Engine detection method and device, storage medium and program product
Through data comparison and analysis of engine entity and digital twin models, combined with multi-dimensional data model and physical process simulation, the problem of precise engine fault diagnosis is solved, efficient state detection and fault prediction is achieved, and the engine management level is improved.
Patent Information
- Application Number
- CN202510454377.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-11
- Publication Date
- 2025-07-25
AI Technical Summary
The existing technology cannot achieve accurate fault diagnosis of engines, cannot detect potential faults and dangers in advance, and it is difficult to meet the refined, intelligent and flexible management needs of vehicle engines.
By obtaining the operating data of the engine entity and the digital twin model, comparing and analyzing whether the engine entity has failed, establishing a multi-dimensional data model of the engine body and the controller, combining fluid, thermodynamics and dynamics models, an engine digital twin model is generated to achieve accurate state detection and fault diagnosis.
Accurate status detection and fault diagnosis are achieved, the detection efficiency and reliability of the engine are improved, future failures can be predicted, and the efficiency and life of the engine are improved.
Smart Images
Figure CN120369336A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vehicles, and particularly relates to a method, device, storage medium and program product for detecting an engine. Background Art
[0002] With the booming development of vehicle technology, users' demand for vehicle safety has also been continuously increasing. For example, by detecting the vehicle engine, vehicle safety is ensured.
[0003] Currently, the traditional method for detecting an engine mainly relies on a passive approach. When the engine sensor detects abnormal data, the engine controller will take measures such as restricting the output power to prevent the failure from deteriorating further.
[0004] However, in the above technical solution, accurate fault diagnosis of the engine cannot be achieved, and some potential faults and dangers cannot be detected and warned in advance, making it difficult to meet the refined, intelligent and flexible management requirements for the vehicle engine. Therefore, how to improve the efficiency of engine detection has become a technical problem to be solved urgently. Summary of the Invention
[0005] The present application provides a method, device, storage medium and program product for detecting an engine to at least solve the technical problem of how to improve the detection efficiency of an engine in the related art. The technical solution of the present application is as follows:
[0006] According to a first aspect of the present application, there is provided a method for detecting an engine, including: obtaining first operation data, where the first operation data is the operation data of an engine entity under a target working condition, the engine entity includes: an engine body and a controller, the operation data includes: multi-dimensional data of the engine body and multi-dimensional data of the controller, and the multi-dimensional data of the engine body includes: fluid dimension data, thermal dimension data and power dimension data. Obtaining second operation data, where the second operation data is the operation data of an engine digital twin model under a target working condition, and the engine digital twin model includes: an engine body digital twin model and a controller digital twin model. Based on the first operation data and the second operation data, a detection result is obtained, and the detection result is used to indicate whether a fault occurs in the engine entity.
[0007] In a possible implementation manner, the fluid dimension data includes fluid flow data, and the thermal dimension data includes device temperature data. The power dimension data includes at least one of the following: pressure data, position and angle data, vibration and noise data.
[0008] In a possible implementation manner, the multi-dimensional data of the controller includes: engine control data and status monitoring data, the engine control data is used to adjust the multi-dimensional data of the engine body, and the status monitoring data is the status data of the engine body.
[0009] In a possible implementation manner, the method further includes: obtaining a fluidics model of the engine body, a thermodynamics model of the engine body, and a dynamics model of the engine body. Generating a digital twin model of the engine body based on the fluidics model, the thermodynamics model, and the dynamics model.
[0010] In a possible implementation manner, the fluidics model includes: an intake system model, an exhaust system model, a cooling system model, a lubrication system model, and a turbocharging system model. The thermodynamics model includes: a cylinder thermodynamics model. The dynamics model includes: a crankshaft connecting rod dynamics model and an engine performance degradation model.
[0011] In a possible implementation manner, the controller digital twin model includes: an engine operating state judgment model, a driver demand torque calculation model, a target throttle position calculation model, a target intake cam phase calculation model, a target exhaust cam phase calculation model, a target fuel injection mass calculation model, and an ignition advance angle calculation model.
[0012] In a possible implementation manner, the first operating data and the second operating data are the operating data at the current moment. After the method of "obtaining a detection result based on the first operating data and the second operating data", the method further includes: when the detection result is used to indicate that the engine entity has not failed, obtaining first historical operating data and second historical operating data, where the first historical operating data is the operating data of the engine entity under the target operating condition at the historical moment. The second historical operating data is the operating data of the engine digital twin model under the target operating condition at the historical moment. Determining first predicted operating data based on the first historical operating data and the first operating data, where the first predicted operating data is the operating data of the engine entity under the target operating condition at the target future moment, and the target future moment is later than the current moment. Determining second predicted operating data based on the second historical operating data and the second operating data, where the second predicted operating data is the operating data of the engine digital twin model under the target operating condition at the target future moment. Obtaining a prediction result based on the first predicted operating data and the second predicted operating data, where the prediction result is used to indicate whether the engine entity will fail at the target future moment.
[0013] According to the second aspect provided by the present application, there is provided a detection device for an engine, and the device includes an acquisition module and a processing module.
[0014] An acquisition module is used to acquire first operation data, where the first operation data is the operation data of the engine entity under target working conditions. The engine entity includes: an engine body and a controller. The operation data includes: multi-dimensional data of the engine body and multi-dimensional data of the controller. The multi-dimensional data of the engine body includes: fluid dimension data, thermal dimension data, and power dimension data. The acquisition module is also used to acquire second operation data, where the second operation data is the operation data of the engine digital twin model under target working conditions. The engine digital twin model includes: an engine body digital twin model and a controller digital twin model. A processing module is used to obtain a detection result based on the first operation data and the second operation data, and the detection result is used to indicate whether a fault occurs in the engine entity.
