Vehicle power control method and system and vehicle

Abstract

The invention provides a vehicle power control method and system and a vehicle, and relates to the technical field of vehicle electronic control, and the method comprises the following steps: determining the intensity of noise energy of the vehicle under a preset operation condition; adjusting the length of a data window of the vehicle noise signal according to the intensity of the noise energy; on the basis of the adjusted length of the data window, historical vehicle speed data at a plurality of continuous moments in a preset time period are obtained; predicting a target vehicle speed difference between the current moment and the next moment based on the historical vehicle speed difference between the historical vehicle speed data at the adjacent moments; and determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference, and performing power control on the vehicle according to the output torque at the next moment. The problem that in the prior art, a vehicle sensing signal is prone to being interfered by the external environment, and consequently the signal performance and reliability become poor is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle electronic control, and particularly to a vehicle power control method, system and vehicle. Background Art

[0002] During the driving process of an electric vehicle, an acceleration sensor collects an acceleration signal of an acceleration pedal and transmits it to a controller ECU. The controller ECU analyzes and judges, and controls the rotational speed and power output by a motor through an actuator ABS, so that the rotational speed increases when the acceleration pedal is depressed and decreases when the acceleration pedal is lifted.

[0003] However, in working conditions such as rapid acceleration of a vehicle, weak signals or other command signals collected by a sensor are liable to attenuate during transmission and are interfered by an external environment, resulting in poor accuracy and reliability of the signal, and being unable to reflect in real time a true vehicle speed difference to be transmitted, thereby affecting subsequent power control of the vehicle. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a vehicle power control method, system and vehicle, which solve the problem that vehicle sensing signals in the prior art are liable to be interfered by an external environment, resulting in poor signal quality and reliability.

[0005] At least one embodiment of the present invention provides a vehicle power control method, including:

[0006] Determining an intensity of noise energy when a vehicle is in a preset operating condition;

[0007] Adjusting a length of a data window of a vehicle noise signal according to the intensity of the noise energy;

[0008] Based on the adjusted length of the data window, obtaining historical vehicle speed data at a plurality of consecutive moments within a preset time period;

[0009] Predicting a target vehicle speed difference between a current moment and a next moment based on a historical vehicle speed difference between the historical vehicle speed data at each adjacent moment;

[0010] Combining a current vehicle torque and the target vehicle speed difference to determine an output torque at the next moment, and performing power control on the vehicle according to the output torque at the next moment.

[0011] The technical solution publicly provided by the present invention at least has the following beneficial effects:

[0012] According to the detection result of the intensity of the noise energy, the length of the data window is adjusted, which can adaptively improve the resistance of the subsequent predicted target vehicle speed difference to noise. That is, when the noise energy under the current working condition is small, the length of the data window can be reduced to improve the calculation rate. When the noise energy under the current working condition is large, the length of the data window can be increased to obtain more data to predict the output torque at the next moment, so as to improve the accuracy and reliability of the data torque at the next moment finally predicted.

[0013] In a vehicle power control method provided in an embodiment of the present invention, the obtaining the intensity of the noise energy when the vehicle is in a preset operating condition includes:

[0014] When the vehicle is in a preset operating condition, based on the signals transmitted between preset devices, at least one of the signal variance, gradient change rate, spectrum change rate, adjacent frame difference, and signal-to-noise ratio is detected for the noise energy, and the detection result of the noise energy is determined.

[0015] In a vehicle power control method provided in an embodiment of the present invention, the obtaining the historical vehicle speed data at a plurality of consecutive moments within the preset time period based on the adjusted length of the data window includes:

[0016] Based on the adjusted length of the data window, historical response frames at a plurality of consecutive moments within the preset time period are obtained, and the response frames represent frame data in the CAN bus that responds to the vehicle speed change;

[0017] From the target data bits of each of the historical response frames, the historical vehicle speed data at the corresponding moment is determined, wherein the determination step of the target data bit includes:

[0018] Obtain the first target response frame;

[0019] Based on the mutual information entropy algorithm, calculate the correlation degree between the data stored in each data bit in the first target response frame and the vehicle speed change to obtain correlation degree data, and the correlation degree data includes the correlation degree corresponding to each data bit;

[0020] Determine the data bit with the highest correlation degree in the correlation degree data as the target data bit storing the vehicle speed data.

[0021] The technical solution provided by the present invention at least has the following beneficial effects:

[0022] By using the data bit with the highest correlation degree as the target data set bit storing the vehicle speed data, the vehicle speed data parameters can be quickly and accurately extracted for different vehicle type CAN protocols, so that the method can support cross-vehicle type protocol parsing and improve the compatibility of the method.

[0023] In a vehicle power control method provided by one embodiment of the present invention, obtaining historical vehicle speed data at a plurality of consecutive moments within the preset time period based on the adjusted length of the data window includes:

[0024] Obtain a preset feature database, where the feature database includes the mapping relationship between the formats of the second target response frames in a plurality of preset vehicle type protocols that respond to vehicle speed changes and the target data bits storing vehicle speed data in the second target response frames;

[0025] Combining the target format of the response frame in response to the control instruction issued by the vehicle condition simulator and the feature database, determine the target data bits corresponding to the target format;

[0026] Based on the adjusted length of the data window, obtain historical response frames at a plurality of consecutive moments within the preset time period, where the response frames are frame data in the CAN bus that respond to vehicle speed changes;

[0027] Determine the historical vehicle speed data at the corresponding moment from the target data bits of each historical response frame.

