Prediction method and prediction device for insulation resistance of extended-range vehicle

Abstract

The present application provides a method and device for predicting the insulation resistance of an extended-range vehicle. After real-time acquisition of the current voltage to ground of the insulation resistance in the insulation resistance detection circuit, the method inputs the current voltage to ground and the predicted time of the business demand into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value over time. The method is based on the existing bridge method for calculating the insulation resistance value, and adopts an adaptive model to improve the efficiency and accuracy of calculating the insulation resistance value.

Description

Technical Field

[0001] The present application relates to the technical field of insulation monitoring, and in particular to a method and device for predicting the insulation resistance of an extended-range vehicle. Background Art

[0002] With the popularization of range-extended technology, the application of high-power, high-purity electric endurance in range-extended vehicles, and the improvement of voltage platforms, the safety issues caused by high-voltage leakage have attracted more and more attention, becoming one of the biggest safety hazards for drivers and passengers besides vehicle fires. When a vehicle leaks electricity, it is also very easy to cause a vehicle fire, or the occupants are electrocuted and injured by electric shock. The monitoring design of high-voltage leakage and insulation has also become an important means to ensure the safety of passengers and vehicles. The current methods for calculating insulation resistance include:

[0003] Method 1: Use the passive bridge national standard method to calculate the insulation resistance: This method takes a long time to calculate, and when the battery pack is open or the voltage is too low, it is impossible to obtain the voltage division to measure the insulation resistance, or when the insulation resistance values ​​of the positive and negative DC busbars to the ground are equal, it is also impossible to directly calculate the insulation resistance by the formula, and the reliability of calculating the insulation resistance is not high;

[0004] Method 2: Use active signal injection method to measure insulation resistance: This method reports insulation resistance quickly and with high accuracy, but requires an independent power supply. Under high-voltage conditions, it consumes a lot of power from the small battery, causing the small battery to run out of power and the vehicle to fail to start. The filter circuit requires complex algorithms and calibration methods, and is expensive. It requires an independent controller and has a high cost. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method and device for predicting the insulation resistance of an extended-range vehicle, so as to solve the above-mentioned problems existing in the prior art, improve the calculation efficiency of the insulation resistance, and improve the reliability and accuracy of the calculated insulation resistance.

[0006] In a first aspect, a method for predicting insulation resistance of an extended-range vehicle is provided, and the method may include:

[0007] Real-time acquisition of the current voltage of the insulation resistance to ground in the insulation resistance detection circuit; the insulation resistance includes the insulation resistance of the positive pole to ground and the insulation resistance of the negative pole to ground;

[0008] The current voltage to ground and the predicted time of business demand are input into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value changing with time.

[0009] In an optional implementation, the insulation resistance detection circuit further includes an optocoupler switch and a field effect switch; and the configuration step of the resistance prediction model includes:

[0010] Collecting a first voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch, and collecting a second voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch; the first voltage curve and the second voltage curve constitute a cycle of the voltage to ground curve;

[0011] On the first voltage curve and the second voltage curve, respectively searching for an identification time period Δt corresponding to a target voltage change rate within a preset voltage change rate range, where the preset voltage change rate range is a preset stable change range of the voltage change rate;

[0012] Calculating each first resistance value of the insulation resistance based on each ground voltage within the identification time period Δt and a known resistance value in the insulation resistance detection circuit;

[0013] A deep learning network is used to learn the voltage to ground and the first resistance values ​​corresponding to the identification time period △t, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model.

[0014] In an optional implementation, before using a deep learning network to learn the voltage to ground corresponding to the identification time period △t and the first resistance values, and the changing trend of the voltage to ground at different times on the voltage to ground curve, the method further includes:

[0015] Calculate the error between each first resistance value and the actual resistance value of the corresponding insulation resistor;

[0016] Obtain a second resistance value corresponding to a target error value that is less than a preset error threshold value among the calculated error values;

[0017] A deep learning network is used to learn the voltage to ground corresponding to the identification time period △t and the first resistance values, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model, including:

[0018] A deep learning network is used to learn the voltage to ground and the second resistance value corresponding to the identification time period △t, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model.

[0019] In an optional implementation, the resistance prediction model includes a ground voltage prediction model and a leakage current prediction model; and the configuration steps of the resistance prediction model include:

[0020] Inputting different first historical times into the ground voltage prediction model to be adjusted, and obtaining the ground predicted voltages at the different first historical times output by the ground voltage prediction model to be adjusted;

[0021] Based on the predicted voltages to the ground at the different first historical times and the actual voltages to the ground at the corresponding times, adjusting the voltage to the ground prediction model to be adjusted to obtain the voltage to the ground prediction model;

[0022] Inputting the historical leakage current collected at different second historical times and corresponding times into the leakage current prediction model to be adjusted, and obtaining the predicted leakage current at the different second historical times output by the leakage current prediction model to be adjusted;

[0023] Based on the predicted leakage currents at the different second historical times and the actual leakage currents at the corresponding times, the leakage current prediction model to be adjusted is adjusted to obtain the leakage current prediction model.

