Vehicle energy consumption monitoring method and system

Abstract

The invention provides a vehicle energy consumption monitoring method and system, and relates to the field of vehicle energy management, and the method comprises the steps: obtaining the energy sensor data of a plurality of monitored vehicles and the vehicle working state data collected by a vehicle terminal in real time through a wireless communication module; detecting whether the energy sensor data and the vehicle working state data are in a reasonable range or not; energy sensor data from different vehicles and vehicle working state data are matched according to timestamps, and the corresponding relation between the vehicle running state and energy consumption in the same time period is established; and constructing a machine learning model for predicting energy consumption based on a linear regression algorithm, a decision tree algorithm and a random forest algorithm to predict energy consumption data of the vehicle, comparing a predicted value with an actual consumption value, and determining that the energy consumption is normal if the deviation is within a preset range. According to the technical scheme provided by the invention, the energy consumption condition of the vehicle can be deeply known, and powerful support is provided for energy-saving optimization and management decision.

Description

Technical Field

[0001] The present invention relates to the field of vehicle energy management, and in particular to a vehicle energy consumption monitoring method and system. Background Art

[0002] With the rapid development of the transportation industry, the energy consumption management of vehicles has become increasingly important. Accurately monitoring the changes in the liquid level / gas volume in the vehicle tank or gas tank is of key significance for optimizing energy use, controlling costs and ensuring the sustainability of operations. In the process of realizing the present invention, the applicant found that some existing vehicle energy management solutions based on liquid level / gas volume change monitoring usually rely on the original on-board computer data provided by the vehicle manufacturer. These data may include the mileage of the vehicle, the average fuel consumption and some basic operating parameters. The energy consumption of the vehicle is estimated by analyzing these limited data. However, this method has obvious limitations. Since the acquired data is relatively basic and general, it cannot accurately reflect the actual energy consumption of the vehicle under different driving conditions (such as frequent start-stop, high-speed driving, heavy-load transportation, etc.). Moreover, these data generally do not contain key information about the quality of oil / gas products and real-time road conditions (such as road slope, traffic congestion degree) that affect energy consumption. In terms of data processing and analysis, it mainly relies on simple statistical methods and empirical formulas, lacking comprehensive consideration and in-depth analysis of complex factors. For example, it is not possible to accurately evaluate the impact of the actual load changes of the vehicle, differences in driving habits and ambient temperature on fuel / gas efficiency. In addition, this solution is difficult to accurately monitor and compare the amount of each refueling / gas filling, and it is also difficult to promptly detect abnormal situations such as possible oil / gas leakage. In general, the existing technical solutions are insufficient in terms of data richness, accuracy, depth and comprehensiveness of analysis, and are difficult to meet the requirements for refined and accurate vehicle energy management, and are difficult to effectively combine with vehicle operating conditions. Therefore, how to achieve more accurate vehicle energy consumption monitoring has become a technical problem that needs to be solved. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art or related technology, and discloses a vehicle energy consumption monitoring method and system, which can realize accurate calculation of vehicle energy consumption and improve monitoring accuracy.

[0004] The first aspect of the present invention discloses a vehicle energy consumption monitoring method, comprising: installing an energy sensor in a monitored vehicle; acquiring energy sensor data of multiple monitored vehicles and vehicle operating status data collected by a vehicle terminal in real time through a wireless communication module; detecting whether the energy sensor data and the vehicle operating status data are within a reasonable range, marking abnormal values ​​that exceed the range, and replacing the marked abnormal values; matching energy sensor data and vehicle operating status data from different vehicles according to timestamps, and establishing a corresponding relationship between the vehicle operating status and energy consumption in the same time period; constructing a machine learning model for predicting energy consumption based on a linear regression algorithm, a decision tree algorithm, and a random forest algorithm to predict the vehicle's energy consumption data; applying the trained model to perform real-time prediction of energy consumption, comparing the predicted energy consumption value with the actual change in energy sensor data or comparing the predicted energy consumption rate with the actual energy consumption rate, thereby calculating the deviation rate, and if the deviation rate is within a predetermined range, it is determined that the vehicle's energy consumption is normal.

