Engine oil temperature measurement method, system, electronic device and readable storage medium

Abstract

This invention provides a method, system, electronic device, and readable storage medium for measuring engine oil temperature. The method includes: obtaining real-time engine coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed, and obtaining the initial coolant temperature; calculating the cumulative engine revolutions based on the real-time engine speed; and calculating the engine oil temperature based on the real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, vehicle speed, and cumulative revolutions. This invention, based on engine operating data, compares the previous moment's oil temperature with the oil start-up threshold temperature to obtain the current engine oil temperature, resulting in lower measurement costs and improved measurement accuracy.

Description

Technical Field

[0001] This invention relates to the field of engineering machinery engine technology, and in particular to an oil temperature measurement method, system, electronic device, and readable storage medium. Background Technology

[0002] Engine oil plays a crucial lubricating role in engine operation, and its failure can cause significant damage to construction machinery engines. Temperature changes in engine oil are critical to its oxidation and degradation; therefore, obtaining real-time oil temperature information is essential for assessing oil quality. However, some engines in construction machinery lack real-time oil temperature data. Obtaining this information requires additional oil temperature sensors, increasing hardware costs and necessitating modifications to the engine structure, consuming significant resources. Engine operating data, such as coolant temperature and engine speed, are readily available parameters for every engine and are correlated with oil temperature. While establishing a relationship between engine operating data and oil temperature can indirectly predict oil temperature, current methods often rely on mechanistic modeling, resulting in predictions that are neither accurate nor timely enough to meet requirements. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, electronic device, and readable storage medium for measuring engine oil temperature, which has low measurement cost and can improve measurement accuracy.

[0004] To achieve the above objectives, the present invention provides a method for measuring engine oil temperature, comprising:

[0005] The engine's real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed are obtained in real time, and the initial coolant temperature of the engine is also obtained.

[0006] The cumulative number of engine revolutions is obtained based on the real-time engine speed.

[0007] The engine oil temperature is calculated based on the real-time coolant temperature, the initial coolant temperature, the engine speed, the engine output torque, the fuel quantity, the fuel flow rate, the vehicle speed, and the cumulative revolutions.

[0008] The formula for calculating the engine oil temperature is:

[0009]

[0010] Among them, Temp oil(T) is the current oil temperature at time T, Temp oil (T-1) is the oil temperature at the previous time T-1, Temp1(T) is the first oil temperature predicted at the current time T based on the initial coolant temperature and the cumulative engine speed, and Temp2(T) is the second oil temperature predicted at the current time T based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. th It is the engine oil start-up threshold temperature, and k is the weighting coefficient for minimum variance.

[0011] Optionally, the formula for the weighting coefficient of the minimum variance is:

[0012]

[0013] Where, σ1 2 σ² is the variance of the first oil temperature predicted at several moments based on the initial coolant temperature and the cumulative revolutions. 2 It is the variance of the second oil temperature predicted at a certain time based on the real-time temperature of the coolant, the engine speed, the engine output torque, the fuel quantity, the fuel flow rate, and the vehicle speed.

[0014] Optionally, the formula for the first oil temperature is:

[0015] Temp1(T) = T ic +η·R e (T);

[0016] Among them, T ic R is the initial temperature of the coolant. e (T) is the cumulative revolutions of the engine at time T, and η is the fitting coefficient.

[0017] Optionally, the cumulative number of engine revolutions is obtained based on the real-time engine speed, and the formula for the cumulative number of revolutions is:

[0018] R e (T)=R e (T-1)+S e (T-1)·Δ;

[0019] Among them, R e (T-1) is the cumulative number of engine revolutions at the previous time point T-1, S e (T-1) is the engine speed at the previous time T-1, and Δ is the sampling time of the engine.