[0015] In a possible implementation manner, the fluid dimension data includes fluid flow rate data, and the thermal dimension data includes device temperature data. The power dimension data includes at least one of the following: pressure data, position and angle data, vibration and noise data. The multi-dimensional data of the controller includes: engine control data and status monitoring data. The engine control data is used to adjust the multi-dimensional data of the engine body, and the status monitoring data is the status data of the engine body.
[0016] In a possible implementation manner, the acquisition module is used to acquire a fluidics model of the engine body, a thermodynamics model of the engine body, and a dynamics model of the engine body. The processing module is used to generate an engine body digital twin model based on the fluidics model, the thermodynamics model, and the dynamics model.
[0017] In a possible implementation manner, the fluidics model includes: an intake system model, an exhaust system model, a cooling system model, a lubrication system model, and a turbocharging system model. The thermodynamics model includes: a cylinder thermodynamics model. The dynamics model includes: a crankshaft connecting rod dynamics model and an engine performance degradation model.
[0018] In a possible implementation manner, the controller digital twin model includes: an engine operation state judgment model, a driver demand torque calculation model, a target throttle position calculation model, an intake cam target phase calculation model, an exhaust cam target phase calculation model, a target fuel injection mass calculation model, and an ignition advance angle calculation model.
[0019] In a possible implementation, the first operation data and the second operation data are operation data at the current moment. When the detection result is used to indicate that the engine entity has not failed, the acquisition module is used to acquire the first historical operation data and the second historical operation data. The first historical operation data is the operation data of the engine entity under the target working condition at the historical moment, and the second historical operation data is the operation data of the engine digital twin model under the target working condition at the historical moment. The processing module is used to determine the first predicted operation data based on the first historical operation data and the first operation data. The first predicted operation data is the operation data of the engine entity under the target working condition at the target future moment, and the target future moment is later than the current moment. The processing module is used to determine the second predicted operation data based on the second historical operation data and the second operation data. The second predicted operation data is the operation data of the engine digital twin model under the target working condition at the target future moment. The processing module is used to obtain a prediction result based on the first predicted operation data and the second predicted operation data. The prediction result is used to indicate whether the engine entity fails at the target future moment.
[0020] According to the third aspect provided by the present application, there is provided a detection device for an engine, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to execute the instructions to implement the method according to the first aspect and any possible implementation thereof.
[0021] According to the fourth aspect provided by the present application, there is provided a detection device for an engine. A vehicle includes the detection device for the engine according to the second aspect, and the vehicle is used to implement the method according to the first aspect and any possible implementation thereof as described above.
[0022] According to the fifth aspect provided by the present application, there is provided a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by the processor of the detection device for the engine, the detection device for the engine can execute the method according to the first aspect and any possible implementation thereof.
[0023] According to the sixth aspect provided by the present application, there is provided a computer program product. The computer program product includes computer instructions. When the computer instructions run on the detection device for the engine, the detection device for the engine is enabled to perform the method according to the first aspect and any possible implementation thereof.
[0024] Advantages of the present invention:
[0025] (1) By acquiring the actual operation data of the engine entity and the simulation data of the engine digital twin model under the same working condition, and comparing the actual operation data with the simulation data, it can be determined whether the engine entity fails. In this way, accurate state detection and fault diagnosis can be achieved, the detection efficiency of the engine can be improved, and further the reliability and performance of the engine can be improved.
[0026] (2) The multi-dimensional data of the engine body can directly reflect the operating state of the engine body and provide support for establishing the corresponding digital twin model of the engine body. By classifying the multi-dimensional data of the engine body into fluid dimension data, thermal dimension data, and power dimension data, the multi-dimensional data of the engine body can be analyzed, making the working state of each part of the engine more transparent, and making the collected data more accurate, capable of quickly locating the problem and providing control and optimization of the engine.
[0027] (3) The multi-dimensional data of the controller can directly reflect the operating state of the controller and provide support for establishing the corresponding digital twin model of the controller. By classifying the multi-dimensional data of the controller into engine control data and state monitoring data, the multi-dimensional data of the controller can be analyzed, which can optimize the working state of each part of the controller, improve the accuracy of data collection, and thus build a more accurate digital twin model of the controller.
[0028] (4) By integrating the fluidics model, thermodynamics model, and kinetics model that respectively describe different physical processes of the engine into a unified digital twin model of the engine body, the behavior and state of the engine can be comprehensively and accurately simulated.
[0029] (5) By refining the specific models corresponding to the fluidics model, thermodynamics model, and kinetics model, it helps to deeply understand the working mechanism of the engine, can more accurately simulate various physical processes of the engine, penetrate into the engine body layer for detailed analysis, and achieve coverage of microscopic physical processes. In this way, these models can provide a solid foundation for realizing efficient and reliable engine simulation and support for realizing more efficient engine management and fault detection.
[0030] (6) The digital twin model of the controller can simulate the behavior of the engine control system. Classifying the digital twin model of the controller into more accurate and diverse models can significantly improve the monitoring accuracy of the engine state and the control optimization ability.
[0031] (7) Based on the operating data of the engine entity and the digital twin model at the target operating conditions at historical moments and the operating data at the target operating conditions at the current moment, the operating performance of the two at future moments can be predicted. And based on these two prediction results, it can be judged whether the engine entity is likely to fail at the target future moment in the future. In this way, it is possible to use the data of the engine entity and the data of the engine digital twin model for comparative analysis, more accurately capture the subtle changes that may indicate a fault, and then predict the operating conditions at future moments, and preventive measures can be taken before the fault occurs to reduce the losses caused by sudden failures and improve the use efficiency and lifespan of the engine entity.
[0032] It should be noted that for the technical effects brought about by any of the implementation manners in the second aspect to the sixth aspect, reference may be made to the technical effects brought about by the corresponding implementation manner in the first aspect, which will not be elaborated herein.
