A method and device for predicting power output data of a vehicle in a multi-driving scenario

Abstract

The present application relates to the technical field of vehicle load prediction, and discloses a power output data prediction method and device of a vehicle in a multiple driving scene, which is based on a power output power prediction value predicted by a first subnetwork, a torque demand prediction value predicted by a second subnetwork, a long-term power demand prediction value predicted by a third subnetwork, and an energy recovery time prediction value, wherein the first subnetwork, the second subnetwork, and the third subnetwork constitute a multi-layer network structure, and a subnetwork corresponding to an optimal state of the vehicle in a current driving scene is acquired; a prediction value output by the optimal state corresponding subnetwork is acquired, and the prediction value is taken as an optimal prediction result in the current driving scene. The present application can dynamically select the most suitable subnetwork, has higher flexibility and adaptability compared with a traditional static model, can match the prediction result output by the optimal subnetwork, and further improves the prediction accuracy of the vehicle power output data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle power output data prediction, and in particular to a vehicle power output data prediction method and device in multiple driving scenarios. BACKGROUND

[0002] In the intelligent transportation and automobile industry, driving system optimization technology plays a relatively large role in improving the energy efficiency, power response and overall driving performance of vehicles. And with the development of intelligent driving technology, the performance of the vehicle driving system not only affects the power output and fuel / battery efficiency of the vehicle, but also directly relates to the safety and driving experience of driving. Therefore, how to effectively optimize the driving system of the vehicle has become an important direction of current research.

[0003] Currently, the traditional vehicle driving system optimization method usually sets preset rules or fixed parameters, but this method is difficult to adapt to dynamic and complex driving scenarios. Vehicles need to cope with various driving scenarios during driving, such as urban congestion, high-speed driving, and slope driving, which makes a single driving system optimization strategy unable to meet different needs. But to improve the adaptability of the driving system, modern vehicles are usually equipped with multiple sensors for real-time collection of vehicle operating conditions, road condition information and environmental data. These data also provide a data-driven basis for driving system optimization to some extent. However, related technologies in predicting power output data in different driving scenarios, due to the detection of complex and diverse data without distinction, and using the same neural network structure to predict various detection data, are prone to cause deviation in the prediction results of the power output data. SUMMARY

[0004] Therefore, the present application provides a vehicle power output data prediction method and device in multiple driving scenarios to solve the problem of deviation in the prediction results of the power output data caused by using the same neural network structure to predict various detection data.

[0005] According to a first aspect, the present application provides a vehicle power output data prediction method in multiple driving scenarios, the method comprising:

[0006] obtaining current detection data, historical average power demand data and historical energy recovery time data of the vehicle in the current driving scenario, the current detection data comprising vehicle operating data, vehicle road condition data, traffic data and driving environment data;

[0007] The first sub-network predicts a power output power prediction value corresponding to the vehicle road condition data, the second sub-network predicts a torque demand prediction value corresponding to the vehicle road condition data, traffic data and driving environment data in combination with the power output power prediction value, and the third sub-network respectively predicts a long-term power demand prediction value corresponding to the historical average power demand data and an energy recovery time prediction value corresponding to the historical energy recovery time data, and the first sub-network, the second sub-network and the third sub-network form a multi-layer network structure.

[0008] Based on the power output power prediction value, the torque demand prediction value, the long-term power demand prediction value and the energy recovery time prediction value, a sub-network corresponding to an optimal state of the vehicle in the current driving scene is obtained.

[0009] The prediction value output by the sub-network corresponding to the optimal state is obtained, and the prediction value is taken as an optimal prediction result in the current driving scene.

[0010] In some optional embodiments, the first sub-network predicts a power output power prediction value corresponding to the vehicle road condition data, including:

[0011] The speed, acceleration and engine speed are obtained from the vehicle road condition data.

[0012] Based on the speed, acceleration and engine speed, the first sub-network predicts a power output power prediction value corresponding to the vehicle road condition data, wherein the power output power prediction value is calculated by the following formula:

[0013]

[0014] wherein, the power output power prediction value is P, the convolution operation factor is C, the speed is V, the acceleration is a, and the engine speed is n.

[0015] In some optional embodiments, the second sub-network predicts a torque demand prediction value corresponding to the vehicle road condition data, traffic data and driving environment data in combination with the power output power prediction value, including:

[0016] The slope is obtained from the vehicle road condition data, the traffic flow is obtained from the traffic data, and the temperature is obtained from the driving environment data.

[0017] Based on the power output power prediction value, the slope, the traffic flow and the temperature, the second sub-network predicts a torque demand prediction value corresponding to the traffic data and the driving environment data, wherein the torque demand prediction value is calculated by the following formula:

[0018]

[0019] wherein, is a torque demand prediction value, is a feature fusion factor, is a power output prediction value, is a slope, is a temperature, is a traffic flow.

[0020] In some optional embodiments, the long-term power demand prediction value corresponding to the historical average power demand data and the energy recovery time prediction value corresponding to the historical energy recovery time data are predicted by the third sub-network respectively, comprising:

[0021] The long-term power demand prediction value and the energy recovery time prediction value are calculated based on the historical average power demand data and the historical energy recovery time data, wherein the long-term power demand prediction value and the energy recovery time prediction value are calculated by the following formula:

[0022]

[0023] wherein, is a long-term power demand prediction value, is an energy recovery time prediction value, is a calculation factor of the third sub-network, is historical average power demand data, is historical energy recovery time data.

