Vehicle engine stall risk prediction method, system and device and storage medium

Abstract

The invention discloses a vehicle engine stall risk prediction method, system and device and a storage medium. The method comprises the steps that environment temperature and humidity time series data, rainfall intensity time series data and vehicle speed time series data of a target vehicle are acquired; inputting the environment temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle; and warning a driver of the target vehicle according to the engine stall risk level. The stall risk level of the vehicle engine under various driving conditions can be predicted, so that a driver can be early warned in time, the driving safety is improved, and the method can be applied to the technical field of vehicles.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method, system, device and storage medium for predicting the stall risk of a vehicle engine. Background Art

[0002] In modern automotive technology, turbocharged engines are widely popular for their efficient power output and fuel economy. However, these engines present potential risks under certain conditions, such as driving in the rain. This is especially true after extended high-speed cruising. The sudden drop in temperature inside the intercooler can cause condensation to form. When this condensation accumulates to a certain level, it can be drawn into the engine, potentially causing a stall and seriously impacting driving safety and vehicle performance.

[0003] Traditionally, the primary approach to addressing this issue has been to verify engine performance under specific conditions through actual road testing. However, these tests suffer from uncontrollable environmental conditions, are time-consuming, and costly. Furthermore, they cannot fully assess engine performance in complex rainy conditions, and therefore cannot effectively assess the risk of engine stalling while driving.

[0004] The above problems need to be solved urgently. Summary of the Invention

[0005] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0006] To this end, an object of an embodiment of the present invention is to provide a vehicle engine stall risk prediction method, which can predict the stall risk level of the vehicle engine under various driving conditions, thereby providing timely warnings to the driver and improving driving safety.

[0007] Another object of an embodiment of the present invention is to provide a vehicle engine stall risk prediction system.

[0008] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0009] In a first aspect, an embodiment of the present invention provides a method for predicting a vehicle engine stall risk, comprising the following steps:

[0010] Obtaining the target vehicle's ambient temperature and humidity time series data, rainfall intensity time series data, and vehicle speed time series data;

[0011] Inputting the ambient temperature and humidity time series data, the rainfall intensity time series data, and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain the engine stall risk level of the target vehicle;

[0012] A warning is issued to the driver of the target vehicle according to the engine stall risk level.

[0013] Furthermore, in one embodiment of the present invention, the step of obtaining the target vehicle's ambient temperature and humidity time series data, rainfall intensity time series data, and vehicle speed time series data specifically includes:

[0014] Acquiring the temperature and humidity of the vehicle's external environment at various times through a temperature and humidity sensor disposed outside the target vehicle to obtain the ambient temperature and humidity time series data;

[0015] Acquiring rainfall intensity at various times in the vehicle's external environment by using a rain sensor disposed outside the target vehicle to obtain rainfall intensity time series data;

[0016] The vehicle speed of the target vehicle at each moment is acquired through the vehicle body controller to obtain the vehicle speed time series data.

[0017] Furthermore, in one embodiment of the present invention, the stall risk prediction model is trained by the following steps:

[0018] Determine the time series sample data of ambient temperature and humidity, rainfall intensity, and vehicle speed under the rotating hub test conditions;

[0019] Simulating the ambient temperature and humidity change curve of an actual vehicle usage scenario in a rotating hub test chamber according to the ambient temperature and humidity time series sample data;

[0020] Simulating a rainfall intensity variation curve of an actual vehicle use scenario in the hub test chamber according to the rainfall intensity time series sample data;

[0021] driving a wheel hub of a test vehicle on a rotating hub test bench according to the vehicle speed time series sample data to perform a rotating hub test on the test vehicle;

[0022] monitoring whether the engine of the test vehicle stalls during a throttle test and the duration of the stall test;

[0023] When the engine of the test vehicle does not stall during the turning test, a first training sample is determined based on the ambient temperature and humidity time series sample data, the rainfall intensity time series sample data, and the vehicle speed time series sample data, and a corresponding sample label is determined as no stall risk;

