A vehicle status assessment and early warning method based on intelligent connected vehicle control center

Abstract

The present invention discloses a vehicle state assessment and early warning method based on an intelligent networked vehicle control center, which belongs to the technical field of vehicle state assessment and early warning. Monitoring equipment and data connection and transmission equipment are installed on a vehicle for state assessment and early warning, and vehicle data, road information data and weather environment data are comprehensively processed to construct a first assessment and early warning model, and driver data is used to construct a second assessment and early warning model. The two models process different data respectively, and independently calculate and integrate at the same time to achieve more accurate risk assessment and early warning. During vehicle driving, data is imported and analyzed in real time to obtain a risk rating and remind the driver in real time. In addition to collecting conventional vehicle data, road information data and weather environment data, driver data collection is also added, so that when performing vehicle state assessment and early warning, the degree of intelligence is higher, the information coverage is more comprehensive, the assessment and early warning results are more accurate, the safety is effectively improved, and the application value is high.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle status assessment and early warning, and specifically relates to a vehicle status assessment and early warning method based on an intelligent networked vehicle control center. Background Art

[0002] Intelligent networked vehicles refer to the organic combination of Internet of Vehicles and smart cars. They are equipped with advanced on-board sensors, controllers, actuators and other devices, and integrate modern communication and network technologies to achieve intelligent information exchange and sharing between vehicles and people, vehicles, roads, and backgrounds, and achieve safe, comfortable, energy-saving, and efficient driving, and eventually replace human operation. Intelligent networked vehicles focus on the use of automotive engineering, artificial intelligence, computers, microelectronics, automatic control, communications and platforms, and are a high-tech complex that integrates environmental perception, planning and decision-making, control execution, and information interaction.

[0003] A Chinese invention patent with publication number CN108961473A discloses a vehicle status assessment and early warning method based on an intelligent networked vehicle control center. The method obtains the real-time driving status information of the vehicle through an on-board intelligent terminal, and then establishes a fuzzy judgment set based on the vehicle information. A typical safety judgment parameter data set is established for the fuzzy judgment set of vehicle safety. Then, a fuzzy rule base with credibility and threshold is established, and a fuzzy relationship matrix library corresponding to each rule of the rule base is established. The real-time driving data of the vehicle under different working conditions and road conditions is applied to the rules of the rule base for credible reasoning. Then, the comprehensive vehicle safety evaluation model established by the control center is applied to comprehensively evaluate the vehicle safety performance. When the vehicle is found to be in an unsafe state, an early warning is issued, and unsafe driving behaviors are recorded as a comprehensive evaluation of the driving state of the vehicle. In the Chinese invention patent with publication number CN115063766A, a method for evaluating and warning the operation safety of an autonomous vehicle is disclosed. The method collects driver status data and vehicle status data through a data acquisition device, identifies driver behavior and vehicle behavior that may affect the operation safety of the vehicle through a pre-built behavior judgment model, and then sends them to the risk level discrimination matrix, outputs the corresponding risk level, and issues corresponding warnings according to the risk level; the entire process is automatically implemented, realizing comprehensive, rapid, automated, and intelligent supervision of the operation safety of autonomous vehicles on public roads; at the same time, based on the risk discrimination matrix, the operation safety risk is judged, and the risk judgment is quantified and calculable, while simplifying the risk judgment logic, reducing the amount of calculation, and improving the algorithm operation efficiency, thereby ensuring the real-time safety evaluation and warning of the technical solution of the present invention. However, although the above two public documents both have a certain degree of intelligence, the collection of relevant data on cars and drivers is still not comprehensive enough, the evaluation accuracy is not high enough, and there is still room for improvement in risk evaluation.

[0004] In view of the technical problems of existing vehicle status assessment and early warning methods, such as insufficient collection of relevant data on cars and drivers and low assessment accuracy, it is urgent to find a new vehicle status assessment and early warning method so that when conducting vehicle status assessment and early warning, the information coverage is more comprehensive and the assessment results are more accurate, thereby effectively improving safety. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a vehicle status assessment and early warning method based on an intelligent connected vehicle control center, so as to solve the technical problems of the existing vehicle status assessment and early warning methods in that the relevant data collection of the vehicle and the driver is not comprehensive enough and the assessment accuracy is low.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] The present invention discloses a vehicle state assessment and early warning method based on an intelligent networked vehicle control center, comprising the following steps:

[0008] S1: Comprehensive data collection

[0009] Conduct status assessment and early warning on vehicles equipped with monitoring equipment and data connection and transmission equipment, and collect vehicle data, driver data, road information data, and weather and environmental data;

