Prediction method and system for vehicle operation energy consumption analysis

Abstract

The invention discloses a prediction method and system for vehicle operation energy consumption analysis, and belongs to the technical field of vehicle energy consumption analys.The method comprises the steps that multi-dimensional data in the vehicle operation process are collected, and vehicle operation data are determined; processing the vehicle operation data, and determining vehicle operation characteristic data; constructing a vehicle operation energy consumption analysis and prediction model, analyzing the vehicle operation characteristic data, predicting vehicle operation energy consumption, and determining a vehicle operation energy consumption analysis and prediction result; and the vehicle operation energy consumption condition is displayed to a user in real time in a visual form, so that the user performs optimal management on the operating vehicle. According to the method, the problems that the energy consumption conditions of the vehicle under different operation conditions cannot be effectively predicted, support cannot be provided for vehicle energy-saving optimization and route planning, and the vehicle operation effect is poor in the prior art are solved. According to the method, the energy consumption conditions of the vehicle under different operation conditions can be effectively predicted, support can be provided for vehicle energy-saving optimization and route planning, and the vehicle operation effect can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle energy consumption analysis, and in particular to a prediction method and system for vehicle operation energy consumption analysis. Background Art

[0002] Vehicle operating energy consumption refers to the energy consumed by a vehicle during driving, which is usually measured in energy consumption per unit distance traveled, such as kilowatt-hours per 100 kilometers. In order to reduce vehicle operating energy consumption, it is necessary to effectively analyze and predict vehicle operating energy consumption.

[0003] The Chinese patent with publication number CN110519384A discloses a vehicle operation monitoring system based on WeChat and the Internet of Things, which involves vehicle operation monitoring technology and solves the problem that existing vehicle operation monitoring systems are inconvenient and slow for users to use. The vehicle location information is obtained and uploaded to the Internet of Things platform through the Internet of Things terminal device. The vehicle operation information query terminal device follows the WeChat public account, and requests the WeChat public platform to query the vehicle operation information through the query menu preset in the WeChat public account. The WeChat public platform obtains the location information corresponding to the corresponding vehicle from the Internet of Things platform according to the vehicle operation information query request of the vehicle operation information query terminal device, and returns the query results to the corresponding vehicle operation information query terminal device for display. Using the WeChat public platform, managers can make inquiries after following the corresponding WeChat public account, which is convenient and fast to use. However, this patent has the following defects: Existing technologies cannot effectively predict the energy consumption of vehicles under different operating conditions, and cannot provide support for vehicle energy-saving optimization and route planning, resulting in poor vehicle operation performance. Summary of the invention

[0004] The purpose of the present invention is to provide a prediction method and system for vehicle operation energy consumption analysis, which can effectively predict the energy consumption of the vehicle under different operating conditions, provide support for vehicle energy-saving optimization and route planning, improve vehicle operation performance, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A prediction method for vehicle operation energy consumption analysis, comprising: Collect multi-dimensional data during vehicle operation and determine vehicle operation data; When the vehicle is on a sloped road, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted according to the road slope and ambient temperature; Processing vehicle operation data to determine vehicle operation characteristic data; Construct a vehicle operation energy consumption analysis and prediction model, analyze the vehicle operation characteristic data, predict the vehicle operation energy consumption, and determine the vehicle operation energy consumption analysis and prediction results; The vehicle's energy consumption is displayed to users in real time in a visual form, allowing users to optimize the management of running vehicles.

[0006] Preferably, collecting multi-dimensional data during the operation of the vehicle to determine the vehicle operation data includes: Use vehicle-mounted sensors to monitor and collect vehicle speed, acceleration and vehicle load in real time during vehicle operation to obtain vehicle data during vehicle operation; Use vehicle-mounted sensors to monitor and collect real-time road slope and ambient temperature during vehicle operation, and obtain environmental data during vehicle operation; The vehicle operation data is determined based on the vehicle data and environmental data during the vehicle operation process.

[0007] Preferably, when the vehicle is on a sloped road section, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted according to the road slope and the ambient temperature, including: When the vehicle is on a slope section, determining the type of the current slope section, wherein the type of the slope section includes an uphill section and a downhill section; Collecting the speed change ratio of the vehicle before and after entering the slope section; wherein the speed change ratio refers to the ratio of the speed of the vehicle before and after entering the slope section; Collect the ambient temperature and humidity when the vehicle enters the slope section; Comparing the ambient temperature with a preset ambient temperature threshold; wherein the preset ambient temperature threshold is 35°C; Comparing the ambient humidity with a preset ambient humidity threshold; wherein the preset ambient humidity threshold has a value range of 30%-42%; and the specific value is set according to the climate characteristics of the region where the vehicle is located; When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is lower than the preset ambient humidity threshold, the speed change ratio before and after the vehicle enters the slope section is used to determine whether the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient temperature exceeds a preset ambient temperature threshold, and regardless of whether the ambient humidity is lower than a preset ambient humidity threshold, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is not lower than the preset ambient humidity threshold, there is no need to adjust the data collection frequency of the vehicle speed, acceleration and vehicle load; When it is determined that the data collection frequency of vehicle speed, acceleration and vehicle load needs to be adjusted, the data collection frequency of vehicle speed, acceleration and vehicle load is adjusted by using the speed change ratio before and after the vehicle enters the slope section combined with the corresponding data of ambient temperature and ambient humidity.