[0024] In some optional embodiments, based on the power output prediction value, the torque demand prediction value, the long-term power demand prediction value, and the energy recovery time prediction value, the sub-network corresponding to the optimal state of the vehicle in the current driving scene is obtained, and the following formula is executed:

[0025]

[0026] wherein, is a state feature vector corresponding to the optimal state of the vehicle by real-time monitoring of the current detection data of the vehicle in the current driving scene so that the current state of the vehicle reaches the optimal state, is an output accuracy of the first sub-network corresponding to the optimal state in the current driving scene, is an input feature of the first sub-network, is a prediction value output by the first sub-network.

[0027] In some optional embodiments, the current driving scene includes an urban congestion scene or a high-speed driving scene or a slope driving scene, and further comprising:

[0028] The current detection data in the urban congestion scene or the high-speed driving scene or the slope driving scene is weighted.

[0029] According to a second aspect, the embodiments of the present disclosure provide a device for predicting power output data of a vehicle in a multi-driving scene, the device comprising:

[0030] The first obtaining module is configured to obtain current detection data, historical average power demand data and historical energy recovery time data of the vehicle in a current driving scene, wherein the current detection data comprises vehicle operation data, vehicle road condition data, traffic data and driving environment data, and the current driving scene comprises an urban congestion scene, a high-speed driving scene or a slope driving scene;

[0031] The data prediction module is configured to predict a power output power prediction value corresponding to the vehicle road condition data through a first sub-network, predict a torque demand prediction value corresponding to the traffic data and the driving environment data by combining the power output power prediction value through a second sub-network, and predict a long-term power demand prediction value corresponding to the historical average power demand data and an energy recovery time prediction value corresponding to the historical energy recovery time data through a third sub-network, wherein the first sub-network, the second sub-network and the third sub-network constitute a multi-layer network structure.

[0032] The second obtaining module is configured to obtain a sub-network corresponding to an optimal state of the vehicle in the current driving scene based on the power output power prediction value, the torque demand prediction value, the long-term power demand prediction value and the energy recovery time prediction value.

[0033] The third obtaining module is configured to obtain a prediction value output by the sub-network corresponding to the optimal state, and take the prediction value as an optimal prediction result in the current driving scene.

[0034] In a third aspect, the embodiments of the present disclosure provide a computer device, comprising:

[0035] The memory and the processor are connected with each other in communication, the memory stores computer instructions, and the processor executes the computer instructions to perform the power output data prediction method of the vehicle in the multi-driving scene according to the first aspect or any of the corresponding embodiments.

[0036] In a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the power output data prediction method of the vehicle in the multi-driving scene according to the first aspect or any of the corresponding embodiments.

[0037] In a fifth aspect, the embodiments of the present disclosure provide a computer program product, including computer instructions for causing a computer to execute the vehicle power output data prediction method in the multiple driving scenarios according to the first aspect or any of the corresponding embodiments.

[0038] The technical scheme of the present application has the following advantages:

[0039] The present application relates to the technical field of vehicle power output data prediction, and discloses a vehicle power output data prediction method and device in a multiple driving scenario, which is based on a power output power prediction value predicted by a first subnetwork, a torque demand prediction value predicted by a second subnetwork, a long-term power demand prediction value predicted by a third subnetwork, and an energy recovery time prediction value, wherein the first subnetwork, the second subnetwork, and the third subnetwork form a multi-layer network structure, and a subnetwork corresponding to an optimal state of the vehicle in the current driving scenario is obtained; the prediction value output by the subnetwork corresponding to the optimal state is obtained, and the prediction value is taken as an optimal prediction result in the current driving scenario. The present application can dynamically select the most suitable subnetwork, has higher flexibility and adaptability compared with a traditional static model, can match the prediction result output by the optimal subnetwork, and further improves the prediction accuracy of the vehicle power output data. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0041] Figure 1 FIG. 1 is a flowchart of a vehicle power output data prediction method in a multiple driving scenario according to an embodiment of the present application;

[0042] Figure 2 FIG. 2 is a simple block diagram of a multi-layer network structure according to an embodiment of the present application;

[0043] Figure 3 FIG. 3 is a flowchart of another vehicle power output data prediction method in a multiple driving scenario according to an embodiment of the present application;

[0044] Figure 4 FIG. 4 is a flowchart of still another vehicle power output data prediction method in a multiple driving scenario according to an embodiment of the present application;

[0045] Figure 5 FIG. 5 is a simple block diagram of real-time collection of current vehicle detection data in a multiple driving scenario according to an embodiment of the present application;

[0046] Figure 6 is a flowchart of another vehicle power output data prediction method in a multi-driving scene according to an embodiment of the present application;

[0047] Figure 7 is a structural block diagram of a vehicle power output data prediction device in a multi-driving scene according to an embodiment of the present application;

[0048] Figure 8 is a hardware structure diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in connection with the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0050] According to an embodiment of the present application, a vehicle power output data prediction method in a multi-driving scene is provided. It should be noted that the steps shown in the flowchart can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0051] In this embodiment, a vehicle power output data prediction method in a multi-driving scene is provided, which can be used in computer devices such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 1 is a flowchart of a vehicle power output data prediction method in a multi-driving scene according to an embodiment of the present application, which includes the following steps:

[0052] Step S101, obtaining current detection data, historical average power demand data and historical energy recovery time data of the vehicle in the current driving scene, the current detection data including vehicle running data, vehicle road condition data, traffic data and driving environment data.

