data, user operation behavior data and vehicle surrounding environment data; a first database DB1 and a second database DB1 configured to store the collected vehicle data in association with the corresponding generation timestamp and sensor identification code; a vehicle fault preliminary diagnosis unit configured to perform a preliminary diagnosis of whether the vehicle has a fault based on the collected vehicle sensor data to obtain a preliminary diagnosis result; a vehicle fault digital twin diagnosis unit configured to perform a digital twin diagnosis of the vehicle fault when the preliminary diagnosis result indicates that the vehicle has a fault; and a visual fault display unit configured to generate a visual display of the fault. In some instances, performing digital twin diagnosis of vehicle faults may include: determining a real-time digital twin model M2 of the vehicle corresponding to the time T when the fault occurs and indicating the actual condition of the vehicle; and determining the location and fault level of the faulty component based on the initial digital twin model M1 of the vehicle, the time T when the fault occurs, and the real-time digital twin model M2 of the vehicle.

[0023] In some embodiments, determining a vehicle real-time digital twin model M2 corresponding to the occurrence time T of the fault and indicating the actual condition of the vehicle may include: (S411) reading the collected vehicle data within a predetermined time period before the time T from the first database DB1, (S412) using the collected vehicle data read in (S411) as input data, and inputting it into the vehicle initial digital twin model M1 in timestamp order for simulation to generate sensor simulation data; and (S413) comparing the sensor simulation data with the collected vehicle data, thereby iteratively optimizing the vehicle initial digital twin model M1 to obtain the vehicle real-time digital twin model M2. The difference between the model parameter values ​​of the vehicle real-time digital twin model M2 and the vehicle initial digital twin model M1 indicates the location and fault level of the faulty component.

[0024] Another aspect of the present disclosure provides a system including one or more computer processors and a computer readable memory. The computer readable memory includes machine executable code. The machine executable code, when executed by the one or more computer processors, implements the vehicle fault diagnosis method based on digital twins as in the first aspect of the present disclosure.

[0025] It should be understood that the present disclosure is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The novel features of the invention are set forth with particularity in the appended claims.A better understanding of the features and advantages of the invention will be obtained by referring to the following detailed description and accompanying drawings which set forth illustrative embodiments utilizing the principles of the invention.

[0027] Figure 1 An example of a vehicle digital twin model of the present disclosure is shown.

[0028] Figure 2 It is a schematic flowchart of a vehicle fault diagnosis method based on digital twin according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In the existing technology, vehicle fault diagnosis technology based on digital twin technology mainly relies on in-vehicle sensor data, which limits the technicians' comprehensive understanding of the actual use of the vehicle. The real driving environment includes factors such as changing weather conditions, complex traffic conditions, and the driver's operating habits, which are difficult to capture with in-vehicle sensor data alone. Therefore, in order to make the digital twin model more accurately reflect the actual use of the vehicle, it is necessary to take into account the environmental data outside the vehicle and the driving behavior data. For example, information on road conditions and traffic flow can be collected through on-board cameras and external sensors, while vehicle networking technology can provide driving data of surrounding vehicles. The integration of these external data will greatly enhance the predictive ability and accuracy of the digital twin model. In addition, another challenge of the digital twin model is its high demand for computing resources. In order to achieve highly accurate simulation, the model must be continuously updated and iterated to reflect the latest data collected. This process requires strong computing power, especially when processing large amounts of data and performing complex calculations.

[0030] In view of the above-mentioned problems in the prior art, the present disclosure proposes an innovative vehicle fault diagnosis method based on digital twins, which comprehensively considers the vehicle's sensor data and real driving environment data, and optimizes the update method of the vehicle's digital twin model, so that the digital twin model will be able to run more efficiently while reducing the time required for simulation.

[0031] Figure 1 An example of a vehicle digital twin model of the present disclosure is shown. The initial digital twin model refers to a complete digital model constructed after the vehicle is produced, based on its design parameters and standard configuration. This model contains all important information about the vehicle, such as engine performance, body structure, electronic systems, etc., as well as their ideal state when leaving the factory. The initial digital twin model provides a benchmark for the entire life cycle of the vehicle. The real-time status of the vehicle monitored during vehicle use can be compared with the initial digital twin model. This comparison helps to detect deviations and potential problems in a timely manner, thereby achieving preventive maintenance and fault diagnosis. For example, if the vehicle's real-time data shows that the engine temperature continues to be higher than the standard temperature in the initial model, the system can warn the owner or maintenance personnel to conduct inspections and maintenance.

