Engine oil life detection method and device, vehicle diagnosis equipment and storage medium

Abstract

The invention relates to the technical field of vehicle diagnosis, and discloses an engine oil service life detection method and device, vehicle diagnosis equipment and a storage medium, and the engine oil service life detection method comprises the steps: obtaining a state collection result of target vehicle engine oil flowing through a transparent guide rail to determine state detection data, and obtaining an engine oil type adaptive to a target vehicle; inputting the state detection data and the engine oil type into an engine oil life detection model to obtain a detection result of the engine oil remaining life of the target vehicle; and feeding back the detection result of the engine oil remaining life to the user terminal. The engine oil state can be comprehensively and accurately detected, the method adapts to various complex working conditions, the engine oil remaining life is comprehensively analyzed through the pre-trained engine oil life detection model, the result more accurate than that of a traditional method is provided, professional equipment and complex operation are not needed, and the method is suitable for daily use of common users.

Description

Technical Field

[0001] This application relates to the technical field of vehicle diagnosis, and particularly to an oil life detection method and device thereof, a vehicle diagnosis device, and a storage medium. Background Art

[0002] During the use of an automobile, engine oil plays a crucial role in the normal operation of the engine, and its performance state directly affects the service life of the engine and the overall performance of the vehicle. At present, there are many deficiencies in common oil life detection methods. On the one hand, it is difficult to accurately judge the actual state of the engine oil, resulting in premature or delayed replacement of the engine oil, which not only causes waste of resources but also increases the risk of engine wear. On the other hand, the process of detecting the state of the engine oil is cumbersome, requires professional operation, and has high costs, and is not suitable for daily vehicle use and maintenance scenarios. Summary of the Invention

[0003] In view of this, embodiments of this application provide an oil life detection method and device thereof, a vehicle diagnosis device, and a storage medium, which can effectively solve the problems of inaccurate oil life detection and high costs.

[0004] In a first aspect, embodiments of this application provide an oil life detection method, including: Obtaining a state acquisition result of the engine oil of a target vehicle flowing through a transparent guide rail to determine state detection data, and obtaining the type of engine oil adapted to the target vehicle; Inputting the state detection data and the type of engine oil into an oil life detection model to obtain a detection result of the remaining life of the engine oil of the target vehicle; Feeding back the detection result of the remaining life of the engine oil to a user terminal.

[0005] In a first possible embodiment of the first aspect, a plurality of groups of light transmittance detection devices are arranged on both sides of the track of the transparent guide rail, the state detection data includes the light transmittance of the engine oil and the flow velocity, and obtaining a state acquisition result of the engine oil of a target vehicle flowing through a transparent guide rail to determine state detection data includes: Obtaining the light intensity of the light passing through the engine oil of the target vehicle collected by the light transmittance detection device, and determining the light transmittance of the engine oil according to the light intensity; Obtaining the flow-through time of the engine oil of the target vehicle recorded by each group of the light transmittance detection devices; Determining the flow velocity of the engine oil of the target vehicle according to the distance between the light transmittance detection devices and the flow-through time.

[0006] In a second possible embodiment of the first aspect, a temperature sensor and a conductivity sensor are further respectively arranged at the output end of the transparent guide rail, the state detection data includes the oil temperature and the oil conductivity, and obtaining the state acquisition result of the target vehicle oil flowing through the transparent guide rail to determine the state detection data includes: Obtaining the temperature acquisition result of the target vehicle oil by the temperature sensor to determine the oil temperature; Obtaining the conductivity acquisition result of the target vehicle oil by the conductivity sensor to determine the oil conductivity.

[0007] In a third possible embodiment of the first aspect, the target vehicle is connected to the communication interface of the vehicle diagnostic device, and the method further includes: Obtaining the state acquisition result and the oil type through the communication interface, and uploading the determined state detection data and the oil type to the database for storage; Uploading the detection result of the remaining oil life to the user terminal through the communication interface.