[0028] The technical solution provided by the present invention at least has the following beneficial effects:

[0029] Through the constructed feature database, it is also possible to quickly and accurately extract vehicle speed data parameters for different vehicle type CAN protocols, improving the compatibility of this method.

[0030] In a vehicle power control method provided by one embodiment of the present invention, predicting the target vehicle speed difference between the current moment and the next moment based on the historical vehicle speed difference between the historical vehicle speed data at each adjacent moment includes:

[0031] According to the time-weighted decay method, assign weights to the historical vehicle speed differences between the historical vehicle speed data at each adjacent moment to obtain multiple labeled historical vehicle speed differences, where the time-weighted decay method is characterized by assigning weights from low to high to each historical vehicle speed difference according to the order of occurrence of the corresponding moments from first to last;

[0032] Based on a preset time series prediction model, predict the target vehicle speed difference between the current moment and the next moment according to the multiple labeled historical vehicle speed differences.

[0033] The technical solution provided by the present invention at least has the following beneficial effects:

[0034] By assigning different weights to the historical vehicle speed differences, when predicting the target vehicle speed difference between the current moment and the next moment subsequently, the weights of recent data can be increased, thereby improving the accuracy of the finally predicted target vehicle speed difference.

[0035] In a vehicle power control method provided by one embodiment of the present invention, before determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference, and performing power control on the vehicle according to the output torque at the next moment, it further includes:

[0036] Obtain the historical target vehicle speed differences and historical actual vehicle speed differences predicted at multiple consecutive moments within the preset time period;

[0037] Determine the differences between each of the historical target vehicle speed differences and the historical actual vehicle speed differences at the corresponding moments;

[0038] Based on the feedforward-feedback composite control module, according to each of the historical target vehicle speed differences, predict the feedforward predicted vehicle speed difference at the next moment through the feedforward path, and calculate the closed-loop correction amount through the feedback path based on each of the differences, and fuse the feedforward predicted vehicle speed difference and the closed-loop correction amount to generate the target difference at the next moment;

[0039] Update the target vehicle speed difference based on the target difference.

[0040] The technical solution provided by the present invention at least has the following beneficial effects:

[0041] After the target vehicle speed difference obtained by preliminary prediction, then use the feedforward-feedback composite control model to correct the detailed error of the target vehicle speed difference, so as to further improve the prediction accuracy of the target vehicle speed difference.

[0042] In a vehicle power control method provided by one embodiment of the present invention, the step of determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference, and performing power control on the vehicle according to the output torque at the next moment includes:

[0043] Obtain the slope value of the environment where the current vehicle is located;

[0044] In the case where the slope value is lower than or equal to the threshold, determine the output torque at the next moment based on the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment;

[0045] In the case where the slope value is higher than the threshold, determine the torque compensation amount at the next moment through a fuzzy logic controller based on the target vehicle speed difference and the slope value;

[0046] Determine the output torque at the next moment based on the current vehicle torque, the target vehicle speed difference, and the torque compensation amount;

[0047] Perform power control on the vehicle according to the output torque at the next moment.

[0048] The technical solution provided by the present invention at least has the following beneficial effects:

[0049] Based on the slope value, the torque compensation amount is calculated to improve the applicability of the method under various road conditions of the vehicle.

[0050] In a vehicle power control method provided by one embodiment of the present invention, the power control of the vehicle according to the output torque at the next moment includes:

[0051] Determine the change rate between the output torque at the next moment and the current vehicle torque;

[0052] When the change rate is greater than the preset maximum torque change rate, based on the maximum torque change rate and the current vehicle torque, determine the maximum output torque at the next moment, and perform power control on the vehicle according to the maximum output torque;

[0053] When the change rate is less than or equal to the preset maximum torque change rate, perform power control on the vehicle according to the output torque at the next moment.

[0054] The technical solution provided by the present invention at least has the following beneficial effects:

[0055] Through the above settings, the change rate of the output torque can be limited, power shock can be avoided, and smooth transition of the torque command can be achieved.

[0056] At least one embodiment of the present invention further provides a vehicle power control system, including:

[0057] A noise energy detection module, configured to determine the intensity of the noise energy when the vehicle is in a preset operating condition;

[0058] A dynamic window adjustment module, configured to adjust the length of the data window of the vehicle noise signal according to the intensity of the noise energy;

[0059] A data acquisition module, configured to acquire historical vehicle speed data at a plurality of consecutive moments within a preset time period based on the adjusted length of the data window;

[0060] A data processing module, configured to predict the target vehicle speed difference between the current moment and the next moment based on the vehicle speed difference between the historical vehicle speed data at adjacent moments;

[0061] A torque output module, configured to determine the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment.

[0062] The present invention also provides a vehicle, including a vehicle body and a vehicle power control system as described above configured on the vehicle body.