[0032] As the vehicle wears and ages during use, its digital twin model will be updated accordingly to reflect the current state of the vehicle. This means that the digital twin model is a dynamic model. The synchronization of the initial digital twin model with the actual vehicle data can be achieved through a series of automated processes. In one example, first, the sensors built into the vehicle can continuously collect various data about the vehicle's performance, including but not limited to engine temperature, fuel consumption, speed, the status of the braking system, etc. This data can then be transmitted to the cloud server in real time through the vehicle communication system. In the cloud, the data processing system can analyze the collected vehicle information and detect any differences from the initial digital twin model. For example, normal wear and tear, potential fault signals, and even the impact of changes in the external environment on vehicle performance can be identified. Once the system detects anomalies or deviations in the data, an alarm can be triggered and relevant information can be fed back to the owner or maintenance team. The maintenance team can determine the specific location and cause of the fault by analyzing the data provided by the model, thereby reducing downtime and improving the efficiency of repair work. This rapid response capability is particularly important for commercial fleet management because it can significantly reduce operational interruptions caused by vehicle failures.

[0033] Throughout the life cycle of the vehicle, the digital twin model can be automatically updated. Based on real-time data, the digital twin model can be adjusted to reflect the current state of the vehicle, which may include the degree of wear and tear of parts, minor changes in performance, or even updates to the vehicle configuration. This dynamic update ensures that the digital twin model always accurately represents the latest condition of the physical vehicle.

[0034] In one embodiment, the digital twin model of the vehicle of the present application may include models of the body structure, power system, braking system, suspension system, steering system and auxiliary system. For example, the digital twin model of the body structure not only includes the parameters of the frame and body, but also simulates its response under different load and impact conditions. The model of the power system can simulate the performance of the engine and transmission system under various operating conditions, including acceleration, fuel efficiency and emission levels. The digital twin model of the braking system can be used to analyze the effectiveness of the brake pedal and handbrake, as well as the reaction time and distance in an emergency. The suspension system can simulate the handling of the vehicle under various road conditions, while evaluating the durability of shock absorbers, wheels and tires. The digital twin of the steering system can analyze the responsiveness and accuracy of the steering wheel, as well as the reliability of the entire system after long-term use. The digital twin models of auxiliary systems such as air conditioning and human-computer interaction systems can be used to evaluate the efficiency and user-friendliness of these systems. The initial digital twin model of the vehicle is a digital twin model of the vehicle in a standard state without any faults.

[0035] Figure 2It is a schematic flow chart of a vehicle fault diagnosis method based on digital twin according to an embodiment of the present disclosure. The vehicle may have an initial digital twin model M1 of the vehicle. In one embodiment, the vehicle fault diagnosis method based on digital twin of the present disclosure may include: (S1) collecting vehicle data of the vehicle, (S2) associating the collected vehicle data with the corresponding generation timestamp and sensor identification code, and storing the associated vehicle data in a first database DB1 and a second database DB2, (S3) performing a preliminary diagnosis on whether the vehicle has a fault based on the collected vehicle sensor data to obtain a preliminary diagnosis result; (S4) when the preliminary diagnosis result indicates that the vehicle has a fault, performing a digital twin diagnosis of the vehicle fault; and (S5) generating a visual display of the fault.

[0036] In some embodiments, the vehicle data collected in step (S1) may include vehicle sensor data, user operation behavior data, and vehicle surrounding environment data. Vehicle sensor data provides the real-time status of the vehicle, including but not limited to engine temperature, oil pressure, battery status, and tire pressure. These data points are the basis for understanding the current operating status of the vehicle. User operation behavior data provides another dimension of information, which reflects the way the driver interacts with the vehicle. For example, the driver's acceleration and braking habits, steering mode, and frequency of using the vehicle control system may affect the performance and health of the vehicle. By analyzing these behavior data, the background context of the failure can be better understood. The vehicle surrounding environment data may include external conditions of vehicle operation, such as road conditions, weather conditions, traffic flow, and surrounding obstacles. These factors may affect the performance of the vehicle, so it is very important to consider these external data in fault diagnosis. By comprehensively analyzing vehicle sensor data, user operation behavior data, and vehicle surrounding environment data, the vehicle fault diagnosis method based on digital twins disclosed in the present invention can build a comprehensive vehicle health profile.

