Engine fault prediction method and device, computer equipment and storage medium

Abstract

The invention relates to an engine fault prediction method and device, computer equipment and a storage medium. The method comprises the steps of obtaining target data of a fault vehicle, and determining an engine fault mode of the fault vehicle according to the target data; based on the engine fault mode and the target data, failure mechanism analysis is conducted on the fault vehicle, and an analysis result is obtained; a fault mechanism model of the engine is constructed according to the analysis result, and a fault prediction model of the engine is constructed according to the fault mechanism model and the target data; and acquiring real-time operation data of the target vehicle, and performing dynamic fault prediction on the engine of the target vehicle according to the real-time operation data of the target vehicle and the fault prediction model of the engine. By the adoption of the method, engine faults can be predicted, active services are provided for users, potential faults are early warned and repaired in time, out-of-plan shutdown is avoided, and user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of engine technology, and in particular to an engine fault prediction method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] As a core component in the automotive system, the engine plays a crucial role in providing power to the entire vehicle, directly impacting its performance and efficiency. Engine efficiency and reliability are particularly important in scenarios requiring long periods of time and high loads, such as commercial trucks. A well-maintained engine can maintain stable power output under a variety of complex road conditions, meeting long-distance transport demands while effectively reducing fuel consumption and maintenance costs. When an engine fails, it can cause unplanned downtime for the vehicle. The longer the downtime, the greater the loss of transport revenue. For long-distance transport operations, this can result in delayed delivery or even damage to the goods, leading to customer dissatisfaction and impacting the driving experience.

[0003] In the prior art, to ensure the normal operation of the engine, regular maintenance and manual inspections are usually relied upon to detect potential faults.

[0004] However, although these measures can reduce the failure rate to a certain extent, it is still difficult to completely avoid the occurrence of sudden failures, especially during maintenance intervals. Once the engine fails, it is very easy to cause unplanned vehicle downtime. Summary of the Invention

[0005] Based on this, it is necessary to provide an engine failure prediction method, device, computer equipment, computer-readable storage medium and computer program product that can predict engine failure and improve engine reliability in response to the above technical problems.

[0006] In a first aspect, the present application provides an engine failure prediction method, comprising:

[0007] Acquiring target data of the faulty vehicle and determining an engine failure mode of the faulty vehicle based on the target data;

[0008] Based on the engine failure mode and target data, the failure mechanism of the faulty vehicle is analyzed to obtain the analysis results;

[0009] Construct an engine failure mechanism model based on the analysis results, and construct an engine failure prediction model based on the failure mechanism model and target data;

[0010] The real-time operating data of the target vehicle is obtained, and dynamic fault prediction of the engine of the target vehicle is performed based on the real-time operating data of the target vehicle and the fault prediction model of the engine.

[0011] In one embodiment, the failure mechanism analysis includes boundary analysis, functional analysis, interaction analysis, and parameter analysis. Based on the engine failure mode and target data, the failure mechanism analysis is performed on the faulty vehicle to obtain analysis results, including:

[0012] Based on the engine failure mode and target data, determine the fault boundary of the faulty vehicle; determine the target component of the faulty vehicle based on the fault boundary, and determine the functional role of the target component;

[0013] According to the functional role of the target components, the interaction between the target components is analyzed to identify the coupling paths between the target components;

[0014] Based on the coupling paths between target components and target data, the key influencing parameters of the faulty vehicle are determined.

[0015] In one embodiment, the failure mechanism model includes a low-cycle fatigue damage model, a high-cycle fatigue damage model, and a thermal-mechanical coupling damage model. The failure mechanism model of the engine is constructed based on the analysis results, including:

[0016] Map the key influencing parameters of the faulty vehicle with low-cycle fatigue damage, high-cycle fatigue damage, and thermal-mechanical coupling damage to determine the key influencing parameters corresponding to each fatigue damage;

[0017] The influence degree of each key influencing parameter in the corresponding fatigue damage is weighted and the weight value of each key influencing parameter in the corresponding fatigue damage is obtained;

[0018] Based on the weight values of the key influencing parameters corresponding to low-cycle fatigue damage, high-cycle fatigue damage and thermal-mechanical coupling damage respectively, the low-cycle fatigue damage model, high-cycle fatigue damage model and thermal-mechanical coupling damage model are determined.