[0063] The present invention also provides an electronic device, including a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements a vehicle power control method as described above.

[0064] The present invention also provides a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a terminal device, the terminal device is caused to execute a vehicle power control method as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flowchart showing a vehicle power control method provided by the present invention;

[0066] Figure 2 It is a schematic structural diagram of a vehicle power control system provided by the present invention;

[0067] Figure 3 It is a schematic structural diagram of the electronic device provided by the present invention.

[0068] In the drawings, the list of components represented by each reference numeral is as follows:

[0069] 100, vehicle power control system; 101, noise energy detection module; 102, dynamic window adjustment module; 103, data acquisition module; 104, data processing module; 105, torque output module;

[0070] 10, electronic device; 11, processor; 12, read-only memory (ROM); 13, random access memory (RAM); 14, bus; 15, input / output (I / O) interface; 16, input unit; 17, output unit; 18, storage unit; 19, communication unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0071] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0072] The present invention provides a vehicle power control method. Please refer here Figure 1 as shown, including:

[0073] S1. Determine the intensity of the noise energy when the vehicle is in a preset operating condition;

[0074] S2. Adjust the length of the data window of the vehicle noise signal according to the intensity of the noise energy;

[0075] S3. Based on the adjusted length of the data window, obtain historical vehicle speed data at multiple consecutive moments within a preset time period;

[0076] S4, predicting a target vehicle speed difference between the current moment and the next moment based on the historical vehicle speed difference between the historical vehicle speed data at each adjacent moment;

[0077] S5. Determine the output torque at the next moment in combination with the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment.

[0078] By adjusting the length of the vehicle noise signal data window according to the detection result of the intensity of the noise energy, the resistance of the subsequent predicted target speed difference to noise can be adaptively improved. That is, when the noise energy under the current working condition is small, the length of the data window can be reduced to increase the calculation rate. When the noise energy under the current working condition is large, the length of the data window can be increased to obtain more data to predict the output torque at the next moment, so as to improve the accuracy and reliability of the final predicted data torque at the next moment.

[0079] Specifically, S1. determining the intensity of noise energy of the vehicle under a preset operating condition, including:

[0080] When the vehicle is in a preset operating condition (preferably a rapid acceleration condition in the present disclosure), based on the signal transmitted between preset devices, in this embodiment, the preset device is a device for transmitting and receiving the response frame described later, and the noise energy of at least one of the signal variance, gradient change rate, spectrum change rate, adjacent frame difference and signal-to-noise ratio is detected, and the detection result of the noise energy is determined.

[0081] Among them, the signal variance (σ 2 ) is used to reflect the degree of data discreteness and measure the intensity of steady-state noise. It is more suitable for broadband noise detection under rapid acceleration and braking conditions. The calculation method of signal variance is:

[0082]

[0083] Among them, the gradient change rate It is used to characterize the degree of signal mutation and detect transient interference. It is more suitable for detection under transient impact conditions such as vehicle shifting and ABS triggering. The calculation method of the gradient change rate is:

[0084]

[0085] Among them, the spectrum change rate (E HF) It is used to represent the proportion of high-frequency noise, distinguish mechanical vibration noise and electromagnetic interference, and is more specifically applicable to the working conditions of high-frequency motor whistling or CAN bus electromagnetic interference. The calculation method of the spectral change rate is as follows:

[0086]

[0087] Among them, the adjacent frame difference (Δν) is used to represent the mutation detection between consecutive frames and identify occasional pulse interference. It is more specifically applicable to the working conditions of sensor transient faults or communication packet loss. The calculation method of the adjacent frame difference is as follows:

[0088] Δν = ||x t -x t-1 ||

[0089] Among them, the signal-to-noise ratio is used to comprehensively evaluate the signal quality and is more specifically applicable to the global noise evaluation under complex working conditions. The calculation method of the signal-to-noise ratio is as follows:

[0090]

[0091] Optionally, in order to comprehensively consider various working conditions that the vehicle may encounter, in step S2, the length adjustment of the data window in the embodiments of the present disclosure refers to the signal variance, gradient change rate, and spectral change rate. The specific adjustment formula is as follows:

[0092]

[0093] Among them, N base = 5 (the length of the basic window), k1, k2, and k3 represent weight coefficients, which can be adjusted according to specific circumstances. In the embodiments of the present disclosure, k1, k2, and k3 are 3, 2, and 1 respectively. N min = 5, N max = 15, which is used to represent that the minimum value of the adjusted window length is 5 and the maximum value is 15.

[0094] Through the above adjustment formula, for example, in the working condition of rapid acceleration, the window length can be extended to 10 by using the above formula, so that the filtering delay is less than 50 ms. In the steady-state working condition, the window length is restored to 5 by using the above formula, and the delay is reduced to 20 ms.

[0095] Specifically, S3. Based on the length of the adjusted data window, obtain historical vehicle speed data at multiple consecutive moments within a preset time period, including:

[0096] Obtain the first target response frame that responds to the vehicle speed change from the CAN bus. Specifically, actively send control instructions of standardized CAN frames through a vehicle condition simulator (under conditions such as acceleration / deceleration / idle). Taking the acceleration instruction of a classic German car as an example, the ID is 0x7E0, the data (DLC) is 8, and at the same time, monitor the ID, data length (DLC), and the variation law of the data field of the first target response frame that responds to the vehicle speed change in the CAN bus.