[0033] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application, and do not constitute an improper limitation to this application.
[0035] Figure 1 is a schematic diagram of a detection system for an engine shown according to an exemplary embodiment;
[0036] Figure 2 is a schematic diagram of another detection system for an engine shown according to an exemplary embodiment;
[0037] Figure 3 is a schematic flowchart of a detection method for an engine shown according to an exemplary embodiment;
[0038] Figure 4 is an example schematic diagram of data interaction of a digital twin cloud platform shown according to an exemplary embodiment;
[0039] Figure 5 is a schematic flowchart of another detection method for an engine shown according to an exemplary embodiment;
[0040] Figure 6 is an example schematic diagram of an engine digital twin model shown according to an exemplary embodiment;
[0041] Figure 7 is a schematic flowchart of another detection method for an engine shown according to an exemplary embodiment;
[0042] Figure 8 is a schematic structural diagram of a detection device for an engine shown according to an exemplary embodiment;
[0043] Figure 9 is a schematic structural diagram of another detection device for an engine shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0044] In order to enable those of ordinary skill in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the drawings.
[0045] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.
[0046] Before introducing the engine detection method of the embodiments of this application in detail, the implementation environment and application scenarios of the embodiments of this application will be introduced first.
[0047] With the vigorous development of vehicle technology, users' demand for vehicle safety is also increasing continuously. For example, by detecting the vehicle engine, vehicle safety can be ensured.
[0048] Traditional automotive engine fault diagnosis mainly relies on passive methods. That is, when the engine sensor detects abnormal data, the engine controller will take measures such as restricting the output power to prevent the fault from deteriorating further. However, this method has disadvantages such as untimely processing, incomplete diagnosis, and possible impact on driving safety. With the improvement of vehicle intelligence level and the increase of system complexity, traditional fault diagnosis methods are difficult to meet the urgent needs of modern vehicles for high precision and intelligence.
[0049] With the rise of digital twin technology, digital twin technology can achieve precise detection of the operating state and performance parameters of physical entities by establishing a mapping and interaction mechanism between physical entities and high-precision digital twin models.
[0050] Some methods can achieve fault prediction and health management of the entire life cycle of the power system by configuring the monitoring strategy for the vehicle power system. However, this method does not have a more perfect modeling system, only focuses on the digital twin model at the controller level, and has not delved into the engine body layer for detailed analysis (such as thermodynamic processes, dynamic analysis, etc.), and cannot achieve comprehensive coverage from macroscopic control to microscopic physical processes. Moreover, it lacks more accurate data processing and analysis and cannot provide more refined and accurate state monitoring and prediction.
[0051] Other methods can achieve the consistency of the operation of the physical entity and the digital twin physical model of the new energy vehicle power system through digital twin technology in the absence of faults. The data analysis module processes and analyzes the sensor data of the physical entity module and the operation data of the corresponding physical model of the digital twin module to realize the fault diagnosis of the new energy vehicle power system. However, this method does not have a stronger data interaction capability, and the information interaction mechanism is not perfect, which only includes the transmission of control signals. The data comparison and discrimination method is relatively simple, and cannot provide a higher level of intelligent analysis, and cannot achieve a technical leap from single fault identification to overall system performance optimization.
[0052] In summary, it is difficult to meet the demand for refined, intelligent and flexible management of vehicle engines due to the inability to accurately diagnose engine faults and the inability to detect and warn potential faults and dangers in advance. How to improve the detection efficiency of the engine during vehicle driving is a technical problem that needs to be solved urgently.
[0053] In order to solve the above problems, the embodiment of the present application provides an engine detection method, which is applied to the scene of detecting the engine, including: by obtaining the actual operation data of the engine entity under the same working conditions and the simulation data of the engine digital twin model, and comparing the actual operation data with the simulation data, it can be determined whether the engine entity has a fault. In this way, accurate state detection and fault diagnosis can be achieved, the detection efficiency of the engine can be improved, and then the reliability and performance of the engine can be improved.
[0054] The implementation environment of the embodiments of the present application is introduced below.
[0055] Figure 1 FIG. 1 is a schematic diagram of a detection system for an engine according to an exemplary embodiment. Figure 1 As shown, the engine detection system includes: a collection device 101 and a detection device 102. The collection device 101 and the detection device 102 can perform wireless communication.
[0056] Specifically, the acquisition device 101 can be used to collect the operating data of the engine entity under the target working condition, that is, the first operating data. The acquisition device 101 can also be used to collect the operating data of the engine digital twin model under the target working condition, that is, the second operating data. The acquisition device 101 can also be used to send the first operating data and the second operating data to the detection device 102.
[0057] The detection device 102 may be used to receive the first operation data and the second operation data. The detection device 102 may also be used to obtain a detection result based on the first operation data and the second operation data to detect whether a failure occurs in the engine entity.
[0058] In some embodiments, the detection device 102 includes: an engine entity 201, an engine digital twin model device 202, and a digital twin cloud platform device 203. Among them, the engine entity 201, the engine digital twin model device 202, and the digital twin cloud platform device 203 are all deployed in the vehicle, and the digital twin cloud platform device 203 can communicate wirelessly with the engine entity 201 and the engine digital twin model device 202.