[0053] Specifically, the vehicle running data includes acceleration, speed, engine speed, wherein the acceleration, wherein, , is the vehicle speed, is the time, Acceleration is detected by an accelerometer, while speed is detected by a vehicle speed sensor. Vehicle road condition data includes: gradient, which can be detected by cameras, LiDAR sensors, and millimeter-wave radar sensors. Traffic data includes: traffic flow. ,in, The current unit road area The number of vehicles on the road is measured using traffic flow sensors. Driving environment data includes temperature, which is detected by temperature sensors.

[0054] Furthermore, the power output data prediction method for vehicles in multiple driving scenarios in this embodiment supports driving in multiple driving environments, thereby meeting the different driving needs of drivers and flexibly predicting power output data in multiple driving scenarios.

[0055] Step S102: The first sub-network predicts the power output power corresponding to the vehicle road condition data; the second sub-network combines the power output power prediction value to predict the torque demand corresponding to the vehicle road condition data, traffic data, and driving environment data; and the third sub-network predicts the long-term power demand corresponding to the historical average power demand data and the energy recovery time corresponding to the historical energy recovery time data, respectively. The first sub-network, the second sub-network, and the third sub-network constitute a multi-layer network structure.

[0056] Specifically, such as Figure 2 The diagram shown is a simplified block diagram of a multi-layer network structure. Figure 2 The network consists of a first subnetwork, a second subnetwork, and a third subnetwork, which together form a multi-layered network structure. The first subnetwork serves as the bottom layer and is used to process basic data. The second subnetwork serves as the middle layer and is used to integrate road condition data, environmental data, and traffic data. The third subnetwork serves as the top layer and is used to process historical data.

[0057] In some optional implementations, the predicted power output value corresponding to the vehicle road condition data is predicted through the first sub-network, including:

[0058] Step a1: Obtain speed, acceleration, and engine speed from vehicle road condition data.

[0059] Step a2: Based on speed, acceleration and engine speed, calculate the predicted power output value corresponding to the vehicle road condition data predicted by the first sub-network, wherein the predicted power output value is calculated by the following formula;

[0060]

[0061] in, This is the predicted value of power output. is a convolution operation factor, is a speed, is an acceleration, is an engine speed.

[0062] Specifically, the speed, the acceleration, and the engine speed are subjected to feature extraction through a plurality of convolution layers of the first sub-network, and then a preliminary power output prediction value is generated through a fully connected layer. The power output prediction value is used as a first prediction task.

[0063] In some optional embodiments, the torque demand prediction value corresponding to the vehicle road condition data, the traffic data, and the driving environment data is predicted by a second sub-network in combination with the power output prediction value, including:

[0064] Step b1, the slope is obtained from the vehicle road condition data, the traffic flow is obtained from the traffic data, and the temperature is obtained from the driving environment data.

[0065] Step b2, based on the power output prediction value, the slope, the traffic flow, and the temperature, the torque demand prediction value corresponding to the traffic data and the driving environment data predicted by the second sub-network is calculated, wherein the torque demand prediction value is calculated by the following formula:

[0066]

[0067] wherein, is the torque demand prediction value, is a feature fusion factor, is the power output prediction value, is the slope, is the temperature, is the traffic flow.

[0068] Specifically, the second sub-network combines the power output prediction value output by the first sub-network, the slope, the traffic flow, and the temperature to generate the torque demand prediction value corresponding to the traffic data and the driving environment data predicted by the second sub-network.

[0069] In some optional embodiments, the long-term power demand prediction value corresponding to the historical average power demand data and the energy recovery time prediction value corresponding to the historical energy recovery time data are predicted by a third sub-network, including:

[0070] Step c1, based on the historical average power demand data and the historical energy recovery time data, the long-term power demand prediction value and the energy recovery time prediction value are calculated, wherein the long-term power demand prediction value and the energy recovery time prediction value are calculated by the following formula:

[0071]

[0072] wherein, a long-term power demand prediction value, an energy recovery time prediction value, a calculation factor of the third sub-network, historical average power demand data, historical energy recovery time data.

[0073] Specifically, the third sub-network performs long-term power demand prediction based on historical data. The embodiment of the present disclosure mainly performs time series modeling based on a long short-term memory network (LSTM). The input is historical average power demand data and historical energy recovery time data , and the output is a long-term power demand prediction value and an energy recovery time prediction value .

[0074] The embodiment of the present disclosure predicts multiple data in the current driving scene through multiple different sub-networks, which is beneficial to improve the prediction result accuracy of the vehicle power output data.

[0075] In step S103, based on the power output power prediction value, the torque demand prediction value, the long-term power demand prediction value, and the energy recovery time prediction value, a sub-network corresponding to an optimal state of the vehicle in the current driving scene is obtained.

[0076] In step S104, the prediction value output by the sub-network corresponding to the optimal state is obtained, and the prediction value is taken as the optimal prediction result in the current driving scene.