[0019] In one embodiment, a fault prediction model for an engine is constructed based on the fault mechanism model and target data, including:

[0020] Based on the target data of the faulty vehicle and the fault mechanism model, determine the damage factor corresponding to the target data;

[0021] The target data and its corresponding damage factors are fused in time series to obtain a multi-dimensional time series input;

[0022] The neural network model is trained using multi-dimensional time series input to obtain a fault prediction model.

[0023] In one embodiment, the engine failure mode includes a failure location classification and a failure phenomenon classification.

[0024] In one embodiment, the target data of the faulty vehicle includes the Internet of Vehicles data and historical fault data of the faulty vehicle.

[0025] In a second aspect, the present application further provides an engine failure prediction device, comprising:

[0026] an acquisition module, configured to acquire target data of the faulty vehicle and determine an engine failure mode of the faulty vehicle based on the target data;

[0027] An analysis module is used to analyze the failure mechanism of the faulty vehicle based on the engine failure mode and target data to obtain analysis results;

[0028] A construction module is used to construct an engine failure mechanism model based on the analysis results, and to construct an engine failure prediction model based on the failure mechanism model and target data;

[0029] The prediction module obtains the real-time operating data of the target vehicle and performs dynamic fault prediction on the engine of the target vehicle based on the real-time operating data of the target vehicle and the engine fault prediction model.

[0030] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] Acquiring target data of the faulty vehicle and determining an engine failure mode of the faulty vehicle based on the target data;

[0032] Based on the engine failure mode and target data, the failure mechanism of the faulty vehicle is analyzed to obtain the analysis results;

[0033] Construct an engine failure mechanism model based on the analysis results, and construct an engine failure prediction model based on the failure mechanism model and target data;

[0034] The real-time operating data of the target vehicle is obtained, and dynamic fault prediction of the engine of the target vehicle is performed based on the real-time operating data of the target vehicle and the fault prediction model of the engine.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0036] Acquiring target data of the faulty vehicle and determining an engine failure mode of the faulty vehicle based on the target data;

[0037] Based on the engine failure mode and target data, the failure mechanism of the faulty vehicle is analyzed to obtain the analysis results;

[0038] Construct an engine failure mechanism model based on the analysis results, and construct an engine failure prediction model based on the failure mechanism model and target data;

[0039] The real-time operating data of the target vehicle is obtained, and dynamic fault prediction of the engine of the target vehicle is performed based on the real-time operating data of the target vehicle and the fault prediction model of the engine.

[0040] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0041] Acquiring target data of the faulty vehicle and determining an engine failure mode of the faulty vehicle based on the target data;

[0042] Based on the engine failure mode and target data, the failure mechanism of the faulty vehicle is analyzed to obtain the analysis results;

[0043] Construct an engine failure mechanism model based on the analysis results, and construct an engine failure prediction model based on the failure mechanism model and target data;

[0044] The real-time operating data of the target vehicle is obtained, and dynamic fault prediction of the engine of the target vehicle is performed based on the real-time operating data of the target vehicle and the fault prediction model of the engine.

[0045] The aforementioned engine fault prediction method, apparatus, computer equipment, storage medium, and computer program product acquire target data of a faulty vehicle and determine the engine fault mode of the faulty vehicle based on the target data. Based on the engine fault mode and target data, the faulty vehicle's failure mechanism is analyzed to obtain analysis results. An engine fault mechanism model is constructed based on the analysis results, and an engine fault prediction model is constructed based on the fault mechanism model and the target data. Real-time operating data of the target vehicle is acquired, and dynamic fault prediction is performed on the target vehicle's engine based on the target vehicle's real-time operating data and the engine fault prediction model. This engine fault prediction method can predict engine faults, provide proactive services to users, provide early warnings of potential faults, and enable timely repairs, avoiding unplanned downtime and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1A diagram showing an application environment of an engine failure prediction method according to an embodiment;

[0048] Figure 2 1 is a flow chart of an engine failure prediction method according to an embodiment;

[0049] Figure 3 A schematic diagram of a process for constructing a failure mechanism model of an engine in one embodiment;

[0050] Figure 4 is a structural block diagram of an engine failure prediction device in one embodiment;