[0059] Figure 2 FIG. is a schematic diagram of another engine detection system shown according to an exemplary embodiment, as Figure 2 shown, the engine entity 201 includes an engine body, engine sensors, and an engine controller. The engine digital twin model device 202 is composed of a controller digital twin model and an engine body digital twin model. Among them, the engine body digital twin model includes an intake system analysis and calculation model, a cylinder thermodynamics process analysis and calculation model, a crankshaft connecting rod dynamics analysis and calculation model, an exhaust system analysis and calculation model, a cooling system analysis and calculation model, a lubrication system analysis and calculation model, and a performance degradation model. The digital twin cloud platform device 203 includes a data interaction module, a digital twin database, and a data analysis module. The data interaction module is responsible for receiving and storing the data of the engine entity 201 (such as the control signals and sensor signals sent by the engine entity 201), as well as the simulation data of the engine digital twin model device 202 (such as the simulation data of the controller digital twin model and the simulation data of the engine digital twin model sent by the engine digital twin model device 202). The digital twin database is divided into an offline database and a real-time database. The offline database stores factory data, design performance indicators, historical operation data of the engine entity 201, and historical simulation data of the digital twin model device 202. The real-time database stores real-time operation data of the engine entity 201 and real-time operation data of the digital twin model device 202. The data analysis module is responsible for analyzing and processing the data in the database to achieve goals such as fault diagnosis, control optimization, performance prediction, and model calibration.
[0060] It should be noted that the engine body specifically covers the crankshaft connecting rod mechanism, valve train, cooling system, lubrication system, fuel supply system, ignition system, and starting system. The engine sensors include an air flow sensor, throttle position sensor, intake pressure sensor, crankshaft position sensor, camshaft position sensor, knock sensor, oxygen sensor, water temperature sensor, and oil pressure sensor. The engine controller is responsible for receiving sensor signals and generating control signals including engine operating state, driver demand torque, target throttle position, intake cam target phase, exhaust cam target phase, target fuel injection mass, and ignition advance angle based on the signals.
[0061] Moreover, the controller digital twin model includes an engine operating state judgment model, a driver demand torque calculation model, a target throttle position calculation model, an intake cam target phase calculation model, an exhaust cam target phase calculation model, a target fuel injection mass calculation model, and an ignition advance angle calculation model.
[0062] As a possible implementation, the detection device of the engine can establish an engine digital twin model device 202 and calibrate it. Secondly, during actual operation, the state data of the engine entity 201 is collected in real time and transmitted through the network to the data interaction module of the digital twin cloud platform device 203, and after preprocessing, it is stored in the database. Subsequently, the engine digital twin model device 202 simulates the engine behavior through algorithms and generates simulation data. Then, the data interaction module is used to synchronously transmit the actual operation data and the simulation data to the data analysis module of the digital twin cloud platform device 203. Next, the data analysis module deeply analyzes the received data, uses machine learning and artificial intelligence technologies to predict performance, diagnose potential faults, and generate a detailed report. Finally, the control strategy is adjusted according to the diagnosis result and the digital twin model is calibrated and optimized to ensure its accuracy and reliability.
[0063] Exemplarily, Figure 3 is a schematic flow chart of a detection method for an engine shown according to an exemplary embodiment, as Figure 3 shown, the engine digital twin model device 202 can establish an engine body digital twin model based on the engine body and set initial parameters. The engine digital twin model device 202 can also establish a controller digital twin model based on the engine controller and set initial parameters. After that, the engine entity 201 is operated in an actual scenario, and the engine sensor and the engine controller can obtain the data of the engine entity, and transmit and store the above data to the data interaction module of the digital twin cloud platform device 203 after processing. Next, the engine digital twin model device 202 executes the same operating state as the engine entity, and collects the simulation data of the controller digital twin model and the simulation data of the engine body digital twin model, and transmits and stores the above data to the data interaction module of the cloud platform after processing. The data interaction module in the digital twin cloud platform device 203 performs interactive processing on the engine entity data and the simulation data of the engine digital twin model, and then sends the interactive data to the digital twin database including the offline database and the real-time database, and the digital twin database stores the historical operation data and the real-time operation data of the engine entity and the engine digital twin model. Then, the data analysis module in the digital twin cloud platform device 203 compares and analyzes the data in the offline database and the real-time database to realize functions such as fault diagnosis, control optimization, performance prediction, and model calibration.
[0064] In the embodiment of the present application, the engine digital twin model device 202 can be deployed in the digital twin database of the digital twin cloud platform device 203. The digital twin cloud platform device 203 can act as a central node, responsible for receiving and processing sensor signals and control signals from each engine entity. These signals are transmitted to the cloud server or data center through the network.
[0065] As Figure 4 shown, the data interaction module receives and stores the control signals and sensor signals (necessary input parameters) of the entity module, and forwards these data to the digital twin database for storage. The data interaction module can obtain real-time data streams from each engine entity through the network interface, and convert these data into a structured format for processing. At the same time, this module is also responsible for receiving the simulation data from the digital twin model and sending it back to the engine entity to adjust the engine entity.
[0066] The digital twin database is used to store data: the offline database can store long-term historical data for tasks such as data analysis and fault diagnosis. The real-time database can store real-time data. The real-time database is used to save the current sensor data and controller data, as well as the data of the current engine ontology digital twin model and the controller digital twin model, to support instant analysis and decision-making. Among them, the digital twin model is deployed in the digital twin database. The digital twin model simulates the behavior of the engine entity through simulation algorithms. Based on the physical model, historical data, and other input parameters, the digital twin model performs complex calculations and simulations to generate detailed simulation data. The simulation data can be transmitted to the data interaction module through the network, and further forwarded to the real-time database or directly sent back to the engine entity.
[0067] The data analysis module can obtain data from the digital twin database and generate optimization suggestions for the engine entity using fault diagnosis algorithms. At the same time, the data analysis module can also use the performance prediction model to generate prediction results to predict whether the engine entity will fail in the future. Then, the data analysis module can forward the prediction results and optimization suggestions to the digital twin database, and then transmit them to the engine entity module through the data interaction module.