[0020] Optionally, the second oil temperature is obtained by predicting the oil temperature using an oil temperature prediction model. The oil temperature prediction model includes a first GRU model, a second GRU model, a first batch normalization layer, a second batch normalization layer, a feature merging layer, and a fully connected regression network. The real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed form an input vector, which is respectively input to the first GRU model and the second GRU model. After the first GRU model outputs, it is processed by the first batch normalization layer to output a first time-related feature vector. After the second GRU model outputs, it is processed by the second batch normalization layer to output a second time-related feature vector. The feature merging layer merges the first time-related feature vector and the second time-related feature vector and inputs them to the fully connected regression network. The fully connected regression network then outputs the second oil temperature.

[0021] Optionally, both the first GRU model and the second GRU model include hidden state variables, candidate hidden state variables, update gates, and reset gates;

[0022] The formula for the update gate of the first GRU model is:

[0023] z 1T =σ(U 1z x T +W 1z h 1T-1 +b 1z );

[0024] The formula for the update gate in the second GRU model is:

[0025] z 2T =σ(U 2z x T +W 2z h 2T-1 +b 2z );

[0026] The formula for the reset gate in the first GRU model is:

[0027] r 1T =σ(U 1r x T +W 1r h 1T-1 +b 1r );

[0028] The formula for the reset gate in the second GRU model is:

[0029] r 2T =σ(U 2r x T +W 2r h2T-1 +b 2r );

[0030] The formula for the hidden state variables of the first GRU model is:

[0031]

[0032] The formula for the hidden state variables in the second GRU model is:

[0033]

[0034] The formula for the candidate hidden state variables of the first GRU model is:

[0035]

[0036] The formula for the candidate hidden state variables of the second GRU model is:

[0037]

[0038] Among them, z 1T It is the update gate of the first GRU model at time T, z 2T It is the update gate of the second GRU model at time T, r 1T It is the reset gate of the first GRU model at time T, r 2T It is the reset gate of the second GRU model at time T, h 1T h is the hidden state variable of the first GRU model at time T. 2T These are the hidden state variables of the second GRU model at time T. These are the candidate hidden state variables of the first GRU model at time T. h is the candidate hidden state variable of the second GRU model at time T. 1T-1 h is the hidden state variable of the first GRU model at the previous time T-1. 2T-1 U is the hidden state variable of the second GRU model at the previous time T-1. 1z U is the weight matrix from the input of the first GRU model to the update gate. 2z U is the weight matrix from the input of the second GRU model to the update gate. 1r U is the weight matrix from the input of the first GRU model to the reset gate. 2r U is the weight matrix from the input of the second GRU model to the reset gate. 1h U is the weight matrix from the input of the first GRU model to the candidate hidden state. 2h x is the weight matrix from the input of the second GRU model to the candidate hidden state. TW is the input vector of the first GRU model and the second GRU model at time T. 1z W is the weight matrix from the hidden state to the update gate of the first GRU model. 2z W is the weight matrix from the hidden state to the update gate in the second GRU model. 1r W is the weight matrix from the hidden state to the reset gate of the first GRU model. 2r W is the weight matrix from the hidden state to the reset gate in the second GRU model. 1h W is the weight matrix from the hidden state to the candidate hidden state in the first GRU model. 2h This is the weight matrix from the hidden state to the candidate hidden state in the second GRU model, b 1z b 2z b 1r b 2r b 1h and b 2h σ is the bias vector, σ() is the Sigmoid function, and ReLU() is the linear rectified function.

[0039] Optionally, the input vector consisting of the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed can be input into the first GRU model and the second GRU model, respectively.

[0040] The first GRU model outputs its hidden state variables to the first batch normalization layer and then outputs the first time-related feature vector; the second GRU model outputs its hidden state variables to the second batch normalization layer and then outputs the second time-related feature vector.

[0041] The feature merging layer merges the first time-related feature vector and the second time-related feature vector into a total time-related feature vector;

[0042] The total time-related feature vector is input into the fully connected regression network to obtain the second oil temperature;

[0043] The formula for the second oil temperature is:

[0044] Temp2(T) = W HT ·ReLU(W FH ·F+b FH )+b HT ;

[0045] Where F is the total time-related feature vector, W HT W is the weight matrix between the hidden layer and the output layer. FHb is the weight matrix between the total time-related feature vector and the hidden layer. FH b is the bias vector between the total temporally correlated feature vector and the hidden layer. HT It is the bias vector from the hidden layer to the output layer, and ReLU() is a linear rectified function.