[0005] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, the energy sensor includes: a liquid level sensor and / or a gas volume sensor.

[0006] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, the vehicle operating status data includes: vehicle speed, acceleration, mileage, driving time and engine speed.

[0007] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, the features extracted by the machine learning model for predicting energy consumption include: current vehicle speed, acceleration, driving time, energy sensor data and weather data.

[0008] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, it also includes: using historical data to train the established model and selecting the optimal model parameters through cross-validation; using a part of the data that did not participate in the training to verify the model and evaluate the accuracy and generalization ability of the model.

[0009] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, the step of replacing the marked outlier includes: replacing the outlier with the average value or median of similar data of the outlier; or predicting the predicted value of the position of the outlier based on a statistical model, and replacing the outlier with the predicted value.

[0010] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, the wireless communication module includes a 4G module, a 5G module or a Bluetooth module.

[0011] According to the vehicle energy consumption monitoring method disclosed in the present invention, preferably, the calculation formula of unit mileage energy consumption is: unit mileage energy consumption = energy change / driving mileage;

[0012] The calculation process of the linear regression model includes:

[0013] Energy consumption forecast value = β 0 +β 1 × vehicle speed + β 2 × Mileage + β 3 ×engine speed+…+∈;

[0014] Among them, β 0 is the intercept, β 1 , β 2 , β 3 is the coefficient of each variable, ∈ is the error term;

[0015] The decision tree algorithm predicts energy consumption by splitting features and building a tree structure;

[0016] The calculation process of the random forest algorithm includes:

[0017]

[0018] Where N is the number of decision trees, Tree i (X) is the predicted value of the input feature X by the i-th decision tree.

[0019] The second aspect of the present invention discloses a vehicle energy consumption monitoring system, comprising: a memory for storing program instructions; a processor for calling the program instructions stored in the memory to implement a vehicle energy consumption monitoring method such as any of the above technical solutions.

[0020] The beneficial effects of the present invention include at least: achieving more accurate liquid level / gas volume monitoring, significantly improving the accuracy of energy consumption calculation and deduction calculation, and providing a more reliable basis for cost control for vehicle operators. The energy consumption evaluation model that comprehensively considers multiple factors can accurately reflect the actual consumption situation and provide strong support for optimizing vehicle operation strategies. It can quickly and accurately calculate energy consumption and improve the overall response speed and performance of the energy consumption monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic flow chart of a vehicle energy consumption monitoring method according to an embodiment of the present invention is shown.

[0022] Figure 2 A schematic block diagram of a vehicle energy consumption monitoring system according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0023] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and therefore, the present invention is not limited to the limitations of the specific embodiments disclosed below.

[0024] According to one embodiment of the present invention, the vehicle energy consumption monitoring method disclosed in the present invention includes: installing an energy sensor in a monitored vehicle; acquiring energy sensor data of multiple monitored vehicles and vehicle operating status data collected by a vehicle terminal in real time through a wireless communication module; detecting whether the energy sensor data and the vehicle operating status data are within a reasonable range, marking abnormal values ​​that exceed the range, and replacing the marked abnormal values; matching energy sensor data and vehicle operating status data from different vehicles according to timestamps, and establishing a corresponding relationship between the vehicle operating status and energy consumption in the same time period; constructing a machine learning model for predicting energy consumption based on a linear regression algorithm, a decision tree algorithm, and a random forest algorithm to predict the vehicle's energy consumption data; applying the trained model to perform real-time prediction of energy consumption, comparing the predicted energy consumption value with the actual change in energy sensor data or comparing the predicted energy consumption rate with the actual energy consumption rate, thereby calculating the deviation rate, and if the deviation rate is within a predetermined range, it is determined that the vehicle's energy consumption is normal.