[0024] In an optional implementation, inputting the current voltage to ground and the predicted time into a preconfigured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time includes:

[0025] Inputting the predicted time into an adjusted ground voltage prediction model to obtain a predicted ground voltage corresponding to the predicted time output by the ground voltage prediction model;

[0026] Inputting the predicted time into the adjusted leakage current prediction model to obtain the predicted leakage current corresponding to the predicted time output by the leakage current prediction model;

[0027] Based on the predicted leakage current and the predicted voltage to ground corresponding to the predicted time, the insulation resistance value corresponding to the predicted time is obtained.

[0028] In an optional implementation, the insulation resistance detection circuit further includes a first resistor, a second resistor, a third resistor, a fourth resistor, a fifth resistor, a first voltage collection resistor, and a second voltage collection resistor;

[0029] One end of the insulation resistance of the positive electrode to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch is connected to the positive electrode of the battery pack, the other end of the insulation resistance of the positive electrode to ground is connected to one end of the insulation resistance of the negative electrode to ground and is grounded, and the other end of the insulation resistance of the negative electrode to ground is connected to the negative electrode of the battery pack;

[0030] One end of the first resistor is connected in series with one end of the second resistor, the other end of the first resistor is connected to the positive electrode of the battery pack; the other end of the second resistor is grounded;

[0031] One end of the third resistor is connected in series with one end of the fourth resistor, and the other end of the third resistor is connected; the other end of the fourth resistor is connected to the negative electrode of the battery pack;

[0032] One end of the fifth resistor is connected to the positive electrode of the battery pack, and the other end of the fifth resistor is grounded;

[0033] One end of the first voltage collection resistor and one end of the second voltage collection resistor are connected in series, the other end of the first voltage collection resistor is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor is connected to the negative electrode of the battery pack.

[0034] In an optional implementation, in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch, one end of the insulation resistance of the positive electrode to ground is connected to the positive electrode of the battery pack, the other end of the insulation resistance of the positive electrode to ground is connected to one end of the insulation resistance of the negative electrode to ground and is grounded, and the other end of the insulation resistance of the negative electrode to ground is connected to the negative electrode of the battery pack;

[0035] One end of the second resistor is grounded, and the other end of the second resistor is connected to the negative electrode of the battery pack;

[0036] One end of the third resistor is connected in series with one end of the fourth resistor, and the other end of the third resistor is connected; the other end of the fourth resistor is connected to the negative electrode of the battery pack;

[0037] One end of the fifth resistor is connected to the positive electrode of the battery pack, and the other end of the fifth resistor is grounded;

[0038] One end of the first voltage collection resistor and one end of the second voltage collection resistor are connected in series, the other end of the first voltage collection resistor is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor is connected to the negative electrode of the battery pack.

[0039] In a second aspect, a device for predicting insulation resistance of an extended-range vehicle is provided, and the device may include:

[0040] A collection unit, used for collecting the current voltage of the insulation resistance to ground in the insulation resistance detection circuit in real time; the insulation resistance includes the insulation resistance of the positive pole to ground and the insulation resistance of the negative pole to ground;

[0041] An acquisition unit is used to input the predicted time of the current voltage to ground and business demand into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value changing with time.

[0042] In an optional implementation, the insulation resistance detection circuit further includes an optocoupler switch and a field effect switch; and the prediction device further includes a first configuration unit:

[0043] The first configuration unit is used to:

[0044] Collecting a first voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch, and collecting a second voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch; the first voltage curve and the second voltage curve constitute a cycle of the voltage to ground curve;

[0045] On the first voltage curve and the second voltage curve, respectively searching for an identification time period Δt corresponding to a target voltage change rate within a preset voltage change rate range, where the preset voltage change rate range is a preset stable change range of the voltage change rate;

[0046] Calculating each first resistance value of the insulation resistance based on each ground voltage within the identification time period Δt and a known resistance value in the insulation resistance detection circuit;

[0047] A deep learning network is used to learn the voltage to ground and the first resistance values ​​corresponding to the identification time period △t, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model.

[0048] In an optional implementation, before using a deep learning network to learn the voltage to ground corresponding to the identification time period △t and the first resistance values, and the changing trend of the voltage to ground at different times on the voltage to ground curve, the configuration unit is further used to:

[0049] Calculate the error between each first resistance value and the actual resistance value of the corresponding insulation resistor;

[0050] Obtain a second resistance value corresponding to a target error value that is less than a preset error threshold value among the calculated error values;

[0051] A deep learning network is used to learn the voltage to ground corresponding to the identification time period △t and the first resistance values, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model, including:

[0052] A deep learning network is used to learn the voltage to ground and the second resistance value corresponding to the identification time period △t, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model.