[0024] when the engine of the test vehicle stalls in the rolling test, the environment temperature and humidity time sequence sample data, the rainfall intensity time sequence sample data and the vehicle speed time sequence sample data are intercepted according to a first time length to obtain an environment temperature and humidity time sequence sample segment, a rainfall intensity time sequence sample segment and a vehicle speed time sequence sample segment, a second training sample is determined according to the environment temperature and humidity time sequence sample segment, the rainfall intensity time sequence sample segment and the vehicle speed time sequence sample segment, and a corresponding sample label is determined as stalling after the second time length, and the sum of the first time length and the second time length is equal to the test time length of stalling;

[0025] The plurality of first training samples and the plurality of second training samples are input into a pre-constructed CNN-LSTM hybrid neural network for training to obtain the trained stalling risk prediction model.

[0026] Further, in an embodiment of the present application, the CNN-LSTM hybrid neural network comprises an input layer, a CNN convolutional layer, a feature fusion layer, an LSTM layer, an attention layer and an output layer, the input layer is used for inputting training samples, the CNN convolutional layer is used for feature extraction of the training samples to obtain local time sequence features, the feature fusion layer is used for feature fusion of the local time sequence features to obtain fused time sequence features, the LSTM layer is used for generating a hidden state sequence according to the fused time sequence features, the attention layer is used for dynamic weight allocation of each dimension of the hidden state sequence based on a multi-head self-attention mechanism, and the output layer is used for mapping the hidden state sequence after dynamic weight allocation to a stalling risk prediction result.

[0027] Further, in an embodiment of the present application, the plurality of first training samples and the plurality of second training samples are input into a pre-constructed CNN-LSTM hybrid neural network for training to obtain the trained stalling risk prediction model, and the specific process comprises:

[0028] the first training sample / second training sample is input through the input layer;

[0029] the first training sample / second training sample is subjected to feature extraction through the CNN convolutional layer to obtain local time sequence features;

[0030] the local time sequence features are subjected to feature fusion through the feature fusion layer to obtain fused time sequence features;

[0031] a hidden state sequence is generated according to the fused time sequence features through the LSTM layer;

[0032] dynamic weight allocation of each dimension of the hidden state sequence is performed based on a multi-head self-attention mechanism through the attention layer.

[0033] mapping, by the output layer, the hidden state sequence after dynamic weight distribution into a stall risk prediction result;

[0034] determining a loss value according to the stall risk prediction result and the corresponding sample label;

[0035] updating parameters of the CNN-LSTM hybrid neural network according to the loss value through a back propagation algorithm to obtain a trained stall risk prediction model.

[0036] Further, in an embodiment of the present application, the environmental temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data are input into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle, which specifically comprises:

[0037] inputting the environmental temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data into the stall risk prediction model to obtain a stall risk prediction probability distribution of the target vehicle;

[0038] determining a plurality of predicted time lengths and corresponding stall probabilities from engine stall according to the stall risk prediction probability distribution;

[0039] weighting and summing the predicted time lengths according to the stall probabilities to obtain an average predicted time length from engine stall;

[0040] determining the engine stall risk level of the target vehicle according to the average predicted time length;

[0041] wherein the engine stall risk level and the average predicted time length are in a negative correlation.

[0042] Further, in an embodiment of the present application, the driver of the target vehicle is warned according to the engine stall risk level, which specifically comprises:

[0043] determining a warning level according to the engine stall risk level, and generating corresponding warning prompt information according to the warning level;

[0044] warning the driver of the target vehicle according to the warning level, and playing the warning prompt information.

[0045] In a second aspect, an embodiment of the present application provides a vehicle engine stall risk prediction system, comprising:

[0046] a data acquisition module configured to acquire environmental temperature and humidity time series data, rainfall intensity time series data and vehicle speed time series data of a target vehicle;

[0047] a stall risk prediction module, configured to input the ambient temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle;

[0048] a warning module, configured to warn a driver of the target vehicle according to the engine stall risk level.

[0049] In a third aspect, an embodiment of the present application provides a vehicle engine stall risk prediction device, comprising:

[0050] at least one processor;

[0051] at least one memory configured to store at least one program;

[0052] When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle engine stall risk prediction method.