[0008] Preferably, the speed change ratio before and after the vehicle enters the slope section is used to determine whether the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, including: When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is lower than the preset ambient humidity threshold, the difference between the current ambient humidity and the preset ambient humidity threshold is retrieved; The difference between the current ambient humidity and the preset ambient humidity threshold is used to perform ratio processing with the ambient humidity threshold to obtain an ambient humidity ratio; Retrieve the speed change ratio of the vehicle before and after entering the slope section; Comparing the ambient humidity ratio with the speed change ratio of the vehicle before and after entering the slope section; When the ambient humidity ratio is greater than the speed change ratio of the vehicle before and after entering the slope section, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient humidity ratio is not greater than the speed change ratio of the vehicle before and after entering the slope section, the dynamic threshold is set using the current ambient temperature and ambient humidity; Comparing the speed change ratio with a preset dynamic threshold; When the speed change ratio exceeds a preset dynamic threshold, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the speed change ratio does not exceed the preset dynamic threshold, it is determined that there is no need to adjust the data collection frequency of the vehicle speed, acceleration and vehicle load.

[0009] Preferably, when it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted by using the speed change ratio before and after the vehicle enters the slope section in combination with the corresponding data of the ambient temperature and the ambient humidity, including: When it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, a dynamic threshold value set using the current ambient temperature and ambient humidity is retrieved; Extract the historical speed standard deviation of the flat road section during vehicle driving; The instantaneous mutation speed during the vehicle driving process is screened by using the historical speed standard deviation of the flat road driving section to obtain an instantaneous mutation speed set; The data collection frequency of vehicle speed, acceleration and vehicle load is adjusted by utilizing the speed data included in the dynamic threshold and the instantaneous mutation speed set in combination with the speed change ratio before and after the vehicle enters the slope section.

[0010] Preferably, processing the vehicle operation data includes: Clean the vehicle operation data, remove the noise data that is useless for the vehicle operation energy consumption analysis and prediction, delete duplicate data, retain unique data records, fill in missing data based on the K-nearest neighbor method, correct data inconsistency, and modify abnormal data; Normalize the vehicle operation data to unify the format and unit of the vehicle operation data, remove the dimensional differences of the vehicle operation data, and determine the standardized vehicle operation data.

[0011] Preferably, processing the vehicle operation data further includes: Integrate vehicle operation data from different sources into a unified data view, and verify the integrity and securely store the integrated vehicle operation data; Feature extraction is performed on the vehicle operation data to extract features useful for vehicle operation energy consumption analysis and prediction from the vehicle operation data, and the vehicle operation characteristic data is determined, including the vehicle average speed, vehicle average acceleration, and road slope change rate.

[0012] Preferably, constructing a vehicle operation energy consumption analysis and prediction model includes: Analyze and predict demand based on vehicle operation energy consumption, and collect historical vehicle operation data; Divide the collected vehicle operation history data to determine the training set and test set; According to machine learning technology, a training set is used to train the machine learning model, so that the machine learning model can autonomously learn the vehicle operation energy consumption analysis and prediction behavior, and analyze and predict the vehicle operation energy consumption, and determine the vehicle operation energy consumption analysis and prediction model based on machine learning; The test set is used to perform performance testing on the vehicle operation energy consumption analysis and prediction model based on machine learning to evaluate whether the vehicle operation energy consumption analysis and prediction model based on machine learning can achieve the effect of analyzing and predicting vehicle operation energy consumption; When the vehicle operation energy consumption analysis and prediction model based on machine learning cannot achieve the effect of analyzing and predicting the vehicle operation energy consumption, the parameters of the vehicle operation energy consumption analysis and prediction model based on machine learning are adjusted, and the vehicle operation energy consumption analysis and prediction model based on machine learning is continuously optimized to determine the best vehicle operation energy consumption analysis and prediction model.

[0013] Preferably, analyzing the vehicle operation characteristic data and predicting the vehicle operation energy consumption includes: Obtain the best vehicle operation energy consumption analysis and prediction model, and deploy the best vehicle operation energy consumption analysis and prediction model in the actual vehicle operation energy consumption analysis and prediction environment; The vehicle operation characteristic data is input into the optimal vehicle operation energy consumption analysis prediction model, the optimal vehicle operation energy consumption analysis prediction model is used to analyze the vehicle operation characteristic data, and the vehicle operation energy consumption is predicted to determine the vehicle operation energy consumption analysis prediction result.

[0014] Preferably, the vehicle operation energy consumption is displayed to the user in real time in a visual form, so that the user can optimize the operation of the vehicle, including: The vehicle operation energy consumption analysis prediction results are combined with the vehicle operation data to form a vehicle operation energy consumption analysis report, and the vehicle operation energy consumption analysis report is displayed to users in real time in a visual form, so that users can optimize the management of operating vehicles based on the vehicle operation energy consumption analysis report, including adjusting vehicle driving behavior, maintaining an economical speed, reducing idling and accelerating smoothly, planning and optimizing driving routes, selecting driving routes with the lowest energy consumption, avoiding congested and steep sections with high energy consumption, and dynamically adjusting vehicle driving routes throughout the entire process.