[0077] In some optional embodiments, based on the power output power prediction value, the torque demand prediction value, the long-term power demand prediction value, and the energy recovery time prediction value, a sub-network corresponding to an optimal state of the vehicle in the current driving scene is obtained, which is executed by the following formula:

[0078]

[0079] wherein, is a state feature vector corresponding to an optimal state of the vehicle in the current driving scene by real-time monitoring of current detection data of the vehicle, is an output accuracy of the th sub-network corresponding to the optimal state in the current driving scene, is an input feature of the th sub-network, is a prediction value output by the th sub-network.

[0080] Compared with the traditional static model, the embodiments of the present disclosure have higher flexibility and adaptability, can match the prediction result output by the optimal sub-network, and further improve the prediction accuracy of the vehicle power output data.

[0081] In some optional embodiments, the current driving scene includes an urban congestion scene or a high-speed driving scene or a slope driving scene, and the method further includes: performing weighted processing on the current detection data in the urban congestion scene or the high-speed driving scene or the slope driving scene.

[0082] Specifically, for the urban congestion scene, the vehicle frequently starts and stops, and the focus is on predicting the brake frequency and the energy consumption in the low-speed state. The current detection data in the urban congestion scene is weighted processed, and the following formula is executed:

[0083]

[0084] wherein, is the weight corresponding to the speed, is the weight corresponding to the acceleration, is the weight corresponding to the brake frequency, is the weight corresponding to the brake operation threshold, is the speed, is the acceleration, is the brake frequency, is the brake operation threshold, is the energy consumption requirement value in the urban congestion scene.

[0085] By weighting the current detection data in the urban congestion scene, the power output of the vehicle in the urban congestion scene can be processed in a timely manner. For example, when the vehicle is in the urban congestion scene, the low-speed braking of the vehicle is focused on, and when exceeds and belongs to the low-speed range, it is determined that it belongs to the urban congestion scene. By executing the steps S101-S104, the prediction value output by the sub-network corresponding to the optimal state is obtained, and the prediction value is used as the optimal prediction result in the urban congestion scene, and the frequent braking and starting in the urban congestion scene are further processed.

[0086] Specifically, for the high-speed driving scene, the load prediction of high-speed stable driving is mainly processed, and the vehicle speed, engine speed, power output power, and energy recovery time are mainly considered. The current detection data in the high-speed driving scene is weighted processed, and the following formula is executed:

[0087]

[0088] wherein, is the weight corresponding to the speed, is the weight corresponding to the engine speed, is the weight corresponding to the power output, is the weight corresponding to the energy recovery time, is the speed, is the engine speed, is the power output, is the energy recovery time, is the power output demand value in the high-speed driving scenario.

[0089] By weighting the current detection data in the high-speed driving scenario, it is convenient to timely process the power output of the vehicle in the high-speed driving scenario, for example, when is continuously higher than the set value and satisfies the preset range, it is determined to belong to the high-speed driving scenario. In the high-speed driving scenario, by executing the above steps S101-S104, the prediction value of the output of the sub-network corresponding to the optimal state is obtained, and the prediction value is taken as the optimal prediction result in the driving scenario, and then the power output in the high-speed driving scenario is executed.

[0090] For the slope driving scenario, mainly processing the case that the slope driving changes greatly, focusing on adjusting the torque demand of the vehicle, focusing on the vehicle speed, acceleration, slope, weighting the current detection data in the slope driving scenario, and executing by the following formula:

[0091]

[0092] wherein, is the weight corresponding to the slope, is the weight corresponding to the speed, is the weight corresponding to the torque, is the slope, is the speed, is the torque, is the acceleration, is the torque demand value in the slope driving scenario.

[0093] By weighting the current detection data in the slope driving scenario, it is convenient to timely process the power output of the vehicle in the slope driving scenario, for example, when and When a specific requirement is met, it is determined that the vehicle is in a hill start scenario. In this hill start scenario, by performing steps S101-S104 described above, the prediction value output by the sub-network corresponding to the optimal state is obtained, and the prediction value is taken as the optimal prediction result in the hill start scenario, and then the power output in the hill start scenario is performed.

[0094] In this embodiment, a power output data prediction method for a vehicle in a multi-driving scenario is provided, which can be used in computer equipment such as mobile phones, tablets, desktop computers, portable notebooks, servers, etc. In step S101, the current detection data of the vehicle in the current driving scenario is obtained, such as Figure 3 As shown in the figure, the flow includes the following steps:

[0095] Step S301: Obtain the data detection results of multiple sensors of the vehicle in the current driving state and the current collection frequency of multiple sensors within a preset time.

[0096] Specifically, the current driving state is the state corresponding to the vehicle in the driving scenario, and the preset time can be the detection time set when the sensor detection mode is started in the current driving state.

[0097] In a specific example, the multiple sensors include: a first sensor for detecting vehicle operation data, a second sensor for detecting vehicle road condition data, a third sensor for detecting traffic data, and a fourth sensor for detecting driving environment data.