[0053] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a processor executable program, and the processor executable program is used to execute the vehicle engine stall risk prediction method when executed by a processor.

[0054] The advantages and beneficial effects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present application:

[0055] The embodiment of the present application obtains the ambient temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data of the target vehicle, inputs the ambient temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle, and warns a driver of the target vehicle according to the engine stall risk level. The embodiment of the present application predicts the engine stall risk based on the ambient temperature and humidity time series data, the rainfall intensity time series data, the vehicle speed time series data and the pre-trained stall risk prediction model of the target vehicle, can predict the stall risk level of the vehicle engine under various driving conditions, and thus can timely warn the driver, thereby improving the driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following introduces the drawings needed to be used in the embodiments of the present application. It should be understood that the drawings introduced in the following are only for facilitating the clear description of the technical solutions in some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without paying any creative labor.

[0057] Figure 1 A step flow chart of a vehicle engine stall risk prediction method provided by the embodiment of the present application is provided.

[0058] Figure 2 A test scene schematic diagram of a rotating hub test provided by the embodiment of the present application is provided.

[0059] Figure 3 A structure schematic diagram of a CNN-LSTM hybrid neural network provided by the embodiment of the present application is provided.

[0060] Figure 4 A structure block diagram of a vehicle engine stall risk prediction system provided by the embodiment of the present application is provided.

[0061] Figure 5 A structure block diagram of a vehicle engine stall risk prediction device provided by the embodiment of the present application is provided. DETAILED DESCRIPTION

[0062] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for facilitating the description and explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0063] In the description of the present application, the meaning of multiple is two or more, and if the first, the second is described, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the sequence of indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art.

[0064] With reference to Figure 1 The embodiment of the present application provides a vehicle engine stall risk prediction method, which specifically comprises the following steps:

[0065] S101, acquire environment temperature and humidity time series data, rainfall intensity time series data and vehicle speed time series data of the target vehicle;

[0066] S102, input the environment temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle;

[0067] S103, warn the driver of the target vehicle according to the engine stall risk level.

[0068] The embodiment of the application can predict the stall risk level of the engine of the vehicle under various driving conditions, so as to timely warn the driver and improve the driving safety.

[0069] Further, as an optional implementation, the environment temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data of the target vehicle are acquired, which specifically include:

[0070] S1011, acquire the temperature and humidity of the external environment of the vehicle at each time point through a temperature and humidity sensor arranged outside the target vehicle to obtain the environment temperature and humidity time series data;

[0071] S1012, acquire the rainfall intensity of the external environment of the vehicle at each time point through a rainfall sensor arranged outside the target vehicle to obtain the rainfall intensity time series data;

[0072] S1013, acquire the vehicle speed of the target vehicle at each time point through a body controller to obtain the vehicle speed time series data.

[0073] Further, as an optional implementation, the stall risk prediction model is trained through the following steps:

[0074] S201, determine environment temperature and humidity time series sample data, rainfall intensity time series sample data and vehicle speed time series sample data under a hub test condition;

[0075] S202, simulate the environment temperature and humidity change curve of the actual vehicle scene in the hub test room according to the environment temperature and humidity time series sample data;

[0076] S203, simulate the rainfall intensity change curve of the actual vehicle scene in the hub test room according to the rainfall intensity time series sample data;

[0077] S204, drive the hub of the test vehicle on the hub test bench according to the vehicle speed time series sample data to perform hub test on the test vehicle;

[0078] S205, monitoring whether the engine of the test vehicle stalls in the test and the test duration of the stall;

[0079] S206, when the engine of the test vehicle does not stall in the test, determining a first training sample according to the environmental temperature and humidity time sequence sample data, the rainfall intensity time sequence sample data and the vehicle speed time sequence sample data, and determining the corresponding sample label as no stall risk;

[0080] S207, when the engine of the test vehicle stalls in the test, the environmental temperature and humidity time sequence sample data, the rainfall intensity time sequence sample data and the vehicle speed time sequence sample data are respectively intercepted according to the first duration, and the environmental temperature and humidity time sequence sample segment, the rainfall intensity time sequence sample segment and the vehicle speed time sequence sample segment are obtained, the second training sample is determined according to the environmental temperature and humidity time sequence sample segment, the rainfall intensity time sequence sample segment and the vehicle speed time sequence sample segment, and the corresponding sample label is determined as stall after the second duration, the sum of the first duration and the second duration is equal to the test duration of the stall;

[0081] S208, inputting the plurality of first training samples and the plurality of second training samples into the pre-constructed CNN-LSTM hybrid neural network for training to obtain the trained stall risk prediction model.