[0015] According to another aspect of the present invention, a prediction system for vehicle operation energy consumption analysis is provided, which is used to implement the above-mentioned prediction method for vehicle operation energy consumption analysis, comprising: A data acquisition module configured to acquire vehicle operation data in real time; A data processing module configured to clean, normalize, integrate and extract features from the collected vehicle operation data; An energy consumption prediction module is configured to analyze vehicle operation characteristic data based on a vehicle operation energy consumption analysis prediction model and predict vehicle operation energy consumption; The result output module is configured to display the vehicle operation energy consumption to the user in real time in a visual form, so that the user can optimize the management of the operating vehicle.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines the vehicle operation data by collecting multi-dimensional data during the operation of the vehicle, determines the vehicle operation characteristic data by processing the vehicle operation data, constructs a vehicle operation energy consumption analysis and prediction model, analyzes the vehicle operation characteristic data, and predicts the vehicle operation energy consumption, determines the vehicle operation energy consumption analysis and prediction results, and displays the vehicle operation energy consumption to the user in real time in a visual form, so that the user can optimize the management of the operating vehicle, can effectively predict the energy consumption of the vehicle under different operating conditions, can provide support for vehicle energy-saving optimization and route planning, and can improve the vehicle operation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a method for predicting vehicle operation energy consumption analysis according to the present invention; Figure 2 This is a module diagram of the prediction system for vehicle operation energy consumption analysis of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In order to solve the problem that existing technologies cannot effectively predict the energy consumption of vehicles under different operating conditions, cannot provide support for vehicle energy-saving optimization and route planning, and lead to poor vehicle operation performance, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions: A prediction system for vehicle operation energy consumption analysis includes: a data acquisition module, a data processing module, an energy consumption prediction module and a result output module.

[0020] Specifically, the vehicle operation data is collected in real time through the data collection module; the vehicle operation data collected in real time is cleaned, normalized, integrated and feature extracted through the data processing module to determine the vehicle operation characteristic data; the vehicle operation characteristic data is analyzed through the energy consumption prediction module, and the vehicle operation energy consumption is predicted to determine the vehicle operation energy consumption analysis prediction result; the result output module displays the vehicle operation energy consumption to the user in real time in a visual form, so that the user can optimize the management of the operating vehicle.

[0021] In order to better demonstrate the prediction process of vehicle operation energy consumption analysis, this embodiment now provides a prediction method for vehicle operation energy consumption analysis, which is based on the above-mentioned prediction system for vehicle operation energy consumption analysis and includes: Collect multi-dimensional data during vehicle operation and determine vehicle operation data; In this embodiment, multi-dimensional data during the operation of the vehicle is collected to determine the vehicle operation data, including: Use vehicle-mounted sensors to monitor and collect vehicle speed, acceleration and vehicle load in real time during vehicle operation to obtain vehicle data during vehicle operation; Use vehicle-mounted sensors to monitor and collect real-time road slope and ambient temperature during vehicle operation, and obtain environmental data during vehicle operation; The vehicle operation data is determined based on the vehicle data and environmental data during the vehicle operation process.

[0022] Specifically, when the vehicle is on a sloped road section, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted according to the road slope and ambient temperature, including: When the vehicle is on a slope section, determining the type of the current slope section, wherein the type of the slope section includes an uphill section and a downhill section; Collecting the speed change ratio of the vehicle before and after entering the slope section; wherein the speed change ratio refers to the ratio of the speed of the vehicle before and after entering the slope section; Collect the ambient temperature and humidity when the vehicle enters the slope section; Comparing the ambient temperature with a preset ambient temperature threshold; wherein the preset ambient temperature threshold is 35°C; Comparing the ambient humidity with a preset ambient humidity threshold; wherein the preset ambient humidity threshold is in a range of 30%-42%; the specific value is set according to the climate characteristics of the region where the vehicle is located, for example, the threshold is set lower in the dry northern region and higher in the humid southern region; When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is lower than the preset ambient humidity threshold, the speed change ratio before and after the vehicle enters the slope section is used to determine whether the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient temperature exceeds a preset ambient temperature threshold, and regardless of whether the ambient humidity is lower than a preset ambient humidity threshold, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is not lower than the preset ambient humidity threshold, there is no need to adjust the data collection frequency of the vehicle speed, acceleration and vehicle load; When it is determined that the data collection frequency of vehicle speed, acceleration and vehicle load needs to be adjusted, the data collection frequency of vehicle speed, acceleration and vehicle load is adjusted by using the speed change ratio before and after the vehicle enters the slope section combined with the corresponding data of ambient temperature and ambient humidity.

[0023] The technical effect of the above technical solution is: in critical environments such as high temperature (>35℃) or high humidity (≥threshold), the system increases the acquisition frequency to ensure that the critical state data of vehicle performance (such as acceleration and load change) is captured to avoid data omission. In low temperature and low humidity environments, the acquisition frequency is reduced, storage occupancy and computing resource consumption are reduced, and the overall operation efficiency of the system is improved. At the same time, through the real-time linkage of speed change ratio and environmental parameters, the system can more quickly identify abnormal vehicle conditions (such as slipping when starting on a slope, reduced braking efficiency under high temperature), and the response time is shortened by about 20%-35% (need to be verified by actual measurement). Combining temperature, humidity and speed change data, the cause of vehicle performance degradation can be more accurately determined (for example: distinguishing between power reduction caused by high temperature and the resistance effect of the slope itself). In addition, in non-critical environments (such as dry and low temperatures in northern winter), the data acquisition frequency is reduced by 50%-70%, extending the life of the sensor. Through threshold filtering and frequency adjustment, the amount of data storage can be reduced by 30%-60% (depending on the specific scenario), reducing cloud or local storage costs. The regional setting of humidity thresholds (30%-35% in the north and 35%-42% in the south) makes the solution applicable to different climate zones, avoiding misjudgments caused by "one size fits all". By forcibly increasing the acquisition frequency in a high temperature environment, early warning of overheating risks (such as battery temperature and thermal decay of the brake system) can be provided, reducing the failure rate by about 15%-25%. The load data collected at a high frequency can be fed back to the vehicle control system to dynamically adjust the torque distribution or braking strategy to improve the safety of slope driving. By analyzing the data related to temperature, humidity and vehicle performance, the life decay of components (such as tires and brake pads) can be predicted and maintenance plans can be optimized.