[0010] S2: Building a data processing model

[0011] The automobile data, road information data and weather environment data collected in step S1 are comprehensively processed to construct a direct evaluation model as a first evaluation and early warning model; the driver data collected in step S1 are used to construct a driver behavior processing model as a second evaluation and early warning model;

[0012] S3: Building a risk assessment algorithm

[0013] First, the first evaluation and warning model constructed in step S2 is calculated to obtain the warning coefficient of the first evaluation and warning model, and then the second evaluation and warning model constructed in step S2 is calculated to obtain the driver fatigue information, and finally the warning coefficient and the driver fatigue information are combined to obtain the final risk assessment warning level;

[0014] S4: Real-time data import and analysis

[0015] During the driving process of the vehicle, various data are transmitted to the cloud data processing platform in real time, and the data and models are analyzed and processed on the cloud platform;

[0016] S5: Real-time reminder after risk rating

[0017] After the data is imported and analyzed in real time to obtain the risk rating, the information is transmitted to the driver in real time and the driver is reminded in the form of voice broadcast.

[0018] Preferably, in step S1, the data connection transmission device is a wireless transmission device; the monitoring device includes a vehicle monitoring device and a driver status monitoring device; the driver status monitoring device includes an infrared thermometer, a camera and a posture sensor.

[0019] Preferably, in step S1, the vehicle data includes vehicle battery status, vehicle operating mode, vehicle speed, cumulative mileage, SOC, highest voltage battery subsystem number, highest battery cell voltage value, highest voltage battery cell code, lowest voltage battery cell code, lowest voltage battery subsystem number, lowest battery cell voltage value, tire condition and general alarm sign.

[0020] Preferably, in step S1, the driver data includes the driver's historical driving data of following, overtaking and lane changing behaviors, and the collected driver data is formed into a driver behavior feature database.

[0021] Preferably, in step S1, the road information data includes road name, width, number of lanes, traffic light conditions, maintenance conditions and real-time vehicle conditions.

[0022] Preferably, in step S1, the weather environment data includes temperature, humidity, amount of rain and snow, wind speed, dust conditions and fog level.

[0023] Preferably, in step S2, the method for constructing a data processing model includes: comprehensively processing three types of objective, stable and controllable data, that is, comprehensively processing vehicle data, road information data and weather environment data to construct a direct evaluation model as the first evaluation and warning model.

[0024] Preferably, in step S2, the method for constructing a data processing model also includes: separately processing relatively unstable driver data, combining the driver data with historical data for comprehensive processing, constructing a driver behavior processing model, and then training it in combination with the vehicle behavior processing model to obtain a driver-relative vehicle behavior processing model as a second evaluation and warning model.

[0025] Preferably, in step S3, the method for obtaining the warning coefficient includes: first performing individual basic evaluation and warning on the automobile data, road information data and weather environment data in the first evaluation and warning model, and then combining different data to perform combined evaluation and warning on dangerous items, and obtaining the warning coefficient of the first evaluation and warning model through the evaluation and warning algorithms of the above two.

[0026] Preferably, in step S3, the method for obtaining the driver's fatigue level information includes: monitoring the driver's body temperature through an infrared thermometer, detecting the driver's body surface condition through a camera, and monitoring and analyzing the driver's body behavior through a posture sensor to obtain the driver's fatigue level information; and combining the driver's historical driving data of following, overtaking and lane changing behaviors, when the driver's fatigue level is high, the risk warning level of the first assessment and warning model is increased.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The present invention discloses a vehicle state assessment and early warning method based on an intelligent networked vehicle control center, including installing a monitoring device and a data connection transmission device on a vehicle for state assessment and early warning, monitoring the vehicle state and the driver state through the monitoring device, connecting all the monitoring devices and the data connection transmission device, so that the vehicle data and the driver data can be transmitted to a cloud data processing center through the data connection transmission device. Collect vehicle data, driver data, road information data and weather environment data. When collecting data, in addition to conventional vehicle data collection, road information data collection and weather environment data collection, driver data collection is also added, so that when performing vehicle state assessment and early warning, the information coverage is more comprehensive and the final assessment result is more accurate, thereby effectively improving safety. The collected vehicle data, driver data, road information data and weather environment data are comprehensively processed, and a direct assessment model is constructed by comprehensively processing the vehicle data, road information data and weather environment data. This model is used as the first assessment and early warning model, and the driver data constructs a driver behavior processing model as the second assessment and early warning model. Different types of data are processed respectively by two models, and the two models are independently calculated while the final comprehensive linkage is achieved to achieve more accurate risk assessment and early warning. The first assessment and warning model is calculated and processed to obtain the warning coefficient of the first assessment and warning model, the second assessment and warning model is calculated to obtain the driver's fatigue level information, and the warning coefficient and the driver's fatigue level information are combined to obtain the final risk assessment and warning level; during vehicle driving, various data are transmitted to the cloud data processing platform in real time, and various data and models are analyzed and processed on the cloud platform; after the data is imported and analyzed in real time to obtain the risk rating, the information is transmitted to the driver in real time, and the driver is reminded in the form of voice broadcast.