[0082] As Figure 2 shown is a test scene schematic diagram of the test of the embodiment of the present application, and the test process of the test of the embodiment of the present application will be described below: Figure 2

[0083] 1) environmental simulation device setting: in the test room, specific environmental temperature and humidity changes are set to simulate the environmental conditions in the actual driving scene.

[0084] ① set the environmental temperature in the range of T env ±t℃, and the relative humidity in the range of RH% (T env is the highest temperature in rainy weather, t is the preset temperature change amplitude, and RH% is the highest humidity in rainy weather).

[0085] ② install a device with adjustable water spraying amount and water spraying height at the vehicle head to simulate rainfall amount and rainfall intensity at different times.

[0086] 2) test preparation steps:

[0087] ① place the vehicle on the test bench, and complete the centering and fixing of the wheels.

[0088] ② warm up the vehicle until the engine water temperature reaches T eng ℃ (T eng ​For engine hot state water temperature.

[0089] ③ Input the set vehicle road resistance curve into the hub test bench to ensure the simulation of real-world scenarios.

[0090] 3) Test process steps (using a specific vehicle speed time series sample data as an example):

[0091] ① Set the hub to resistance mode, and let the vehicle run at idle speed for T idle minutes (T idle is defined according to the engine state, ensuring smooth engine operation).

[0092] ② Simulate long-time high-speed cruising, set a specific vehicle speed V crs (km / h) and duration T crs (hours) (V crs is the vehicle speed most likely to cause water accumulation in the intercooler; T rcs is the time for the water accumulation in the intercooler to reach equilibrium).

[0093] ③ Operate the vehicle to perform full throttle acceleration test until the vehicle speed exceeds the preset speed V max , and maintain for T seconds, then slowly reduce the speed to the cruising speed (V max is the maximum speed during overtaking; T is the time for continuous driving after overtaking).

[0094] ④ Simultaneously record the vehicle instrument fault light status and engine data, especially the engine misfire signal.

[0095] 4) Data analysis and judgment:

[0096] ① Analyze the status change of the vehicle instrument fault light during acceleration.

[0097] ② Collect and analyze engine data, focusing on the engine misfire signal.

[0098] ③ Determine whether the engine has stalled by analyzing the changes in fault light status and engine data.

[0099] 5) Repeat the test and determine the sample:

[0100] ① Repeat the above test process multiple times (each time using different environmental temperature and humidity time series sample data, rainfall intensity time series sample data, and vehicle speed time series sample data) to ensure the diversity of training samples.

[0101] ② Determine multiple training samples based on the results of multiple tests. Specifically, when the engine of the test vehicle does not stall during the transition test, the first training sample is determined based on the ambient temperature and humidity time series sample data, the rainfall intensity time series sample data, and the vehicle speed time series sample data, and the corresponding sample label is determined as no stall risk; when the engine of the test vehicle stalls during the transition test, assuming that the stall test duration is 1 hour, the ambient temperature and humidity time series sample data, the rainfall intensity time series sample data, and the vehicle speed time series sample data can be respectively intercepted based on 55 minutes to obtain the ambient temperature and humidity time series sample segments, the rainfall intensity time series sample segments, and the vehicle speed time series sample segments. The second training sample is determined based on the ambient temperature and humidity time series sample segments, the rainfall intensity time series sample segments, and the vehicle speed time series sample segments, and the corresponding sample label is determined as "stall occurs after 5 minutes." It should be noted that the above-mentioned time lengths for intercepting the ambient temperature and humidity time series sample data, rainfall intensity time series sample data, and vehicle speed time series sample data are only examples. During implementation, different proportions of the test time can be selected for interception to ensure sample diversity.