[0025] In this embodiment, the real-time transmission and processing of truck liquid level / gas volume data (data collected by energy sensors) are realized through the real-time monitoring platform and wireless communication technology, integrating high-precision on-board sensors, powerful cloud data processing capabilities and reliable wireless communication networks to ensure the real-time, accuracy and reliability of the data. The whole process from collection, transmission to processing and analysis is automated and intelligent. This not only improves transportation efficiency and safety, but also provides more accurate and timely information support for logistics companies and cargo owners, which helps to optimize transportation plans, reduce operating costs and improve customer satisfaction. By introducing intelligent management functions and early warning mechanisms, the truck liquid level and gas volume monitoring system can achieve comprehensive monitoring and intelligent management of the transportation process. This not only reduces the time cost of manual intervention and fault handling, but also reduces the risk of transportation delays and losses caused by equipment failures, thereby reducing overall maintenance costs. At the same time, intelligent management also improves the operating efficiency and customer satisfaction of logistics companies, providing strong support for the sustainable development of enterprises.

[0026] like Figure 1As shown, according to another embodiment of the present invention, a specific implementation method of a vehicle energy consumption monitoring method is also disclosed, including the following steps: data collection and transmission; server-side processing; data fusion and association; feature extraction; model training; consumption analysis and dynamic update.

[0027] The steps of data collection and transmission specifically include:

[0028] The liquid level / gas volume data monitored in real time are transmitted to the vehicle data processing unit through the liquid level / gas volume sensor. The vehicle terminal acquisition device also sends the collected data such as vehicle speed, mileage and working status to the vehicle data processing unit. The vehicle data processing unit preliminarily integrates and encodes these data and transmits the data to the remote server through the wireless communication module (such as 4G / 5G or Bluetooth).

[0029] The server-side processing steps include:

[0030] Clean the uploaded data to remove duplicate, erroneous and missing data. Check the reasonableness of the data, whether the vehicle speed is within the possible physical limit, whether the change in liquid level / gas volume conforms to the physical characteristics of the fuel tank / gas tank, etc. Mark and process outliers, and choose to replace them with the mean, median or predicted value based on statistical models.

[0031] The steps of data fusion and association include:

[0032] Fusion and correlation of various data from different vehicle-mounted sensors. Matching of liquid level / gas volume data with vehicle speed and mileage data according to timestamps, establishing a corresponding relationship between vehicle operating status and energy consumption in the same time period.

[0033] The steps of feature extraction specifically include:

[0034] Extract key features from real-time data, including current vehicle speed, acceleration, driving time, liquid level data, etc. Build a feature extraction model based on linear regression, decision tree, and random forest algorithms. The formula for calculating energy consumption per unit mileage is: Energy consumption per unit mileage = Energy change / Mileage;

[0035] The calculation process of the linear regression model includes:

[0036] Energy consumption forecast value = β 0 +β 1 × vehicle speed + β 2 × Mileage + β 3 ×engine speed+…+∈;

[0037] Among them, β 0 is the intercept, β 1 , β 2, β 3 is the coefficient of each variable, ∈ is the error term;

[0038] The decision tree algorithm predicts energy consumption by splitting features and building a tree structure;

[0039] The calculation process of the random forest algorithm includes:

[0040]

[0041] Where N is the number of decision trees, Tree i (X) is the predicted value of the input feature X by the i-th decision tree.

[0042] The steps of model training include:

[0043] Use historical data to train the established model, and select the optimal model parameters through cross-validation and other techniques. Use a portion of data that was not involved in the training to validate the model and evaluate the accuracy and generalization ability of the model.

[0044] The steps of consumption analysis include:

[0045] For newly uploaded real-time data, the trained model is used to perform real-time analysis of energy consumption. The predicted consumption value is compared with the actual liquid level / gas volume change, and the predicted energy consumption rate is compared with the actual energy consumption rate. The deviation between the two is calculated. If the deviation is within an acceptable range, the vehicle's energy consumption is considered normal and recorded as the actual "consumption" and determined as the liquid level change value.

[0046] The steps of dynamic update include:

[0047] As new data is continuously received, the analysis results are continuously updated to achieve real-time analysis and detection of vehicle energy consumption.