[0029] Furthermore, in step S1, the data connection transmission device is a wireless transmission device; the monitoring device includes a vehicle monitoring device and a driver status monitoring device; the driver status monitoring device includes an infrared thermometer, a camera and a posture sensor; the infrared thermometer monitors the driver's body temperature, the camera detects the driver's body surface condition, and the posture sensor monitors and analyzes the driver's body behavior to obtain the driver's fatigue level information, and then combines the driver's historical driving data of following, overtaking and lane changing behaviors to perform comprehensive data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The present invention discloses a basic flow chart of a vehicle status assessment and early warning method based on an intelligent networked vehicle control center. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0034] See also Figure 1 The basic flow chart of a vehicle state evaluation and early warning method based on an intelligent networked vehicle control center disclosed in the present invention is as follows; as can be seen from the figure, the vehicle state evaluation and early warning method based on an intelligent networked vehicle control center disclosed in the present invention comprises the following steps:

[0035] S1: Equipment installation and data connection. Monitoring equipment and data connection transmission equipment are installed on the vehicle for status assessment and early warning. The vehicle status and driver status are monitored through the monitoring equipment. The monitoring equipment already in the vehicle does not need to be installed again. Then all monitoring equipment and data connection transmission equipment are connected so that the vehicle data and driver data can be transmitted to the cloud data processing center through the data connection transmission equipment.

[0036] S2: Comprehensive data collection, including data collection of cars, drivers, road information and weather environment. In addition to conventional data collection of cars, road information and weather environment, driver data collection is also added, so that when conducting vehicle status assessment and early warning, the information coverage is more comprehensive and the final assessment result is more accurate, thereby effectively improving safety;

[0037] S3: Construct a data processing model, and comprehensively process the car data, driver data, road information data, and weather environment data collected in step S2. The car data, road information data, and weather environment data are comprehensively processed to construct a direct assessment model, and this model is used as the first assessment and early warning model. The driver data is used to construct a driver behavior processing model, which is used as the second assessment and early warning model. Different types of data are processed by the two models respectively. The two models are independently calculated and finally integrated to achieve more accurate risk assessment and early warning;

[0038] S4: Constructing a risk assessment algorithm, firstly calculating and processing the first assessment warning model and the second assessment warning model respectively to obtain the warning coefficient of the first assessment warning model, then calculating the second assessment warning model, and combining the data of the first assessment warning model and the second assessment warning model to obtain the final risk assessment warning level;

[0039] S5: Real-time data import and analysis. During the driving process of the vehicle, various data are transmitted to the cloud data processing platform in real time, and various data and models are analyzed and processed on the cloud platform;

[0040] S6: Real-time reminder after risk rating. After the data is imported in real time and analyzed to obtain the risk rating, the information is transmitted to the driver in real time and the driver is reminded in the form of voice broadcast.

[0041] The present invention discloses a vehicle state assessment and early warning method based on an intelligent networked vehicle control center, comprising the following steps:

[0042] S1: Equipment installation and data connection: installing monitoring equipment and data connection transmission equipment on the vehicle for status assessment and early warning;

[0043] S2: Comprehensive data collection, including data collection of cars, data collection of drivers, data collection of road information, and data collection of weather environment;

[0044] S3: construct a data processing model, comprehensively process the car data, driver data, road information data and weather environment data collected in step S2, and construct a direct evaluation model by comprehensively processing the car data, road information data and weather environment data. This model is used as the first evaluation and early warning model, and the driver data is used to construct a driver behavior processing model as the second evaluation and early warning model;

[0045] S4: Constructing a risk assessment algorithm, firstly calculating and processing the first assessment warning model and the second assessment warning model respectively to obtain the warning coefficient of the first assessment warning model, then calculating the second assessment warning model, and combining the data of the first assessment warning model and the second assessment warning model to obtain the final risk assessment warning level;

[0046] S5: Real-time data import and analysis. During the driving process of the vehicle, various data are transmitted to the cloud data processing platform in real time, and various data and models are analyzed and processed on the cloud platform;

[0047] S6: Real-time reminder after risk rating. After the data is imported in real time and analyzed to obtain the risk rating, the information is transmitted to the driver in real time and the driver is reminded in the form of voice broadcast.