[0102] Through the above-mentioned rotating hub test, the embodiment of the present invention can accurately simulate actual vehicle usage scenarios under laboratory conditions and comprehensively evaluate the stability of the engine in complex rainy environments, thereby obtaining a sufficient number of training samples for training the stall risk prediction model, thereby effectively preventing engine stall caused by condensed water and ensuring the safe and reliable operation of the vehicle in various weather conditions.

[0103] Further as an optional implementation, the CNN-LSTM hybrid neural network includes an input layer, a CNN convolution layer, a feature fusion layer, an LSTM layer, an attention layer and an output layer. The input layer is used to input training samples, the CNN convolution layer is used to extract features of the training samples to obtain local time series features, the feature fusion layer is used to fuse the local time series features to obtain fused time series features, the LSTM layer is used to generate a hidden state sequence based on the fused time series features, the attention layer is used to dynamically assign weights to each dimension of the hidden state sequence based on a multi-head self-attention mechanism, and the output layer is used to map the hidden state sequence after dynamic weight assignment to a stall risk prediction result.

[0104] Specifically, if Figure 3The figure shows the structure of the CNN-LSTM hybrid neural network provided by an embodiment of the present invention. The input data is standardized through the input layer and then input into the CNN convolution layer. The local time series features are extracted using a one-dimensional convolution kernel. The extracted local time series features are subjected to the feature fusion operation of the feature fusion layer to generate fused time series features. The fused time series features are then used as the feature input of the LSTM layer to capture long-term dependencies and generate a hidden state sequence. Then, based on the multi-head self-attention mechanism, the attention weight is calculated through the SoftMax function, and the various dimensions of the hidden state sequence output by the LSTM layer are dynamically weighted. The hidden state sequence after dynamic weight allocation by the output layer is mapped to the stall risk prediction result. The loss value is then determined in combination with the corresponding sample label. The loss value is back-propagated using the Adam algorithm, and the model parameters are gradually updated layer by layer. The loss function can adopt binary cross entropy or weighted loss function (to address data imbalance).

[0105] As an optional implementation, multiple first training samples and multiple second training samples are input into a pre-built CNN-LSTM hybrid neural network for training to obtain a trained stall risk prediction model, which specifically includes:

[0106] S2081. Input the first training sample / the second training sample through the input layer;

[0107] S2082. Perform feature extraction on the first training sample / the second training sample through a CNN convolutional layer to obtain a local temporal feature;

[0108] S2083. Perform feature fusion on the local time series features through a feature fusion layer to obtain a fused time series feature;

[0109] S2084, generating a hidden state sequence based on the fused time series features through the LSTM layer;

[0110] S2085. Dynamically assign weights to each dimension of the hidden state sequence based on the multi-head self-attention mechanism through the attention layer;

[0111] S2086. Mapping the hidden state sequence after dynamic weight allocation to a stall risk prediction result through the output layer;

[0112] S2087. Determine a loss value based on the stall risk prediction result and the corresponding sample label;

[0113] S2088. Update the parameters of the CNN-LSTM hybrid neural network using the back propagation algorithm based on the loss value to obtain a trained stall risk prediction model.

[0114] Specifically, the first training sample and the second training sample are input into the pre-constructed CNN-LSTM hybrid neural network to obtain a stall risk prediction result, a loss value is determined according to the stall risk prediction result and a corresponding sample label by using a preset loss function, and then parameters of the CNN-LSTM hybrid neural network are updated based on the loss value by using a back propagation algorithm, so that a trained stall risk prediction model is obtained after a preset number of iterations or the loss value reaches a preset threshold or an accuracy on a validation set reaches a preset threshold.