[0068] In summary, the present application establishes an engine digital twin operation and maintenance platform based on digital twin technology, uses the operation data of the engine entity to drive the digital twin model, so as to realize the real-time synchronous operation of the engine entity and the digital twin model. It not only improves the real-time monitoring ability of the engine operation state, but also realizes the accuracy of fault diagnosis and the precision of control optimization, providing strong support for the operation and maintenance management of the engine.
[0069] For the convenience of understanding, the following specifically introduces the engine detection method provided by the present application in combination with the accompanying drawings.Figure 5 is a flowchart of a method for detecting an engine shown according to an exemplary embodiment. As Figure 5 shown, the method includes the following steps:
[0070] S501. Obtain first operating data.
[0071] Among them, the first operating data is the operating data of the engine entity under the target operating condition, and the engine entity includes: an engine body and a controller.
[0072] It should be noted that the target operating condition is the operating state of the engine under specific operating conditions. The specific operating conditions may include parameters such as the load, speed, temperature, and pressure of the engine.
[0073] In the embodiments of the present application, the operating data includes: multi-dimensional data of the engine body and multi-dimensional data of the controller.
[0074] Among them, the multi-dimensional data of the engine body includes: fluid dimension data, thermal dimension data, and power dimension data. The fluid dimension data includes fluid flow data, the thermal dimension data includes device temperature data, and the power dimension data includes at least one of the following: pressure data, position and angle data, vibration and noise data.
[0075] As a possible implementation, the detection device can collect the multi-dimensional data of the engine body and / or the multi-dimensional data of the controller corresponding to the engine entity under the target operating condition to obtain the first operating data.
[0076] It should be noted that in the embodiments of the present application, the engine entity further includes engine sensors, and the multi-dimensional data of the engine body is the operating data collected by the engine sensors. Among them, the engine body includes at least one of the following: a crankshaft connecting rod mechanism, a valve train, a cooling system, a lubrication system, a fuel supply system, an ignition system, and a starting system. The engine sensors include at least one of the following: an air flow sensor, a throttle position sensor, an intake pressure sensor, a crankshaft position sensor, a camshaft position sensor, a knock sensor, an oxygen sensor, a water temperature sensor, and an oil pressure sensor.
[0077] Exemplarily, the fluid dimension data may include air flow data, throttle position data, intake pressure data, and oxygen content data, the thermal dimension data may include oil pressure data and water temperature data, and the power dimension data may include crankshaft position data, camshaft position data, and knock data.
[0078] It can be understood that the multi-dimensional data of the engine body can directly reflect the operating state of the engine body and provide support for establishing the corresponding digital twin model of the engine body. By classifying the multi-dimensional data of the engine body into fluid dimension data, thermal dimension data, and power dimension data, the multi-dimensional data of the engine body can be analyzed, making the working state of each part of the engine more transparent, and making the collected data more accurate, capable of quickly locating the problem and providing control and optimization of the engine.
[0079] It should be noted that the controller is responsible for receiving sensor signals and generating multi-dimensional data of the controller according to the signals. The multi-dimensional data of the controller includes: engine control data and status monitoring data. The engine control data is used to adjust the multi-dimensional data of the engine body, and the status monitoring data is the status data of the engine body.
[0080] Exemplarily, the engine control data may include the target throttle position, the target phase of the intake cam, the target phase of the exhaust cam, the target fuel injection mass, and the ignition advance angle. The status monitoring data may include the engine operating state and the driver demand torque.
[0081] It can be understood that the multi-dimensional data of the controller can directly reflect the operating state of the controller and provide support for establishing the corresponding digital twin model of the controller. By classifying the multi-dimensional data of the controller into engine control data and status monitoring data, the multi-dimensional data of the controller can be analyzed, optimizing the working state of each part of the controller, improving the accuracy of data collection, and thus constructing a more accurate digital twin model of the controller.
[0082] S502. Obtain the second operating data.
[0083] Among them, the second operating data is the operating data of the engine digital twin model under the target working condition. The engine digital twin model includes: the digital twin model of the engine body and the digital twin model of the controller.
[0084] As a possible implementation, the detection device can collect the multi-dimensional data of the engine body and / or the multi-dimensional data of the controller corresponding to the engine digital twin model under the target working condition to obtain the second operating data.
[0085] It should be noted that the digital twin model of the controller includes: an engine operating state judgment model, a driver demand torque calculation model, a target throttle position calculation model, an intake cam target phase calculation model, an exhaust cam target phase calculation model, a target fuel injection mass calculation model, and an ignition advance angle calculation model.
[0086] As a possible implementation, the detection device can determine the corresponding digital twin model of the controller based on the multi-dimensional data of the engine entity's controller.
[0087] It can be understood that the digital twin model of the controller can simulate the behavior of the engine control system. Classifying the digital twin model of the controller into more precise and diverse models can significantly improve the monitoring accuracy of the engine state and the control optimization ability.
[0088] In some embodiments, the detection device can obtain the fluidics model of the engine body, the thermodynamics model of the engine body, and the dynamics model of the engine body, and generate the digital twin model of the engine body based on the fluidics model of the engine body, the thermodynamics model of the engine body, and the dynamics model of the engine body.
[0089] Among them, the fluidics model includes: intake system model, exhaust system model, cooling system model, lubrication system model, turbocharging system model. The thermodynamics model includes: cylinder thermodynamics model. The dynamics model includes: crankshaft connecting rod dynamics model and engine performance degradation model.
[0090] It can be understood that by refining the specific models corresponding to the fluidics model, the thermodynamics model, and the dynamics model, it helps to deeply understand the working mechanism of the engine, can more precisely simulate various physical processes of the engine, penetrate to the engine body layer for detailed analysis, and achieve coverage of microscopic physical processes. In this way, these models can provide a solid foundation for realizing efficient and reliable engine simulation and support for realizing more efficient engine management and fault detection.