[0008] In a fourth possible embodiment of the first aspect, the pre-training process of the oil life detection model includes: Establishing a data set including historical state detection data of different types of oil and the corresponding remaining oil life; Selecting a basic model according to the data set and the oil life prediction target and building the structure of the basic model; Training the model based on the data set, and using the trained model as the oil life detection model.

[0009] In a fifth possible embodiment of the first aspect, the structure of the basic model includes an input layer, a hidden layer and an output layer. Selecting a basic model according to the data set and the oil life prediction target and building the structure of the basic model includes: Selecting a deep neural network model as the basic model; Determining the dimension of the input layer based on the historical state detection data and the oil type; Adjusting the number of layers of the hidden layer and the number of neurons in each hidden layer according to the change of the oil type; Taking the oil life prediction target as the output target of the output layer.

[0010] In a second aspect, an embodiment of the present application provides an oil life detection device, including: A transparent guide rail for introducing the target vehicle oil from the input end; Multiple groups of light transmittance detection devices are respectively arranged on both sides of the transparent guide rail, used to collect the light intensity of the engine oil of the target vehicle flowing through, and record the time when the engine oil of the target vehicle flows through; A temperature sensor is arranged at the output end of the transparent guide rail, used to collect the engine oil temperature; A conductivity sensor is arranged at the output end of the transparent guide rail, used to collect the engine oil conductivity; A vehicle diagnostic device is used for the above-mentioned engine oil life detection method.

[0011] In the first possible embodiment of the second aspect, each group of the light transmittance detection devices includes a light source and a photosensitive sensor, and the light source and the photosensitive sensor are respectively arranged on both sides of the transparent guide rail.

[0012] In a third aspect, an embodiment of the present application provides a vehicle diagnostic device, which includes a processor and a memory. The memory stores a computer program, and the processor is used to execute the computer program to implement the above-mentioned engine oil life detection method.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed on a processor, the above-mentioned engine oil life detection method is implemented.

[0014] The embodiments of the present application have the following beneficial effects: An engine oil life detection method in this embodiment includes: obtaining the state acquisition result of the engine oil of the target vehicle flowing through the transparent guide rail to determine the state detection data, and obtaining the engine oil type suitable for the target vehicle; inputting the state detection data and the engine oil type into the engine oil life detection model to obtain the detection result of the remaining life of the engine oil of the target vehicle; feeding back the detection result of the remaining life of the engine oil to the user terminal. The present application can comprehensively detect the engine oil state, adapt to various complex working conditions, use the pre-trained engine oil life detection model to comprehensively analyze the remaining life of the engine oil, provide more accurate results than traditional methods, and does not require professional equipment and complex operations, making it suitable for daily use by ordinary users. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, so they should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0016] Figure 1 Shows a frame scenario diagram of the engine oil life detection device in the embodiment of the present application; Figure 2 Figure 1 shows a first schematic flow diagram of the engine oil life detection method according to an embodiment of the present application; Figure 3 Figure 2 shows a second schematic flow diagram of the engine oil life detection method according to an embodiment of the present application.

[0017] Description of main component symbols: 100 - Engine oil life detection device; 110 - Transparent guide rail; 120 - Light transmittance detection device; 121 - Light source; 122 - Photosensitive sensor; 130 - Temperature sensor; 140 - Conductivity sensor; 150 - Vehicle diagnostic device; 151 - Communication interface. Detailed implementation manners