[0098] For example, the first sensor includes an acceleration sensor, a speed sensor, and a generator speed sensor, wherein the acceleration sensor is used to detect the acceleration of the vehicle, and the speed sensor is used to detect the speed of the vehicle. The acceleration sensor transmits data to the electronic control unit through the CAN bus at the vehicle chassis, ensuring that the speed sensor synchronously collects the speed of the vehicle. The motor speed sensor monitors the speed of the engine and the motor, and reflects it to the data monitoring system in real time, and monitors the current driving force and the battery power. The data detection results detected by the above-mentioned first sensor belong to vehicle operation data. For example, the acceleration wherein, is the vehicle speed, is the time. The generator speed sensor collects the engine speed .

[0099] For example, the second sensor includes a camera, a laser radar sensor, and a millimeter wave radar sensor, which detects the slope of the road by the second sensor. The second sensor is used to detect vehicle road condition data.

[0100] For example, the third type of sensor includes: a sensor for detecting traffic flow and a sensor for detecting traffic light data, which estimates traffic flow using the following formula: ,in, The current unit road area The number of vehicles on the road. The third type of sensor is used to detect traffic data.

[0101] For example, the fourth type of sensor includes a temperature sensor that detects the current ambient temperature. The fourth type of sensor is used to detect driving environment data.

[0102] This disclosure embodiment acquires data detection results of the vehicle under the current driving state through various types of sensors, which facilitates timely knowledge of the vehicle's current operating status, current road conditions, current traffic flow, and the driver's current operation.

[0103] Step S302: Based on the data detection results of the target sensor and the current acquisition frequency of the target sensor, obtain the current data change rate of the target sensor; wherein, the target sensor is any one of a variety of sensors.

[0104] Specifically, for example, the target sensor is the first sensor among multiple sensors. The current acquisition frequency of the first sensor is 5 acquisitions every 10 minutes. Based on the data detection results of the first sensor in 5 acquisitions, the current data change rate of the first sensor is obtained. For example, the first sensor is specifically a vehicle speed sensor. The vehicle speed detected in the first acquisition is 30 km / h, the second is 31 km / h, the third is 30 km / h, the fourth is 33 km / h, and the fifth is 32 km / h. The change between the first and second acquisitions is 1, the change between the second and third is 1, the change between the third and fourth is 3, and the change between the fourth and fifth is 1. The current data change rate of the target sensor is... = (1+1+3+1) / 4 = 1.5.

[0105] Step S303: Calculate the dynamic adjustment result of the target sensor data based on the current acquisition frequency and the current data change rate of the target sensor.

[0106] Step S304: Based on the data dynamic adjustment results, adjust the current acquisition frequency of the target sensor.

[0107] Specifically, due to the sudden change of the environment encountered by the vehicle during driving, for example, sudden rain or slope or highway, taking the sudden rain as an example, if the current environmental humidity is collected by the sensor collecting the driving environment at a fixed frequency, it cannot adapt to the change of the external rain environment in time, resulting in that the driving system cannot adjust the power output or other key control parameters in time. If the sensor collects data at a fixed frequency all the time under the condition that the actual working condition of the vehicle is stable, it is easy to cause data redundancy and increase the calculation burden of the driving system, thereby affecting the overall efficiency of the driving system. In addition, when multiple sensors work together, collecting data at a fixed frequency for all sensors will increase the system delay and resource consumption. Therefore, it is necessary to flexibly adjust the current collection frequency of the target sensor in combination with the actual driving condition.

[0108] In some optional embodiments, the data dynamic adjustment result of the target sensor is calculated by the following formula:

[0109]

[0110] Wherein, is the current collection frequency of the target sensor, is the current data change rate of the target sensor, is a preset threshold, is a first collection frequency, is a second collection frequency. The first collection frequency can be a high frequency, and the second collection frequency can be a low frequency. The target sensor can be any one of a plurality of sensors.

[0111] For example, when in heavy rain, the friction coefficient of the road surface affects the driving performance of the vehicle, so the data priority of the friction coefficient sensor in the fourth sensor for detecting driving environment data will be improved, and the data priority of the friction coefficient sensor in the fourth sensor for detecting driving environment data will be improved According to = , the data is collected at a high frequency. In the case where the air humidity has little effect on the vehicle, the data priority of the humidity sensor in the fourth sensor for detecting driving environment data will be reduced , according to

[0112] to ensure that the data is collected at a low frequency, thereby saving system resources and avoiding redundant transmission of irrelevant data.

[0113] For another example, when the vehicle is driving at a constant speed on a flat road, if the data is collected at a specific high frequency all the time, it will also cause waste of data resources. At this time, the data priority of the speed sensor in the first sensor for detecting vehicle running data will be reduced , according to , ensure that the data is collected according to the low frequency, so as to save system resources, avoid the redundant transmission of irrelevant data.

[0114] In the embodiment, a power output data prediction method of a vehicle in a multi-driving scene is provided, which can be used in computer equipment such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. After the step S301 of obtaining the data detection results of multiple sensors of the vehicle in the current driving state and the current collection frequency of multiple sensors within a preset time, the flow further includes the following steps: Figure 4

[0115] Step S401, based on the data detection results of multiple sensors and the weight parameters of multiple sensors, the multi-sensor cooperative detection result is calculated.

[0116] In some optional embodiments, the multi-sensor cooperative detection result is calculated by the following formula:

[0117]

[0118] wherein, is the multi-sensor cooperative detection parameter, is the weight parameter of the i-th sensor, is the detection result of the i-th sensor, is the total number of multiple sensors.