[0091] It should be noted that the fluidics model, the thermodynamics model, and the dynamics model of the engine body can be determined according to the fluid dimension data, the thermal dimension data, and the power dimension data of the multi-dimensional data of the engine body.
[0092] Optionally, such as Figure 6As shown, the controller digital twin model includes an engine operating state judgment model, a driver demand torque calculation model, a target throttle position calculation model, a target intake cam phase calculation model, a target exhaust cam phase calculation model, a target fuel injection mass calculation model, an ignition advance angle calculation model, etc. The engine body digital twin model in the engine digital twin model includes, but is not limited to, an intake system analysis and calculation model (i.e., the intake system model), a cylinder thermodynamic process analysis and calculation model (i.e., the cylinder thermodynamic model), a crank connecting rod dynamics analysis and calculation model (i.e., the crank connecting rod dynamics model), an exhaust system analysis and calculation model (i.e., the exhaust system model), a turbocharging system analysis and calculation model (i.e., the turbocharging system model), a cooling system analysis and calculation model (i.e., the cooling system model), a lubrication system analysis and calculation model (i.e., the lubrication system model), and a performance degradation model (i.e., the engine performance degradation model), and each model can affect each other.
[0093] Among them, the intake system analysis and calculation model establishes an air filter model, a throttle model, and an intake manifold model according to the components included in the engine intake system. The air filter model internally includes an air filter flow analysis and calculation model, an air filter temperature analysis and calculation model, and an air filter pressure analysis and calculation model; the throttle model is a throttle flow analysis and calculation model; the intake manifold model internally includes an intake manifold flow analysis and calculation model, an intake manifold temperature analysis and calculation model, an intake manifold pressure analysis and calculation model, and an intake manifold working fluid characteristic parameter analysis and calculation model.
[0094] The cylinder thermodynamic process analysis and calculation model establishes an intake valve model, a fuel injection quantity model, a cylinder instantaneous volume model, a combustion heat release model, a heat transfer model, an exhaust valve model, and a cylinder model according to the working principle of each cylinder of the engine. The intake valve model is an intake valve flow analysis and calculation model; the fuel injection quantity model takes the output of the intake valve flow model as input and combines the target air-fuel ratio to establish a fuel injection quantity calculation model for each cylinder per working cycle; the cylinder instantaneous volume model takes the engine speed as input and establishes a cylinder instantaneous volume calculation model; the combustion heat release model takes the output of the fuel injection quantity model and the ignition angle as input and establishes a combustion heat release model; the heat transfer model takes the output of the cylinder instantaneous volume model as input and establishes a heat transfer model; the exhaust valve model is an exhaust valve flow analysis and calculation model; the cylinder model takes the outputs of the intake valve model, the fuel injection quantity model, the cylinder instantaneous volume model, the combustion heat release model, the heat transfer model, and the exhaust valve model as input and establishes an internal cylinder mass analysis and calculation model, a cylinder pressure analysis and calculation model, a cylinder temperature analysis and calculation model, and a cylinder working fluid characteristic parameter analysis and calculation model. Then, the crank connecting rod dynamics analysis and calculation model takes the output of the cylinder thermodynamic process analysis and calculation model as input to establish an engine crankshaft dynamics analysis and calculation model.
[0095] The analytical calculation model of the exhaust system establishes an exhaust manifold model, a three-way catalytic converter model, and a muffler model according to the components included in the engine exhaust system. The exhaust manifold model internally includes an analytical calculation model of exhaust manifold flow, an analytical calculation model of exhaust manifold temperature, an analytical calculation model of exhaust manifold pressure, and an analytical calculation model of working fluid characteristic parameters of the exhaust manifold; the three-way catalytic converter model internally includes an analytical calculation model of three-way catalytic converter flow, an analytical calculation model of three-way catalytic converter temperature, and an analytical calculation model of three-way catalytic converter pressure; the muffler model internally includes an analytical calculation model of muffler flow, an analytical calculation model of muffler temperature, and an analytical calculation model of muffler pressure. Then, the analytical calculation model of the turbocharging system is established with the output of the analytical calculation model of the exhaust system as the input.
[0096] The analytical calculation model of the cooling system includes an intercooler model and a radiator model. Then, the analytical calculation model of the engine lubrication system is established with the output of the analytical calculation model of the cooling system as the input. Then, the performance degradation model is established with the output of the analytical calculation model of the lubrication system as the input.
[0097] It can be understood that by integrating the fluidics model, the thermodynamics model, and the dynamics model that respectively describe different physical processes of the engine into a unified digital twin model of the engine body, the behavior and state of the engine can be comprehensively and accurately simulated.
[0098] S503. Obtain a detection result based on the first operating data and the second operating data.
[0099] Among them, the detection result is used to indicate whether the engine entity has a fault.
[0100] As a possible implementation, the detection device may pre-store a preset threshold. Then, the detection device can obtain the time stamp of the first operating data and sort the first operating data and the corresponding second operating data according to the time. Then, the detection device can calculate the deviation between the first operating data and the second operating data at the same moment and compare the deviation with the preset threshold. When the deviation between the first operating data and the second operating data is greater than the preset threshold, the engine entity has a fault; when the deviation between the first operating data and the second operating data is less than or equal to the preset threshold, the engine entity has no fault.
[0101] The technical solutions provided by the above embodiments at least bring the following beneficial effects: By obtaining the actual operation data of the engine entity and the simulation data of the engine digital twin model under the same working conditions, and comparing the actual operation data with the simulation data, it can be determined whether the engine entity has a fault. In this way, accurate condition detection and fault diagnosis can be achieved, the detection efficiency of the engine can be improved, and further the reliability and performance of the engine can be improved.