[0018] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0019] Generally, the components of the embodiments of the present application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0020] In the following, the terms "include", "have" and their cognates that can be used in various embodiments of the present application are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence or addition of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0021] Unless otherwise defined, all terms (including technical terms and scientific terms) used here have the same meaning as commonly understood by those of ordinary skill in the art to which the various embodiments of the present application belong. Terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0022] The following will describe in detail some embodiments of the present application in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0023] There are many deficiencies in traditional engine oil life detection methods. For example, the traditional method of replacing engine oil based on fixed mileage does not fully consider the impact of various factors such as engine working mode, model, user driving habits, and driving road conditions on the engine oil life. This may lead to premature replacement of engine oil, resulting in waste of resources and increased maintenance costs. Or, it may lead to delayed replacement of engine oil, resulting in a decline in engine oil performance and an increased risk of engine wear. The method of using an engine oil test strip to detect the impurity content of engine oil can only roughly judge the situation of some impurities in the engine oil, and cannot effectively reflect problems such as deterioration and thinning of engine oil caused by high temperature, oxidation, etc., and cannot comprehensively evaluate the overall state of engine oil. Moreover, although professional instrument chemical detection is accurate, the detection process is cumbersome, the operation requirements are high, complex instruments must be operated by professional personnel, it is difficult for ordinary users to complete it by themselves, the detection cost is relatively high, it is not suitable for the need to frequently monitor the engine oil state, and it is difficult to meet the requirements of real-time monitoring and daily vehicle maintenance scenarios.

[0024] In view of the above problems, the present application provides an engine oil life detection method, its device, a vehicle diagnostic device, and a storage medium, which comprehensively consider various factors and detect the state of the engine oil of the target vehicle, and provide an accurate, convenient, and low-cost engine oil life detection solution.

[0025] First, an embodiment of the present application provides an engine oil life detection device 100. The engine oil life detection device 100 includes a transparent guide rail 110, multiple groups of light transmittance detection devices 120, a temperature sensor 130, a conductivity sensor 140, and a vehicle diagnostic device 150. Among them, each group of light transmittance detection devices 120 is respectively arranged on both sides of the transparent guide rail 110, the temperature sensor 130 and the conductivity sensor 140 are respectively arranged at the output end of the transparent guide rail 110, and the vehicle diagnostic device 150 can be directly or indirectly electrically connected to multiple groups of light transmittance detection devices 120, the temperature sensor 130, and the conductivity sensor 140 to realize data transmission and interaction. For example, these components can be electrically connected to each other through a bus and / or signal lines.

[0026] In this embodiment, the input end of the transparent guide rail 110 is used to introduce the engine oil of the target vehicle. Each group of light transmittance detection devices 120 is used to collect the light intensity of the engine oil of the target vehicle flowing through, and record the time when the engine oil of the target vehicle flows through. The temperature sensor 130 is used to collect the engine oil temperature, and the conductivity sensor 140 is used to collect the engine oil conductivity. The transparent guide rail 110 can be a transparent glass rail, which is not limited here.

[0027] The vehicle diagnostic device 150 can process information and / or data related to the engine oil life detection method to perform one or more functions described in this application. The vehicle diagnostic device 150 is used to obtain the status collection result of the engine oil of the target vehicle in the transparent guide rail 110 to determine the status detection data, and obtain the engine oil type suitable for the target vehicle; input the status detection data and the engine oil type into a pre-trained engine oil life detection model; obtain the detection result of the remaining life of the engine oil of the target vehicle by the engine oil life detection model; and feedback the detection result of the remaining life of the engine oil to the user terminal. The user terminal is used to display the detection result of the remaining life of the engine oil and input the engine oil type suitable for the target vehicle.

[0028] In one embodiment, the target vehicle is connected to the communication interface 151 of the vehicle diagnostic device 150. The vehicle diagnostic device 150 is used to obtain the status collection result and the engine oil type through the communication interface 151, and upload the determined status detection data and the engine oil type to the database for storage; upload the detection result of the remaining life of the engine oil to the user terminal through the communication interface 151.