[0119] Since the data detection result of a sensor can be shared with other sensors when the data detection result of a sensor is always in a stable state during the driving of the vehicle, the data detection result of the sensor is shared with other sensors, thereby avoiding repeated collection of mutually related data.

[0120] Step S402, based on the data dynamic adjustment result and the multi-sensor cooperative detection result, the data sharing result of multiple sensors is obtained.

[0121] In a specific example, the step S402 of obtaining the data sharing result of multiple sensors based on the data dynamic adjustment result and the multi-sensor cooperative detection result includes:

[0122] Step d1, based on the data dynamic adjustment result, the current collection frequency of the target sensor after dynamic adjustment is obtained.

[0123] Specifically, for example, when in heavy rain weather, the friction coefficient of the road surface affects the driving performance of the vehicle, therefore, the data priority of the friction coefficient sensor in the fourth sensor for detecting the driving environment data will be improved, and usually , according to = ​, ensure that the data is collected according to the high frequency, at this time, the dynamic adjustment result of the data of the target sensor is = , the current collection frequency of the target sensor after dynamic adjustment is . In the case where the air humidity has less influence on the vehicle, the data priority of the humidity sensor in the fourth sensor for detecting the driving environment data is reduced, , according to , at this time, the dynamic adjustment result of the data of the target sensor is = .

[0124] Step d2, if the current collection frequency of the target sensor after dynamic adjustment remains stable within a preset time, the data detection result of the target sensor after multi-sensor cooperation is obtained in the stable state;

[0125] Step d3, the data detection result of the target sensor after multi-sensor cooperation is taken as the data sharing result of the multiple sensors.

[0126] Specifically, for example, in the process of uphill driving of the vehicle, the road visual information is obtained by the camera, the laser radar sensor and the millimeter wave radar sensor in the second sensor. Since the camera, the laser radar sensor and the millimeter wave sensor can be used to detect the road visual information, when the current collection frequency of the camera after dynamic adjustment of the target sensor remains stable within a preset time, the data detection result of the camera can be taken as the data sharing result of the multiple sensors.

[0127] The embodiment of the present disclosure is advantageous to flexibly adjust the current collection frequency of the target sensor by obtaining the dynamic adjustment result of the data of the target sensor, so as to facilitate timely adaptation to the rapidly changing external environment, and further make the driving system timely adjust the power output or other key control parameters. At the same time, it can also avoid the situation that in the case where the actual working condition of the vehicle is stable, a large amount of similar data is collected, which is easy to cause data redundancy and increase the calculation burden of the driving system, and significantly improve the overall efficiency of the driving system. In addition, the embodiment of the present disclosure combines the dynamic adjustment result of the data and calculates the multi-sensor cooperation detection result, which is advantageous to realize the cooperative calculation and information sharing among the multiple sensors, so as to improve the efficiency of the overall system and the effectiveness of the data processing, and finally make the driving system make efficient intelligent response in the complex environment.

[0128] As shown in Figure 5 , it is a simple block diagram of real-time collection of current vehicle detection data of the vehicle in the multi-driving scene in the embodiment of the present disclosure, in Figure 5In the embodiment, the vehicle in the current driving state collects data detection results of multiple sensors in real time, mainly including five types of detection data, which are vehicle operation data, vehicle road condition data, traffic data, and driving environment data. The data detection results of the five types are preprocessed and optimized. After the optimization, the data dynamic adjustment results and the multi-sensor collaborative detection results are obtained based on the data sharing results of multiple sensors.

[0129] A power output data prediction method for a vehicle in a multi-driving scene is provided in the embodiment, which can be used in computer equipment such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 6 As shown in the flowchart, the flow further includes the following steps:

[0130] Step S601, preprocessing the data detection results of multiple sensors.

[0131] In some optional embodiments, preprocessing the data detection results of multiple sensors includes:

[0132] Step b1, preprocessing the data detection results of multiple sensors.

[0133] In a specific example, the preprocessing method includes an outlier processing method and a missing value filling processing method.

[0134] Specifically, due to environmental interference or hardware errors during vehicle driving, the data detection results of the sensors may have unreasonable outliers. For example, a temperature sensor may have a mutation in a stable environment, and such abnormal data needs to be identified and filtered.

[0135] In a specific example, the outlier processing method is to identify outliers by using the mean standard deviation method, which is expressed by the following formula:

[0136]

[0137] When exceeds a predetermined threshold ( ), the data is considered to be an outlier and is processed.

[0138] In a specific example, the missing value filling processing method is to fill the missing values by using the linear interpolation method, which is expressed by the following formula:

[0139]

[0140] wherein, is a normal data point before the missing value, is a normal data point after the missing value, is a time point corresponding to the missing value before the missing value, t represents the time point following the missing value, and t represents the current time point.

[0141] Step b2 involves processing the preprocessed data detection results from multiple sensors again using an adaptive Kalman filter algorithm.

[0142] In a specific example, the adaptive Kalman filter algorithm is executed using the following formula:

[0143]

[0144] in, for Time of the first State estimation matrix of the sensor, for Time of the first The state transition matrix of the sensor, Let be the control input matrix at time t. Let be the Kalman gain matrix at time t. for Time of the first The covariance matrix of the sensors, For the observation matrix, To observe the noise covariance matrix, for Time of the first State estimation matrix of the sensor, Let be the prediction result of the i-th sensor at time t.