[0046] The present invention also provides an oil temperature measurement system for measuring the oil temperature of an engine, comprising:

[0047] The data acquisition module is used to obtain the engine's real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate and vehicle speed, and to obtain the engine's initial coolant temperature.

[0048] The counting module is used to obtain the cumulative number of engine revolutions based on the real-time engine speed.

[0049] The calculation module is used to calculate the engine oil temperature based on the real-time coolant temperature, the initial coolant temperature, the engine speed, the engine output torque, the fuel quantity, the fuel flow rate, the vehicle speed, and the cumulative revolutions.

[0050] The formula for calculating the engine oil temperature is:

[0051]

[0052] Among them, Temp oil (T) is the current oil temperature at time T, Temp oil (T-1) is the oil temperature at the previous time T-1, Temp1(T) is the first oil temperature predicted at the current time T based on the initial coolant temperature and the cumulative engine speed, and Temp2(T) is the second oil temperature predicted at the current time T based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. th It is the engine oil start-up threshold temperature, and k is the weighting coefficient for minimum variance.

[0053] The present invention also provides an electronic device, the electronic device comprising:

[0054] One or more actuators; and,

[0055] Memory, used to store one or more programs; and,

[0056] When the one or more programs are executed by the one or more actuators, the one or more actuators perform the oil temperature measurement method as described above.

[0057] The present invention also provides a readable storage medium having a computer program stored thereon, which, when executed by an actuator, implements the oil temperature measurement method as described above.

[0058] In the oil temperature measurement method, system, electronic device, and readable storage medium provided by this invention, the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed of the engine are obtained in real time, and the initial coolant temperature of the engine is also obtained; the cumulative engine speed is obtained based on the real-time engine speed; and the engine oil temperature is calculated based on the real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, vehicle speed, and cumulative engine speed. This invention, based on engine operating data, compares the oil temperature at the previous moment with the oil start-up threshold temperature to obtain the current engine oil temperature, resulting in lower measurement costs and improved measurement accuracy. Attached Figure Description

[0059] Figure 1 This is a flowchart of an oil temperature measurement method provided in an embodiment of the present invention.

[0060] Figure 2 This is a block diagram of an oil temperature measurement system provided in an embodiment of the present invention.

[0061] The attached figures are labeled as follows:

[0062] 10 - Data acquisition module; 20 - Counting module; 30 - Calculation module; 31 - First prediction unit; 32 - Second prediction unit. Detailed Implementation

[0063] The specific embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. The advantages and features of the present invention will become clearer from the following description. It should be noted that the drawings are all in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0064] Figure 1 This is a flowchart of the oil temperature measurement method provided in this embodiment. Please refer to it. Figure 1 This embodiment provides a method for measuring engine oil temperature, including:

[0065] Step S1: Obtain the real-time engine coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate and vehicle speed, and obtain the initial engine coolant temperature.

[0066] Step S2: Calculate the cumulative engine speed based on the real-time engine speed;

[0067] Step S3: Calculate the engine oil temperature based on the real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, vehicle speed, and cumulative revolutions.

[0068] The oil temperature measurement method provided in this embodiment will be described in detail below.

[0069] Step S1: While the engine is running, obtain the real-time engine coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed, as well as the initial engine coolant temperature. These parameters constitute the engine's operating condition data, which is obtained through sensors originally installed in the engine or vehicle. Since the engine's operating condition data changes in real time while the engine is running, real-time sampling is required according to a set sampling frequency to obtain the real-time engine coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed at several points in time. The initial engine coolant temperature is the temperature of the coolant when the engine starts.

[0070] Step S2: Calculate the current cumulative engine speed based on the real-time engine speed. The formula for the cumulative engine speed is:

[0071] R e (T)=R e (T-1)+S e (T-1)·Δ;

[0072] Among them, R e (T) is the cumulative engine speed at time T, R e (T-1) is the cumulative engine speed at the previous time point T-1, S e (T-1) is the engine speed at the previous time T-1, Δ is the engine sampling time, and the engine sampling time represents the working time of the engine after it is started. After the engine is started, it begins to sample in real time according to the set sampling frequency.