[0029] In one implementation manner, the communication interface 151 can be an in-vehicle OBD (On-Board Diagnostics) communication interface. The in-vehicle OBD communication interface is a standard diagnostic interface in an automobile and can provide various operating parameters and configuration information of the vehicle. In this application, the vehicle diagnostic device 150 obtains the collection results of multiple groups of light transmittance detection devices 120, temperature sensors 130, and conductivity sensors 140 through the in-vehicle OBD communication interface, and obtains the vehicle configuration information stored in the ECU, including the engine oil type currently suitable for the target vehicle. The user can input the engine oil type on the user terminal, and the vehicle diagnostic device 150 can obtain the engine oil type input by the user through the in-vehicle OBD communication interface.

[0030] Among them, the engine oil type includes the engine oil brand and engine oil parameters. For example, the engine oil parameters of a certain type of engine oil include 5W-30, 5W-40, and 0W-40, etc. Among them, 5W and 0W represent the low-temperature fluidity index. W represents the flow performance of the engine oil under low-temperature conditions. The smaller the number, the better the fluidity of the engine oil in a low-temperature environment, and it can lubricate the key components of the engine faster during cold start.

[0031] In one embodiment, each light transmittance detection device 120 includes a light source 121 and a photosensitive sensor 122, which are respectively arranged on both sides of the transparent guide rail 110. The transparent guide rail 110 is a transparent channel through which the engine oil flows, ensuring that light can pass through the engine oil; the light source 121 is used to emit light of a specific wavelength, and the photosensitive sensor 122 is used to receive the light passing through the engine oil and measure its light intensity. The vehicle diagnostic device 150 obtains the light intensity collected by the light transmittance detection device 120 and determines the engine oil light transmittance according to the light intensity and the light intensity emitted by the light source 121. For example, the engine oil light transmittance can be the ratio of the light intensity emitted by the light source 121 to the measured light intensity.

[0032] In another embodiment, the vehicle diagnostic device 150 is configured to obtain the temperature acquisition result of the engine oil of the target vehicle by the temperature sensor 130 to determine the engine oil temperature; and obtain the conductivity acquisition result of the engine oil of the target vehicle by the conductivity sensor 140 to determine the engine oil conductivity.

[0033] Next, for the sake of easy understanding, the following embodiments of the present application will take Figure 1 the shown engine oil life detection device 100 as an example, and in combination with Figure 1 of the accompanying drawings, elaborate on the engine oil life detection method provided by the embodiments of the present application.

[0034] Figure 2 Fig. 1 shows a flowchart of an engine oil life detection method according to an embodiment of the present application. Exemplarily, the engine oil life detection method includes the following steps: S210, obtaining the state acquisition result of the engine oil of the target vehicle flowing through the transparent guide rail 110 to determine the state detection data, and obtaining the engine oil type adapted to the target vehicle.

[0035] In one embodiment, the state detection data includes engine oil light transmittance, flow velocity, engine oil temperature, and engine oil conductivity. In the present application, the vehicle diagnostic device 150 obtains the light intensity of the light passing through the engine oil of the target vehicle collected by the light transmittance detection device and determines the engine oil light transmittance according to the light intensity. Since the light transmittance of the engine oil changes due to different impurities, moisture, oxidation degree, etc. in the engine oil, the pollution and deterioration of the engine oil can be preliminarily judged by detecting the light transmittance. For example, when impurities such as carbon particles and metal powders in the engine oil increase or the oxidation degree deepens, the light transmittance will decrease. In one embodiment, the vehicle diagnostic device 150 obtains the flow-through time of the target vehicle's engine oil recorded by each group of light transmittance detection devices 120; and determines the flow velocity of the target vehicle's engine oil based on the distance between the respective light transmittance detection devices and the flow-through time. For example, the distance between each group of light transmittance detection devices 120 is fixed. In this application, based on the time when the engine oil flows through each group of light transmittance detection devices 120 and the distance between each group of light transmittance detection devices 120, a relevant algorithm in fluid mechanics is used to calculate the flow velocity of the engine oil. The formula for calculating the flow velocity of the engine oil is: , represents the flow velocity of the engine oil, represents the distance between the light transmittance detection device A and the light transmittance detection device B, is the time for the engine oil to flow through the light transmittance detection device B, is the time for the engine oil to flow through the light transmittance detection device . In this application, by calculating the flow velocity of the engine oil flowing through adjacent light transmittance detection devices 120, the final flow velocity of the engine oil can be determined by calculating the average value of the flow velocities at adjacent light transmittance detection devices 120.