[0037] In some embodiments, the vehicle sensor data may include vehicle speed, acceleration, vehicle temperature, air flow, battery voltage, battery charge, coolant temperature, vehicle levelness, etc. collected from various sensors in the vehicle (e.g., vehicle speed sensor, acceleration sensor, vehicle temperature sensor, gas flow sensor, battery voltage sensor, battery charge sensor, coolant temperature sensor, vehicle levelness sensor, etc.). User operation behavior data may include: steering wheel angle, brake pedal displacement, accelerator pedal displacement, air conditioning on and off, air conditioning temperature adjustment amplitude, seat adjustment operation, etc. Vehicle surrounding environment data may include: distance to the vehicle in front, distance to the vehicle behind, signal light data, lane information, road congestion, weather conditions, traffic flow, etc.

[0038] In step (S2), the collected vehicle data is stored in the first database DB1 and the second database DB2. In the application of digital twin technology, the organization and management of data are crucial. In order to achieve efficient data processing, it is necessary to design corresponding data formats according to different data processing algorithms. This method can not only improve the efficiency of data processing, but also ensure the compatibility of data formats with processing tasks. In the process of digital twin simulation, vehicle data collected over a period of time is usually used as input. These data can be stored in different databases according to different combinations of generation timestamps and sensor identification codes. For example, the first database DB1 can use the timestamp of generated data as the primary key and the sensor identification code as the secondary key to store vehicle data. Such a data structure design helps to quickly retrieve vehicle data at a specific time point, thereby simulating the operating status of the vehicle during the time period. This helps to analyze the performance and behavior patterns of the vehicle and predict future operating trends. On the other hand, the second database DB2 can use the sensor identification code as the primary key and the generation timestamp as the secondary key to store vehicle data. This design enables the second database DB2 to efficiently handle fault analysis and location tasks, because it can quickly retrieve data based on the sensor identification code, and then analyze the operating status of components monitored by a specific sensor at different time points.

[0039] This data organization method disclosed in the present invention also helps to restore the spatial distribution characteristics of faults, which is very valuable for understanding the environment and conditions in which faults occur, optimizing maintenance strategies and preventive measures. In actual operation, when performing digital twin simulation, data can be extracted from the first database DB1 to simulate and analyze the operating conditions of the vehicle within a certain period of time. When performing fault analysis and location, data can be extracted from the second database DB2 to focus on the operating conditions of the target components monitored by the sensor.

[0040] In step (S3), a preliminary diagnosis is performed on whether the vehicle has a fault based on the collected vehicle sensor data to obtain a preliminary diagnosis result. In one example, the preliminary diagnosis method of the present disclosure may include comparing the vehicle sensor data at a certain time T with a corresponding preset threshold or threshold range. These thresholds or threshold ranges are pre-set based on the data model under normal operating conditions of the vehicle, and any data exceeding these thresholds or threshold ranges may indicate that the vehicle has a potential fault. The preliminary diagnosis process is not just a simple data comparison. It also includes monitoring the rate of change of data and analyzing user operating behavior. For example, if the data of a sensor is suddenly lost, or the rate of change of its data is significantly different from the normal mode, this may be a strong fault signal. Similarly, if the user's operating behavior shows abnormal changes, such as a sudden increase or decrease in the frequency of use of the accelerator pedal, this may also indicate that a system of the vehicle is abnormal.

[0041] In step (S4), when the preliminary diagnosis result indicates that the vehicle has a fault, a digital twin diagnosis of the vehicle fault may be performed. In some embodiments, step (S4) may further include:

[0042] (S41) determining a vehicle real-time digital twin model M2 corresponding to the time T of occurrence of the fault and indicating the actual condition of the vehicle; and

[0043] (S42) Determine the location and fault level of the faulty component based on the vehicle initial digital twin model M1, the time T when the fault occurs, and the vehicle real-time digital twin model M2.

[0044] The initial digital twin model of the vehicle serves as a reference point, representing the ideal state of the vehicle without any faults, and is usually built based on the vehicle design and factory parameters. By comparing the initial digital twin model M1 of the vehicle and the real-time digital twin model M2 of the vehicle at the time of fault T, the differences and inconsistencies between the two can be identified. These differences point to the specific location of the fault, such as an abnormal sensor reading or a degraded performance of a mechanical component. In addition, the severity of these differences can be evaluated to determine the level of the fault.