[0051] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] In the prior art, engine fault troubleshooting typically relies on regular maintenance and manual inspections. While these measures can reduce the probability of failure to a certain extent, unexpected failures during maintenance cycles are still difficult to avoid. To improve the real-time nature of fault detection, some technical solutions have introduced sensor-based monitoring systems. By deploying high-precision sensors in key engine locations to capture key parameters such as temperature, pressure, and vibration, they enable real-time monitoring and early warning of the engine's operating status. However, due to the compact internal structure and complex operating environment (e.g., high temperature and high pressure), these sensors must meet high technical requirements in terms of environmental resistance and installation. This often requires expensive industrial-grade sensors, significantly increasing system costs. Furthermore, sensor placement can affect the engine's structural integrity, reducing reliability and ease of maintenance. Therefore, this application proposes an engine fault prediction method that uses passive signals to identify and predict faults. These passive signals are existing onboard signals that do not require the acquisition of new sensors. This method enables fault prediction without increasing vehicle-side hardware costs, significantly reducing overall system costs. On the other hand, by analyzing the failure mechanism of the target data of historical faulty vehicles, exploring the correlation between the target data and the fault type, and then building a fault prediction model, the accuracy of engine fault prediction can be guaranteed, thereby improving the reliability of the engine.

[0054] The engine fault prediction method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or placed on a cloud or other network server. Terminal 102 sends an engine fault prediction request to server 104. Server 104 receives the engine fault prediction request, obtains target data of the faulty vehicle, and determines the engine fault mode of the faulty vehicle based on the target data. Based on the engine fault mode and target data, it performs a failure mechanism analysis on the faulty vehicle to obtain analysis results. It constructs an engine fault mechanism model based on the analysis results, and constructs an engine fault prediction model based on the fault mechanism model and target data. It obtains real-time operating data of the target vehicle and performs dynamic fault prediction on the target vehicle's engine based on the real-time operating data of the target vehicle and the engine fault prediction model. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. Portable wearable devices can be smart watches, smart bracelets, etc. Server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0055] In an exemplary embodiment, Figure 2 As shown, a method for predicting engine failure is provided. Figure 1 The server in the example is used to illustrate the process, including the following steps 202 to 208.

[0056] Step 202: Acquire target data of the faulty vehicle and determine the engine failure mode of the faulty vehicle based on the target data.

[0057] The target data of the faulty vehicle includes the vehicle network data and historical fault data of the faulty vehicle; the engine fault mode includes the fault location classification and the fault phenomenon classification. The faulty vehicle is taken as an example of a faulty vehicle with an engine failure.

[0058] Exemplarily, the Internet of Vehicles data of a faulty vehicle refers to the Internet of Vehicles data continuously collected and stored from the date the faulty vehicle was sold to the date before the most recent engine failure occurred. The above-mentioned Internet of Vehicles data may include but is not limited to the following parameters: vehicle speed, engine speed, engine output torque, engine friction torque, fuel consumption rate, accelerator pedal opening, oil pressure, intake pressure, coolant temperature, upstream oxygen sensor output value, and downstream oxygen sensor output value. The historical fault data of a faulty vehicle refers to the fault-related information recorded from the date the vehicle was sold to the date before the most recent engine failure occurred. Specifically, it can be derived from after-sales maintenance records, warranty claim systems or other fault information collection platforms. The historical fault data may include but is not limited to information such as the time node of the fault, the fault location, the fault image, and the fault description.

[0059] Optionally, the specific location of the engine fault can be identified and classified based on fault image information in historical fault data (e.g., images of the faulted vehicle's faulty area). Specifically, fault location classifications may include cracks between cylinder head exhaust valves, cracks between cylinder head spark plugs, cracks between cylinder head intake valves, and cracks between cylinder head exhaust passages. Engine fault symptoms can also be identified and classified based on connected vehicle data corresponding to the fault, combined with vehicle operating status information. These symptoms may include insufficient power output, engine backflow, vehicle vibration during operation, engine misfire, and abnormally high coolant temperature.

[0060] Step 204 : Based on the engine failure mode and target data, a failure mechanism analysis is performed on the faulty vehicle to obtain an analysis result.