[0036] In this embodiment, this application adopts a combination method of multiple light transmittance detection devices 120 and temperature sensors 130. A plurality of combinations of light transmittance detection devices 120 and temperature sensors 130 are equidistantly installed at the position of the transparent guide rail 110 through which the engine oil flows to determine the flow velocity of the engine oil and the engine oil temperature. During the use of the engine oil, under the action of high temperature, shear force, etc., the molecular chains will gradually be cut off, the viscosity will decrease, and the flow velocity will increase; if the engine oil is oxidized, emulsified, etc., resulting in an increase in viscosity, the flow velocity will slow down.

[0037] For example, the kinematic viscosity of a certain type of engine oil A is: the flow velocity is 78 mm² / s at 40 °C, and the flow velocity is 13.8 mm² / s at 100 °C. The kinematic viscosity of a certain type of engine oil B is: the flow velocity at 40 °C is 55 mm² / s, and the flow velocity at 100 °C is 9.5 mm² / s. The kinematic viscosity of a certain type of engine oil C is: the flow velocity at 40 °C is 46.3 mm² / s; the flow velocity at 100 °C is 8.8 mm² / s. Among them, the kinematic viscosity represents the flow velocity at different temperatures.

[0038] It can be understood that this application comprehensively and accurately detects the state detection data of the engine oil. By multi-dimensionally detecting parameters such as the light transmittance of the engine oil, the flow velocity (viscosity) at different temperatures, and the conductivity, etc., it can comprehensively and accurately reflect the performance changes of the engine oil during use, overcomes the limitations of traditional detection methods that only focus on single or partial indicators, and greatly improves the accuracy and reliability of the engine oil life detection.

[0039] S220, Input the status detection data and oil type into the oil life detection model to obtain the detection result of the remaining oil life of the target vehicle.

[0040] Exemplarily, the pre-trained oil life detection model conducts a comparative analysis with the pre-trained labeled data set based on the status detection data and oil type to judge the health status of the current oil and predict the service life of the oil.

[0041] In one embodiment, as Figure 3 shown, the pre-training process of the oil life detection model includes the following steps: S221, Establish a data set including the historical status detection data of different types of oil and the corresponding remaining oil life.

[0042] In one embodiment, this application cooperates with oil manufacturers, automobile manufacturing enterprises and professional automobile testing institutions to collect a large amount of usage data of different brands and models of oil under various engine conditions (such as different speeds, loads, temperatures, etc.), including detection parameters such as the light transmittance, flow velocity, conductivity, temperature, etc. of the oil at different usage time nodes, as well as the corresponding remaining oil life data (obtained through laboratory simulated aging tests and actual vehicle tracking tests).

[0043] In one implementation manner, this application sorts and labels the collected data to establish a data set. When sorting the data, the collected data can be cleaned to remove outliers and invalid data to ensure data accuracy; the data can be normalized to convert parameters with different units into a unified format. When labeling the data, label the remaining oil life of different types of oil under different detection parameters such as oil light transmittance, flow velocity, conductivity, temperature, etc.

[0044] S222, Select a basic model and build the structure of the basic model according to the data set and the oil life prediction target.

[0045] In one embodiment, since the data set includes various status detection data and there are multiple mapping relationships between the oil life prediction target and the status detection data, this application selects a deep neural network model as the basic model and builds a model structure based on the basic model. The deep neural network model can be a Multilayer Perceptron (MLP), a Recurrent Neural Network (RNN), a Long Short-Term Memory (LSTM), etc., which are not limited here.