[0053] In an optional implementation, the resistance prediction model includes a ground voltage prediction model and a leakage current prediction model; the prediction device also includes a second configuration unit:

[0054] The second configuration unit is used to:

[0055] Inputting different first historical times into the ground voltage prediction model to be adjusted, and obtaining the ground predicted voltages at the different first historical times output by the ground voltage prediction model to be adjusted;

[0056] Based on the predicted voltages to the ground at the different first historical times and the actual voltages to the ground at the corresponding times, adjusting the voltage to the ground prediction model to be adjusted to obtain the voltage to the ground prediction model;

[0057] Inputting the historical leakage current collected at different second historical times and corresponding times into the leakage current prediction model to be adjusted, and obtaining the predicted leakage current at the different second historical times output by the leakage current prediction model to be adjusted;

[0058] Based on the predicted leakage currents at the different second historical times and the actual leakage currents at the corresponding times, the leakage current prediction model to be adjusted is adjusted to obtain the leakage current prediction model.

[0059] In an optional implementation, the acquisition unit is specifically used to:

[0060] Inputting the predicted time into an adjusted ground voltage prediction model to obtain a predicted ground voltage corresponding to the predicted time output by the ground voltage prediction model;

[0061] Inputting the predicted time into the adjusted leakage current prediction model to obtain the predicted leakage current corresponding to the predicted time output by the leakage current prediction model;

[0062] Based on the predicted leakage current and the predicted voltage to ground corresponding to the predicted time, the insulation resistance value corresponding to the predicted time is obtained.

[0063] In an optional implementation, the insulation resistance detection circuit further includes a first resistor, a second resistor, a third resistor, a fourth resistor, a fifth resistor, a first voltage collection resistor, and a second voltage collection resistor;

[0064] One end of the insulation resistance of the positive electrode to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch is connected to the positive electrode of the battery pack, the other end of the insulation resistance of the positive electrode to ground is connected to one end of the insulation resistance of the negative electrode to ground and is grounded, and the other end of the insulation resistance of the negative electrode to ground is connected to the negative electrode of the battery pack;

[0065] One end of the first resistor is connected in series with one end of the second resistor, the other end of the first resistor is connected to the positive electrode of the battery pack; the other end of the second resistor is grounded;

[0066] One end of the third resistor is connected in series with one end of the fourth resistor, and the other end of the third resistor is connected; the other end of the fourth resistor is connected to the negative electrode of the battery pack;

[0067] One end of the fifth resistor is connected to the positive electrode of the battery pack, and the other end of the fifth resistor is grounded;

[0068] One end of the first voltage collection resistor and one end of the second voltage collection resistor are connected in series, the other end of the first voltage collection resistor is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor is connected to the negative electrode of the battery pack.

[0069] In an optional implementation, in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch, one end of the insulation resistance of the positive electrode to ground is connected to the positive electrode of the battery pack, the other end of the insulation resistance of the positive electrode to ground is connected to one end of the insulation resistance of the negative electrode to ground and is grounded, and the other end of the insulation resistance of the negative electrode to ground is connected to the negative electrode of the battery pack;

[0070] One end of the second resistor is grounded, and the other end of the second resistor is connected to the negative electrode of the battery pack;

[0071] One end of the third resistor is connected in series with one end of the fourth resistor, and the other end of the third resistor is connected; the other end of the fourth resistor is connected to the negative electrode of the battery pack;

[0072] One end of the fifth resistor is connected to the positive electrode of the battery pack, and the other end of the fifth resistor is grounded;

[0073] One end of the first voltage collection resistor and one end of the second voltage collection resistor are connected in series, the other end of the first voltage collection resistor is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor is connected to the negative electrode of the battery pack.

[0074] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0075] Memory, used to store computer programs;

[0076] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0077] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0078] The present application provides a method and device for predicting the insulation resistance of an extended-range vehicle. After real-time acquisition of the current voltage to ground of the insulation resistance in the insulation resistance detection circuit, the method inputs the current voltage to ground and the predicted time of the business demand into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value over time. The method is based on the existing bridge method for calculating the insulation resistance value, and adopts an adaptive model to improve the efficiency and accuracy of calculating the insulation resistance value. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0080] Figure 1 A schematic diagram of the structure of an insulation resistance detection circuit provided in an embodiment of the present application;

[0081] Figure 2 A schematic diagram of the structure of an equivalent circuit of an insulation resistance detection circuit provided in an embodiment of the present application;

[0082] Figure 3 A schematic diagram of the structure of an equivalent circuit of another insulation resistance detection circuit provided in an embodiment of the present application;

[0083] Figure 4 A schematic flow chart of a method for predicting insulation resistance of an extended-range vehicle provided in an embodiment of the present application;

[0084] Figure 5 A schematic diagram of a voltage curve to ground provided in an embodiment of the present application;

[0085] Figure 6 A schematic diagram of the structure of a device for predicting insulation resistance of an extended-range vehicle provided in an embodiment of the present application;

[0086] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0088] Figure 1 This is a schematic diagram of the structure of an insulation resistance detection circuit provided in an embodiment of the present application. Figure 1 As shown, the insulation resistance detection circuit may include a battery pack, an insulation resistor RP between the positive electrode and the ground, an insulation resistor RN between the negative electrode and the ground, an optocoupler switch K1, a field effect switch Q1, a first resistor R1, a second resistor R2, a third resistor R3, a fourth resistor R4, a fifth resistor R5, a first voltage collection resistor RV1, and a second voltage collection resistor RV2.

