Vehicle energy consumption early warning method and system based on big data and storage medium

Abstract

The invention discloses a vehicle energy consumption early warning method based on big data. The vehicle energy consumption early warning method comprises the following steps that 1, a vehicle machine collects and uploads vehicle parameter information; 2, the platform obtains parameter information of each communication vehicle and lists the parameter information into a model; 3, judging whether the vehicle is in an abnormal energy consumption state or not based on the model; and step 4, informing the owner of the automobile with the abnormal energy consumption. According to the method, vehicles with high electricity / fuel consumption in the market are actively identified through the data of the Internet of Vehicles in combination with other judgment basis and normal distribution, the problem is solved before customer complaint, and the customer satisfaction is improved.

Description

Technical Field

[0001] This invention relates to the field of automotive energy consumption statistics technology. Background Technology

[0002] Many vehicle problems are only discovered by OEMs after customers complain and raise issues, especially perceived problems such as high electricity / fuel consumption.

[0003] Most current calculations of electricity / fuel consumption are based on the vehicle itself. For example, the patent document with publication number CN107856564B, publication date June 30, 2020, entitled "A Method, Device, Controller and Vehicle for Calculating Average Energy Consumption of Electric Vehicles," discloses a method for calculating the average energy consumption of electric vehicles that includes: calculating the current cumulative mileage after the vehicle is powered on in real time; determining whether the current cumulative mileage is an integer multiple of a preset mileage value; if the current cumulative mileage is an integer multiple of the preset mileage value, calculating the current cumulative energy consumption; and calculating the current average energy consumption of the electric vehicle based on the current cumulative energy consumption and the current cumulative mileage.

[0004] However, similar methods of calculating electricity / fuel consumption only accumulate data during user usage. If we can identify high energy consumption in advance before customers complain, we can greatly reduce customer complaints and improve customer satisfaction. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to realize a method that can actively identify high vehicle power / fuel consumption and actively identify faults.

[0006] To achieve the above objectives, the technical solution adopted by this invention is: a vehicle energy consumption early warning method based on big data, comprising the following steps:

[0007] Step 1: The vehicle's infotainment system collects and uploads vehicle parameter information;

[0008] Step 2: The platform acquires the parameter information of each communication vehicle and incorporates it into the model;

[0009] Step 3: Determine whether the vehicle is currently in an abnormal energy consumption state based on the model;

[0010] Step 4: Notify the owners of vehicles with abnormal energy consumption.

[0011] In step 1, the vehicle parameters include vehicle type, vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location.

[0012] In step 1, vehicle parameters are recorded each time the vehicle is started, and data is recorded as valid when the data recording time exceeds a set time. After the vehicle is turned off, the valid data is uploaded to the platform.

[0013] In step 2, the model is preset for different vehicles, and the platform substitutes the parameters into different models for calculation based on the vehicle model information.

[0014] In step 2, the vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location information are pre-constructed into a standard normal distribution curve, and a standard interval of the normal distribution curve is defined. When the calculation result is outside the standard interval, it is defined as an energy consumption anomaly.

[0015] In step 2, the left side of the model standard interval is the faulty vehicle, and the right side of the model standard interval is the area with excessive energy consumption. The area with excessive energy consumption is divided into three levels, which are low-risk excessive energy consumption area, medium-risk excessive energy consumption area and high-risk excessive energy consumption area from the model standard interval to the farthest.

[0016] In step 3, when the judgment result is:

[0017] When the low-risk energy consumption zone is too high, the platform will combine the data from the previous five uploads. If three or more of the six uploads show low-risk energy consumption, the platform will notify the vehicle's infotainment system to issue an alarm.

[0018] When the energy consumption is too high in the medium-risk area, the platform will combine the data from the previous five uploads. If there is a low-risk or medium-risk energy consumption among the previous five uploads, the vehicle system will be notified to issue an alarm.

[0019] When high-risk areas have excessively high energy consumption, manual analysis and investigation should be conducted.

[0020] A vehicle energy consumption early warning system based on big data includes:

[0021] TBOX: Used for data transmission and to deliver vehicle parameter information to the TSP platform;

[0022] TSP Platform: Used to store and process data uploaded by TBox, and classifies vehicle data according to operating conditions based on the vehicle's uploaded data.

[0023] A storage medium, wherein the storage medium is a computer-readable storage medium for storing software program code for executing the big data-based vehicle energy consumption early warning method.