[0045] In some embodiments, step (S41) may include:

[0046] (S411) reading vehicle data collected within a predetermined period of time before time T from the first database DB1;

[0047] (S412) using the collected vehicle data read in (S411) as input data, and inputting it into the vehicle initial digital twin model M1 in a timestamp order for simulation, so as to generate sensor simulation data; and

[0048] (S413) The sensor simulation data is compared with the collected vehicle data, thereby iteratively optimizing the vehicle initial digital twin model M1 to obtain the vehicle real-time digital twin model M2.

[0049] The difference between the model parameter values ​​of the vehicle real-time digital twin model M2 and the vehicle initial digital twin model M1 can indicate the location and fault level of the faulty component.

[0050] Step S411 provides basic data for subsequent simulation by extracting vehicle data within a specific time period from the first database DB1. Step S412 uses these vehicle data as input and inputs them into the vehicle initial digital twin model M1 in the order of timestamps. The key to this step is to use the model for high-precision simulation to generate sensor simulation data. Step S413 compares the generated sensor simulation data with the actual collected vehicle data. This comparison process can be iterative, which means that through continuous comparison and adjustment, the vehicle initial digital twin model M1 will gradually be optimized to more accurately reflect the actual operation of the vehicle. In this way, the vehicle real-time digital twin model M2 is generated. This updated model contains various updates to the vehicle initial digital twin model M1, enabling it to better simulate the real-time status of the vehicle.

[0051] In some embodiments, step S412 of generating sensor simulation data may include:

[0052] (S4121) Define the state transition equation as shown in formula (1) to generate current sensor estimation data based on previous vehicle data:

[0053] x(t|t-1)=f(y(t-1),u(t-1),s(t-1)) (1)

[0054] Wherein, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, y(t-1) is the vehicle sensor data at time t-1, u(t-1) is the user operation behavior data at time t-1, s(t-1) is the vehicle surrounding environment data at time t-1, and f(·) is the associated characteristic equation; and

[0055] (S4122) Define the update equation as shown in formula (2):

[0056] x(t)=x(t|t-1)+x' (t-1)*Ts (2)

[0057] Among them, x(t) is the sensor simulation data at time t, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, x'(t-1) is the derivative of the sensor simulation data at time t-1, and Ts is the time step.

[0058] Step S412 provides a method for generating current sensor estimation data based on historical vehicle data. This process involves two equations: state transfer equation (1) and update equation (2). State transfer equation (1) uses the vehicle sensor data, user operation behavior data and vehicle surrounding environment data of the previous moment to predict the sensor data of the current moment. This equation reflects the dynamic nature of the system of the present disclosure and can generate new estimation values ​​according to the changing input data. Update equation (2) is based on the state transfer equation, and further corrects the sensor estimation value by adding the time step and the derivative of the sensor data to obtain the simulation data of the sensor. This equation takes into account the continuity of time and the change trend of the data, making the estimation more accurate. Different vehicles may have different sensor configurations and user operation habits, and this method can adapt to these differences by adjusting the associated characteristic equation f(·). At the same time, the selection of the time step Ts also provides flexibility. The appropriate Ts value can be determined according to the frequency of sensor data collection and the required prediction accuracy. In some instances, the time step Ts can be less than the collection interval of the vehicle data.

[0059] In some embodiments, step S413 of generating the vehicle real-time digital twin model M2 may include:

[0060] (S4131) Define the objective function of iterative optimization as shown in formula (3):

[0061] min{|y(t)-x(t)|}(3)

[0062] where y(t) is the vehicle data collected at time t; and

[0063] (S4132) Using the iterative optimization objective function, determine the vehicle real-time digital twin model M2 that corresponds to the time T when the vehicle failure occurs and indicates the actual condition of the vehicle.

[0064] The objective function defined in step S4131 is an iterative optimization problem that aims to find a solution that minimizes the absolute difference between y(t) (which represents the real vehicle data collected at time t) and x(t) (which represents the model's prediction of the vehicle state). This difference can be understood as the error between the actual data and the model prediction, and the goal of the optimization process is to minimize this error as much as possible. In practical applications, the optimization process may include gradient descent, genetic algorithms, or other iterative methods to gradually adjust the model parameters until a solution with the minimum error is found.