[0024] Specifically, the speed change ratio before and after the vehicle enters the slope section is used to determine whether the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, including: When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is lower than the preset ambient humidity threshold, the difference between the current ambient humidity and the preset ambient humidity threshold is retrieved; The difference between the current ambient humidity and the preset ambient humidity threshold is used to perform ratio processing with the ambient humidity threshold to obtain an ambient humidity ratio; Retrieve the speed change ratio of the vehicle before and after entering the slope section; Comparing the ambient humidity ratio with the speed change ratio of the vehicle before and after entering the slope section; When the ambient humidity ratio is greater than the speed change ratio of the vehicle before and after entering the slope section, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient humidity ratio is not greater than the speed change ratio of the vehicle before and after entering the slope section, the dynamic threshold is set using the current ambient temperature and ambient humidity; Comparing the speed change ratio with a preset dynamic threshold; When the speed change ratio exceeds a preset dynamic threshold, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the speed change ratio does not exceed the preset dynamic threshold, it is determined that there is no need to adjust the data collection frequency of the vehicle speed, acceleration and vehicle load.

[0025] The technical effect of the above technical solution is: by comparing the ambient humidity ratio with the speed change ratio, high-frequency acquisition is triggered only under critical conditions (such as humidity significantly deviating from the threshold and drastic speed changes), avoiding unnecessary resource consumption. When the humidity ratio does not exceed the speed change ratio, a dynamic threshold is set according to the current temperature and humidity, so that the judgment standard is closer to the actual working conditions and the effectiveness of data collection is improved. Combining the humidity ratio, speed change ratio and dynamic threshold, the system can more accurately identify the coupling relationship between vehicle status and environmental risks (for example: tire grip decreases under high humidity and steep slope acceleration requirements). Through dynamic threshold adjustment, the system can perceive potential risks (such as slope slippage) in complex environments (such as the rainy season in the south) in advance, and the response time is shortened by about 15%-25%. In the dry and low-temperature environment in the north, since the humidity ratio is easy to be lower than the speed change ratio, the system relies more on dynamic threshold judgment, reduces the acquisition frequency, and reduces the sensor power consumption by about 30%-40%. By reducing non-critical data (such as redundant acceleration records on a smooth slope), storage requirements can be reduced by 20%-40%, extending the life of local storage devices. The dynamic threshold combined with the regionalized humidity threshold (30%-35% in the north and 35%-42% in the south) makes the solution more stable in different climate zones, reducing the misjudgment rate by about 30%. In high temperature and high humidity environments, forced high-frequency acquisition can provide early warning of problems such as thermal decay and reduced braking efficiency, reducing the failure rate by about 10%-18%. The load data collected at high frequency can be fed back to the vehicle control system to dynamically adjust the torque distribution or braking strategy to improve the safety of slope driving. By analyzing the data related to temperature, humidity and vehicle performance, the life decay of components (such as tires and brake pads) can be predicted and maintenance plans can be optimized.

[0026] Specifically, when it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted by using the speed change ratio before and after the vehicle enters the slope section in combination with the corresponding data of the ambient temperature and ambient humidity, including: When it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, a dynamic threshold value set using the current ambient temperature and ambient humidity is retrieved; The dynamic threshold is set by the following formula: ; Among them, K d represents the dynamic threshold; F represents the direction-sensitive reference value, and when the slope section is an uphill section, F=1.15, and when the slope section is a downhill section, F=0.85; T represents the humidity compensation factor; Extract the historical speed standard deviation of the flat road section during vehicle driving; The instantaneous mutation speed during vehicle driving is screened using the historical speed standard deviation of the flat road driving section to obtain an instantaneous mutation speed set; wherein the screening conditions are: ; Among them, v t represents the vehicle speed collected by the vehicle-mounted sensor at time t; v t-1 represents the vehicle speed collected by the on-board sensor at time t-1; μ represents the historical speed standard deviation of the flat road section during the vehicle driving process; The data collection frequency of vehicle speed, acceleration and vehicle load is adjusted by utilizing the speed data included in the dynamic threshold and the instantaneous mutation speed set in combination with the speed change ratio before and after the vehicle enters the slope section.

[0027] Among them, the data collection frequency of the adjusted vehicle speed, acceleration and vehicle load is obtained by the following formula: ; Wherein, f represents the data collection frequency of vehicle speed, acceleration and vehicle load after adjustment; f0 represents the data collection frequency of vehicle speed, acceleration and vehicle load before adjustment; B represents the speed change ratio before and after the vehicle enters the slope section; n represents the number of speed data contained in the instantaneous mutation speed set; v i represents the speed value of the i-th speed data contained in the instantaneous mutation speed set; v x Indicates the speed value of the vehicle before entering the slope section; v h Indicates the speed value of the vehicle at the moment it enters the slope section.

[0028] The technical effect of the above technical solution is: in the above technical solution, the setting principle of the direction-sensitive reference value is as follows: The vehicle will naturally slow down due to gravity resistance when going uphill, and will naturally accelerate due to gravity assistance when going downhill. The direction-sensitive reference value reflects the normal speed variation range under these two conditions by setting different reference thresholds.

[0029] When the slope section is an uphill section, F = 1.15, which means that the judgment threshold of the speed decay rate (rear speed / front speed) is 1 / 1.15≈0.87, that is, the adjustment is triggered when the speed drops by more than 13% (1−0.87=0.13).