[0089] One end of the positive electrode-to-ground insulation resistor RP is connected to the positive electrode of the battery pack, the other end of the positive electrode-to-ground insulation resistor RP is connected to one end of the negative electrode-to-ground insulation resistor RN and is grounded, and the other end of the negative electrode-to-ground insulation resistor RN is connected to the negative electrode of the battery pack;

[0090] One end of the first resistor R1 is connected in series with one end of the second resistor R2, and the other end of the first resistor R1 is connected to the positive electrode of the battery pack; the other end of the second resistor R2 is connected to the first end of the optocoupler switch K1; the second end of the optocoupler switch K1 is grounded, the third end of the optocoupler switch K1 is connected to the voltage VCC, and the fourth end of the optocoupler switch K1 is connected to the MCU of the electric vehicle;

[0091] The source of the field effect switch Q1 is connected to the negative electrode of the battery pack, the drain is connected to the other end of the insulation resistor RP between the positive electrode and the ground, and the gate is connected to the mode converter ADC outside the circuit;

[0092] One end of the third resistor R3 is connected in series with one end of the fourth resistor R4, and the other end of the third resistor R3 is connected to the other end of the second resistor R2; the other end of the fourth resistor is connected to the negative electrode of the battery pack; wherein the output voltage at the connection point of the third resistor R3 and the fourth resistor R4 is V; the output voltage is input to the mode converter ADC outside the circuit;

[0093] One end of the fifth resistor R5 is connected to the positive electrode of the battery pack, and the other end of the fifth resistor R5 is connected to the other end of the second resistor R2;

[0094] One end of the first voltage collection resistor RV1 is connected in series with one end of the second voltage collection resistor RV2, the other end of the first voltage collection resistor RV1 is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor RV2 is connected to the negative electrode of the battery pack. The output voltage at the connection point of the first voltage collection resistor RV1 and the second voltage collection resistor RV2 is VB; the output voltage is input to the mode converter ADC outside the circuit;

[0095] Further, when the optocoupler switch K1 and the field effect switch Q1 are closed, one end of the first resistor R1 is connected in series with the second resistor R2, such as Figure 2 As shown, at this time, the voltage at the connection point of the third resistor R3 and the fourth resistor R4 in series is V1, and the voltage at the connection point of the first voltage collection resistor RV1 and the second voltage collection resistor RV2 in series is VB1; when the optocoupler switch K1 is closed and the field effect switch Q1 is opened, one end of the first resistor R1 is disconnected, and at this time, one end of the second resistor R2 is grounded, and the other end is connected to the negative electrode of the battery pack, as shown in FIG. Figure 3 As shown, at this time, the voltage at the third resistor R3 and the fourth resistor R4 in series is V2, and the voltage at the first voltage collection resistor RV1 and the second voltage collection resistor RV2 in series is VB2. That is, the insulation resistance detection circuit provided in the embodiment of the present application has the above two equivalent circuit states.

[0096] It should be noted that Figure 2 and Figure 3 The mode converter ADC outside the circuit is not drawn. The output voltage of the battery pack, the voltage values ​​of V1, VB1, V2 and VB2 are all known quantities, the resistance values ​​of the first resistor R1, the second resistor R2, the third resistor R3, the fourth resistor R4, the fifth resistor R5, the first voltage acquisition resistor RV1 and the second voltage acquisition resistor RV2 are all known quantities, and the insulation resistance RP of the positive electrode to the ground and the insulation resistance RN of the negative electrode to the ground are all unknown quantities. Compared with the prior art, the insulation resistance detection circuit of the embodiment of the present application only uses a single optical coupler relay to realize the above two equivalent circuit states, which reduces the cost.

[0097] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0098] Based on the two connection states of the insulation resistance detection circuit provided in the above embodiment, Figure 4 As shown, the embodiment of the present application provides a flow chart of a method for predicting insulation resistance of an extended-range vehicle, which is applied to a battery management system BMS, including:

[0099] Step S410: collecting the current voltage of the insulation resistance to ground in the insulation resistance detection circuit in real time.

[0100] The insulation resistance may include the insulation resistance of the positive pole to the ground and the insulation resistance of the negative pole to the ground, so the current voltage of the insulation resistance to the ground includes the current voltage of the insulation resistance of the positive pole to the ground and the current voltage of the insulation resistance of the negative pole to the ground.

[0101] The insulation resistance detection circuit also includes an optocoupler switch K1 and a field effect switch Q1, a first resistor R1, a second resistor R2, a third resistor R3, a fourth resistor R4, a fifth resistor R5, a first voltage collection resistor RV1 and a second voltage collection resistor RV2.

[0102] Step S420: Input the current voltage to ground and the predicted time of the service demand into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time.

[0103] In the specific implementation, a resistance prediction model is first configured based on the voltage to ground in the historical time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value over time.