[0073] Step S3: Calculate the engine oil temperature based on the real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, vehicle speed, and cumulative revolutions.

[0074] Specifically, during the initial engine start-up phase, as the oil temperature rises, it is directly related to the initial coolant temperature and the engine's cumulative RPM, with the relationship between oil temperature and cumulative RPM being roughly linear. Therefore, based on mechanistic modeling, the first oil temperature predicted using the initial coolant temperature and the current engine's cumulative RPM is calculated using the following formula:

[0075] Temp1(T) = T ic +η·R e (T);

[0076] Among them, T ic It is the initial temperature of the coolant, R e (T) is the cumulative engine speed at time T, and η is the fitting coefficient.

[0077] Furthermore, a second oil temperature is predicted based on data-driven modeling using real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. This second oil temperature is obtained through an oil temperature prediction model. The oil temperature prediction model includes a first GRU model, a second GRU model, a first batch normalization layer, a second batch normalization layer, a feature merging layer, and a fully connected regression network. The real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed form an input vector, which is input to the first GRU model and the second GRU model, respectively. The output of the first GRU model is processed by the first batch normalization layer to output a first time-related feature vector, and the output of the second GRU model is processed by the second batch normalization layer to output a second time-related feature vector. The feature merging layer merges the first and second time-related feature vectors and inputs them into the fully connected regression network, which then outputs the second oil temperature.

[0078] Specifically, the input vector consisting of real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate and vehicle speed is input into the first GRU model and the second GRU model respectively. Both the first GRU model and the second GRU model include hidden state variables, candidate hidden state variables, update gates and reset gates.

[0079] The formula for the update gate in the first GRU model is:

[0080] z 1T =σ(U 1z x T +W 1z h 1T-1 +b 1z );

[0081] The formula for the update gate in the second GRU model is:

[0082] z 2T =σ(U 2z x T +W 2z h 2T-1 +b 2z );

[0083] The formula for the reset gate in the first GRU model is:

[0084] r 1T =σ(U 1r x T +W 1r h 1T-1 +b 1r );

[0085] The formula for the reset gate in the second GRU model is:

[0086] r 2T =σ(U 2r x T +W 2r h 2T-1 +b 2r );

[0087] The formula for the hidden state variables in the first GRU model is:

[0088]

[0089] The formula for the hidden state variables in the second GRU model is:

[0090]

[0091] The formula for the candidate hidden state variables in the first GRU model is:

[0092]

[0093] The formula for the candidate hidden state variables in the second GRU model is:

[0094]

[0095] Among them, z 1T It is the update gate of the first GRU model at time T, z 2T It is the update gate of the second GRU model at time T, r 1T It is the reset gate of the first GRU model at time T, r 2T It is the reset gate of the second GRU model at time T, h 1T h is the hidden state variable of the first GRU model at time T. 2T These are the hidden state variables of the second GRU model at time T. These are the candidate hidden state variables of the first GRU model at time T. h is the candidate hidden state variable of the second GRU model at time T. 1T-1 h is the hidden state variable of the first GRU model at time T-1. 2T-1 U is the hidden state variable of the second GRU model at the previous time T-1. 1z It is the weight matrix from the input to the update gate of the first GRU model, U2z U is the weight matrix from the input of the second GRU model to the update gate. 1r It is the weight matrix from the input of the first GRU model to the reset gate, U 2r It is the weight matrix from the input of the second GRU model to the reset gate, U 1h U is the weight matrix from the input of the first GRU model to the candidate hidden states. 2h This is the weight matrix from the input of the second GRU model to the candidate hidden states, x T W is the input vector of the first GRU model and the second GRU model at time T. 1z W is the weight matrix from the hidden state to the update gate in the first GRU model. 2z W is the weight matrix from the hidden state to the update gate in the second GRU model. 1r W is the weight matrix from the hidden state to the reset gate in the first GRU model. 2r W is the weight matrix from the hidden state to the reset gate in the second GRU model. 1h W is the weight matrix from the hidden state to the candidate hidden state in the first GRU model. 2h This is the weight matrix from the hidden state to the candidate hidden state in the second GRU model, b 1z b 2z b 1r b 2r b 1h and b 2h These are the update gates of the first GRU model, the update gate of the second GRU model, the reset gate of the first GRU model, the reset gate of the second GRU model, the bias vectors of the hidden state variables of the first GRU model and the hidden state variables of the second GRU model, respectively. σ() is the Sigmoid function, ReLU() is the linear rectified function, and ⊙ is the element-wise multiplication sign.