[0061] Based on the engine failure mode and the target data of the faulty vehicle, a failure mechanism analysis is performed on the faulty vehicle to identify the cause, process, and influencing factors of the engine failure. Specifically, the engine failure mode refers to the characteristic performance of the engine during a failure, typically including the fault location (e.g., cracks between the cylinder head exhaust valves, cracks between the spark plugs, etc.) and the fault symptoms (e.g., engine power loss, abnormally high coolant temperature, vehicle jitter, etc.). The target data includes two types of information: dynamic operating data continuously collected by the Internet of Vehicles system, such as vehicle speed, engine speed, throttle position, coolant temperature, oil pressure, and intake pressure; and historical failure data, such as maintenance records, warranty claim information, and failure photos. By combining the engine failure mode with the target data of the faulty vehicle, a failure mechanism analysis (FMA) method is used to identify key influencing factors and fault propagation paths, thereby obtaining failure mechanism analysis results.

[0062] Step 206: constructing an engine failure mechanism model based on the analysis results, and constructing an engine failure prediction model based on the failure mechanism model and the target data.

[0063] Optionally, the failure mechanism model is used to quantify the cumulative damage process of the engine under different operating conditions based on the physical laws derived from the failure mechanism analysis (such as key influencing factors and fault propagation paths). It can also convert the vehicle-to-vehicle data of the faulty vehicle into quantifiable damage indicators. For example, based on the results of the failure mechanism analysis, the key influencing parameters that have the greatest impact on the engine failure are identified, and the contribution weight of each key influencing parameter to the failure mechanism model is determined. The calculation formula for the failure mechanism model is then determined based on the contribution weight.

[0064] For example, the Internet of Vehicles data of the faulty vehicle is input into the fault mechanism model, and the damage accumulation value (damage factor) corresponding to the Internet of Vehicles data at each time point is calculated; the damage accumulation value is aligned with the original data (i.e., the Internet of Vehicles data of the faulty vehicle) in time series to form a training data set; the training data set is used to train the LSTM model to learn the mapping relationship from the original data plus the damage accumulation value (damage factor) to the failure probability.

[0065] Step 208 : Acquire the real-time operating data of the target vehicle, and perform dynamic fault prediction on the engine of the target vehicle based on the real-time operating data of the target vehicle and the engine fault prediction model.

[0066] The target vehicle's real-time operating data may include vehicle speed, rotational speed, coolant temperature, intake pressure, oil pressure, etc. This real-time operating data is used as input to the fault prediction model, which then uses this data to make judgments and implement dynamic assessments and early warnings of engine faults.

[0067] Traditional fault prediction methods mostly rely on a single data-driven model and lack an in-depth understanding of the fault mechanism, which makes it difficult to accurately predict faults under complex working conditions. However, this application introduces failure mechanism analysis and combines the target data of the faulty vehicle to establish a physically explainable fault mechanism model, which makes up for the limitations of traditional data models. On the other hand, this application combines the real-time operating data of the target vehicle with the fault prediction model to dynamically track changes in vehicle status, achieve dynamic early warning of faults, avoid the limitation of repairs only after the fault occurs, and improve the timeliness and accuracy of fault prediction. In addition, the above-mentioned engine failure method predicts engine failures and provides proactive services to users. It can warn of potential faults and repair them in a timely manner, avoid unplanned downtime, and improve user experience.

[0068] In an exemplary embodiment, the failure mechanism analysis includes boundary analysis, functional analysis, interaction analysis and parameter analysis. Based on the engine failure mode and target data, the failure mechanism analysis is performed on the faulty vehicle to obtain analysis results, including: determining the fault boundary of the faulty vehicle based on the engine failure mode and target data; determining the target components of the faulty vehicle based on the fault boundary, and determining the functional role of the target components; analyzing the interaction between the target components according to the functional role of the target components, and identifying the coupling path between the target components; determining the key influencing parameters of the faulty vehicle according to the coupling path between the target components and the target data.

[0069] Optionally, boundary analysis is used to clarify which components will directly affect the engine, which can limit the scope of failure mechanism analysis; functional analysis is used to determine the functional role of the target components obtained by boundary analysis; interaction analysis is used to analyze the mutual influence relationship between each target component; and identify the key parameters that affect the evolution of the fault in the target data of the faulty vehicle.