[0024] This invention proactively identifies vehicles with high electricity / fuel consumption in the market by using vehicle network data, combined with other judgment criteria and normal distribution, and resolves the problem before customers complain, thereby improving customer satisfaction. Attached Figure Description

[0025] The following is a brief explanation of the content represented by each figure in this specification:

[0026] Figure 1 This is a flowchart of a vehicle energy consumption early warning method based on big data. Detailed Implementation

[0027] The following description, with reference to the accompanying drawings, details the specific implementation of the present invention, including the shape and structure of each component, the relative positions and connections between the parts, the function and working principle of each part, the manufacturing process, and the operation and use methods, to help those skilled in the art to have a more complete, accurate, and in-depth understanding of the inventive concept and technical solution of the present invention.

[0028] With the advent of the Internet of Vehicles (IoV), OEMs can collect a wealth of vehicle data, and effectively utilizing this data can generate significant profits for the company. This invention primarily relies on IoV data, employing big data modeling to proactively identify customer-perceived problems, such as high vehicle energy / fuel consumption. The prerequisite for this big data-based vehicle energy consumption warning method is that the vehicle is equipped with a TBOX module supporting IoV. Specifically, the entire control method includes the following steps:

[0029] Step 1: The vehicle's infotainment system collects and uploads vehicle parameter information;

[0030] Each vehicle uploads its own vehicle parameter information to the platform, typically the TSP platform. These parameters include vehicle model, speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location. Start-stop parameters can also be added or removed depending on the specific vehicle model. The TSP platform pre-designs corresponding models for each vehicle model, and the first vehicle parameter information it processes is the model. By identifying the model, it can directly input the data into the corresponding model. Model information can also include vehicle code information; each car has its own code, similar to an ID number. After reading the agent information, the TSP platform can create a file for each user's car, store the data, and facilitate later retrieval.

[0031] Each time the vehicle starts, it begins recording vehicle parameters. Data is considered valid only if the recording time exceeds a set time. For example, data is only considered valid if the vehicle is used for more than 30 minutes. This avoids data from short-term vehicle use misleading the platform and causing inaccurate statistics. For example, moving the vehicle or changing parking spaces may not reflect the true vehicle status due to energy consumption. Therefore, valid data is only uploaded to the platform after the vehicle is turned off when it has been used for more than 30 minutes. Of course, valid data also requires the mileage to exceed a set value, such as more than 1 kilometer. Time spent stopping for rest needs to be excluded, especially for electric vehicles, where this situation is more common.

[0032] Step 2: The platform acquires the parameter information of each communication vehicle and incorporates it into the model;

[0033] Engineers conduct tests on different vehicles during the design phase. The tests are based on vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location information to build a model. Therefore, each vehicle model has its own model. When the TSP platform obtains the valid data uploaded by the vehicle, it will input the valid data into the model and obtain the vehicle's energy information based on the model.

[0034] Step 3: Determine whether the vehicle is currently in an abnormal energy consumption state based on the model;

[0035] The model uses a normal distribution curve and defines a standard interval for the normal distribution curve. Calculation results outside the standard interval are defined as abnormal energy consumption. TBOX collects vehicle data and uploads it to the TSP platform. All vehicles are classified according to operating conditions and boundary conditions. A normal distribution is applied to each vehicle category. Vehicles on the right side of the normal distribution standard (high electricity / fuel consumption) or exceeding the expert-confirmed standard are considered faulty vehicles. Manual investigation is also possible; experts can analyze and investigate faulty vehicles to confirm the cause and then adjust the standard parameters based on the analysis results.

[0036] The left side of the model's standard range represents a faulty vehicle. This area has excessively low energy consumption because a car's base energy consumption is a fixed value. Normally, this indicates a problem with a vehicle's components. The left side of the model's standard range only appears when abnormal vehicle parameters are detected. Therefore, this situation indicates a faulty vehicle condition. The right side of the model's standard range represents excessively high energy consumption, which is divided into three levels. For example, if the energy consumption is less than 10% above the maximum value of the normal range, it is classified as Level 1, a low-risk high-energy-consumption zone, indicating a generally mild fault. If it exceeds the maximum value of the normal range by 10%-25%, it is classified as Level 2, a medium-risk high-energy-consumption zone, indicating a relatively high energy consumption risk requiring emergency maintenance. If it exceeds the maximum value of the normal range by 25%, it is classified as Level 3, a high-risk high-energy-consumption zone, indicating a serious vehicle problem requiring emergency maintenance.