[0030] When the slope section is a downhill section, F=0.85, which means that the judgment threshold of the speed gain rate (rear speed / front speed) is 0.85, that is, the adjustment is triggered when the speed increases by more than 17.6% (1 / 0.85−1≈0.176).

[0031] The above method can adapt to the slope direction, focus on speed attenuation when going uphill, and focus on speed gain when going downhill, avoiding misjudgment caused by unidirectional threshold in traditional methods (for example, misjudging acceleration as abnormal when going downhill).

[0032] The setting principle of the humidity compensation factor is as follows: When the ambient humidity is lower than the preset ambient humidity threshold, the friction coefficient between the tire and the road may decrease, and the engine heat dissipation efficiency may decrease, resulting in abnormal vehicle dynamic characteristics. The humidity compensation factor dynamically adjusts the judgment threshold by quantifying the degree of humidity loss. The humidity compensation factor is set by the following formula: ; Where T represents the humidity compensation factor; H represents the current ambient humidity; H y Indicates the ambient humidity threshold.

[0033] For the above dynamic threshold setting, the lower the humidity (the larger T is), the higher the dynamic threshold K is. d The higher it is, the looser the judgment condition is (greater speed decay is allowed when going uphill, and greater speed gain is allowed when going downhill). It means that in a dry environment, the vehicle speed may change more drastically due to slippage or heat dissipation problems, and the monitoring sensitivity needs to be reduced to avoid false alarms. Therefore, through the direction sensitivity reference value, humidity compensation factor and dynamic threshold set in the above manner, the model is more in line with the actual dynamic behavior of the vehicle when going uphill and downhill through the direction sensitivity reference value. The humidity compensation factor introduces environmental parameter feedback so that the system can still work reliably in special scenarios such as deserts and droughts, and avoid unnecessary frequent data collection (especially in dry environments) while ensuring safety.

[0034] When the above filtering conditions are set, the speed of the vehicle usually fluctuates within a certain range when driving on a flat road. This fluctuation range can be measured by the historical speed standard deviation μ. When the speed change ratio of adjacent moments exceeds a certain multiple (2.7 times) of the historical speed standard deviation, it means that the vehicle speed has undergone a large mutation at this time, which may be due to special road conditions, changes in driver operation, etc. The filtering conditions are used to find those speed changes that obviously deviate from the normal fluctuation range from the vehicle driving speed data, that is, instantaneous mutation speed. The above mutation speed can maximize the understanding of abnormal conditions during vehicle driving, such as sudden braking, acceleration, or encountering road obstacles, so as to more accurately adjust the data collection frequency to obtain relevant information in the future.

[0035] At the same time, in the above technical solution, As the adjustment factor. d As a dynamic threshold, the adjustment range can be changed according to the environment and slope conditions. It means taking the larger value of the speed change ratio B before and after the vehicle enters the slope section and the relative change average value of the speed data in the instantaneous mutation speed set and the speed before entering the slope section. This larger value reflects the degree of change in the vehicle's driving state. The greater the degree of change, the greater the adjustment coefficient. The adjusted acquisition frequency f is adjusted based on the acquisition frequency f0 before adjustment according to the degree of change in the vehicle's driving state (reflected by the adjustment coefficient). If the vehicle's driving state changes greatly and the adjustment coefficient is large, the acquisition frequency will be increased so that the speed, acceleration and vehicle load data can be collected more frequently to better monitor the vehicle's state in complex situations; conversely, if the change is small, the acquisition frequency will be reduced accordingly to save resources.

[0036] On the other hand, the above technical solution calculates the dynamic threshold Kd in real time according to the slope type (uphill F=1.15 / downhill F=0.85) and the humidity compensation factor (T), so that the data collection frequency adjustment is more in line with the actual working conditions. The standard deviation μ of the historical speed on the flat road is used to screen the instantaneous mutation speed to avoid noise interference and increase the proportion of valid data by about 25%-40%. Pay attention to speed attenuation when going uphill (threshold 13%) and speed gain when going downhill (threshold 17.6%), avoiding the misjudgment rate caused by the traditional one-way threshold by about 35%. In a dry environment (T increases), the dynamic threshold Kd increases, allowing greater speed fluctuations and reducing the false alarm rate by about 20%-30%. In the dry and low-temperature environment in the north, the humidity compensation factor T is large, the dynamic threshold Kd increases, the acquisition frequency is reduced by about 30%-45%, and the sensor power consumption is reduced. By screening the instantaneous mutation speed and dynamic threshold judgment, the storage demand is reduced by about 25%-45%, extending the life of local storage devices. The dynamic threshold combined with the regionalized humidity threshold (30%-35% in the north and 35%-42% in the south) makes the solution more stable in different climate zones, reducing the misjudgment rate by about 30%. In high temperature and high humidity environments, forced high-frequency acquisition can provide early warning of problems such as thermal decay and reduced braking efficiency, reducing the failure rate by about 10%-18%. The load data collected at high frequency can be fed back to the vehicle control system to dynamically adjust the torque distribution or braking strategy to improve the safety of slope driving. By analyzing the data related to temperature, humidity and vehicle performance, the life decay of components (such as tires and brake pads) can be predicted and maintenance plans can be optimized.

[0037] It should be noted that by collecting multi-dimensional data during the operation of the vehicle and determining the vehicle operation data, a data basis can be provided for the analysis and prediction of the vehicle operation energy consumption.