[0104] Obtain the predicted time of business demand, that is, the insulation resistance value at the predicted time after a period of time that the business demand wants to know;

[0105] The current voltage to ground and the predicted time are input into a pre-configured resistance prediction model. The resistance prediction model outputs the insulation resistance value corresponding to the predicted time based on the temporal relationship between the voltage to ground and the insulation resistance value.

[0106] It can be seen that the above embodiment can quickly calculate the insulation resistance value corresponding to the prediction time in the same insulation resistance detection circuit through the pre-configured resistance prediction model, thereby improving the calculation efficiency.

[0107] In some embodiments, the step of configuring the resistance prediction model may include:

[0108] Step A, collecting a first voltage curve of the voltage to ground in the insulation resistance detection circuit of the closed optocoupler switch K1 and the field effect switch Q1, and collecting a second voltage curve of the voltage to ground in the insulation resistance detection circuit of the closed optocoupler switch K1 and the open field effect switch Q1.

[0109] The curve of the voltage to ground formed by the insulation resistance detection circuit that controls the closing and opening of the field effect switch Q1 at each time is as follows: Figure 5The voltage curve to ground shown in the figure, the first voltage curve is a curve formed by the voltage to ground in the insulation resistance detection circuit of the closed field effect switch Q1, and the second voltage curve is a curve formed by the voltage to ground in the insulation resistance detection circuit of the open field effect switch Q1. The first voltage curve and the second voltage curve constitute a cycle of the voltage curve to ground.

[0110] Step B: searching for an identification time period Δt corresponding to a target voltage change rate within a preset voltage change rate range on the first voltage curve and the second voltage curve respectively.

[0111] The preset voltage change rate range is a preset range of stable change of the voltage change rate, such as (K1, K2), K1 represents the starting value of the stable change of the voltage change rate, and K2 represents the ending value of the stable change of the voltage change rate.

[0112] Specifically, on the first voltage curve and the second voltage curve, the ratio of the change amount of each adjacent voltage to the ground on the corresponding voltage curve to the corresponding time change amount, that is, the voltage change rate corresponding to each adjacent voltage to the ground is calculated respectively;

[0113] Find the target voltage change rate that meets the preset voltage change rate range, and obtain the identification time period △t corresponding to the corresponding target voltage change rate. Figure 4 , the identification time period on the first voltage curve is △t1, and the voltage value to ground within the identification time period △t1 is recorded at the same time; the identification time period on the second voltage curve is △t2, and the voltage value to ground within the identification time period △t1 is recorded at the same time.

[0114] Step C: Calculate each first resistance value of the insulation resistance based on each ground voltage within the identification time period Δt and the known resistance value in the insulation resistance detection circuit.

[0115] Combination Figure 2 and Figure 3 For the two equivalent circuit states shown, the voltage-resistance association algorithm can be used to calculate the known resistance values ​​in the respective ground voltages and the insulation resistance detection circuit within the identification time period △t, and obtain the first resistance value of the insulation resistance corresponding to each ground voltage, that is, the resistance value of the insulation resistance RP and the insulation resistance RN corresponding to each ground voltage.

[0116] The known resistance values ​​include the resistance values ​​of the first resistor R1 , the second resistor R2 , the third resistor R3 , the fourth resistor R4 , the fifth resistor R5 , the first voltage collection resistor RV1 , and the second voltage collection resistor RV2 .

[0117] Combination Figure 2 and Figure 3 In the two equivalent circuit states shown, the calculation formula for the first resistance value of the insulation resistance corresponding to any voltage to ground can be expressed as:

[0118] (VB1 / V1-1)=(1 / Rn+1 / Rb) / (1 / Rp+1 / Ra);

[0119] Ra=(R1+R2) / / R5;

[0120] Rb=R3+R4;

[0121] (VB2 / V2-1)=(1 / Rn+1 / Rb2) / (1 / Rp+1 / Ra2);

[0122] Ra2=R5;

[0123] Rb2=(R3+R4) / / R2;

[0124] It should be noted that, under ideal conditions where there are no errors in the calculation or voltage measurement processes, the first resistance values ​​of the insulation resistance RP or the insulation resistance RN corresponding to the voltage to ground at each time should be the same. However, since errors may exist in the calculation or voltage measurement processes, the first resistance values ​​of the insulation resistance RP or the insulation resistance RN corresponding to the voltage to ground at each time may be different.

[0125] Step D: using a deep learning network to learn the voltage to ground and each first resistance value corresponding to the identification time period △t, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model.

[0126] Based on the above embodiment, in order to further improve the accuracy of the resistance prediction model, the accuracy of each calculated first resistance value may be tested, that is, before executing step D, the error value between each first resistance value and the actual resistance value of the corresponding insulation resistance is calculated;

[0127] The second resistance value corresponding to the target error value less than the preset error threshold value in the calculated error value is obtained; the target error value is the minimum error value allowed by the business, such as 0.01Ω. At the same time, the change trend of the voltage to ground at different times on the voltage to ground curve is obtained.

[0128] Afterwards, a deep learning network is used to learn the voltage to ground and the second resistance value corresponding to the identification time period △t, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model.