[0096] The first GRU model outputs its time-dependent latent state variables to the first batch normalization layer, and then outputs a first time-dependent feature vector between engine parameters. The second GRU model outputs its time-dependent latent state variables to the second batch normalization layer, and then outputs a second time-dependent feature vector between engine parameters. In this embodiment, the first GRU model is a short-time-dependent GRU model, and the second GRU model is a long-time-dependent GRU model; therefore, the first time-dependent feature vector is a short-time-dependent feature vector, and the second time-dependent feature vector is a long-time-dependent feature vector.

[0097] The formula for the first-time relevant feature vector is:

[0098]

[0099] The formula for the second time-related feature vector is:

[0100]

[0101] Where F1 is the first time-related feature vector, F2 is the second time-related feature vector, and h 1T h is the hidden state variable of the first GRU model at time T. 2T σ is the hidden state variable of the second GRU model at time T, μ is the mean vector of the engine's operating data at several times (including the current time), and σ is the standard deviation of the engine's operating data at several times (including the current time).

[0102] Furthermore, the feature merging layer merges the first time-related feature vector and the second time-related feature vector into a total time-related feature vector;

[0103] Then, the total time-related feature vector is input into a fully connected regression network to obtain the second oil temperature;

[0104] The formula for the second oil temperature is:

[0105] Temp2(T) = W HT ·ReLU(W FH ·F+b FH )+b HT ;

[0106] Where F is the total time-related feature vector, W HT W is the weight matrix between the hidden layer and the output layer. FH It is the weight matrix between the total temporally relevant feature vectors and the hidden layer, b FH It is the bias vector between the total temporally relevant feature vector and the hidden layer, b HT This is the bias vector from the hidden layer to the output layer, and ReLU() is the linear rectified function. In this embodiment, there is only one hidden layer, and the hidden layer and output layer belong to the basic structure of a fully connected regression network.

[0107] Furthermore, the engine oil temperature at the current moment is obtained by combining the first oil temperature predicted based on mechanism modeling and the second oil temperature predicted based on data-driven modeling. When the engine is first started, the engine oil temperature is assumed to be lower than a set oil start-up threshold temperature. In this embodiment, the oil start-up threshold temperature can be set to 80 degrees Celsius, meaning that the engine oil temperature is assumed to be lower than 80 degrees Celsius when the engine is first started. When the engine oil temperature at the current moment is lower than the oil start-up threshold temperature, the engine oil temperature at the current moment is the fused value of the first oil temperature predicted based on mechanism modeling and the second oil temperature predicted based on data-driven modeling; when the engine oil temperature at the current moment is greater than or equal to the oil start-up threshold temperature, the engine oil temperature at the current moment is the second oil temperature predicted based on data-driven modeling.

[0108] The formula for calculating engine oil temperature is:

[0109]

[0110] Among them, Temp oil (T) is the current oil temperature at time T, Temp oil (T-1) is the oil temperature at the previous time T-1, Temp1(T) is the first oil temperature predicted at the current time T based on the initial coolant temperature and cumulative engine speed, and Temp2(T) is the second oil temperature predicted at the current time T based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. th It is the engine oil start-up threshold temperature, and k is the weighting coefficient for minimum variance.

[0111] The formula for the weighting coefficient of minimum variance is:

[0112]

[0113] Where, σ1 2 σ² is the variance of the first oil temperature predicted at several moments based on the initial coolant temperature and cumulative engine speed. 2 σ1 is the variance of the second oil temperature predicted at several moments based on real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. 2 and σ2 2 The variance is a fixed value obtained from a large number of experiments.