[0145] Specifically, in the above formula, through the state transition matrix and control input matrix Predict the state estimation matrix for the next time step, and further base it on the error covariance matrix. Observation matrix Observation noise covariance matrix Calculate Kalman gain Using Kalman gain Update the current state estimation matrix To make the data more closely resemble actual observations, in this embodiment, an adaptive Kalman filter algorithm is used to adjust the Kalman gain in real time to dynamically adjust the sensor's data detection results. The error covariance matrix is ​​used to estimate the difference between the current observation and the predicted value, and the sensor's data detection results are corrected based on this difference, making the updated estimate closer to the actual data, ultimately achieving a data optimization prediction effect. For example, when the sensor noise is low or the data is relatively stable, the Kalman gain... It will decrease, reducing the sensor's current amplitude to adapt to current changes; for example, when noise is high or data fluctuations are significant, the Kalman gain will decrease. It will increase or decrease the current amplitude of the sensor to adapt to the current changes.

[0146] Step S602: Obtain acceleration and velocity from the data detection results of multiple sensors.

[0147] Step S603: Create physical constraints for acceleration and velocity using the following formula.

[0148]

[0149] Step S604: Based on the physical constraints of acceleration and velocity, the preset optimization algorithm is expressed by the following formula.

[0150] ;

[0151] in, This is the minimum speed value. The first speed threshold, The second speed threshold, for The speed of time The first acceleration threshold, Second acceleration threshold, for Acceleration at any moment;

[0152] Step S605: Optimize the filtered data detection results of multiple sensors according to the preset optimization algorithm.

[0153] Specifically, since speed and acceleration are directly related to a vehicle's dynamic performance during operation, physical constraints on acceleration and speed are created. A pre-defined optimization algorithm ensures that the filtered data better reflects the vehicle's actual operating conditions, thereby improving the accuracy of data detection results from multiple sensors.

[0154] This embodiment also provides a power output data prediction device for a vehicle in multiple driving scenarios. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0155] This embodiment provides a device for predicting vehicle power output data in multiple driving scenarios, such as... Figure 7 As shown, the device includes:

[0156] The first obtaining module 701 is configured to obtain current detection data of a vehicle in a current driving scene, historical average power demand data, and historical energy recovery time data, wherein the current detection data comprises vehicle operation data, vehicle road condition data, traffic data, and driving environment data, and the current driving scene comprises an urban congestion scene, a high-speed driving scene, or a slope driving scene.

[0157] The data prediction module 702 is configured to predict a power output power prediction value corresponding to the vehicle road condition data through a first sub-network, predict a torque demand prediction value corresponding to the vehicle road condition data, the traffic data, and the driving environment data by combining the power output power prediction value through a second sub-network, and predict a long-term power demand prediction value corresponding to the historical average power demand data and an energy recovery time prediction value corresponding to the historical energy recovery time data through a third sub-network, wherein the first sub-network, the second sub-network, and the third sub-network constitute a multi-layer network structure.

[0158] The second obtaining module 703 is configured to obtain a sub-network corresponding to an optimal state of the vehicle in the current driving scene based on the power output power prediction value, the torque demand prediction value, the long-term power demand prediction value, and the energy recovery time prediction value.

[0159] The third obtaining module 704 is configured to obtain a prediction value output by the sub-network corresponding to the optimal state, and take the prediction value as an optimal prediction result in the current driving scene.

[0160] Further function descriptions of the above-mentioned modules and units are the same as those of the corresponding embodiments, and will not be described here.

[0161] The vehicle power output data prediction device in the multiple driving scenes in the embodiment is presented in the form of a functional unit, wherein the unit refers to an ASIC (Application Specific Integrated Circuit, Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices that can provide the above functions.

[0162] The embodiment of the present application also provides a computer device with the vehicle power output data prediction device in the multiple driving scenes shown above.

[0163] Please refer to Figure 8 , Figure 8 is a structural schematic diagram of a computer device provided by an optional embodiment of the present application, as Figure 8As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for the various components to communicate with one another. The various components communicate through one or more buses, and can be mounted on a common motherboard or in other manners as appropriate. The processor 10 can execute instructions, for example, stored in the memory 20 to display graphical information for a GUI on an external input / output device, such as a display device coupled to the interface. In some optional implementations, multiple processors and / or multiple buses can be employed as appropriate, such as about the memory 20. Also, various components can be distributed, such as over a network to provide greater functionality and / or redundancy. For example, components can be located on either or both of the same device or distributed among multiple devices. Figure 8 The processor 10 is taken as an example.

[0164] The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0165] The memory 20 stores instructions that are executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods illustrated in the above embodiments.

[0166] The memory 20 can include a program region and a data region. The program region can store an operating system and applications required by at least one function. The data region can store data created according to the use of the computer device, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some optional implementations, the memory 20 can optionally include a memory that is remotely located with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0167] The memory 20 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned types of memories.