[0129] It can be seen that the resistance prediction model is configured based on the ground voltage and the actual insulation resistance value of the same insulation resistance detection circuit, which improves the accuracy of calculating the insulation resistance value.

[0130] In some other embodiments, the resistance prediction model may include a ground voltage prediction model and a leakage current prediction model; in this case, the configuration steps of the resistance prediction model may include:

[0131] Step 1: Input different first historical times into the ground voltage prediction model to be adjusted to obtain the ground predicted voltages at different first historical times output by the ground voltage prediction model to be adjusted.

[0132] Step 2: Based on the predicted voltages to the ground at different first historical times and the actual voltages to the ground at corresponding times, the voltage to the ground prediction model to be adjusted is adjusted to obtain a voltage to ground prediction model.

[0133] Step 3: input different second historical times into the leakage current prediction model to be adjusted, and obtain the predicted leakage currents at different second historical times output by the leakage current prediction model to be adjusted.

[0134] Step 4: Based on the predicted leakage currents at different second historical times and the actual leakage currents at corresponding times, the leakage current prediction model to be adjusted is adjusted to obtain a leakage current prediction model.

[0135] Further, based on the above resistance prediction model, step S320 may specifically include:

[0136] Inputting the predicted time into the adjusted ground voltage prediction model to obtain the predicted ground voltage corresponding to the predicted time output by the ground voltage prediction model;

[0137] Input the predicted time into the adjusted leakage current prediction model to obtain the predicted leakage current corresponding to the predicted time output by the leakage current prediction model;

[0138] Based on the predicted leakage current corresponding to the predicted time and the predicted voltage to ground, the insulation resistance value corresponding to the predicted time is obtained.

[0139] Furthermore, the above two types of resistance prediction models are suitable for different working stages of the vehicle, that is, the above two types of resistance prediction models will be triggered or adopted only when they are suitable for the working stages of the vehicle to improve the accuracy of calculation.

[0140] Specifically, the resistance prediction model based on the deep learning network is suitable for the vehicle startup phase and realizes the fast check mode (Fast Check), which reports the insulation resistance value in about 1 second.

[0141] The resistance prediction model composed of the ground voltage prediction model and the leakage current prediction model is suitable for the quasi-static working stage after the battery pack is powered on with high voltage, and realizes the normal detection mode (Normal Check). The time for reporting the insulation resistance value in this mode is about 15 seconds.

[0142] In some embodiments, in order to further improve the accuracy of the resistance prediction model based on the deep learning network, after determining the identification time period △t, the voltage curve of the voltage to ground can be re-searched for the identification time period △t corresponding to the target voltage change rate within the preset voltage change rate range, that is, the voltage collection interval is re-determined, and the change trend of the voltage to ground at different times on the voltage to ground curve after a period of time is re-obtained, thereby updating the resistance prediction model.

[0143] In summary, compared with the prior art, the method for predicting the insulation resistance of an extended-range vehicle provided in the embodiment of the present application adopts an adaptive model based on the existing bridge method for calculating the insulation resistance value, thereby improving the efficiency and accuracy of calculating the insulation resistance value and avoiding false alarms and missed alarms to the BMS.

[0144] Corresponding to the above method, the embodiment of the present application also provides a prediction device for the insulation resistance of an extended-range vehicle, such as Figure 6 As shown, the prediction device includes: a collection unit 610 and an acquisition unit 620;

[0145] The acquisition unit 610 is used to acquire the current voltage of the insulation resistance to ground in the insulation resistance detection circuit in real time; the insulation resistance includes the insulation resistance of the positive electrode to ground and the insulation resistance of the negative electrode to ground;

[0146] The acquisition unit 620 is used to input the predicted time of the current voltage to ground and business demand into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value changing with time.

[0147] The functions of the various functional units of the device for predicting the insulation resistance of an extended-range vehicle provided in the above-mentioned embodiments of the present application can be achieved through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the device for predicting the insulation resistance of an extended-range vehicle provided in the embodiments of the present application will not be repeated here.

[0148] The present application also provides an electronic device, such as Figure 7 As shown, it includes a processor 710 , a communication interface 720 , a memory 730 and a communication bus 740 , wherein the processor 710 , the communication interface 720 , and the memory 730 communicate with each other via the communication bus 740 .

[0149] Memory 730, for storing computer programs;

[0150] The processor 710 is used to execute the program stored in the memory 730 to implement the following steps:

[0151] Real-time acquisition of the current voltage of the insulation resistance to ground in the insulation resistance detection circuit; the insulation resistance includes the insulation resistance of the positive pole to ground and the insulation resistance of the negative pole to ground;

[0152] The current voltage to ground and the predicted time of business demand are input into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time. The resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value changing with time.

[0153] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0154] The communication interface is used for communication between the above electronic device and other devices.

[0155] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0156] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be 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, discrete hardware components.

[0157] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 4 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0158] In another embodiment provided in the present application, a computer-readable storage medium is also provided, which stores instructions. When the computer-readable storage medium is executed on a computer, the computer executes the method for predicting the insulation resistance of an extended-range vehicle described in any of the above embodiments.