[0114] In this embodiment, readily available engine operating data, including real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed, are used. The cumulative engine speed is obtained based on the real-time engine speed, eliminating the need for additional hardware and reducing measurement costs. Furthermore, based on the engine operating data, the current engine oil temperature is obtained by comparing the previous oil temperature with the oil start-up threshold temperature and combining the first oil temperature predicted by mechanism modeling and the second oil temperature predicted by data-driven modeling. This improves measurement accuracy and timeliness.

[0115] Figure 2 This is a block diagram of the oil temperature measurement system provided in this embodiment. Please refer to... Figure 2 Based on the same inventive concept, this embodiment also provides an oil temperature measurement system, including:

[0116] The data acquisition module 10 is used to obtain the real-time temperature of the engine coolant, engine speed, engine output torque, fuel quantity, fuel flow rate and vehicle speed, and to obtain the initial temperature of the engine coolant.

[0117] The counting module 20 is used to obtain the cumulative number of engine revolutions based on the real-time engine speed.

[0118] The calculation module 30 is used to calculate the engine oil temperature based on the real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, vehicle speed, and cumulative revolutions.

[0119] The calculation module 30 includes a first prediction unit 31 and a second prediction unit 32. The first prediction unit 31 predicts the first oil temperature based on mechanism modeling, and the second prediction unit 32 predicts the second oil temperature based on data-driven modeling. Specifically, the first prediction unit 31 predicts the first oil temperature based on the initial coolant temperature and the current cumulative engine speed, while the second prediction unit 22 predicts the second oil temperature based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. The formulas for the first and second oil temperatures are provided in the oil temperature measurement method of this embodiment.

[0120] Furthermore, the calculation module 30 also includes an oil temperature comparison unit and an output unit. The engine oil temperature at the current moment is obtained by combining the first oil temperature predicted based on mechanism modeling and the second oil temperature predicted based on data-driven modeling. When the engine is first started, the engine oil temperature is assumed to be lower than a set oil start-up threshold temperature. In this embodiment, the oil start-up threshold temperature can be set to 80 degrees Celsius, meaning that when the engine is first started, the engine oil temperature is assumed to be lower than 80 degrees Celsius.

[0121] The oil temperature comparison unit compares the engine oil temperature at the previous moment with the oil start-up threshold temperature. When the engine oil temperature at the previous moment is lower than the oil start-up threshold temperature, the output unit outputs a fused value of the first oil temperature predicted based on mechanism modeling and the second oil temperature predicted based on data-driven modeling; when the engine oil temperature at the previous moment is greater than or equal to the oil start-up threshold temperature, the output unit outputs the second oil temperature predicted based on data-driven modeling.

[0122] The formula for calculating engine oil temperature is:

[0123]

[0124] Among them, Temp oil (T) is the current oil temperature at time T, Temp oil (T-1) is the oil temperature at the previous time T-1, Temp1(T) is the first oil temperature predicted at the current time T based on the initial coolant temperature and cumulative engine speed, and Temp2(T) is the second oil temperature predicted at the current time T based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. th It is the engine oil start-up threshold temperature, and k is the weighting coefficient for minimum variance.

[0125] The formula for the weighting coefficient of minimum variance is:

[0126]

[0127] Where, σ1 2 σ² is the variance of the first oil temperature predicted at several moments based on the initial coolant temperature and cumulative engine speed. 2 σ1 is the variance of the second oil temperature predicted at several moments based on real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. 2 and σ2 2 The variance is a fixed value obtained from a large number of experiments.

[0128] Furthermore, this embodiment also provides an electronic device for measuring the engine oil temperature, the electronic device comprising:

[0129] One or more actuators; and,

[0130] Memory, used to store one or more programs; and,

[0131] When one or more programs are executed by one or more actuators, the one or more actuators implement the oil temperature measurement method as described in the above embodiments.

[0132] In this embodiment, there is one actuator and one memory, which can be connected via a bus or other means.