[0046] In another embodiment, the model structure includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the status detection data and pass it to the subsequent network layers for processing. This application determines the dimension of the input layer based on the historical status detection data and the type of engine oil. For example, the input features include the following main variables: light transmittance, flow velocity, conductivity, temperature, and the type of engine oil. The dimensions of light transmittance, flow velocity, conductivity, and temperature are all A, and the type of engine oil can be represented by one-hot encoding. Assuming there are N types of engine oil models, the dimension is N, and the total dimension of the input layer is 4A + N.

[0047] The hidden layer is used to extract complex patterns in the input data and gradually convert low-level features into high-level features, ultimately completing the non-linear mapping of the input data. In this application, the hidden layer learns the data distribution and feature patterns of each type of engine oil through layer-by-layer calculation. If the model only contains a small number of hidden layers or neurons, it may not be able to fully capture the complexity brought by the newly added type of engine oil. When a new type of engine oil appears, this application adjusts the number of hidden layers and the number of neurons in each hidden layer according to the change in the type of engine oil.

[0048] In one implementation, the newly added type of engine oil will introduce more complex non-linear relationships. Increasing the number of hidden layers can enhance the expressive power of the model, enabling it to better fit complex data distributions. Each type of engine oil requires the model to learn its specific feature patterns. If there are more newly added types of engine oil, the model needs more neurons to represent these patterns. This application increases the number of neurons in the existing hidden layer or sets an appropriate number of neurons in the newly added hidden layer to ensure that the model can fully capture the characteristics of the newly added type of engine oil.

[0049] In another implementation, this application uses the engine oil life prediction target as the output target of the output layer. The output layer is used to generate the final prediction result of the model and calculate the specific prediction value based on the features extracted by the hidden layer. The output layer can include one or more neurons, and directly output the prediction value using a linear activation function, or output the probability distribution using a Softmax or Sigmoid activation function.

[0050] S223, train the model based on the data set, and use the trained model as the engine oil life detection model.

[0051] In one embodiment, this application divides the data set into a training set, a validation set, and a test set. For example, the division ratio can be set to 70%, 15%, 15%. This application sets training parameters based on the training set to train the model and adjusts the model weights through the backpropagation algorithm.

[0052] In one embodiment, the model training process includes: initializing model parameters (weights and biases), for example, initializing model parameters by means such as Xavier initialization or He initialization. Inputting the training set data into the model, obtaining the predicted values through layer-by-layer calculation, calculating the loss between the predicted values and the true values, and completing the forward propagation process. Calculating the gradients of the loss function with respect to each model parameter through the chain rule, updating the model parameters according to the gradients to gradually reduce the loss, and completing the backpropagation process. Using an optimizer (such as the Adam optimizer) to update the parameters according to the learning rate and gradients. Repeating the above steps until the set number of iterations is reached or the loss converges.

[0053] In one embodiment, the present application evaluates the model performance based on a validation set to judge the fitting degree of the model according to the model performance, and adjusts the model when it is judged that the model is overfitting; under the condition that the performance of the model on the validation set reaches a preset index, the model training is stopped. In this embodiment, the main purpose of the validation set is to monitor the performance of the model on unseen data, help adjust the model parameters and structure, and prevent overfitting. During the training process, every certain number of iterations (such as every time an epoch is completed), the loss value or accuracy of the model is calculated using the validation set data. By observing the performance metrics on the validation set (such as the mean squared error MSE or the R² score), it can be judged whether the model is gradually learning the patterns in the data or whether overfitting has occurred. If the performance of the model on the training set continues to improve, but the performance on the validation set begins to decline, it indicates that the model may have overfitted. For example, training can be stopped in advance, or the number of hidden layers or neurons can be reduced to alleviate overfitting. When the performance of the model on the validation set reaches a stable state (i.e., the loss value or accuracy fluctuates less) and meets the preset accuracy requirements, it can be considered that the model has been fully trained.