[0097] The encoding rule of the above standardized CAN frame is as follows: In terms of numerical types, the throttle opening degree uses the UInt8 type, and the value range 0x00 - 0xFF corresponds to the actual 0 - 100%; the target vehicle speed uses the Float32 type to meet the high-precision numerical expression requirements. In terms of byte order, German cars follow Little-Endian, and some Japanese cars use Big-Endian. To ensure data accuracy, the CRC8 (polynomial 0x1D) check algorithm is used, and the calculated check value is embedded at the end of the data field.

[0098] Subsequently, based on the mutual information entropy algorithm, calculate the correlation degree between the data stored in each data bit in the response frame and the vehicle speed change to locate the encoding area of the vehicle speed parameter, and use the data bit with the highest correlation degree as the target data bit storing the vehicle speed data. For example, the vehicle speed value of a certain vehicle model is located in bytes 3 - 4 of ID = 0x2F4 and uses Little-Endian encoding;

[0099] Based on the adjusted length of the data window, obtain multiple consecutive historical response frames within a preset time period, that is, the current moment and multiple previous historical response frames. The data obtained from the historical response frames is consistent with the length of the data window. For example, if the adjusted length of the data window is 8, then obtain 8 historical response frames starting from the current moment and before it;

[0100] Determine the historical vehicle speed data at the corresponding moment from the target data bits of each historical response frame.

[0101] By using the data bit with the highest correlation degree as the target data set bit storing the vehicle speed data, the vehicle speed data parameters can be quickly and accurately extracted for different vehicle model CAN protocols, enabling this method to support cross-vehicle model protocol parsing and improving the compatibility of this method.

[0102] Optionally, to improve the correct rate of the vehicle model protocol matching of this disclosure, step S3 above, based on the adjusted length of the data window, obtain the historical vehicle speed data at multiple consecutive moments within a preset time period, may further include:

[0103] Before vehicle power control, it is necessary to establish a feature database, which includes the mapping relationship between the formats of response frames that respond to vehicle speed changes in multiple preset vehicle type protocols (covering the protocol rules of mainstream manufacturers) and the target data bits storing vehicle speed data in the response frames. The above formats can specifically be arbitration ID ranges, data bit definition modes (such as scale factors, offsets), etc.

[0104] For example: If it is detected that ID = 0x0CF00400 and DLC = 8, the German brand protocol library is preferentially matched, and the speed parameter is extracted as (data byte 2 × 256 + data byte 3) × 0.1 km / h.

[0105] Real vehicle acquisition: By collecting vehicle CAN bus data in real time under different working conditions, a large number of real and effective data samples are obtained.

[0106] Reverse parsing is performed on the engineering diagnostic protocols (ODiS files) of multiple manufacturers to deeply explore the protocol rules therein.

[0107] Integrate open-source DBC files such as CANdb++ and OpenXC to expand the compatibility of the database with different vehicle type protocols, enabling the database to be compatible with more than 200 vehicle types.

[0108] Feature extraction rules:

[0109] Arbitration ID range: Through a large amount of data statistical analysis, it is found that the IDs of speed-related data in German cars are mostly in the range of 0x2F0 - 0x3FF. By accurately defining the ID range, data frames related to speed parameters can be quickly screened out.

[0110] Data bit definition: For example, the speed value calculation rule for some vehicle types is (byte 2 << 8 + byte 3) × 0.1 km / h. By clarifying the definition and operation rules of data bits, the numerical value of the speed parameter can be accurately extracted.

[0111] Coding rules: There are segmented coding situations in Japanese cars, such as encoding speed parameters in the high 4 bits and low 8 bits of a byte. According to the coding characteristics of different vehicle types, corresponding parsing rules are formulated to ensure accurate parsing of speed parameters.

[0112] After presetting the above feature database, when it is necessary to determine vehicle speed data, the above feature database can be obtained;

[0113] Subsequently, in combination with the target format of the response frame in response to the control instruction issued by the vehicle condition simulator and the feature database, the target data bits corresponding to the target format are determined;

[0114] Based on the adjusted length of the data window, historical response frames at multiple consecutive moments within a preset time period are obtained;

[0115] Determine the historical vehicle speed data at the corresponding moment from the target data bits of each historical response frame.

[0116] In the present disclosure, the use of the feature database and the above-mentioned correlation degree can rely on any one of them alone to confirm and judge the target data bits, or the two can be used together for cross-verification.