[0037] Each car has its own database, allowing the TSP platform to systematically evaluate each vehicle. When the evaluation result for a particular car is:

[0038] When the low-risk energy consumption is too high, the test is not a big problem. The TSP platform will combine the data from the previous five uploads and make a unified judgment based on the six known data. (If the vehicle has just been used and there is no data for the six uploads, the low-risk energy consumption problem will not be processed until all six data are collected.) If three or more of the six uploads show low-risk energy consumption, the vehicle system will be notified to alarm, indicating that the vehicle has been in a high energy consumption state for a long time, rather than due to the driver's aggressive driving. This can also avoid false alarms caused by sudden high energy consumption in some special situations. Through this judgment mechanism, the vehicle alarm can be more accurate and avoid false alarms that affect the user experience.

[0039] When the energy consumption is in the medium-risk high zone, the energy consumption problem is more serious. The TSP platform will combine the data from the previous five uploads and make a unified judgment based on the six known data. (If the vehicle has just been used and there are not six data, the vehicle system will be notified to directly alarm if there are not enough data. New cars will not normally have this problem. Therefore, the occurrence of medium-risk high energy consumption should be a product quality issue and requires immediate return for maintenance.) If there are enough data, the platform will combine the data from the previous five uploads. If there is one low-risk or medium-risk energy consumption among the previous five uploads, the vehicle system will be notified to alarm. This is because this state indicates that the vehicle's energy consumption problem is worsening and requires timely maintenance.

[0040] When a high-risk energy consumption zone is reached, manual analysis and investigation will be conducted. Through expert judgment, the vehicle's operating condition will be classified. Experts can analyze and investigate the faulty vehicle, confirm the cause, and then adjust the standard parameters based on the analysis results before notifying the vehicle owner.

[0041] Step 4: Notify the owners of vehicles with abnormal energy consumption;

[0042] The vehicle's fault status will be directly notified to the owner, that is, the fault information will be sent to the vehicle and displayed on the vehicle's instrument panel (which may include audible and visual prompts), so that users can discover the problem in time and carry out maintenance and repairs at a service station (4S store, etc.).

[0043] The vehicle energy consumption early warning system based on big data includes: a normal distribution model based on operating conditions, TBOX, other controllers, TSP platform, operating condition type parameters, operating condition type, standard parameters, and abnormal vehicles;

[0044] Normal distribution model based on operating conditions: used to identify high electric / fuel consumption vehicles. It analyzes vehicles in the same category of operating conditions that are in an abnormal state from the normal distribution. For example, vehicles outside the 3 sigma range are considered to be in an abnormal state, and those to the right of the 3 sigma range are high electric / fuel consumption vehicles.

[0045] TBOX: Used for data transmission, transmitting data from the vehicle controller to the TSP platform, such as parameters like vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location.

[0046] Other controllers: Used to send data to the TBOX.

[0047] TSP Platform: Used to store and process data uploaded by TBox, and classifies vehicle data according to operating conditions based on the vehicle's uploaded data.

[0048] Operating condition parameters: vehicle speed, torque, thermal management status, battery / fuel level, power supply status, ambient temperature, and vehicle weight (calculated using acceleration ΔV / Δt and torque). Used to classify operating conditions.

[0049] Standard parameters: Confirm the standard under the same operating conditions. For example, if the standard is greater than 3 sigma or the electricity / fuel consumption is greater than 40 kWh or 12 L / 100km, the vehicle is considered abnormal.

[0050] Abnormal vehicles: Abnormal vehicles are identified by analyzing the normal distribution of electricity / fuel consumption under the same operating conditions, combined with standard parameters.

[0051] The big data-based vehicle energy consumption warning system is a system that connects the vehicle's infotainment system and the TSP platform to work together. Therefore, each infotainment system has a program for uploading data and executing alarms, while the TSP platform has a program for collecting, processing, and judging data. The programs are all stored in storage media. The vehicle's infotainment system uses a TBOX for storage, while the TSP platform uses a system hard drive. Both of these storage media are computer-readable storage media used to store software program code. The two storage media work together with the corresponding hardware system to execute the software program code, which is the aforementioned big data-based vehicle energy consumption warning method.

[0052] This system and method collect parameters related to operating conditions, including vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location. Through expert judgment, vehicle operating conditions are categorized. Because this method involves human intervention (expert evaluation), and the system can continuously refine its approach based on acquired data, the TSP platform becomes more accurate, improving the precision of energy consumption condition assessments. Furthermore, in addition to directly acquiring the vehicle's current energy consumption, this method also considers vehicle speed, load, and other information for comprehensive judgment, further enhancing the accuracy of the method's assessment.