[0115] Further, as an optional implementation, the environmental temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data are input into the pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle, which specifically includes:

[0116] S1021, the environmental temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data are input into the stall risk prediction model to obtain a stall risk prediction probability distribution of the target vehicle;

[0117] S1022, a plurality of prediction time lengths and corresponding stall probabilities of the target vehicle from the engine stall are determined according to the stall risk prediction probability distribution;

[0118] S1023, the prediction time lengths are weighted and summed according to the stall probabilities to obtain an average prediction time length from the engine stall;

[0119] S1024, the engine stall risk level of the target vehicle is determined according to the average prediction time length;

[0120] Wherein, the engine stall risk level and the average prediction time length are in a negative correlation.

[0121] Specifically, the ambient temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data of the target vehicle are input into the stall risk prediction model, and the stall risk prediction probability distribution of the target vehicle is obtained. As known from the foregoing model training process, the time length information (for example, "stall occurs after 5 minutes") is introduced when determining the sample label, and therefore the stall risk prediction probability distribution includes a plurality of prediction time lengths and corresponding stall probabilities from the occurrence of engine stall, for example, {(5min, 30%), (10min, 60%), (20min, 10%)}. The prediction time lengths are weighted and summed according to the stall probabilities, and the average prediction time length from the occurrence of engine stall is obtained. Taking {(5min, 30%), (10min, 60%), (20min, 10%)} as an example, the finally calculated average prediction time length from the occurrence of engine stall is 9.5min. The engine stall risk level of the target vehicle is determined according to the average prediction time length. For example, a plurality of engine stall risk levels are divided according to different time length ranges in advance. When the average prediction time length is in (0, 1min], the engine stall risk level is the highest (emergency), when the average prediction time length is in (1min, 3min], the engine stall risk level is the second (important), when the average prediction time length is in (3min, 10min], the engine stall risk level is the third (ordinary), and when the average prediction time length is greater than 10min, the engine stall risk level is the lowest (mild).

[0122] Further as an optional implementation, the driver of the target vehicle is warned according to the engine stall risk level, which specifically includes:

[0123] S1031, determining a warning level according to the engine stall risk level, and generating corresponding warning prompt information according to the warning level;

[0124] S1032, warning the driver of the target vehicle according to the warning level, and playing the warning prompt information.

[0125] Specifically, a plurality of corresponding warning levels are determined according to different engine stall risk levels in advance, and different warning levels are configured with corresponding warning prompt information templates. After the engine stall risk level is determined, the warning level is determined according to the engine stall risk level, and the corresponding warning prompt information is generated according to the warning level. Then, the driver of the target vehicle is warned according to the warning level, and the warning prompt information is played. For example, when the engine stall risk level is ordinary risk, the corresponding warning level can be determined as ordinary warning, and the ordinary warning can be displayed through the preset indicator light or display screen, and the prompt information "the vehicle has stall risk, please drive at a slow speed" is played.

[0126] The method steps of the embodiment of the present application are described above. It can be recognized that the embodiment of the present application predicts the engine stall risk based on the environment temperature and humidity time series data, the rainfall intensity time series data, the vehicle speed time series data of the target vehicle and the pre-trained stall risk prediction model, can predict the stall risk level of the vehicle engine under various driving conditions, so as to timely warn the driver and improve the driving safety.

[0127] With reference to Figure 4 The embodiment of the present application provides a vehicle engine stall risk prediction system, comprising:

[0128] A data acquisition module is configured to acquire environment temperature and humidity time series data, rainfall intensity time series data and vehicle speed time series data of a target vehicle.

[0129] A stall risk prediction module is configured to input the environment temperature and humidity time series data, the rainfall intensity time series data and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle.

[0130] A warning module is configured to warn a driver of the target vehicle according to the engine stall risk level.

[0131] The contents in the above method embodiment are applicable to the system embodiment, the system embodiment specifically realizes the same functions as the above method embodiment, and achieves the same beneficial effects as the above method embodiment.

[0132] With reference to Figure 5 The embodiment of the present application provides a vehicle engine stall risk prediction device, comprising:

[0133] At least one processor;

[0134] At least one memory configured to store at least one program;

[0135] When the above at least one program is executed by the above at least one processor, the above at least one processor realizes the above vehicle engine stall risk prediction method.