[0070] For example, based on the engine failure mode and the target data of the faulty vehicle, the fault boundary is first determined to limit the subsequent failure mechanism analysis to the fault-related systems, thereby improving the relevance and effectiveness of the analysis. The fault boundary may include components or systems such as the cylinder head body, cylinder gasket, cooling system interface, intake and exhaust interfaces, exhaust gas recirculation (EGR) system, and oil pump. The components within this fault boundary are the target components. After determining the target components of the faulty vehicle, a functional analysis is performed on the target components of each faulty vehicle to clarify their specific role in engine operation. For example, the cylinder head and its associated components are generally used to form the combustion space and have functions such as sealing, heat dissipation, and support. Based on the results of this functional analysis, the interactive influence relationships between the target components are further analyzed to identify possible coupling paths between them. For example, the exhaust gas recirculation (EGR) system requires coolant for cooling. When an EGR leak occurs, coolant enters the combustion chamber and rapidly vaporizes upon encountering the hot cylinder head baseplate, causing severe thermal shock in the cylinder head combustion zone and resulting in thermal damage. Furthermore, failure to replenish coolant promptly or the addition of substandard coolant can cause engine overheating, further damaging the cylinder head. After identifying the coupling paths between these target components, the target data of the faulty vehicle can be combined to identify the influencing parameters (i.e., key influencing parameters) that play a key role in the coupling paths. These parameters serve as an important basis for subsequent fault mechanism model construction. For example, coolant leakage has the greatest impact on cylinder head cracking, including reduced cooling capacity due to external coolant leakage and thermal shock caused by internal coolant leakage into the combustion chamber. Symptoms of the fault include reduced power, shortened starting water temperature stabilization time, excessive coolant temperature, vehicle jitter, reduced oil pressure, and sudden stalling.

[0071] In this embodiment, failure mechanism analysis based on engine failure modes and target data can gradually sort out the structural paths and influencing mechanisms of the failure, improving the accuracy of fault modeling. Specifically, boundary analysis helps narrow the analysis targets and focus on components closely related to the failure; interactive impact analysis identifies the coupling paths between components, helping to reveal the fault propagation chain; and parameter analysis further extracts key influencing parameters highly correlated with the failure, providing support for the subsequent construction of a highly accurate fault mechanism model.

[0072] In an exemplary embodiment, the failure mechanism model includes a low cycle fatigue damage model, a high cycle fatigue damage model and a thermal mechanical coupling damage model, such as Figure 3 As shown, building the engine failure mechanism model based on the analysis results includes steps 302 to 306. Among them:

[0073] Step 302 : Mapping the key influencing parameters of the faulty vehicle with low-cycle fatigue damage, high-cycle fatigue damage, and thermal-mechanical coupling damage to determine the key influencing parameters corresponding to each fatigue damage.

[0074] Step 304 : weighting the influence of each key influencing parameter on the corresponding fatigue damage to obtain the weight value of each key influencing parameter on the corresponding fatigue damage.

[0075] Step 306 : determining a low-cycle fatigue damage model, a high-cycle fatigue damage model, and a thermal-mechanical coupling damage model based on the weight values of the key influencing parameters corresponding to low-cycle fatigue damage, high-cycle fatigue damage, and thermal-mechanical coupling damage, respectively.

[0076] Optionally, the key influencing parameters of the faulty vehicle are associated with different types of fatigue damage in the fault mechanism model. That is, each key influencing parameter is mapped to low-cycle fatigue damage, high-cycle fatigue damage, and thermo-mechanical coupling damage, respectively, to clarify the key influencing parameters corresponding to each fatigue damage type. For example, low-cycle fatigue damage is primarily associated with parameters reflecting mechanical load changes, such as engine torque fluctuation amplitude and friction torque; high-cycle fatigue damage is primarily associated with parameters reflecting high-frequency vibration or dynamic disturbances, such as speed fluctuation and oil pressure anomalies; and thermo-mechanical coupling damage is primarily associated with thermal-fluid anomalies, such as coolant temperature fluctuation and EGR system leakage. Based on finite element simulation results or statistical analysis of historical fault data, the contribution of each key influencing parameter to the corresponding fatigue damage is further evaluated and weighted to determine the weight of each key influencing parameter for different fatigue damage types. Finally, based on these weights, low-cycle fatigue damage models, high-cycle fatigue damage models, and thermo-mechanical coupling damage models are constructed to achieve quantitative modeling and comprehensive characterization of the engine's multi-source damage mechanisms.