[0053] This invention changes the traditional approach still used in the industry. Instead of passively receiving customer complaints and having personnel go to the site to troubleshoot vehicle problems after they occur in the market, it proactively identifies high vehicle power / fuel consumption and the cause of the fault by using vehicle network data and establishing digital models.

[0054] It has the following advantages

[0055] 1. High initiative and efficiency: It can make judgments independently, proactively test and judge the vehicle's energy consumption, and promptly notify the owner after discovering problems. Not only is the testing initiative high, but the notification efficiency is also high.

[0056] 2. Intelligent and convenient: The system and methods can integrate historical vehicle data and combine it with human judgment, and will continuously optimize the model, greatly improving the efficiency and accuracy of the platform's automatic judgment.

[0057] 3. Cost savings: The entire vehicle infotainment TBOX module supports vehicle networking and uses existing systems. Only software updates are needed to make the system work. While adding functions, there are almost no hardware costs, making the system and method low-cost. It also allows users to detect faults in time when fuel consumption is too high and carry out repairs, reducing the cost of car ownership.

[0058] The present invention has been described above by way of example with reference to the accompanying drawings. Obviously, the specific implementation of the present invention is not limited to the above-described manner. Any non-substantial improvements made using the inventive concept and technical solution of the present invention, or the direct application of the inventive concept and technical solution of the present invention to other occasions without modification, are all within the protection scope of the present invention.

Claims

1. A vehicle energy consumption early warning method based on big data, characterized in that, Includes the following steps: Step 1: The vehicle's infotainment system collects and uploads vehicle parameter information; Step 2: The platform acquires the parameter information of each communication vehicle and incorporates it into the model; Step 3: Determine whether the vehicle is currently in an abnormal energy consumption state based on the model; Step 4: Notify the owners of vehicles with abnormal energy consumption.

2. The vehicle energy consumption early warning method based on big data according to claim 1, characterized in that: In step 1, the vehicle parameters include vehicle type, vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location.

3. The vehicle energy consumption early warning method based on big data according to claim 2, characterized in that: In step 1, vehicle parameters are recorded each time the vehicle is started, and data is recorded as valid when the data recording time exceeds a set time. After the vehicle is turned off, the valid data is uploaded to the platform.

4. The vehicle energy consumption early warning method based on big data according to claim 1, 2 or 3, characterized in that: In step 2, the model is preset for different vehicles, and the platform substitutes the parameters into different models for calculation based on the vehicle model information.

5. The vehicle energy consumption early warning method based on big data according to claim 4, characterized in that: In step 2, the vehicle speed, torque, thermal management status, battery / fuel level, power status, temperature, and vehicle location information are pre-constructed into a standard normal distribution curve, and a standard interval of the normal distribution curve is defined. When the calculation result is outside the standard interval, it is defined as an energy consumption anomaly.

6. The vehicle energy consumption early warning method based on big data according to claim 5, characterized in that: In step 2, the left side of the model standard interval is the faulty vehicle, and the right side of the model standard interval is the area with excessive energy consumption. The area with excessive energy consumption is divided into three levels, which are low-risk excessive energy consumption area, medium-risk excessive energy consumption area and high-risk excessive energy consumption area from the model standard interval to the farthest.

7. The vehicle energy consumption early warning method based on big data according to claim 6, characterized in that: In step 3, when the judgment result is: When the low-risk energy consumption zone is too high, the platform will combine the data from the previous five uploads. If three or more of the six uploads show low-risk energy consumption, the platform will notify the vehicle's infotainment system to issue an alarm. When the energy consumption is too high in the medium-risk area, the platform will combine the data from the previous five uploads. If there is a low-risk or medium-risk energy consumption among the previous five uploads, the vehicle system will be notified to issue an alarm. When high-risk areas have excessively high energy consumption, manual analysis and investigation should be conducted.

8. A vehicle energy consumption early warning system based on big data, characterized in that, include: TBOX: Used for data transmission and to deliver vehicle parameter information to the TSP platform; TSP Platform: Used to store and process data uploaded by TBox, and classifies vehicle data according to operating conditions based on the vehicle's uploaded data.

9. A storage medium, said storage medium being a computer-readable storage medium for storing software program code, characterized in that: The software program code is used to execute the vehicle energy consumption early warning method based on big data as described in any one of claims 1-7.

Images