[0117] Optionally, to further improve the prediction effect of the target vehicle speed difference, step S4 above, predicting the target vehicle speed difference between the current moment and the next moment based on the historical vehicle speed differences between the historical vehicle speed data at each adjacent moment, may further include:

[0118] According to the time-weighted decay method, assign weights to the historical vehicle speed differences between the historical vehicle speed data at each adjacent moment to obtain multiple labeled historical vehicle speed differences, where the time-weighted decay method is characterized by assigning weights from low to high to each historical vehicle speed difference according to the order of occurrence of the corresponding moments from first to last;

[0119] The formula for assigning the weight (W i ) is as follows:

[0120]

[0121] Among them, when i = 1, it represents the latest data, that is, the vehicle speed data at the current moment, and so on. When i = 2, it represents the vehicle speed data at the moment before the current moment;

[0122] Based on a preset time series prediction model, predict the target vehicle speed difference between the current moment and the next moment according to the multiple labeled historical vehicle speed differences.

[0123] In this embodiment, the above-mentioned preset time series prediction model is a moving average model, and its specific prediction process is as follows:

[0124] First, it is necessary to determine the length of the moving average window. For example, select the historical vehicle speed differences of the historical vehicle speed data of the past 5 time points to calculate the average value.

[0125] Sum up the historical vehicle speed differences within the window size before and including the current moment, and then divide by the window size to obtain the moving average value. For example, if the window size is 5 and the current moment is t, then calculate the average value of the historical vehicle speed differences at the five moments of t and t - 1, t - 1 and t - 2, t - 2 and t - 3, t - 3 and t - 4, t - 4 and t - 5.

[0126] Take the calculated moving average value as the prediction between the current moment and the next moment, that is, the target vehicle speed difference.

[0127] By assigning different weights to historical vehicle speed data, when predicting the target vehicle speed difference between the current moment and the next moment subsequently, the weight of recent data can be increased, thereby improving the accuracy of the finally predicted target vehicle speed difference.

[0128] Optionally, after the target vehicle speed difference is predicted in step S4, in order to further improve the prediction accuracy of the target vehicle speed difference, before determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference and performing power control on the vehicle according to the output torque at the next moment, this method further includes:

[0129] Obtain the historical target vehicle speed differences predicted at multiple consecutive moments within a preset time period and the historical actual vehicle speed differences at the corresponding moments;

[0130] Determine the difference between each historical target vehicle speed difference and the historical actual vehicle speed difference at the corresponding moment;

[0131] Based on the feedforward-feedback composite control module, according to each historical target vehicle speed difference, predict the feedforward predicted vehicle speed difference at the next moment through the feedforward path, and based on each difference, calculate the closed-loop correction amount through the feedback path, and fuse the feedforward predicted vehicle speed difference and the closed-loop correction amount to generate the target difference at the next moment. In this embodiment, the gain of the feedforward path of this feedforward-feedback composite control model is set to 0.8, and the gain of the feedback path is set to 1.2.

[0132] Update the target vehicle speed difference based on the target difference.

[0133] After the target vehicle speed difference is obtained according to the preliminary prediction, then use the feedforward-feedback composite control model to correct the detailed error of the target vehicle speed difference to further improve the prediction accuracy of the target vehicle speed difference.

[0134] Optionally, to improve the applicability of this method, when determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference and performing power control on the vehicle according to the output torque at the next moment, it can specifically further include:

[0135] Obtain the slope value of the environment where the current vehicle is located through the in-vehicle IMU (Inertial Measurement Unit);

[0136] In the case where the slope value is lower than or equal to the threshold, determine the output torque at the next moment based on the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment;

[0137] In the case where the slope value is higher than the threshold, determine the torque compensation amount at the next moment through a fuzzy logic controller based on the target vehicle speed difference and the slope value;

[0138] Determine the output torque at the next moment by combining the current vehicle torque, the target vehicle speed difference, and the torque compensation amount, and perform power control on the vehicle according to the output torque at the next moment. For example, when the target vehicle speed difference is greater than 0.5 km / h, the above slope value is higher than the threshold (2° in this embodiment, which can be adjusted according to the actual situation) by 5°, and at this time, the torque compensation amount is 15%. That is, after determining the output torque at the next moment based on the current vehicle torque and the target vehicle speed difference, an additional 15% torque compensation amount is added.

[0139] Optionally, in step S5, performing power control on the vehicle according to the output torque at the next moment specifically includes:

[0140] Determine the change rate between the output torque at the next moment and the current vehicle torque;

[0141] When the change rate is greater than the preset maximum torque change rate, the maximum torque change rate set in the embodiment of the present disclosure is ±10%, determine the maximum output torque at the next moment based on the maximum torque change rate and the current vehicle torque, and perform power control on the vehicle according to the maximum output torque;

[0142] When the change rate is less than or equal to the preset maximum torque change rate, perform power control on the vehicle according to the output torque at the next moment.

[0143] More specifically, this step includes:

[0144] Set the maximum torque change rate, for example, set it to ±10% of the current torque per second.

[0145] Obtain the current vehicle output torque T current .

[0146] Determine the system control period dt, for example, update the torque command every 100 milliseconds.

[0147] Obtain the output torque T at the next moment from the multi-mode difference controller of the vehicle target , which is obtained based on the vehicle driving condition and the control strategy.

[0148] Calculate the difference ΔT between the current vehicle output torque T current and the output torque T at the next moment target :

[0149] ΔT = T target - T current

[0150] Calculate the maximum allowable torque change amount ΔT in each control period max = 0.1 * dt * ΔT actual .