[0136] The contents in the above method embodiment are applicable to the device embodiment, the device embodiment specifically realizes the same functions as the above method embodiment, and achieves the same beneficial effects as the above method embodiment.

[0137] The embodiment of the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a program executable by a processor, and the program executable by the processor is used to execute the above vehicle engine stall risk prediction method when executed by the processor.

[0138] The computer readable storage medium of the embodiment of the present application can execute the vehicle engine stall risk prediction method provided by the method embodiment of the present application, and can execute the step of any combination of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0139] The embodiment of the present application also discloses a computer program product or a computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the method shown in the embodiment of the present application. Figure 1 The method shown in the embodiment of the present application.

[0140] In some alternative embodiments, the functions / operations mentioned in the block diagram can not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two blocks shown in succession can actually be executed substantially simultaneously or the above blocks can be executed in reverse order at times. In addition, the embodiments presented and described in the flowcharts of the present application are provided by way of example, and the purpose is to provide a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are independently executed.

[0141] In addition, although the present application is described in the context of functional modules, it should be understood that one or more of the above functions and / or features can be integrated in a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules, unless otherwise specified. It can also be understood that detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. Rather, given the properties, functions and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skill of an engineer. Therefore, those skilled in the art can implement the present application as set forth in the claims without undue experimentation using ordinary skill. It can also be understood that the disclosed specific concepts are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.

[0142] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or parts of the technical solutions that essentially contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described above in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0143] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or in conjunction with these instructions execution systems, apparatus or devices. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by or in connection with an instruction execution system, apparatus or device, or in conjunction with these instruction execution systems, apparatus or devices.

[0144] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the above programs are printed, because the programs can be obtained electronically, for example, by optical scanning of the paper or other medium, followed by editing, interpreting or otherwise processing, if necessary, in other suitable ways, to be electronically obtained and then stored in the computer memory.

[0145] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0146] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0147] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0148] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for predicting the risk of a vehicle engine stall, characterized in that: The following steps are involved: Obtaining the target vehicle's ambient temperature and humidity time series data, rainfall intensity time series data, and vehicle speed time series data; Inputting the ambient temperature and humidity time series data, the rainfall intensity time series data, and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain the engine stall risk level of the target vehicle; A warning is issued to the driver of the target vehicle according to the engine stall risk level.

2. A vehicle engine stall risk prediction method according to claim 1, characterized in that: The step of obtaining the target vehicle's ambient temperature and humidity time series data, rainfall intensity time series data, and vehicle speed time series data specifically includes: Acquiring the temperature and humidity of the vehicle's external environment at various times through a temperature and humidity sensor disposed outside the target vehicle to obtain the ambient temperature and humidity time series data; Acquiring rainfall intensity at various times in the vehicle's external environment by using a rain sensor disposed outside the target vehicle to obtain rainfall intensity time series data; The vehicle speed of the target vehicle at each moment is acquired through the vehicle body controller to obtain the vehicle speed time series data.

3. The method for predicting the risk of a vehicle engine stall according to claim 1, wherein: The stall risk prediction model is trained by the following steps: Determine the time series sample data of ambient temperature and humidity, rainfall intensity, and vehicle speed under the rotating hub test conditions; Simulating the ambient temperature and humidity change curve of an actual vehicle usage scenario in a rotating hub test chamber according to the ambient temperature and humidity time series sample data; Simulating a rainfall intensity variation curve of an actual vehicle use scenario in the hub test chamber according to the rainfall intensity time series sample data; driving a wheel hub of a test vehicle on a rotating hub test bench according to the vehicle speed time series sample data to perform a rotating hub test on the test vehicle; monitoring whether the engine of the test vehicle stalls during a throttle test and the duration of the stall test; When the engine of the test vehicle does not stall during the turning test, a first training sample is determined based on the ambient temperature and humidity time series sample data, the rainfall intensity time series sample data, and the vehicle speed time series sample data, and a corresponding sample label is determined as no stall risk; When the engine of the test vehicle stalls during a throttle test, the ambient temperature and humidity time series sample data, the rainfall intensity time series sample data, and the vehicle speed time series sample data are respectively intercepted according to a first duration to obtain ambient temperature and humidity time series sample segments, rainfall intensity time series sample segments, and vehicle speed time series sample segments; a second training sample is determined based on the ambient temperature and humidity time series sample segments, the rainfall intensity time series sample segments, and the vehicle speed time series sample segments, and a corresponding sample label is determined as stalling after a second duration, and the sum of the first duration and the second duration is equal to the test duration during which the stall occurs; Inputting a plurality of the first training samples and a plurality of the second training samples into a pre-built CNN-LSTM hybrid neural network for training, thereby obtaining the trained stall risk prediction model.