[0133] A memory, as a readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the oil temperature measurement method in this embodiment of the invention. The actuator executes the software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the electronic device, thereby realizing the aforementioned oil temperature measurement method.

[0134] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory for the oil temperature measurement method may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include memory remotely located relative to the actuator, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0135] The electronic device proposed in this embodiment and the oil temperature measurement method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0136] This embodiment also provides a readable storage medium storing a computer program that, when executed by an executor, implements the oil temperature measurement method proposed in the above embodiments.

[0137] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the aid of software and necessary general-purpose hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0138] In summary, the oil temperature measurement method, system, electronic device, and readable storage medium provided by this invention obtain the real-time engine coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed, and also obtain the initial engine coolant temperature; the cumulative engine speed is obtained based on the real-time engine speed; and the engine oil temperature is calculated based on the real-time coolant temperature, initial coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, vehicle speed, and cumulative engine speed. This invention, based on engine operating data, compares the oil temperature at the previous moment with the oil start-up threshold temperature to obtain the current engine oil temperature, resulting in lower measurement costs and improved measurement accuracy.

[0139] The above are merely preferred embodiments of the present invention and do not constitute any limitation on the present invention. Any equivalent substitutions or modifications made by those skilled in the art to the technical solutions and content disclosed in the present invention without departing from the scope of the present invention shall be deemed to have remained within the protection scope of the present invention.

Claims

1. An engine oil temperature measuring method for measuring the engine oil temperature of an engine, characterized by, include: The engine's real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed are obtained in real time, and the initial coolant temperature of the engine is also obtained. The cumulative number of engine revolutions is obtained based on the real-time engine speed. The engine oil temperature is calculated based on the real-time coolant temperature, the initial coolant temperature, the engine speed, the engine output torque, the fuel quantity, the fuel flow rate, the vehicle speed, and the cumulative revolutions. The formula for calculating the engine oil temperature is: ； in, It is the current oil temperature at time T. It is the oil temperature at the previous time T-1. It is the first oil temperature predicted at time T based on the initial coolant temperature and the cumulative revolutions. The second oil temperature is predicted at time T based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. It is the engine oil start-up threshold temperature, and k is the weighting coefficient for minimum variance; The formula for the first oil temperature is: ； in, It is the initial temperature of the coolant. It is the cumulative number of engine revolutions at the current time T. These are the fitting coefficients; The second oil temperature is predicted based on an oil temperature prediction model, which includes a first GRU model, a second GRU model, a first batch normalization layer, a second batch normalization layer, a feature merging layer, and a fully connected regression network. The real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed form an input vector, which is respectively input to the first GRU model and the second GRU model. After the first GRU model outputs, it is processed by the first batch normalization layer to output a first time-related feature vector. After the second GRU model outputs, it is processed by the second batch normalization layer to output a second time-related feature vector. The feature merging layer merges the first time-related feature vector and the second time-related feature vector and inputs them to the fully connected regression network. The fully connected regression network then outputs the second oil temperature.

2. The oil temperature measurement method as described in claim 1, characterized in that, The formula for the weighting coefficient of the minimum variance is: ； in, It is the variance of the first oil temperature predicted at a certain number of moments based on the initial coolant temperature and the cumulative revolutions. It is the variance of the second oil temperature predicted at a certain time based on the real-time temperature of the coolant, the engine speed, the engine output torque, the fuel quantity, the fuel flow rate, and the vehicle speed.

3. The oil temperature measurement method as described in claim 1, characterized in that, The cumulative number of engine revolutions is obtained based on the real-time engine speed, and the formula for the cumulative number of revolutions is: ； in, It is the cumulative number of engine revolutions mentioned at the previous time point T-1. It is the engine speed mentioned at the previous time point T-1. It is the sampling time of the engine.