[0065] By iteratively optimizing the objective function, we can build a highly accurate real-time digital twin model M2 of the vehicle. The real-time digital twin model M2 of the vehicle can basically dynamically reproduce the real-time fault situation of the current vehicle, that is, the real-time digital twin model M2 of the vehicle is a digital twin model with the current vehicle fault. The dynamic nature of this model means that it can adapt to changing operating conditions and environmental factors, thereby providing more accurate fault detection. For example, the real-time digital twin model M2 of the vehicle can simulate the blockage of the air filter element by adjusting its model parameters, or simulate the cylinder and piston clearance size at a value exceeding the normal threshold, or simulate the coolant at a value below the normal threshold. The real-time digital twin model M2 of the vehicle can also simulate more than one vehicle fault. Therefore, the real-time digital twin model M2 of the vehicle is similar to the model structure of the initial digital twin model M1 of the vehicle, but is different from the initial digital twin model M1 of the vehicle in terms of model parameter values, and different model parameter values ​​can be used to assist in determining the location of the faulty component and the fault level.

[0066] In some embodiments, the step S42 of determining the location and fault level of the faulty component may include: when the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a first empirical threshold, it is determined that one or more components have a general fault; when the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a second empirical threshold, it is determined that one or more components have a moderate fault; and when the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a third empirical threshold, it is determined that one or more components have a serious fault. In some instances, the third empirical threshold may be greater than the second empirical threshold, and the second empirical threshold may be greater than the first empirical threshold.

[0067] In some embodiments, step S5 of generating a visual display of the fault may include: reading the vehicle data at the time T when the fault occurs from the second database DB2, displaying the real-time digital twin model M2 of the vehicle, and highlighting the model component corresponding to the faulty component in the real-time digital twin model M2 of the vehicle. By extracting the vehicle data at a specific time T from the second database DB2, the fault diagnosis system of the present disclosure can quickly locate the faulty component and display it visually in the digital twin model M2. This display not only includes the location of the faulty component, but also can display other vehicle system information related to the fault, providing maintenance personnel with a comprehensive fault context.

[0068] Using three.js as a rendering tool, the vehicle's digital twin model M2 can be displayed in 3D in a web browser, which provides users with an intuitive and interactive fault diagnosis interface. three.js is a JavaScript library based on WebGL, which can render complex 3D graphics in most modern web browsers without the need for any special plug-ins. In the display of the digital twin model, the use of three.js makes the model not only visually attractive to users, but also provides a smooth interactive experience.

[0069] Since the rendering of 3D models is a computationally intensive task, it may place a significant burden on computer resources. To address this problem, a multi-level display approach can be adopted. In this approach, the digital twin model M2 of the vehicle initially displays only the most critical features and components. Doing so not only reduces the computing resources required for the initial rendering, but also speeds up the loading of the model, allowing users to interact with the model without delay. Only when the user needs to see more details will the system load and display higher-resolution model parts. This gradually refined display method not only improves the system's responsiveness, but also optimizes the user's interactive experience. In addition, this multi-level display method also helps protect sensitive data. In the primary display stage, it is possible to avoid displaying details that are unnecessary for maintenance, thereby reducing the risk of data leakage. Only after the user's explicit operation, such as clicking or touching, will the system provide more details. This design not only ensures the security of information, but also meets the user's demand for information.

[0070] Another aspect of the present disclosure provides a vehicle fault diagnosis system based on digital twins. In some embodiments, the vehicle fault diagnosis system of the present disclosure may include: an initial digital twin model M1 of the vehicle, a vehicle data collection unit, a first database DB1 and a second database DB2, a preliminary vehicle fault diagnosis unit, a vehicle fault digital twin diagnosis unit, and a visual fault display unit. In some embodiments, the vehicle data collection unit may be configured to collect vehicle data of the vehicle. The vehicle data may include vehicle sensor data, user operation behavior data, and vehicle surrounding environment data. The first database DB1 and the second database DB2 may be configured to store the associated vehicle data after the collected vehicle data is associated with the corresponding generation timestamp and sensor identification code. The preliminary vehicle fault diagnosis unit may be configured to perform a preliminary diagnosis of whether the vehicle has a fault based on the collected vehicle sensor data to obtain a preliminary diagnosis result. The vehicle fault digital twin diagnosis unit may be configured to perform a digital twin diagnosis of the vehicle fault when the preliminary diagnosis result indicates that the vehicle has a fault. Performing digital twin diagnosis of vehicle faults may include: (S41) determining a vehicle real-time digital twin model M2 corresponding to the time T of the fault occurrence and indicating the actual condition of the vehicle; and (S42) determining the location and fault level of the fault component according to the vehicle initial digital twin model M1, the time T of the fault occurrence, and the vehicle real-time digital twin model M2. The visual fault display unit may be configured to generate a visual display of the fault.