[0159] In another embodiment provided in the present application, a computer program product including instructions is also provided. When the computer program product is executed on a computer, the computer executes the method for predicting the insulation resistance of an extended-range vehicle described in any of the above embodiments.

[0160] Those skilled in the art will appreciate that the embodiments in the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt a complete hardware embodiment, a complete software embodiment, or a form of an embodiment combining software and hardware. Moreover, the present application may adopt a form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0162] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0164] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0165] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application fall within the scope of the claims and their equivalents in the embodiments of the present application, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A method for predicting insulation resistance of an extended-range vehicle, characterized in that: Applied to a battery management system, the method comprises: Real-time acquisition of the current voltage of the insulation resistance to ground in the insulation resistance detection circuit; the insulation resistance includes the insulation resistance of the positive pole to ground and the insulation resistance of the negative pole to ground; Input the current voltage to ground and the predicted time of the service demand into a pre-configured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time, wherein the resistance prediction model is used to describe the relationship between the voltage to ground and the insulation resistance value changing with time; Wherein, the insulation resistance detection circuit further includes an optocoupler switch and a field effect switch; and the configuration steps of the resistance prediction model include: Collecting a first voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch, and collecting a second voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch; the first voltage curve and the second voltage curve constitute a cycle of the voltage to ground curve; On the first voltage curve and the second voltage curve, respectively searching for an identification time period Δt corresponding to a target voltage change rate within a preset voltage change rate range, where the preset voltage change rate range is a preset stable change range of the voltage change rate; Calculating each first resistance value of the insulation resistance based on each ground voltage within the identification time period Δt and a known resistance value in the insulation resistance detection circuit; Using a deep learning network, the voltage to ground corresponding to the identification time period △t and the first resistance values, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve are learned to obtain a resistance prediction model; Before learning the voltage to ground and the first resistance values ​​corresponding to the identification time period Δt and the changing trend of the voltage to ground at different times on the voltage to ground curve using a deep learning network, the method further includes: Calculate the error between each first resistance value and the actual resistance value of the corresponding insulation resistor; Obtain a second resistance value corresponding to a target error value that is less than a preset error threshold value among the calculated error values; A deep learning network is used to learn the voltage to ground corresponding to the identification time period △t and the first resistance values, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model, including: Using a deep learning network, the voltage to ground and the second resistance value corresponding to the identification time period △t, as well as the change trend of the voltage to ground at different times on the voltage to ground curve are learned to obtain a resistance prediction model; Alternatively, the resistance prediction model includes a ground voltage prediction model and a leakage current prediction model; and the configuration steps of the resistance prediction model include: Inputting different first historical times into the ground voltage prediction model to be adjusted, and obtaining the ground predicted voltages at the different first historical times output by the ground voltage prediction model to be adjusted; Based on the predicted voltages to the ground at the different first historical times and the actual voltages to the ground at the corresponding times, adjusting the voltage to the ground prediction model to be adjusted to obtain the voltage to the ground prediction model; Inputting the historical leakage current collected at different second historical times and corresponding times into the leakage current prediction model to be adjusted, and obtaining the predicted leakage current at the different second historical times output by the leakage current prediction model to be adjusted; Based on the predicted leakage currents at the different second historical times and the actual leakage currents at the corresponding times, the leakage current prediction model to be adjusted is adjusted to obtain the leakage current prediction model; Inputting the current voltage to ground and the predicted time into a preconfigured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time, including: Inputting the predicted time into an adjusted ground voltage prediction model to obtain a predicted ground voltage corresponding to the predicted time output by the ground voltage prediction model; Inputting the predicted time into the adjusted leakage current prediction model to obtain the predicted leakage current corresponding to the predicted time output by the leakage current prediction model; Based on the predicted leakage current and the predicted voltage to ground corresponding to the predicted time, the insulation resistance value corresponding to the predicted time is obtained.

2. The method according to claim 1, characterized in that The insulation resistance detection circuit also includes a first resistor, a second resistor, a third resistor, a fourth resistor, a fifth resistor, a first voltage collection resistor and a second voltage collection resistor; One end of the insulation resistance of the positive electrode to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch is connected to the positive electrode of the battery pack, the other end of the insulation resistance of the positive electrode to ground is connected to one end of the insulation resistance of the negative electrode to ground and is grounded, and the other end of the insulation resistance of the negative electrode to ground is connected to the negative electrode of the battery pack; One end of the first resistor is connected in series with one end of the second resistor, the other end of the first resistor is connected to the positive electrode of the battery pack; the other end of the second resistor is grounded; One end of the third resistor is connected in series with one end of the fourth resistor, and the other end of the third resistor is connected; the other end of the fourth resistor is connected to the negative electrode of the battery pack; One end of the fifth resistor is connected to the positive electrode of the battery pack, and the other end of the fifth resistor is grounded; One end of the first voltage collection resistor and one end of the second voltage collection resistor are connected in series, the other end of the first voltage collection resistor is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor is connected to the negative electrode of the battery pack.