[0151] If ΔT > ΔTmax , the actual torque change ΔT actual = ΔT max ; if ΔT < -ΔT max , then ΔT actual = -ΔT max ; otherwise ΔT = ΔT actual .

[0152] Finally, update the output torque according to the actual torque change;

[0153] Output the updated output torque as a torque command to the vehicle powertrain for execution to achieve smooth torque transition.

[0154] Repeat the above steps in each control cycle, continuously adjust the actual output torque according to the torque command, and ensure smooth torque change.

[0155] Through the above settings, the change rate of the output torque can be limited, power shock can be avoided, and smooth transition of the torque command can be achieved.

[0156] After testing, taking the Japanese model A (ID = 0x2E4, speed parameter bits 5 - 6) vs. the German model B (ID = 0x2F4, speed parameter bits 2 - 3) as the test objects:

[0157] The test results show that the parsing accuracy of the target data bits has been improved from 68% of the traditional method to 98%, and the matching time < 2 seconds.

[0158] In the noise suppression comparison experiment:

[0159] Under the condition of rapid vehicle acceleration (peak electromagnetic interference 50 mV), the traditional mean filter has a delay of 210 ms, while after adopting the adaptive sliding window filter of this technology, the delay can be reduced to 45 ms. At the same time, the signal-to-noise ratio (SNR) of the speed signal is increased by 12 dB.

[0160] Regarding the control effect on the slope road surface, when the test slope angle θ is 8° and the expected vehicle speed is 60 km / h. The test results of this item show that the steady-state error of the traditional PID algorithm is +1.2 km / h, while the error of this technology is ±0.25 km / h, and the response time is shortened by 40%.

[0161] In summary, for the vehicle power control method provided by the present disclosure, first, the response frame and historical vehicle speed data are collected in real time using CAN data. Subsequently, the position of the target data bit is determined through dynamic frame feature matching (calculating the correlation degree of the data with respect to the vehicle speed) and / or static protocol library mapping. Then, the window length is dynamically adjusted according to the noise energy detection result, and different weights are assigned to the vehicle speed differences of the historical vehicle speed data. The vehicle speed difference at the next moment is predicted in sequence. After that, the vehicle speed difference is compensated according to the feedforward-feedback composite control model and the fuzzy logic controller to obtain the final torque braking instruction, so as to control the vehicle power system.

[0162] After the above steps, the method has high compatibility: it supports cross-model protocol parsing, and the error rate is reduced from 32% to less than 5%; low latency: the filtering latency < 50 ms (a 75% improvement compared to the traditional mean filtering); high-precision control: the steady-state error on the slope road surface < ±0.3 km / h (an 80% improvement compared to the PID algorithm); energy-saving and safe: the energy consumption of fuel vehicles is reduced by 6.8%, and the risk of traffic accidents is reduced by 19%.

[0163] The present invention also provides a vehicle power control system 100, please refer to Figure 2 as shown, including:

[0164] A noise energy detection module 101, configured to determine the intensity of the noise energy when the vehicle is in a preset operating condition;

[0165] A dynamic window adjustment module 102, configured to adjust the length of the data window according to the intensity of the noise energy;

[0166] A data acquisition module 103, configured to adjust the length of the data window of the vehicle noise signal according to the intensity of the noise energy;

[0167] A data processing module 104, configured to predict the target vehicle speed difference between the current moment and the next moment based on the vehicle speed differences between the historical vehicle speed data at adjacent moments;

[0168] A torque output module 105, configured to determine the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment.

[0169] Furthermore, the noise energy detection module 101 specifically includes:

[0170] When the vehicle is in a preset operating condition, based on the signals transmitted between preset devices, at least one of the signal variance, gradient change rate, spectrum change rate, adjacent frame difference, and signal-to-noise ratio is detected for the noise energy, and the detection result of the noise energy is determined.

[0171] Furthermore, the data acquisition module 103 specifically includes:

[0172] Based on the length of the adjusted data window, obtain historical response frames at multiple consecutive moments within a preset time period, where the response frames represent frame data in the CAN bus that responds to vehicle speed changes;

[0173] From the target data bits of each historical response frame, determine the historical vehicle speed data at the corresponding moment. Among them, the steps for determining the target data bits include:

[0174] Obtain the first target response frame;

[0175] Based on the mutual information entropy algorithm, calculate the correlation degree between the data stored in each data bit of the first target response frame and the vehicle speed change, and obtain correlation degree data, where the correlation degree data includes the correlation degree corresponding to each data bit;

[0176] Determine the data bit with the highest correlation degree in the correlation degree data as the target data bit storing the vehicle speed data.

[0177] Furthermore, the data acquisition module 103 specifically further includes:

[0178] Obtain a preset feature database, where the feature database includes the mapping relationship between the formats of the second target response frames in multiple preset vehicle type protocols that respond to vehicle speed changes and the target data bits storing the vehicle speed data in the second target response frames;

[0179] Combined with the target format of the response frame in response to the control instruction issued by the vehicle condition simulator and the feature database, determine the target data bits corresponding to the target format;

[0180] Based on the length of the adjusted data window, obtain historical response frames at multiple consecutive moments within a preset time period, where the response frames represent frame data in the CAN bus that responds to vehicle speed changes;

[0181] From the target data bits of each historical response frame, determine the historical vehicle speed data at the corresponding moment.