[0071] In some embodiments, the first database DB1 can be configured to store the vehicle data to be collected using the generation timestamp as the primary key and the sensor identification code as the secondary key. The second database DB2 can be configured to store the vehicle data to be collected using the sensor identification code as the primary key and the generation timestamp as the secondary key.

[0072] In some embodiments, operation S41 of the vehicle fault digital twin diagnosis unit may include:

[0073] (S411) reading vehicle data collected within a predetermined period of time before time T from the first database DB1;

[0074] (S412) using the collected vehicle data read in (S411) as input data, and inputting it into the vehicle initial digital twin model M1 in a timestamp order for simulation, so as to generate sensor simulation data; and

[0075] (S413) The sensor simulation data is compared with the collected vehicle data, thereby iteratively optimizing the vehicle initial digital twin model M1 to obtain the vehicle real-time digital twin model M2.

[0076] The difference between the model parameter values ​​of the vehicle real-time digital twin model M2 and the vehicle initial digital twin model M1 can indicate the location and fault level of the faulty component.

[0077] In some embodiments, processing S412 may include:

[0078] (S4121) Define the state transition equation as shown in formula (1) to generate current sensor estimation data based on previous vehicle data:

[0079] x(t|t-1)=f(y(t-1),u(t-1),s(t-1)) (1)

[0080] Wherein, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, y(t-1) is the vehicle sensor data at time t-1, u(t-1) is the user operation behavior data at time t-1, s(t-1) is the vehicle surrounding environment data at time t-1, and f(·) is the associated characteristic equation; and

[0081] (S4122) Define the update equation as shown in formula (2):

[0082] x(t)=x(t|t-1)+x' (t-1)*Ts (2)

[0083] Among them, x(t) is the sensor simulation data at time t, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, x'(t-1) is the derivative of the sensor simulation data at time t-1, and Ts is the time step.

[0084] Ts may be smaller than the vehicle data collection interval.

[0085] In some embodiments, processing S413 may include:

[0086] (S4131) Define the objective function of iterative optimization as shown in formula (3):

[0087] min{|y(t)-x(t)|}(3)

[0088] Where y(t) is the vehicle data collected at time t; and

[0089] (S4132) Using the iterative optimization objective function, determine the vehicle real-time digital twin model M2 that corresponds to the time T when the vehicle failure occurs and indicates the actual condition of the vehicle.

[0090] In some embodiments, the operation S42 of the vehicle fault digital twin diagnosis unit may include: when the absolute value of the parameter of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differs by more than a first empirical threshold, it is determined that one or more components have a general fault; when the absolute value of the parameter of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differs by more than a second empirical threshold, it is determined that one or more components have a moderate fault; and when the absolute value of the parameter of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differs by more than a third empirical threshold, it is determined that one or more components have a serious fault. The third empirical threshold may be greater than the second empirical threshold. The second empirical threshold may be greater than the first empirical threshold.

[0091] In some embodiments, the visual fault display unit can be configured to: read the vehicle data at the time T when the fault occurs from the second database DB2, display the vehicle real-time digital twin model M2, and highlight the model component corresponding to the fault component in the vehicle real-time digital twin model M2. In some embodiments, the visual fault display unit can be configured to: when the end user clicks or touches a component in the vehicle real-time digital twin model M2, further display detailed model detail information of the component.

[0092] The present disclosure also provides a system including one or more computer processors and a computer readable memory. The computer readable memory may include machine executable code, which implements the vehicle fault diagnosis method based on digital twins of the present disclosure when executed by the one or more computer processors.