[0168] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0169] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0170] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, the method and / or technical solutions according to the present application can be called or provided. Those skilled in the art should understand that the form of computer program instructions in a computer readable medium includes but is not limited to source files, executable files, installation package files, etc. Correspondingly, the way of executing computer program instructions by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0171] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method for predicting the power output data of a vehicle under multiple driving scenarios, characterized in that, The method includes: The system acquires current detection data, historical average power demand data, and historical energy recovery time data of the vehicle in the current driving scenario. The current detection data includes: vehicle operation data, vehicle road condition data, traffic data, and driving environment data. The first subnetwork predicts the power output power corresponding to the vehicle road condition data, the second subnetwork combines the power output power prediction value to predict the torque demand corresponding to the vehicle road condition data, the traffic data, and the driving environment data, and the third subnetwork predicts the long-term power demand corresponding to the historical average power demand data and the energy recovery time corresponding to the historical energy recovery time data, respectively. The first subnetwork, the second subnetwork, and the third subnetwork constitute a multi-layer network structure. Based on the predicted power output, the predicted torque demand, the predicted long-term power demand, and the predicted energy recovery time, a sub-network corresponding to the optimal state of the vehicle under the current driving scenario is obtained. Obtain the predicted value output by the subnetwork corresponding to the optimal state, and use the predicted value as the optimal prediction result under the current driving scenario.

2. The method according to claim 1, characterized in that, The step of predicting the predicted power output value corresponding to the vehicle road condition data through the first sub-network includes: Speed, acceleration, and engine speed are obtained from the vehicle road condition data; Based on the speed, the acceleration, and the engine speed, the first sub-network calculates the predicted power output power value corresponding to the vehicle road condition data, wherein the predicted power output power value is calculated by the following formula; in, The predicted value of the power output is... The convolution operation factor, For the speed, For the acceleration, The engine speed is [value missing].

3. The method according to claim 1, characterized in that, The step of predicting the torque demand corresponding to the vehicle road condition data, traffic data, and driving environment data by combining the predicted power output value with the second sub-network includes: The gradient is obtained from the vehicle road condition data, the traffic flow is obtained from the traffic data, and the temperature is obtained from the driving environment data. Based on the predicted power output, the gradient, the traffic flow, and the temperature, the second sub-network calculates the predicted torque demand corresponding to the traffic data and the driving environment data, wherein the predicted torque demand is calculated using the following formula; in, The torque demand prediction value is... As a feature fusion factor, The predicted value of the power output is... The slope is mentioned. The temperature is... The traffic flow is described above.

4. The method according to claim 1, characterized in that, The step of predicting the long-term power demand forecast corresponding to the historical average power demand data and the energy recovery time forecast corresponding to the historical energy recovery time data through the third sub-network includes: Based on the historical average power demand data and the historical energy recovery time data, the long-term power demand forecast and the energy recovery time forecast are calculated, wherein the long-term power demand forecast and the energy recovery time forecast are calculated by the following formulas; in, The long-term power demand forecast value is... The predicted energy recovery time is... The calculation factor of the third sub-network, The historical average power demand data, This refers to the historical energy recovery time data.

5. The method according to claim 1, characterized in that, Based on the predicted power output, predicted torque demand, predicted long-term power demand, and predicted energy recovery time, the sub-network corresponding to the optimal state of the vehicle in the current driving scenario is obtained, and executed using the following formula: in, The state feature vector corresponding to the method of real-time monitoring of the vehicle's current detection data in the current driving scenario to achieve the optimal state of the vehicle's current state. To achieve the optimal state corresponding to the current driving scenario The output accuracy of each subnetwork For the first The input features of each subnetwork for The predicted value output by each sub-network.

6. The method according to claim 1, characterized in that, The current driving scenario includes urban congestion scenarios, highway driving scenarios, or incline driving scenarios, and also includes: The current detection data in the urban congestion scenario, the highway driving scenario, or the slope driving scenario are weighted.

7. A device for predicting vehicle power output data under multiple driving scenarios, characterized in that, The device includes: The first acquisition module is used to acquire the current detection data, historical average power demand data, and historical energy recovery time data of the vehicle in the current driving scenario. The current detection data includes: vehicle operation data, vehicle road condition data, traffic data, and driving environment data. The current driving scenario includes urban congestion scenario, highway driving scenario, or slope driving scenario. The data prediction module is used to predict the power output power prediction value corresponding to the vehicle road condition data through a first sub-network, predict the torque demand prediction value corresponding to the traffic data and the driving environment data through a second sub-network combined with the power output power prediction value, and predict the long-term power demand prediction value corresponding to the historical average power demand data and the energy recovery time prediction value corresponding to the historical energy recovery time data through a third sub-network. The first sub-network, the second sub-network and the third sub-network constitute a multi-layer network structure. The second acquisition module is used to acquire the sub-network corresponding to the vehicle reaching the optimal state in the current driving scenario based on the predicted power output value, the predicted torque demand value, the predicted long-term power demand value, and the predicted energy recovery time value. The third acquisition module is used to acquire the predicted value output by the sub-network corresponding to the optimal state, and to use the predicted value as the optimal prediction result under the current driving scenario.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the power output data prediction method for a vehicle in multiple driving scenarios as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the power output data prediction method for a vehicle in multiple driving scenarios as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The method includes computer instructions for causing a computer to execute the power output data prediction method for a vehicle in multiple driving scenarios as described in any one of claims 1 to 6.

Images