3. The method according to claim 2, characterized in that One end of the insulation resistance of the positive electrode to ground in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch is connected to the positive electrode of the battery pack, the other end of the insulation resistance of the positive electrode to ground is connected to one end of the insulation resistance of the negative electrode to ground and is grounded, and the other end of the insulation resistance of the negative electrode to ground is connected to the negative electrode of the battery pack; One end of the second resistor is grounded, and the other end of the second resistor is connected to the negative electrode of the battery pack; One end of the third resistor is connected in series with one end of the fourth resistor, and the other end of the third resistor is connected; the other end of the fourth resistor is connected to the negative electrode of the battery pack; One end of the fifth resistor is connected to the positive electrode of the battery pack, and the other end of the fifth resistor is grounded; One end of the first voltage collection resistor and one end of the second voltage collection resistor are connected in series, the other end of the first voltage collection resistor is connected to the positive electrode of the battery pack, and the other end of the second voltage collection resistor is connected to the negative electrode of the battery pack.

4. A device for predicting insulation resistance of an extended-range vehicle, characterized in that: Applied in a battery management system, the prediction device comprises: A collection unit, used for collecting the current voltage of the insulation resistance to ground in the insulation resistance detection circuit in real time; the insulation resistance includes the insulation resistance of the positive pole to ground and the insulation resistance of the negative pole to ground; An acquisition unit, used for inputting the current voltage to ground and the predicted time of the service demand into a pre-configured resistance prediction model, and acquiring the insulation resistance value corresponding to the predicted time, wherein the resistance prediction model is used for describing the relationship between the voltage to ground and the insulation resistance value changing with time; Wherein, the insulation resistance detection circuit further includes an optocoupler switch and a field effect switch; and the configuration process of the resistance prediction model includes: Collecting a first voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and the field effect switch, and collecting a second voltage curve of the voltage to ground in the insulation resistance detection circuit that closes the optocoupler switch and opens the field effect switch; the first voltage curve and the second voltage curve constitute a cycle of the voltage to ground curve; On the first voltage curve and the second voltage curve, respectively searching for an identification time period Δt corresponding to a target voltage change rate within a preset voltage change rate range, where the preset voltage change rate range is a preset stable change range of the voltage change rate; Calculating each first resistance value of the insulation resistance based on each ground voltage within the identification time period Δt and a known resistance value in the insulation resistance detection circuit; Using a deep learning network, the voltage to ground corresponding to the identification time period △t and the first resistance values, as well as the changing trend of the voltage to ground at different times on the voltage to ground curve are learned to obtain a resistance prediction model; Before learning the voltage to ground and the first resistance values ​​corresponding to the identification time period △t and the changing trend of the voltage to ground at different times on the voltage to ground curve by using a deep learning network, the device further includes a calculation unit and a learning unit; The calculation unit is used to calculate the error value between each first resistance value and the actual resistance value of the corresponding insulation resistor; The acquisition unit is further used to acquire a second resistance value corresponding to a target error value that is less than a preset error threshold value among the calculated error values; The learning unit is used to use a deep learning network to learn the voltage to ground corresponding to the identification time period △t and the first resistance values, as well as the change trend of the voltage to ground at different times on the voltage to ground curve to obtain a resistance prediction model, including: And, using a deep learning network, learning the voltage to ground and the second resistance value corresponding to the identification time period △t, and the change trend of the voltage to ground at different times on the voltage to ground curve, to obtain a resistance prediction model; Alternatively, the resistance prediction model includes a ground voltage prediction model and a leakage current prediction model; and the configuration steps of the resistance prediction model include: Inputting different first historical times into the ground voltage prediction model to be adjusted, and obtaining the ground predicted voltages at the different first historical times output by the ground voltage prediction model to be adjusted; Based on the predicted voltages to the ground at the different first historical times and the actual voltages to the ground at the corresponding times, adjusting the voltage to the ground prediction model to be adjusted to obtain the voltage to the ground prediction model; Inputting the historical leakage current collected at different second historical times and corresponding times into the leakage current prediction model to be adjusted, and obtaining the predicted leakage current at the different second historical times output by the leakage current prediction model to be adjusted; Based on the predicted leakage currents at the different second historical times and the actual leakage currents at the corresponding times, the leakage current prediction model to be adjusted is adjusted to obtain the leakage current prediction model; Inputting the current voltage to ground and the predicted time into a preconfigured resistance prediction model to obtain the insulation resistance value corresponding to the predicted time, including: Inputting the predicted time into an adjusted ground voltage prediction model to obtain a predicted ground voltage corresponding to the predicted time output by the ground voltage prediction model; Inputting the predicted time into the adjusted leakage current prediction model to obtain the predicted leakage current corresponding to the predicted time output by the leakage current prediction model; Based on the predicted leakage current and the predicted voltage to ground corresponding to the predicted time, the insulation resistance value corresponding to the predicted time is obtained.

5. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 3 when executing a program stored in a memory.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 3 are implemented.

Images