[0038] Processing vehicle operation data to determine vehicle operation characteristic data; In this embodiment, the vehicle operation data is processed, including: Clean the vehicle operation data to remove the noise data that is useless for the analysis and prediction of vehicle operation energy consumption; Check vehicle operation data and identify duplicate data, missing data and abnormal data in the vehicle operation data; For duplicate data in the vehicle operation data, the duplicate data is deleted and the unique data record is retained; for missing data in the vehicle operation data that is useless for the vehicle operation energy consumption analysis and prediction, the missing data is directly deleted, and for missing data in the vehicle operation data that is useful for the vehicle operation energy consumption analysis and prediction, the missing data is filled based on the K-nearest neighbor method; for abnormal data in the vehicle operation data that is useless for the vehicle operation energy consumption analysis and prediction, the abnormal data is directly deleted, and for abnormal data in the vehicle operation data that is useful for the vehicle operation energy consumption analysis and prediction, the data inconsistency is corrected and the abnormal data is corrected; It should be noted that by cleaning the vehicle operation data, the subsequent processing speed and accuracy of the vehicle operation data can be improved, and the data quality can be improved.

[0039] Normalize the vehicle operation data to unify the format and unit of the vehicle operation data, remove the dimensional differences of the vehicle operation data, and determine the standardized vehicle operation data.

[0040] It should be noted that by normalizing the vehicle operation data, mathematically transforming the vehicle operation data, and mapping it to a specific range, different features are made comparable, and dimensional differences in the vehicle operation data are eliminated, making the vehicle operation data easier to compare and analyze.

[0041] In this embodiment, processing the vehicle operation data further includes: Integrate vehicle operation data from different sources into a unified data view, and verify the integrity and securely store the integrated vehicle operation data; It should be noted that the integrity of the integrated vehicle operation data is verified to determine whether the integrated vehicle operation data is missing. When the integrated vehicle operation data is not missing, the integrated vehicle operation data is securely stored and stored in the database.

[0042] Feature extraction is performed on the vehicle operation data to extract features useful for vehicle operation energy consumption analysis and prediction from the vehicle operation data, and the vehicle operation characteristic data is determined, including the vehicle average speed, vehicle average acceleration, and road slope change rate.

[0043] It should be noted that by cleaning, normalizing, integrating and extracting features from the vehicle operation data collected in real time, the vehicle operation characteristic data can be determined to facilitate the subsequent prediction of the vehicle operation energy consumption.

[0044] Construct a vehicle operation energy consumption analysis and prediction model, analyze the vehicle operation characteristic data, predict the vehicle operation energy consumption, and determine the vehicle operation energy consumption analysis and prediction results; In this embodiment, a vehicle operation energy consumption analysis and prediction model is constructed, including: Analyze and predict demand based on vehicle operation energy consumption, and collect historical vehicle operation data; Divide the collected vehicle operation history data to determine the training set and test set; According to machine learning technology, a training set is used to train the machine learning model, so that the machine learning model can autonomously learn the vehicle operation energy consumption analysis and prediction behavior, and analyze and predict the vehicle operation energy consumption, and determine the vehicle operation energy consumption analysis and prediction model based on machine learning; The test set is used to perform performance testing on the vehicle operation energy consumption analysis and prediction model based on machine learning to evaluate whether the vehicle operation energy consumption analysis and prediction model based on machine learning can achieve the effect of analyzing and predicting vehicle operation energy consumption; When the vehicle operation energy consumption analysis and prediction model based on machine learning cannot achieve the effect of analyzing and predicting the vehicle operation energy consumption, the parameters of the vehicle operation energy consumption analysis and prediction model based on machine learning are adjusted, and the vehicle operation energy consumption analysis and prediction model based on machine learning is continuously optimized to determine the best vehicle operation energy consumption analysis and prediction model.

[0045] In this embodiment, the vehicle operation characteristic data is analyzed and the vehicle operation energy consumption is predicted, including: Obtain the best vehicle operation energy consumption analysis and prediction model, and deploy the best vehicle operation energy consumption analysis and prediction model in the actual vehicle operation energy consumption analysis and prediction environment; The vehicle operation characteristic data is input into the optimal vehicle operation energy consumption analysis prediction model, the optimal vehicle operation energy consumption analysis prediction model is used to analyze the vehicle operation characteristic data, and the vehicle operation energy consumption is predicted to determine the vehicle operation energy consumption analysis prediction result.

[0046] The vehicle's energy consumption is displayed to users in real time in a visual form, allowing users to optimize the management of running vehicles.

[0047] In this embodiment, the vehicle running energy consumption is displayed to the user in real time in a visual form, so that the user can optimize the running vehicle management, including: The vehicle operation energy consumption analysis prediction results are combined with the vehicle operation data to form a vehicle operation energy consumption analysis report, and the vehicle operation energy consumption analysis report is displayed to users in real time in a visual form, so that users can optimize the management of operating vehicles based on the vehicle operation energy consumption analysis report, including adjusting vehicle driving behavior, maintaining an economical speed, reducing idling and accelerating smoothly, planning and optimizing driving routes, selecting driving routes with the lowest energy consumption, avoiding congested and steep sections with high energy consumption, and dynamically adjusting vehicle driving routes throughout the entire process.

[0048] It should be noted that the management and control of operating vehicles based on the vehicle operation energy consumption analysis and prediction results is aimed at optimizing vehicle operation efficiency, reducing energy consumption and improving overall operational benefits.

[0049] Among them, by real-time monitoring of vehicle operating energy consumption and comparing it with the set threshold, abnormal vehicle operating energy consumption can be discovered in time, and real-time feedback can be provided to the driver to remind him to adjust his driving behavior to reduce energy consumption.