[0054] In one embodiment, the present application performs a performance test on the model based on a test set to evaluate the prediction accuracy and generalization ability of the model. In this embodiment, the test set is data that is completely independent of the training set and the validation set and is used for the final evaluation of the trained model.

[0055] In one embodiment, the present application uses the trained model to predict each sample in the test set, obtains the predicted values, compares the predicted values with the true values, and calculates relevant evaluation metrics. For example, this evaluation metric can measure the average squared difference between the predicted value and the true value through the mean squared error. The smaller the average squared difference, the more accurate the model prediction. According to the actual application scenario, this evaluation metric can also define specific evaluation metrics. For example, in the prediction of engine oil life, the proportion of prediction errors within a preset range is concerned. If the proportion of all prediction errors within the preset range is large, the prediction accuracy of the model can be evaluated as high.

[0056] In another embodiment, the generalization ability refers to the performance of the model on unseen data. This application can compare the performance of the training set, the validation set, and the test set to judge the generalization ability of the model. If the performance of the model on the test set is comparable to that on the training set and the validation set, it indicates that the model has good generalization ability. If the performance on the test set is significantly lower than that on the training set and the validation set, there may be overfitting or underfitting problems.

[0057] In this embodiment, the vehicle diagnostic device 150 of this application can be connected to the model through a wireless data transmission module or a USB interface, and the model can be trained using a large amount of state detection data of oils of different brands and models at different usage stages and working conditions, as well as the corresponding actual oil life data. The trained model can learn the complex mapping relationship between the state detection data and the oil life. During the actual use of the vehicle, after receiving the real-time detected state detection data, the oil life detection model performs predictive analysis on the oil life and outputs an evaluation result of the remaining oil life.

[0058] S230, feedback the detection result of the remaining oil life to the user terminal.

[0059] In one embodiment, the oil life result predicted by the oil life detection model is fed back to the user through the user terminal, and the user terminal includes but is not limited to a vehicle dashboard, an in-vehicle infotainment system, a user interaction interface, etc. When the remaining oil life is lower than the set threshold, the system issues an alarm to prompt the user to change the oil in time to ensure that the engine is always in a good lubrication state; the prediction result can also be directly displayed through the user terminal to judge whether the oil meets the standard.

[0060] In this embodiment, the state detection data collected in real time by this application is transmitted to the oil life detection model for analysis, which can timely reflect the current state change of the oil, adapt to the influence of complex working conditions such as different vehicle engine working modes, user driving habits, and driving road conditions on the oil life, and provide users with dynamic and accurate oil life prediction. This application can also distinguish a certain amount of fake oil on the market, which can reduce the serious consequences brought to vehicle owners and vehicle maintenance institutions by using fake oil. This application does not need to send the oil to a professional institution for detection with expensive professional instruments. The oil life detection can be realized through the vehicle's own light transmittance detection device 120, sensors and other devices and the oil life detection model, reducing the detection cost. At the same time, the detection process is automatic, and the user does not need to perform additional complex operations, only need to pay attention to the detection result prompts fed back by the vehicle, which is suitable for the daily use and maintenance needs of the majority of ordinary vehicle users.

[0061] The present application also provides a vehicle diagnostic device 150. Exemplarily, the vehicle diagnostic device 150 includes a processor and a memory. Among them, the memory stores a computer program, and the processor executes the above-mentioned engine oil life detection method by running the computer program.

[0062] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0063] The memory can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the memory is used to store the computer program, and after receiving the execution instruction, the processor can execute the computer program accordingly.

[0064] The present application also provides a computer-readable storage medium for storing the computer program used in the above vehicle diagnostic device. For example, the computer-readable storage medium can include, but is not limited to: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0065] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the part of the module, program segment, or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and / or flowchart, as well as the combination of blocks in the structure diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0066] In addition, each functional module or unit in various embodiments of this application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0067] If the described function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.