[0048] like Figure 2 As shown, according to another embodiment of the present invention, a vehicle energy consumption monitoring system 200 is also disclosed, including: a memory 201, used to store program instructions; a processor 202, used to call the program instructions stored in the memory to implement the vehicle energy consumption monitoring method as described in the above embodiment.

[0049] According to the above embodiments, the high-precision on-board liquid level / gas volume sensor can ensure the accurate measurement of the changes in the liquid level / gas volume in the fuel tank / gas tank, which is the basis for accurately calculating energy consumption. Effectively integrating various vehicle operation data such as vehicle speed, mileage, engine status, etc., comprehensively reflecting the actual working conditions of the vehicle, can improve the accuracy of energy consumption analysis. By constructing and optimizing machine learning models, energy consumption can be accurately predicted and adapted to changes in different vehicle models and usage environments. The present invention detects real-time data of liquid level / gas volume and uploads it to the server to complete cleaning and feature extraction. At the same time, according to the current vehicle speed, weather and other reasons, an energy consumption model is built, and the established model is trained using historical data to complete the optimal model parameter setting. The accuracy rate is improved by analyzing and evaluating the model, and finally the precise changes in the vehicle liquid level / gas volume are completed, which can deeply understand the energy consumption of the vehicle and provide strong support for energy-saving optimization and management decisions.

[0050] All or part of the steps in the various methods of the above embodiments can be completed by controlling the relevant hardware through a program, and the program can be stored in a readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other readable medium that can be used to carry or store data.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle energy consumption monitoring method, characterized in that: include: Installing energy sensors in monitored vehicles; The wireless communication module is used to obtain the energy sensor data of multiple monitored vehicles and the vehicle working status data collected by the vehicle terminal in real time; Detecting whether the energy sensor data and the vehicle operating status data are within a reasonable range, marking abnormal values ​​that are out of range, and replacing the marked abnormal values; Match the energy sensor data and vehicle operating status data from different vehicles according to timestamps to establish the corresponding relationship between vehicle operating status and energy consumption in the same time period; Building a machine learning model for predicting energy consumption based on linear regression algorithm, decision tree algorithm and random forest algorithm to predict the energy consumption data of the vehicle; Use the trained model to make real-time predictions of energy consumption, compare the predicted energy consumption value with the actual change in energy sensor data, or compare the predicted energy consumption rate with the actual energy consumption rate, so as to calculate the deviation rate. If the deviation rate is within a predetermined range, it is determined that the vehicle's energy consumption is normal.

2. The vehicle energy consumption monitoring method according to claim 1, characterized in that: The energy sensor includes: a liquid level sensor and / or a gas volume sensor.

3. The vehicle energy consumption monitoring method according to claim 1, characterized in that: The vehicle operating status data includes: vehicle speed, acceleration, mileage, driving time and engine speed.

4. The vehicle energy consumption monitoring method according to claim 1, characterized in that: The features extracted by the machine learning model for predicting energy consumption include: current vehicle speed, acceleration, driving time, energy sensor data and weather data.

5. The vehicle energy consumption monitoring method according to claim 1, characterized in that: Also includes: Use historical data to train the established model and select the optimal model parameters through cross-validation; Use a portion of data that was not used in training to validate the model and evaluate its accuracy and generalization ability.

6. The vehicle energy consumption monitoring method according to claim 1, characterized in that: The steps of replacing the marked outliers specifically include: The outlier is replaced with the mean or median of similar data.

7. The vehicle energy consumption monitoring method according to claim 6, characterized in that: Also includes: A predicted value at the position where the abnormal value is located is predicted based on a statistical model, and the abnormal value is replaced by the predicted value.

8. The vehicle energy consumption monitoring method according to claim 1, characterized in that: The wireless communication module includes a 4G module, a 5G module or a Bluetooth module.

9. A vehicle energy consumption monitoring system, characterized in that: include: A memory for storing program instructions; A processor, configured to call the program instructions stored in the memory to implement the vehicle energy consumption monitoring method as described in any one of claims 1 to 8.

Images