[0102] It should be noted that when the detection result is used to indicate that the engine entity has no fault, the detection device can respectively use the historical operation data of the engine entity and the historical operation data of the engine digital twin model to predict the future operation data of the engine entity and the future operation data of the engine digital twin model, and further predict whether the engine entity will have a fault at a future moment, so as to evaluate the future working state and operation trend of the engine entity.
[0103] In some embodiments, after obtaining the detection result (i.e., S503) based on the first operation data and the second operation data, if the detection result indicates that the engine entity has no fault, the detection device can obtain the first historical operation data and the second historical operation data, where the first historical operation data is the operation data of the engine entity at the target working condition at a historical moment, and the second historical operation data is the operation data of the engine digital twin model at the target working condition at a historical moment. Then, the detection device can determine the first predicted operation data based on the first historical operation data and the first operation data, and determine the second predicted operation data based on the second historical operation data and the second operation data. Then, the detection device can obtain a prediction result based on the first predicted operation data and the second predicted operation data to judge whether the engine entity will have a fault at the target future moment.
[0104] Among them, the first predicted operation data is the operation data of the engine entity at the target working condition at the target future moment, the second predicted operation data is the operation data of the engine digital twin model at the target working condition at the target future moment, and the target future moment is later than the current moment.
[0105] As a possible implementation manner, the detection device can predict the future performance of the engine based on the historical operation data of the engine entity, the digital twin model, and the real-time collected data, and the prediction result will be used to evaluate the working state and future operation trend of the engine.
[0106] It should be noted that the type of the machine learning algorithm is not limited in the embodiments of the present application. For example, the machine learning algorithm can be a linear regression model, for another example, the machine learning algorithm can be a random forest model, and for another example, the machine learning algorithm can be an extreme random tree model.
[0107] It is understandable that based on the operating data of the engine entity and the digital twin model under the target operating conditions at the historical moment and the current moment, the operating performance of both at the future moment can be predicted. And based on these two prediction results, it is judged whether the engine entity is likely to fail at the target future moment in the future. In this way, the data of the engine entity and the data of the engine digital twin model can be used for comparative analysis to more accurately capture the subtle changes that may indicate a failure, and then predict the operating conditions at the future moment. Preventive measures can be taken before the failure occurs to reduce the losses caused by sudden failures and improve the service efficiency and life of the engine entity.
[0108] The following introduces the engine detection method provided by the embodiments of the present application in combination with specific examples. As Figure 7 shown, it includes the following steps 1-step 7:
[0109] Step 1, data collection: First, various sensors and data input interfaces installed on the engine are used for data collection, and various types of data during the operation of the engine are collected in real time, including key parameters such as temperature, pressure, and speed.
[0110] Step 2, data transmission: The collected data is transmitted to the data interaction module of the digital twin cloud platform. Through network connection, these data are preliminarily processed and stored in the cloud server to provide basic data support for subsequent analysis.
[0111] Step 3, data processing: Data cleaning, feature extraction, and fault mode recognition and other data processing are performed inside the digital twin cloud platform, and the data analysis module is used to perform in-depth processing and analysis on the received data.
[0112] Step 4, performance prediction: And based on the key feature parameters, based on the historical operating data and the real-time collected data, advanced machine learning algorithms are used to predict the future performance of the engine and evaluate the working state and future operating trends of the engine.
[0113] Step 5, fault diagnosis: The received data is analyzed in detail through the fault diagnosis module, and expert systems or artificial intelligence technologies are used to detect and locate the possible causes of faults.
[0114] Step 6, result output: The results of performance prediction and fault diagnosis are presented in the form of reports or data output. These results not only provide detailed prediction reports, but also include specific fault diagnosis conclusions and recommended measures.
[0115] Step 7, Feedback and Optimization: Based on the above prediction and diagnosis results, generate corresponding feedback information and make real-time adjustments to the engine control strategy. At the same time, calibrate and optimize the digital twin model according to the diagnosis results to ensure the continuous improvement of its accuracy and reliability.
[0116] In summary, this application monitors the operating data of the engine entity in real time through sensors, parameterizes it, and transmits it to the cloud platform and the digital twin model, thereby achieving goals such as engine performance prediction, control optimization, and fault diagnosis. This method can achieve comprehensive monitoring and refined management of the engine operating state through multi-level modeling and intelligent data analysis.
[0117] The above mainly introduces the solution provided by the embodiment of this application from the perspective of the method. To implement the above functions, the detection device of the engine includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combined with the units and algorithm steps of each example described in the embodiments disclosed in this article, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.
[0118] The embodiment of this application can divide the function modules of the engine detection device according to the above method. For example, the engine detection device can include each function module corresponding to each function division, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software function module. It should be noted that the division of modules in the embodiment of this application is illustrative, only a logical function division, and there can be other division methods in actual implementation.
[0119] Figure 8 is a schematic structural diagram of a detection device for an engine shown according to an exemplary embodiment. Refer to Figure 8 , the engine detection device 800 includes an acquisition module 801 and a processing module 802.
[0120] The acquisition module 801 is used to acquire first operating data, where the first operating data is the operating data of the engine entity under the target working condition. The engine entity includes: an engine body and a controller. The operating data includes: multi-dimensional data of the engine body and multi-dimensional data of the controller. The multi-dimensional data of the engine body includes: fluid dimension data, thermal dimension data, and power dimension data. Acquire second operating data.
[0121] The acquisition module 801 is further configured to acquire second operation data, where the second operation data is the operation data of the engine digital twin model under a target working condition, and the engine digital twin model includes: an engine body digital twin model and a controller digital twin model.
[0122] The processing module 802 is configured to obtain a detection result based on the first operation data and the second operation data.
[0123] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0124] Figure 9 It is a schematic structural diagram of another engine detection device shown according to an exemplary embodiment. As Figure 9 shown, the engine detection device 900 includes but is not limited to: a processor 901 and a memory 902.