[0077] In this embodiment, by associating key influencing parameters with different types of fatigue damage and calibrating the contribution weights of key influencing parameters, it is possible to achieve fine modeling and differentiation of multiple types of fatigue damage, thereby improving the accuracy and interpretability of the fault mechanism model; further, by constructing multiple damage models such as low-cycle fatigue, high-cycle fatigue, and thermal-mechanical coupling, the fault prediction model can comprehensively cover the damage evolution process under different working conditions and fault inducements, thereby enhancing the pertinence and robustness of fault prediction, thereby significantly improving the accuracy and practical value of engine fault prediction.

[0078] In an exemplary embodiment, a fault prediction model of an engine is constructed based on a fault mechanism model and target data, including: determining a damage factor corresponding to the target data based on the target data of the faulty vehicle and the fault mechanism model; fusing the target data and its corresponding damage factor in a time series to obtain a multi-dimensional time series input; and training a neural network model using the multi-dimensional time series input to obtain a fault prediction model.

[0079] Based on the target data of the faulty vehicle (i.e., the IoV data of the faulty vehicle) and various damage models (low-cycle fatigue damage model, high-cycle fatigue damage model, and thermal-mechanical coupling damage model), key influencing parameters corresponding to each damage model are extracted from the IoV data. Based on these parameters, damage factors corresponding to the IoV data at each time point are calculated. Damage factors may include low-cycle damage values, high-cycle damage values, and thermal-mechanical damage values. For example, IoV data of the faulty vehicle at a specific moment is obtained, and key influencing parameters in the IoV data are input into the corresponding damage models to obtain the low-cycle damage values, high-cycle damage values, and thermal-mechanical damage values corresponding to that moment. The calculated damage factors (low-cycle damage values, high-cycle damage values, and thermal-mechanical damage values) are aligned with the original data (i.e., IoV data) by time point and fused in chronological order to obtain time series input data containing multidimensional features (i.e., multidimensional time series input). This multidimensional time series input is used to train a neural network model (e.g., an LSTM (long short-term memory network)) to enable the neural network model to predict failure probability from the time series input data.

[0080] In this embodiment, the neural network model is used to train multi-dimensional time series inputs, which can effectively adapt to complex working conditions and nonlinear dynamics, significantly improve the generalization ability and prediction accuracy of the fault prediction model in multiple scenarios, and thus achieve more efficient and accurate engine fault warning.

[0081] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0082] Based on the same inventive concept, embodiments of the present application also provide an engine failure prediction device for implementing the aforementioned engine failure prediction method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more engine failure prediction device embodiments provided below can be found in the aforementioned limitations of the engine failure prediction method and will not be further elaborated here.

[0083] In an exemplary embodiment, Figure 4 As shown, an engine fault prediction device is provided, including: an acquisition module 402, an analysis module 404, a construction module 406 and a prediction module 408, wherein:

[0084] An acquisition module 402 is configured to acquire target data of the faulty vehicle and determine an engine fault mode of the faulty vehicle based on the target data;

[0085] An analysis module 404 is configured to analyze the failure mechanism of the faulty vehicle based on the engine failure mode and target data to obtain analysis results;

[0086] A construction module 406 is used to construct an engine failure mechanism model based on the analysis results, and to construct an engine failure prediction model based on the failure mechanism model and the target data;

[0087] The prediction module 408 obtains the real-time operating data of the target vehicle and performs dynamic fault prediction on the engine of the target vehicle based on the real-time operating data of the target vehicle and the engine fault prediction model.

[0088] In an exemplary embodiment, the failure mechanism analysis includes boundary analysis, functional analysis, interaction analysis and parameter analysis. The analysis module 404 is also used to determine the fault boundary of the faulty vehicle based on the engine failure mode and target data; determine the target components of the faulty vehicle based on the fault boundary, and determine the functional role of the target components; analyze the interaction between the target components according to the functional role of the target components, and identify the coupling path between the target components; determine the key influencing parameters of the faulty vehicle according to the coupling path between the target components and the target data.

[0089] In an exemplary embodiment, the fault mechanism model includes a low-cycle fatigue damage model, a high-cycle fatigue damage model, and a thermo-mechanical coupling damage model. The construction module 406 is also used to map the key influencing parameters of the faulty vehicle with the low-cycle fatigue damage, high-cycle fatigue damage, and thermo-mechanical coupling damage to determine the key influencing parameters corresponding to each fatigue damage; weight the influence degree of each key influencing parameter in the corresponding fatigue damage to obtain the weight value of each key influencing parameter in the corresponding fatigue damage; based on the weight values of the key influencing parameters corresponding to the low-cycle fatigue damage, high-cycle fatigue damage, and thermo-mechanical coupling damage, determine the low-cycle fatigue damage model, high-cycle fatigue damage model, and thermo-mechanical coupling damage model.