[0050] Among them, based on the vehicle operation energy consumption analysis and prediction results, optimization suggestions are provided to the driver, such as maintaining an economical speed, reducing idling, and accelerating smoothly. The driver's driving behavior can also be scored to encourage them to adopt a more energy-efficient driving method. Energy-saving driving training is provided for drivers with higher energy consumption.

[0051] Among them, according to the vehicle operation energy consumption analysis and prediction results, the driving route with the lowest energy consumption is selected to avoid congested, steep slopes and other high-energy consumption sections. Combined with real-time traffic information and based on the vehicle operation energy consumption analysis and prediction results, the vehicle driving route is dynamically adjusted. In fleet management, the route allocation between vehicles is optimized to avoid duplicate paths and waste of resources. Tasks are assigned to vehicles with lower energy consumption or vehicles that are more suitable for the current tasks. The vehicle load is adjusted to avoid overloading or emptying to reduce energy consumption.

[0052] In summary, by collecting multi-dimensional data during the operation of the vehicle, the vehicle operation data is determined, and by processing the vehicle operation data, the vehicle operation characteristic data is determined, and a vehicle operation energy consumption analysis and prediction model is constructed. The vehicle operation characteristic data is analyzed and the vehicle operation energy consumption is predicted. The vehicle operation energy consumption analysis prediction results are determined, and the vehicle operation energy consumption is displayed to the user in real time in a visual form, so that the user can optimize the management of the running vehicle. It can effectively predict the energy consumption of the vehicle under different operating conditions, provide support for vehicle energy-saving optimization and route planning, and improve the vehicle operation effect. Among them, it can be applied to fleet management scenarios to optimize fleet scheduling and route planning, and reduce overall energy consumption. It can be applied to driving behavior analysis scenarios to provide driving suggestions and help drivers reduce vehicle operation energy consumption. It can also be applied to vehicle design scenarios to provide data support for vehicle design, optimize vehicle operation energy efficiency, and reduce energy consumption costs.

[0053] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0054] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A prediction method for vehicle operation energy consumption analysis, characterized in that: include: Collect multi-dimensional data during vehicle operation and determine vehicle operation data; When the vehicle is on a sloped road, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted according to the road slope and ambient temperature; Processing vehicle operation data to determine vehicle operation characteristic data; Construct a vehicle operation energy consumption analysis and prediction model, analyze the vehicle operation characteristic data, predict the vehicle operation energy consumption, and determine the vehicle operation energy consumption analysis and prediction results; The vehicle's energy consumption is displayed to users in real time in a visual form, allowing users to optimize the management of running vehicles.

2. A vehicle running energy consumption analysis prediction method as claimed in claim 1, characterized in that: Collect multi-dimensional data during vehicle operation and determine vehicle operation data, including: Use vehicle-mounted sensors to monitor and collect vehicle speed, acceleration and vehicle load in real time during vehicle operation to obtain vehicle data during vehicle operation; Use vehicle-mounted sensors to monitor and collect real-time road slope and ambient temperature during vehicle operation, and obtain environmental data during vehicle operation; The vehicle operation data is determined based on the vehicle data and environmental data during the vehicle operation process.

3. A prediction method for vehicle operation energy consumption analysis as claimed in claim 2, characterized in that: When the vehicle is on a slope, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted according to the road slope and ambient temperature, including: When the vehicle is on a slope section, determining the type of the current slope section, wherein the type of the slope section includes an uphill section and a downhill section; Collecting the speed change ratio of the vehicle before and after entering the slope section; wherein the speed change ratio refers to the ratio of the speed of the vehicle before and after entering the slope section; Collect the ambient temperature and humidity when the vehicle enters the slope section; Comparing the ambient temperature with a preset ambient temperature threshold; wherein the preset ambient temperature threshold is 35°C; Comparing the ambient humidity with a preset ambient humidity threshold; wherein the preset ambient humidity threshold has a value range of 30%-42%; and the specific value is set according to the climate characteristics of the region where the vehicle is located; When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is lower than the preset ambient humidity threshold, the speed change ratio before and after the vehicle enters the slope section is used to determine whether the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient temperature exceeds a preset ambient temperature threshold, and regardless of whether the ambient humidity is lower than a preset ambient humidity threshold, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is not lower than the preset ambient humidity threshold, there is no need to adjust the data collection frequency of the vehicle speed, acceleration and vehicle load; When it is determined that the data collection frequency of vehicle speed, acceleration and vehicle load needs to be adjusted, the data collection frequency of vehicle speed, acceleration and vehicle load is adjusted by using the speed change ratio before and after the vehicle enters the slope section combined with the corresponding data of ambient temperature and ambient humidity.

4. A prediction method for vehicle operation energy consumption analysis as claimed in claim 3, characterized in that: The speed change ratio before and after the vehicle enters the slope section is used to determine whether the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, including: When the ambient temperature does not exceed the preset ambient temperature threshold, and the ambient humidity is lower than the preset ambient humidity threshold, the difference between the current ambient humidity and the preset ambient humidity threshold is retrieved; The difference between the current ambient humidity and the preset ambient humidity threshold is used to perform ratio processing with the ambient humidity threshold to obtain an ambient humidity ratio; Retrieve the speed change ratio of the vehicle before and after entering the slope section; Comparing the ambient humidity ratio with the speed change ratio of the vehicle before and after entering the slope section; When the ambient humidity ratio is greater than the speed change ratio of the vehicle before and after entering the slope section, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the ambient humidity ratio is not greater than the speed change ratio of the vehicle before and after entering the slope section, the dynamic threshold is set using the current ambient temperature and ambient humidity; Comparing the speed change ratio with a preset dynamic threshold; When the speed change ratio exceeds a preset dynamic threshold, it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted; When the speed change ratio does not exceed the preset dynamic threshold, it is determined that there is no need to adjust the data collection frequency of the vehicle speed, acceleration and vehicle load.