[0182] Furthermore, the data processing module 104 specifically includes:

[0183] According to the time-weighted decay method, assign weights to the historical vehicle speed differences between the historical vehicle speed data at adjacent moments, and obtain multiple labeled historical vehicle speed differences, where the time-weighted decay method means that according to the order of occurrence of the corresponding moments from first to last, assign weights to the historical vehicle speed differences from low to high;

[0184] Based on a preset time series prediction model, according to multiple labeled historical vehicle speed differences, predict the target vehicle speed difference between the current moment and the next moment.

[0185] Furthermore, this system further includes a target vehicle speed correction module:

[0186] Obtain the historical target vehicle speed difference and historical actual vehicle speed difference predicted at multiple consecutive moments within a preset time period;

[0187] Determine the difference between each historical target vehicle speed difference and the historical actual vehicle speed difference at the corresponding moment;

[0188] Based on the feedforward-feedback composite control module, according to each historical target vehicle speed difference, predict the feedforward predicted vehicle speed difference at the next moment through the feedforward path, and based on each difference, calculate the closed-loop correction amount through the feedback path, and fuse the feedforward predicted vehicle speed difference and the closed-loop correction amount to generate the target difference at the next moment;

[0189] Update the target vehicle speed difference based on the target difference.

[0190] Further, the torque output module 105 specifically includes:

[0191] Obtain the slope value of the environment where the current vehicle is located;

[0192] When the slope value is lower than or equal to the threshold, determine the output torque at the next moment based on the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment;

[0193] When the slope value is higher than the threshold, determine the torque compensation amount at the next moment based on the target vehicle speed difference and the slope value through a fuzzy logic controller;

[0194] Determine the output torque at the next moment based on the current vehicle torque, the target vehicle speed difference, and the torque compensation amount;

[0195] Perform power control on the vehicle according to the output torque at the next moment.

[0196] Further, the torque output module 105 specifically further includes:

[0197] Determine the change rate between the output torque at the next moment and the current vehicle torque;

[0198] When the change rate is greater than the preset maximum torque change rate, determine the maximum output torque at the next moment based on the maximum torque change rate and the current vehicle torque, and perform power control on the vehicle according to the maximum output torque;

[0199] When the change rate is less than or equal to the preset maximum torque change rate, perform power control on the vehicle according to the output torque at the next moment.

[0200] The present invention also provides a vehicle, including a vehicle body and a vehicle power control system as described above configured on the vehicle body.

[0201] The present invention also provides an electronic device, including a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements a vehicle power control method as described above.

[0202] The present invention also provides a computer-readable storage medium storing instructions, which, when running on a terminal device, cause the terminal device to execute a vehicle power control method as described above.

[0203] It should be noted that in this disclosure, all actions of obtaining signals, information, or data are carried out on the basis of strictly following the relevant data protection regulations and policies of the country where the location is located and with the authorization of the owner of the corresponding device. The owners mainly include:

[0204] (1) Automobile manufacturers: As developers of vehicle hardware and systems, they control the underlying vehicle hardware and software platforms and have management and control rights over the data generated by vehicle operation, such as driving and fault data.

[0205] (2) Component suppliers: Provide key components for automobiles and have certain ownership of the data collected and processed by the components for product optimization and after-sales, such as data generated by sensors and chips.

[0206] (3) Vehicle owners or users: The actual users of the vehicle, who have the right to decide on the usage mode and scope of vehicle data, such as whether to share data such as driving trajectories and driving habits, and have the need and right to protect their own relevant data privacy.

[0207] (4) Service providers: Provide services such as software and data analysis, and have the right to use and manage the data obtained and processed within the framework of the agreement, but the ownership usually belongs to other entities.

[0208] Figure 3 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0209] As Figure 3As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0210] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0211] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a vehicle power control method.

[0212] In some embodiments, a vehicle power control method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the vehicle power control method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute a vehicle power control method in any other appropriate manner (e.g., by means of firmware).

[0213] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0214] The computer program for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer program can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0215] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0216] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or an LCD (liquid crystal display)); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0217] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0218] The computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0219] In the description of this specification, the descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0220] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A vehicle power control method, characterized in that, Including: Determine the intensity of the noise energy when the vehicle is in a preset operating condition; Adjust the length of the data window of the vehicle noise signal according to the intensity of the noise energy; Based on the adjusted length of the data window, obtain historical vehicle speed data at multiple consecutive moments within a preset time period; Predict the target vehicle speed difference between the current moment and the next moment based on the historical vehicle speed differences between the historical vehicle speed data at adjacent moments; Combine the current vehicle torque and the target vehicle speed difference to determine the output torque at the next moment, and perform power control on the vehicle according to the output torque at the next moment.

2. The vehicle power control method according to claim 1, wherein The determination of the intensity of the noise energy when the vehicle is in a preset operating condition includes: When the vehicle is in a preset operating condition, based on the signals transmitted between preset devices, detect the noise energy of at least one of the signal variance, gradient change rate, spectral change rate, adjacent frame difference, and signal-to-noise ratio to determine the intensity of the noise energy.