4. The oil temperature measurement method as described in claim 1, characterized in that, Both the first GRU model and the second GRU model include hidden state variables, candidate hidden state variables, update gates, and reset gates; The formula for the update gate of the first GRU model is: ； The formula for the update gate in the second GRU model is: ； The formula for the reset gate in the first GRU model is: ； The formula for the reset gate in the second GRU model is: ； The formula for the hidden state variables of the first GRU model is: ； The formula for the hidden state variables in the second GRU model is: ； The formula for the candidate hidden state variables of the first GRU model is: ； The formula for the candidate hidden state variables of the second GRU model is: ； in, It is the update gate of the first GRU model at time T. It is the update gate of the second GRU model at time T. It is the reset gate of the first GRU model at time T. It is the reset gate of the second GRU model at time T. These are the hidden state variables of the first GRU model at time T. These are the hidden state variables of the second GRU model at time T. These are the candidate hidden state variables of the first GRU model at time T. These are the candidate hidden state variables of the second GRU model at time T. These are the hidden state variables of the first GRU model at the previous time step T-1. These are the hidden state variables of the second GRU model at the previous time step T-1. It is the weight matrix from the input of the first GRU model to the update gate. It is the weight matrix from the input of the second GRU model to the update gate. It is the weight matrix from the input of the first GRU model to the reset gate. It is the weight matrix from the input of the second GRU model to the reset gate. It is the weight matrix from the input of the first GRU model to the candidate hidden state. It is the weight matrix from the input of the second GRU model to the candidate hidden state. It is the input vector of the first GRU model and the second GRU model at time T. It is the weight matrix from the hidden state to the update gate of the first GRU model. This is the weight matrix from the hidden state to the update gate in the second GRU model. It is the weight matrix from the hidden state to the reset gate of the first GRU model. This is the weight matrix from the hidden state to the reset gate in the second GRU model. It is the weight matrix from the hidden state to the candidate hidden state in the first GRU model. It is the weight matrix from the hidden state to the candidate hidden state in the second GRU model. , , , , and It is a bias vector. It is the Sigmoid function. It is a linear rectifier function.

5. The oil temperature measurement method as described in claim 1, characterized in that, The input vector consisting of the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed is obtained in real time is input into the first GRU model and the second GRU model, respectively. The first GRU model outputs its hidden state variables to the first batch normalization layer and then outputs the first time-related feature vector; the second GRU model outputs its hidden state variables to the second batch normalization layer and then outputs the second time-related feature vector. The feature merging layer merges the first time-related feature vector and the second time-related feature vector into a total time-related feature vector; The total time-related feature vector is input into the fully connected regression network to obtain the second oil temperature; The formula for the second oil temperature is: ； in, It is the total time-related feature vector. It is the weight matrix between the hidden layer and the output layer. It is the weight matrix between the total time-related feature vector and the hidden layer. It is the bias vector between the total time-related feature vector and the hidden layer. It is the bias vector from the hidden layer to the output layer. It is a linear rectifier function.

6. An oil temperature measurement system for performing the oil temperature measurement method as described in claim 1 to measure the oil temperature of an engine, characterized in that, include: The data acquisition module is used to obtain the engine's real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate and vehicle speed, and to obtain the engine's initial coolant temperature. The counting module is used to obtain the cumulative number of engine revolutions based on the real-time engine speed. The calculation module is used to calculate the engine oil temperature based on the real-time coolant temperature, the initial coolant temperature, the engine speed, the engine output torque, the fuel quantity, the fuel flow rate, the vehicle speed, and the cumulative revolutions. The formula for calculating the engine oil temperature is: ； in, It is the current oil temperature at time T. It is the oil temperature at the previous time T-1. It is the first oil temperature predicted at time T based on the initial coolant temperature and the cumulative revolutions. The second oil temperature is predicted at time T based on the real-time coolant temperature, engine speed, engine output torque, fuel quantity, fuel flow rate, and vehicle speed. It is the engine oil start-up threshold temperature, and k is the weighting coefficient for minimum variance.

7. An electronic device, characterized in that, The electronic device includes: One or more actuators; and, Memory, used to store one or more programs; and, When the one or more programs are executed by the one or more actuators, the one or more actuators implement the oil temperature measurement method as described in any one of claims 1-5.

8. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the executor, it implements the oil temperature measurement method as described in any one of claims 1-5.

Images