[0093] Compared with traditional diagnostic methods, the vehicle fault diagnosis method based on the real-time digital twin model of the vehicle disclosed in the present invention can provide more efficient, accurate and comprehensive fault detection. Traditional vehicle diagnostic methods usually rely on physical inspection and the driver's intuitive judgment. These methods may require a lot of time and manpower, and often seem powerless in the face of complex or hidden faults. In contrast, the vehicle fault diagnosis method based on the real-time digital twin model of the vehicle disclosed in the present invention uses real-time data and advanced algorithms to accurately reproduce and simulate the real-time status of the vehicle in a virtual environment, including various potential fault conditions.

[0094] By continuously collecting the vehicle's operating data and comparing it with the pre-set model parameters, the digital twin model M2 disclosed in the present invention can monitor the vehicle status in real time and detect anomalies in a timely manner. This method not only improves the speed of fault detection, but also reduces human errors in the diagnosis process due to its high degree of automation and accuracy. In addition, the digital twin model M2 can simulate a variety of different fault scenarios, which is often difficult to achieve with traditional methods. For example, it can simultaneously simulate the conditions of air filter blockage and insufficient coolant, which is very valuable for understanding the interaction between different faults and their impact on overall vehicle performance.

[0095] The digital twin model M2 also has the ability to predict potential future failures, which is not available in traditional diagnostic methods. By analyzing long-term data trends and patterns, the digital twin model can predict which components may have problems in the future, allowing the maintenance team to take measures in advance to avoid failures. This preventive maintenance strategy can not only extend the service life of the vehicle, but also reduce unexpected downtime and improve vehicle reliability and safety. In the field of autonomous driving and intelligent vehicles, the advantages of the digital twin model M2 are even more obvious. It can interact with the vehicle's control system in real time, provide instant feedback and adjustment suggestions, and thus optimize the vehicle's performance and driving strategy. This kind of real-time data analysis and decision support is unimaginable in traditional diagnostic methods. The application of the digital twin model M2 enables the vehicle to maintain optimal condition in complex environments and conditions, ensuring driving safety.

[0096] Although preferred embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that these embodiments are provided by way of example only. Other variations, changes and substitutions may be conceived by those skilled in the art without departing from the present invention.

Claims

1. A vehicle fault diagnosis method based on digital twins, the method comprising: (S1) collecting vehicle data of a vehicle, wherein the vehicle data includes vehicle sensor data, user operation behavior data, and vehicle surrounding environment data, wherein the vehicle has an initial vehicle digital twin model M1; (S2) storing the collected vehicle data in association with corresponding generation timestamps and sensor identification codes in the first database DB1 and the second database DB2; (S3) performing a preliminary diagnosis on whether the vehicle has a fault based on the collected vehicle sensor data to obtain a preliminary diagnosis result; (S4) when the preliminary diagnosis result indicates that the vehicle has a fault, performing a digital twin diagnosis of the vehicle fault; as well as (S5) generating a visual representation of the fault, The processing (S4) further comprises: (S41) determining a vehicle real-time digital twin model M2 corresponding to the occurrence time T of the fault and indicating the actual condition of the vehicle; and (S42) Determine the location and fault level of the faulty component based on the vehicle initial digital twin model M1, the time T when the fault occurs, and the vehicle real-time digital twin model M2.

2. The method according to claim 1, wherein the processing (S2) comprises: The collected vehicle data is stored in the first database DB1 with the generation timestamp as the primary key and the sensor identification code as the secondary key; as well as The collected vehicle data is stored in the second database DB2 with the sensor identification code as the primary key and the generation timestamp as the secondary key.

3. The method according to claim 1, wherein the processing (S41) comprises: (S411) reading the collected vehicle data within a predetermined time period before time T from the first database DB1; (S412) taking the collected vehicle data read in (S411) as input data, and inputting it into the vehicle initial digital twin model M1 in a timestamp order for simulation, so as to generate sensor simulation data; as well as (S413) comparing the sensor simulation data with the collected vehicle data, thereby iteratively optimizing the initial vehicle digital twin model M1 to obtain the real-time vehicle digital twin model M2, The difference between the model parameter values ​​of the vehicle real-time digital twin model M2 and the vehicle initial digital twin model M1 indicates the location and fault level of the faulty component.