3. A vehicle power control method according to claim 1, characterized in that, The obtaining of the historical vehicle speed data at multiple consecutive moments within a preset time period based on the adjusted length of the data window includes: Based on the adjusted length of the data window, obtain historical response frames at multiple consecutive moments within the preset time period, where the response frames represent frame data in the CAN bus that responds to vehicle speed changes; Determine the historical vehicle speed data at the corresponding moment from the target data bits of each of the historical response frames, where the determination step of the target data bits includes: Obtain a first target response frame; Based on the mutual information entropy algorithm, calculate the correlation degree between the data stored in each data bit of the first target response frame and the vehicle speed change to obtain correlation degree data, where the correlation degree data includes the correlation degree corresponding to each data bit; Determine the data bit with the highest correlation degree in the correlation degree data as the target data bit storing the vehicle speed data.

4. A vehicle power control method according to claim 1, characterized in that The obtaining of the historical vehicle speed data at multiple consecutive moments within a preset time period based on the adjusted length of the data window includes: Obtain a preset feature database, where the feature database includes the mapping relationship between the formats of second target response frames that respond to vehicle speed changes in multiple preset vehicle models and the target data bits storing the vehicle speed data in the second target response frames; Combine the target format of the response frame in response to the control instruction issued by the vehicle condition simulator and the feature database to determine the target data bit corresponding to the target format; Based on the adjusted length of the data window, obtain historical response frames at multiple consecutive moments within the preset time period, where the response frames represent frame data in the CAN bus that responds to vehicle speed changes; Determine the historical vehicle speed data at the corresponding moment from the target data bits of each of the historical response frames.

5. A vehicle power control method according to claim 1, wherein, The prediction of the target vehicle speed difference between the current moment and the next moment based on the historical vehicle speed differences between the historical vehicle speed data at adjacent moments includes: According to the time-weighted attenuation method, assign weights to the historical vehicle speed differences between the historical vehicle speed data at adjacent moments to obtain multiple labeled historical vehicle speed differences, where the time-weighted attenuation method is characterized by assigning weights from low to high to each of the historical vehicle speed differences according to the order of occurrence of the corresponding moments from first to last; Based on a preset time series prediction model, predict the target vehicle speed difference between the current moment and the next moment according to multiple historical vehicle speed differences of the tags.

6. The vehicle power control method according to claim 1, wherein Before determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference and performing power control on the vehicle according to the output torque at the next moment, it further includes: Obtain the historical target vehicle speed differences and historical actual vehicle speed differences predicted at multiple consecutive moments within the preset time period; Determine the difference between each historical target vehicle speed difference and the historical actual vehicle speed difference at the corresponding moment; Based on the feedforward-feedback composite control module, predict the feedforward predicted vehicle speed difference at the next moment through the feedforward path according to each historical target vehicle speed difference, and calculate the closed-loop correction amount through the feedback path based on each difference, and fuse the feedforward predicted vehicle speed difference and the closed-loop correction amount to generate the target difference at the next moment; Update the target vehicle speed difference based on the target difference.

7. A vehicle power control method according to claim 1, characterized in that The determining the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference and performing power control on the vehicle according to the output torque at the next moment includes: Obtain the slope value of the environment where the current vehicle is located; In the case where the slope value is lower than or equal to the threshold, determine the output torque at the next moment based on the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment; In the case where the slope value is higher than the threshold, determine the torque compensation amount at the next moment through a fuzzy logic controller based on the target vehicle speed difference and the slope value; Determine the output torque at the next moment based on the current vehicle torque, the target vehicle speed difference, and the torque compensation amount; Perform power control on the vehicle according to the output torque at the next moment.

8. A vehicle power control method according to claim 1, characterized in that The performing power control on the vehicle according to the output torque at the next moment includes: Determine the change rate between the output torque at the next moment and the current vehicle torque; When the change rate is greater than the preset maximum torque change rate, determine the maximum output torque at the next moment based on the maximum torque change rate and the current vehicle torque, and perform power control on the vehicle according to the maximum output torque; When the change rate is less than or equal to the preset maximum torque change rate, perform power control on the vehicle according to the output torque at the next moment.

9. A vehicle power control system, characterized in that, It includes: A noise energy detection module configured to determine the intensity of the noise energy when the vehicle is in a preset operating condition; A dynamic window adjustment module configured to adjust the length of the data window of the vehicle noise signal according to the intensity of the noise energy; A data acquisition module configured to obtain historical vehicle speed data at multiple consecutive moments within a preset time period based on the adjusted length of the data window; A data processing module configured to predict the target vehicle speed difference between the current moment and the next moment based on the vehicle speed difference between the historical vehicle speed data at adjacent moments; A torque output module configured to determine the output torque at the next moment by combining the current vehicle torque and the target vehicle speed difference, and perform power control on the vehicle according to the output torque at the next moment.

10. A vehicle, characterized in that, It includes a vehicle body and a vehicle power control system as described in Claim 9 configured on the vehicle body.

Images