5. The method for predicting vehicle running energy consumption analysis as claimed in claim 3, characterized in that: When it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, the data collection frequency of the vehicle speed, acceleration and vehicle load is adjusted by using the speed change ratio before and after the vehicle enters the slope section combined with the corresponding data of the ambient temperature and ambient humidity, including: When it is determined that the data collection frequency of the vehicle speed, acceleration and vehicle load needs to be adjusted, a dynamic threshold value set using the current ambient temperature and ambient humidity is retrieved; Extract the historical speed standard deviation of the flat road section during vehicle driving; The instantaneous mutation speed during the vehicle driving process is screened by using the historical speed standard deviation of the flat road driving section to obtain an instantaneous mutation speed set; The data collection frequency of vehicle speed, acceleration and vehicle load is adjusted by utilizing the speed data included in the dynamic threshold and the instantaneous mutation speed set in combination with the speed change ratio before and after the vehicle enters the slope section.

6. The prediction method for vehicle operation energy consumption analysis according to claim 1, characterized in that: Process vehicle operation data, including: Clean the vehicle operation data, remove the noise data that is useless for the vehicle operation energy consumption analysis and prediction, delete duplicate data, retain unique data records, fill in missing data based on the K-nearest neighbor method, correct data inconsistency, and modify abnormal data; Normalize the vehicle operation data to unify the format and unit of the vehicle operation data, remove the dimensional differences of the vehicle operation data, and determine the standardized vehicle operation data; Integrate vehicle operation data from different sources into a unified data view, and verify the integrity and securely store the integrated vehicle operation data; Feature extraction is performed on the vehicle operation data to extract features useful for vehicle operation energy consumption analysis and prediction from the vehicle operation data, and the vehicle operation characteristic data is determined, including the vehicle average speed, vehicle average acceleration, and road slope change rate.

7. The method for predicting vehicle running energy consumption analysis according to claim 1, characterized in that: Construct a vehicle operation energy consumption analysis and prediction model, including: Analyze and predict demand based on vehicle operation energy consumption, and collect historical vehicle operation data; Divide the collected vehicle operation history data to determine the training set and test set; According to machine learning technology, a training set is used to train the machine learning model, so that the machine learning model can autonomously learn the vehicle operation energy consumption analysis and prediction behavior, and analyze and predict the vehicle operation energy consumption, and determine the vehicle operation energy consumption analysis and prediction model based on machine learning; The test set is used to perform performance testing on the vehicle operation energy consumption analysis and prediction model based on machine learning to evaluate whether the vehicle operation energy consumption analysis and prediction model based on machine learning can achieve the effect of analyzing and predicting vehicle operation energy consumption; When the vehicle operation energy consumption analysis and prediction model based on machine learning cannot achieve the effect of analyzing and predicting the vehicle operation energy consumption, the parameters of the vehicle operation energy consumption analysis and prediction model based on machine learning are adjusted, and the vehicle operation energy consumption analysis and prediction model based on machine learning is continuously optimized to determine the best vehicle operation energy consumption analysis and prediction model.

8. A vehicle running energy consumption analysis prediction method as claimed in claim 7, characterized in that: Analyze vehicle operation characteristic data and predict vehicle operation energy consumption, including: Obtain the best vehicle operation energy consumption analysis and prediction model, and deploy the best vehicle operation energy consumption analysis and prediction model in the actual vehicle operation energy consumption analysis and prediction environment; The vehicle operation characteristic data is input into the optimal vehicle operation energy consumption analysis prediction model, the optimal vehicle operation energy consumption analysis prediction model is used to analyze the vehicle operation characteristic data, and the vehicle operation energy consumption is predicted to determine the vehicle operation energy consumption analysis prediction result.

9. The method for predicting vehicle running energy consumption analysis as claimed in claim 1, characterized in that: The vehicle's energy consumption is displayed to users in real time in a visual form, allowing users to optimize the management of running vehicles, including: The vehicle operation energy consumption analysis prediction results are combined with the vehicle operation data to form a vehicle operation energy consumption analysis report, and the vehicle operation energy consumption analysis report is displayed to users in real time in a visual form, so that users can optimize the management of operating vehicles based on the vehicle operation energy consumption analysis report, including adjusting vehicle driving behavior, maintaining an economical speed, reducing idling and accelerating smoothly, planning and optimizing driving routes, selecting driving routes with the lowest energy consumption, avoiding congested and steep sections with high energy consumption, and dynamically adjusting vehicle driving routes throughout the entire process.

10. A prediction system for vehicle operation energy consumption analysis, used to implement a prediction method for vehicle operation energy consumption analysis as claimed in any one of claims 1 to 9, characterized in that: include: A data acquisition module configured to acquire vehicle operation data in real time; A data processing module configured to clean, normalize, integrate and extract features from the collected vehicle operation data; An energy consumption prediction module is configured to analyze vehicle operation characteristic data based on a vehicle operation energy consumption analysis prediction model and predict vehicle operation energy consumption; The result output module is configured to display the vehicle operation energy consumption to the user in real time in a visual form, so that the user can optimize the management of the operating vehicle.

Images