[0125] Among them, the above-mentioned memory 902 is used to store executable instructions of the above-mentioned processor 901. It can be understood that the above-mentioned processor 901 is configured to execute instructions to implement the engine detection method in the above embodiments.
[0126] It should be noted that those skilled in the art can understand that Figure 9 the structural diagram of the engine detection device shown in Figure 9 does not constitute a limitation on the engine detection device. The engine detection device may include more or fewer components than
[0127] shown, or combine certain components, or have different component arrangements.
[0128] The memory 902 can be used to store software programs and various data. The memory 902 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required by at least one functional module (such as a determination unit, a processing unit, etc.). In addition, the memory 902 can include high-speed random access memory and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0129] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as the memory 902 including instructions. The above instructions can be executed by the processor 901 of the detection device of the engine to implement the method in the above embodiment.
[0130] In actual implementation, Figure 8 the functions of the acquisition module 801 and the processing module 802 in Figure 9 can be implemented by the processor 901 in
[0131] calling a computer program stored in the memory 902. The specific execution process can refer to the description of the method part in the above embodiment and will not be elaborated here.
[0132] In an exemplary embodiment, the embodiment of the present application also provides a computer program product including one or more instructions. The one or more instructions can be executed by the processor 901 of the detection device of the engine to complete the method in the above embodiment.
[0133] It should be noted that when the instructions in the above computer-readable storage medium or the one or more instructions in the computer program product are executed by the processor of the detection device of the engine, each process of the above method embodiment is implemented, and the same technical effects as the above method can be achieved. To avoid repetition, it will not be elaborated here.
[0134] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.
[0135] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.
[0136] The units described as separate components may or may not be physically separated. The components displayed as units may be one physical unit or multiple physical units, that is, they can be located in one place, or they can be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0137] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks or optical discs that can store program codes.
[0139] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A detection method for an engine, characterized in that, The method includes: Obtaining first operating data, where the first operating data is the operating data of an engine entity under a target operating condition. The engine entity includes: an engine body and a controller; the operating data includes: multi-dimensional data of the engine body and multi-dimensional data of the controller. The multi-dimensional data of the engine body includes: fluid dimension data, thermal dimension data, and power dimension data; Obtaining second operating data, where the second operating data is the operating data of an engine digital twin model under the target operating condition. The engine digital twin model includes: an engine body digital twin model and a controller digital twin model; Based on the first operating data and the second operating data, obtaining a detection result, where the detection result is used to indicate whether a fault has occurred in the engine entity.
2. The method according to claim 1, wherein The fluid dimension data includes fluid flow data, the thermal dimension data includes device temperature data, and the power dimension data includes at least one of the following: pressure data, position and angle data, vibration and noise data.
3. The method according to claim 1, characterized in that, The multi-dimensional data of the controller includes: engine control data and status monitoring data. The engine control data is used to adjust the multi-dimensional data of the engine body, and the status monitoring data is the status data of the engine body.
4. The method according to claim 1, wherein The method further includes: Obtaining a fluidics model of the engine body, a thermodynamics model of the engine body, and a dynamics model of the engine body; Based on the fluidics model, the thermodynamics model, and the dynamics model, generating an engine body digital twin model.
5. The method according to claim 4, characterized in that, The fluidics model includes: an intake system model, an exhaust system model, a cooling system model, a lubrication system model, and a turbocharging system model; the thermodynamics model includes: a cylinder thermodynamics model; the dynamics model includes: a crankshaft connecting rod dynamics model and an engine performance degradation model.
6. The method according to claim 1, characterized in that, The controller digital twin model includes: an engine operating state judgment model, a driver demand torque calculation model, a target throttle position calculation model, an intake cam target phase calculation model, an exhaust cam target phase calculation model, a target fuel injection mass calculation model, and an ignition advance angle calculation model.
7. The method according to any one of claims 1-6, characterized in that, The first operating data and the second operating data are the operating data at the current moment; After obtaining the detection result based on the first operating data and the second operating data, the method further includes: In the case where the detection result is used to indicate that no fault has occurred in the engine entity, obtaining first historical operating data and second historical operating data. The first historical operating data is the operating data of the engine entity under the target operating condition at a historical moment, and the second historical operating data is the operating data of the engine digital twin model under the target operating condition at the historical moment; Based on the first historical operating data and the first operating data, determining first predicted operating data, where the first predicted operating data is the operating data of the engine entity under the target operating condition at a target future moment, and the target future moment is later than the current moment; Determine second predicted operation data based on the second historical operation data and the second operation data, where the second predicted operation data is the operation data of the engine digital twin model under the target operating condition at the target future moment; Obtain a prediction result based on the first predicted operation data and the second predicted operation data, where the prediction result is used to indicate whether a fault occurs in the engine entity at the target future moment.
8. A detection device for an engine, characterized in that, The device includes: An acquisition module, configured to acquire first operation data, where the first operation data is the operation data of an engine entity under a target operating condition, and the engine entity includes: an engine body and a controller; the operation data includes: multi-dimensional data of the engine body and multi-dimensional data of the controller, and the multi-dimensional data of the engine body includes: fluid dimension data, thermal dimension data, and power dimension data; An acquisition module, configured to acquire second operation data, where the second operation data is the operation data of an engine digital twin model under the target operating condition, and the engine digital twin model includes: an engine body digital twin model and a controller digital twin model; The processing module is configured to obtain a detection result based on the first operation data and the second operation data, where the detection result is used to indicate whether a fault occurs in the engine entity.
9. A detection device for an engine, characterized in that, Includes: A processor; A memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the detection device of the engine, the detection device of the engine can execute the method according to any one of claims 1 to 7.
11. A computer program product, characterized in that, The computer program product includes computer program instructions, and when the computer program instructions are executed, the method according to any one of claims 1 to 7 is implemented.