4. The method according to claim 3, The processing (S412) includes: (S4121) Define the state transition equation as shown in formula (1) to generate the current sensor estimation data based on the previous vehicle data: x(t|t-1)=f(y(t-1),u(t-1),s(t-1)) (1) Wherein, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, wherein y(t-1) is the vehicle sensor data at time t-1, u(t-1) is the user operation behavior data at time t-1, s(t-1) is the vehicle surrounding environment data at time t-1, and f(·) is the associated characteristic equation; and (S4122) Define the update equation as shown in formula (2): x(t)=x(t|t-1)+x' (t-1)*Ts (2) Wherein, x(t) is the sensor simulation data at time t, x(t|t-1) is the sensor estimation data at time t generated based on the vehicle data at time t-1, x'(t-1) is the derivative of the sensor simulation data at time t-1, and Ts is the time step, wherein Ts is less than the collection interval of the vehicle data; The processing (S413) includes: (S4131) Define the objective function of the iterative optimization as shown in formula (3): min{|y(t)-x(t)|}(3) Wherein, y(t) is the vehicle data collected at time t; and (S4132) Using the objective function of the iterative optimization, determine the vehicle real-time digital twin model M2 corresponding to the occurrence time T of the vehicle failure and indicating the actual condition of the vehicle.

5. The method according to claim 3, wherein the processing (S42) comprises: When the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a first empirical threshold, it is determined that the one or more components have a general fault; When the absolute values ​​of the parameters of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differ by more than a second empirical threshold, it is determined that the one or more components have a moderate fault; as well as When the absolute value of the parameter of one or more components in the vehicle initial digital twin model M1 and the vehicle real-time digital twin model M2 differs by more than a third empirical threshold, it is determined that the one or more components have a serious fault. The third experience threshold is greater than the second experience threshold, and the second experience threshold is greater than the first experience threshold.

6. The method according to claim 3, wherein the processing (S5) comprises: The vehicle data at the time T when the fault occurs is read from the second database DB2, the vehicle real-time digital twin model M2 is displayed, and the model component corresponding to the faulty component in the vehicle real-time digital twin model M2 is highlighted.

7. The method according to claim 1, wherein the processing (S5) further comprises: When the terminal user clicks or touches a component in the vehicle real-time digital twin model M2, detailed model detail information of the component is further displayed.

8. A vehicle fault diagnosis system based on digital twins, the vehicle fault diagnosis system comprising: The initial digital twin model of the vehicle M1; A vehicle data collection unit configured to collect vehicle data of the vehicle, wherein the vehicle data includes vehicle sensor data, user operation behavior data, and vehicle surrounding environment data; a first database DB1 and a second database DB1 configured to store the collected vehicle data in association with corresponding generation timestamps and sensor identification codes; A vehicle fault preliminary diagnosis unit, configured to perform preliminary diagnosis on whether the vehicle has a fault based on the collected vehicle sensor data to obtain a preliminary diagnosis result; A vehicle fault digital twin diagnosis unit, configured to perform digital twin diagnosis of the vehicle fault when the preliminary diagnosis result indicates that the vehicle has a fault, wherein the digital twin diagnosis of the vehicle fault comprises: determining a vehicle real-time digital twin model M2 corresponding to the time T of occurrence of the fault and indicating the actual condition of the vehicle; and determining the location and fault level of the fault component according to the vehicle initial digital twin model M1, the time T of occurrence of the fault and the vehicle real-time digital twin model M2; and A visual fault display unit is configured to generate a visual display of the fault.

9. The system according to claim 8, wherein determining the vehicle real-time digital twin model M2 corresponding to the occurrence time T of the fault and indicating the actual condition of the vehicle comprises: (S411) reading the collected vehicle data within a predetermined time period before time T from the first database DB1, (S412) taking the collected vehicle data read in (S411) as input data, and inputting it into the vehicle initial digital twin model M1 in a timestamp order for simulation, so as to generate sensor simulation data; as well as (S413) comparing the sensor simulation data with the collected vehicle data, thereby iteratively optimizing the initial vehicle digital twin model M1 to obtain the real-time vehicle digital twin model M2, The difference between the model parameter values ​​of the vehicle real-time digital twin model M2 and the vehicle initial digital twin model M1 indicates the location and fault level of the faulty component.

10. A system comprising one or more computer processors and a computer-readable memory, wherein the computer-readable memory comprises machine executable code, and the machine executable code, when executed by the one or more computer processors, implements the vehicle fault diagnosis method based on digital twins as described in any one of claims 1-7.

Images