[0068] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. An engine oil life detection method, characterized in that, Including: Obtain the status acquisition result of the target vehicle oil flowing through the transparent guide rail to determine the status detection data, and obtain the oil type suitable for the target vehicle; Input the status detection data and the oil type into the oil life detection model to obtain the detection result of the remaining oil life of the target vehicle; Feed back the detection result of the remaining oil life to the user terminal.

2. The oil life detection method according to claim 1, characterized in that Multiple groups of light transmittance detection devices are arranged on both sides of the track of the transparent guide rail. The status detection data includes the oil light transmittance and the flow velocity. Obtaining the status acquisition result of the target vehicle oil flowing through the transparent guide rail to determine the status detection data includes: Obtain the light intensity of the light passing through the vehicle oil of the target vehicle collected by the light transmittance detection device, and determine the oil light transmittance according to the light intensity; Obtain the flow-through time of the target vehicle oil recorded by each group of the light transmittance detection devices; Determine the flow velocity of the target vehicle oil according to the distance between the light transmittance detection devices and the flow-through time.

3. The oil life detection method according to claim 1, wherein A temperature sensor and a conductivity sensor are respectively arranged at the output end of the transparent guide rail. The status detection data includes the oil temperature and the oil conductivity. Obtaining the status acquisition result of the target vehicle oil flowing through the transparent guide rail to determine the status detection data includes: Obtain the temperature acquisition result of the target vehicle oil by the temperature sensor and determine the oil temperature; Obtain the conductivity acquisition result of the target vehicle oil by the conductivity sensor and determine the oil conductivity.

4. The oil life detection method according to claim 1, characterized in that, The target vehicle is connected to the communication interface of the vehicle diagnostic device, and the method further includes: Obtain the status acquisition result and the oil type through the communication interface, and upload the determined status detection data and the oil type to the database for storage; Upload the detection result of the remaining oil life to the user terminal through the communication interface.

5. The oil life detection method according to claim 1, characterized in that, The pre-training process of the oil life detection model includes: Establish a data set including the historical status detection data of different types of oil and the corresponding remaining oil life; Select a basic model according to the data set and the oil life prediction target and build the structure of the basic model; Train the model based on the data set, and use the trained model as the oil life detection model.

6. The oil life detection method according to claim 5, wherein The structure of the basic model includes an input layer, a hidden layer, and an output layer. Selecting a basic model according to the data set and the oil life prediction target and building the structure of the basic model includes: Select a deep neural network model as the basic model; Determine the dimension of the input layer based on the historical status detection data and the oil type; Adjust the number of layers of the hidden layer and the number of neurons in each hidden layer according to the change of the oil type; Use the oil life prediction target as the output target of the output layer.

7. An engine oil life detection device, characterized in that, Including: A transparent guide rail for introducing the target vehicle oil from the input end; Multiple groups of light transmittance detection devices are respectively arranged on both sides of the transparent guide rail, and are used for collecting the light intensity of the flowing vehicle oil of the target vehicle and recording the flow-through time of the target vehicle oil; A temperature sensor, arranged at the output end of the transparent guide rail, for collecting the oil temperature; A conductivity sensor, arranged at the output end of the transparent guide rail, for collecting the oil conductivity; A vehicle diagnostic device, for implementing the oil life detection method according to any one of claims 1-6.

8. The oil life detection device according to claim 7, characterized in that, Each group of the light transmittance detection devices includes a light source and a photosensitive sensor, and the light source and the photosensitive sensor are respectively arranged on both sides of the transparent guide rail.

9. A vehicle diagnostic device, characterized in that, The vehicle diagnostic device includes a processor and a memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the oil life detection method according to any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, It stores a computer program, and when the computer program is executed on a processor, it implements the oil life detection method according to any one of claims 1-6.

Images