4. A vehicle engine stall risk prediction method according to claim 3, characterized in that: The CNN-LSTM hybrid neural network includes an input layer, a CNN convolutional layer, a feature fusion layer, an LSTM layer, an attention layer and an output layer. The input layer is used to input training samples. The CNN convolutional layer is used to extract features from the training samples to obtain local time series features. The feature fusion layer is used to fuse the local time series features to obtain fused time series features. The LSTM layer is used to generate a hidden state sequence based on the fused time series features. The attention layer is used to dynamically assign weights to each dimension of the hidden state sequence based on a multi-head self-attention mechanism. The output layer is used to map the hidden state sequence after dynamic weight assignment into a stall risk prediction result.

5. The method for predicting the risk of a vehicle engine stall according to claim 4, characterized in that: Inputting the plurality of first training samples and the plurality of second training samples into a pre-built CNN-LSTM hybrid neural network for training to obtain the trained stall risk prediction model specifically includes: Input the first training sample / the second training sample through the input layer; Performing feature extraction on the first training sample / the second training sample through the CNN convolutional layer to obtain local temporal features; Performing feature fusion on the local time series features through the feature fusion layer to obtain fused time series features; Generate a hidden state sequence according to the fused time series features through the LSTM layer; Dynamically weighting each dimension of the hidden state sequence based on a multi-head self-attention mechanism through the attention layer; Mapping the hidden state sequence after dynamic weight allocation into a stall risk prediction result through the output layer; Determine a loss value according to the stall risk prediction result and the corresponding sample label; The parameters of the CNN-LSTM hybrid neural network are updated according to the loss value through a back propagation algorithm to obtain the trained stall risk prediction model.

6. The method for predicting the risk of a vehicle engine stall according to claim 1, characterized in that: The step of inputting the ambient temperature and humidity time series data, the rainfall intensity time series data, and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain the engine stall risk level of the target vehicle specifically includes: Inputting the ambient temperature and humidity time series data, the rainfall intensity time series data, and the vehicle speed time series data into the stall risk prediction model to obtain a stall risk prediction probability distribution of the target vehicle; Determining a plurality of predicted time periods until the engine stalls and corresponding stall probabilities according to the stall risk prediction probability distribution; Performing a weighted summation of the predicted durations according to the stall probability to obtain an average predicted duration until the engine stalls; determining an engine stall risk level of the target vehicle according to the average predicted duration; The engine stall risk level is negatively correlated with the average predicted duration.

7. A vehicle engine stall risk prediction method according to any one of claims 1 to 6, characterized in that: The step of providing an early warning to the driver of the target vehicle according to the engine stall risk level specifically includes: Determining a warning level according to the engine stall risk level, and generating corresponding warning prompt information according to the warning level; The driver of the target vehicle is warned according to the warning level, and the warning prompt information is broadcast.

8. A vehicle engine stall risk prediction system, characterized in that: include: A data acquisition module is used to obtain the target vehicle's ambient temperature and humidity time series data, rainfall intensity time series data, and vehicle speed time series data; a stall risk prediction module, configured to input the ambient temperature and humidity time series data, the rainfall intensity time series data, and the vehicle speed time series data into a pre-trained stall risk prediction model to obtain an engine stall risk level of the target vehicle; The early warning module is used to warn the driver of the target vehicle according to the engine stall risk level.

9. A vehicle engine stall risk prediction device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle engine stall risk prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to execute a vehicle engine stall risk prediction method according to any one of claims 1 to 7 when executed by the processor.

Images