[0090] In an exemplary embodiment, the construction module 406 is also used to determine the damage factor corresponding to the target data based on the target data of the faulty vehicle and the fault mechanism model; fuse the target data and its corresponding damage factor in time series to obtain a multi-dimensional time series input; and use the multi-dimensional time series input to train the neural network model to obtain a fault prediction model.

[0091] In an exemplary embodiment, the engine failure mode includes a failure location classification and a failure phenomenon classification; the target data of the faulty vehicle includes the vehicle networking data and historical failure data of the faulty vehicle.

[0092] Each module in the aforementioned engine failure prediction device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0093] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store target data of the faulty vehicle. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an engine fault prediction method is implemented.

[0094] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0095] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0096] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0097] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0098] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0099] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0100] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for predicting engine failure, characterized in that: The method comprises: Acquiring target data of a faulty vehicle, and determining an engine failure mode of the faulty vehicle based on the target data; Based on the engine failure mode and the target data, performing a failure mechanism analysis on the faulty vehicle to obtain an analysis result; Constructing a failure mechanism model of the engine according to the analysis results, and constructing a failure prediction model of the engine according to the failure mechanism model and the target data; Real-time operating data of a target vehicle is acquired, and dynamic fault prediction is performed on the engine of the target vehicle based on the real-time operating data of the target vehicle and a fault prediction model of the engine.

2. The method according to claim 1, characterized in that The failure mechanism analysis includes boundary analysis, functional analysis, interaction analysis, and parameter analysis. Based on the engine failure mode and the target data, the failure mechanism analysis is performed on the faulty vehicle to obtain analysis results, including: Determining a fault boundary of the faulty vehicle based on the engine failure mode and the target data; determining a target component of the faulty vehicle based on the fault boundary, and determining a functional role of the target component; Analyzing the interaction between the target components based on their functional roles, and identifying coupling paths between the target components; According to the coupling paths between the target components and the target data, key influencing parameters of the faulty vehicle are determined.

3. The method according to claim 2, characterized in that The failure mechanism model includes a low-cycle fatigue damage model, a high-cycle fatigue damage model, and a thermal-mechanical coupling damage model. The failure mechanism model of the engine is constructed according to the analysis results, including: Mapping the key influencing parameters of the faulty vehicle with low-cycle fatigue damage, high-cycle fatigue damage, and thermal-mechanical coupling damage to determine the key influencing parameters corresponding to each fatigue damage; Performing weight calibration on the influence degree of each key influencing parameter in the corresponding fatigue damage to obtain the weight value of each key influencing parameter in the corresponding fatigue damage; Based on the weight values of the key influencing parameters corresponding to the low-cycle fatigue damage, high-cycle fatigue damage and thermal-mechanical coupling damage respectively, a low-cycle fatigue damage model, a high-cycle fatigue damage model and a thermal-mechanical coupling damage model are determined.

4. The method according to claim 1, wherein The constructing of the engine fault prediction model according to the fault mechanism model and the target data includes: Determining a damage factor corresponding to the target data based on the target data of the faulty vehicle and the fault mechanism model; fusing the target data and its corresponding damage factors in time series to obtain a multi-dimensional time series input; The multi-dimensional time series input is used to train a neural network model to obtain the fault prediction model.

5. The method according to claim 1, wherein The engine failure mode includes a failure location classification and a failure phenomenon classification.

6. The method according to claim 1, characterized in that The target data of the faulty vehicle includes the Internet of Vehicles data and historical fault data of the faulty vehicle.

7. An engine failure prediction device, characterized in that: The device comprises: an acquisition module, configured to acquire target data of a faulty vehicle and determine an engine fault mode of the faulty vehicle based on the target data; an analysis module, configured to perform a failure mechanism analysis on the faulty vehicle based on the engine failure mode and the target data to obtain an analysis result; A construction module, configured to construct a failure mechanism model of the engine according to the analysis result, and to construct a failure prediction model of the engine according to the failure mechanism model and the target data; The prediction module obtains real-time operating data of the target vehicle and performs dynamic fault prediction on the engine of the target vehicle based on the real-time operating data of the target vehicle and the fault prediction model of the engine.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images