[0048] Among them, in step S1, the data connection transmission device is specifically a wireless transmission device, the monitoring device is specifically a vehicle monitoring device and a driver status monitoring device, the driver status monitoring device is specifically an infrared thermometer, a camera and a posture sensor, the infrared thermometer monitors the driver's body temperature, the camera detects the driver's body surface condition, and the posture sensor monitors and analyzes the driver's body behavior to obtain the driver's fatigue level information, and then combines the driver's historical driving data of following, overtaking and lane changing behaviors to perform comprehensive data processing.

[0049] In step S2, the data collection of the car specifically includes the vehicle battery status, vehicle operation mode, vehicle speed, cumulative mileage, SOC, highest voltage battery subsystem number, battery cell voltage maximum value, highest voltage battery cell code, lowest voltage battery cell code, lowest voltage battery subsystem number, battery cell voltage minimum value, tire condition and general alarm sign. The data collection of the driver specifically collects the driver's historical driving data of following, overtaking and lane changing behaviors to form a driver behavior feature database. The data collection of road information includes road name, width, number of lanes, traffic light conditions, maintenance conditions and real-time vehicle conditions. The data collection of weather environment includes temperature, humidity, rain and snow, wind force, sand and dust conditions and fog level.

[0050] In step S3, the specific method of constructing the data processing model is: comprehensively process the three types of objective, stable and controllable data, that is, comprehensively process the vehicle data, road information data and weather environment data, to construct a direct evaluation model, and use this model as the first evaluation and early warning model. In addition, the relatively unstable driver data, including the driver's body temperature, body surface condition and posture, are processed separately, and a driver behavior feature database is formed by collecting the driver's historical driving data of following, overtaking and lane changing behaviors. The historical data in the database is comprehensively processed to construct a driver behavior processing model, and then combined with the vehicle behavior processing model for training to obtain the driver relative to the vehicle behavior processing model as the second evaluation and early warning model.

[0051] In step S4, the specific method of constructing the risk assessment algorithm is as follows: initially, the first assessment and warning model and the second assessment and warning model are calculated and processed separately, and the automobile data, road information data and weather environment data in the first assessment and warning model are firstly subjected to single basic assessment and warning, such as when the danger level increases during strong winds and heavy rains, and then different data are combined to conduct combined assessment and warning of dangerous items, such as when the vehicle tire has a long service life and encounters high temperature weather, the risk warning level is upgraded, and the warning coefficient of the first assessment and warning model is obtained through the above two assessment algorithms, and then the second assessment and warning model is calculated, the infrared thermometer monitors the driver's body temperature, the camera detects the driver's body surface state, and the posture sensor monitors and analyzes the driver's body behavior to obtain the driver's fatigue level information, and then combined with the driver's historical driving data of following, overtaking and lane changing behaviors, when the driver's fatigue level is high, the risk warning level of the first assessment and warning model is improved, and finally, the data of the first assessment and warning model and the second assessment and warning model are combined to obtain the final risk assessment and warning level.

[0052] In actual application, the equipment is installed first. Monitoring equipment and data connection transmission equipment are installed on the vehicle for status assessment and early warning. The data connection transmission equipment is specifically wireless transmission equipment, and the monitoring equipment is specifically vehicle monitoring equipment and driver status monitoring equipment. The driver status monitoring equipment is specifically infrared thermometer, camera and posture sensor. Then data collection is carried out, including data collection of the car, data collection of the driver, data collection of road information and data collection of weather environment. Then a data processing model is constructed, and the car data, driver data, road information data and weather environment data are comprehensively processed. The car data, road information data and weather environment data are comprehensively processed to construct a direct assessment model. This model is used as the first assessment and early warning model, and the driver data is processed individually. A driver behavior feature database is formed by collecting the driver's historical driving data of following, overtaking and lane changing behaviors. The historical data in the database is comprehensively processed to construct a driver behavior processing model, which is then trained in conjunction with the vehicle behavior processing model to obtain the driver relative vehicle behavior processing model as the second assessment and early warning model. Then the first evaluation and warning model and the second evaluation and warning model are calculated and processed separately. First, the automobile data, road information data and weather environment data in the first evaluation and warning model are evaluated and warned separately. For example, the danger level increases during strong winds and heavy rains. Then, different data are combined to conduct combined evaluation and warning of dangerous items. For example, if the vehicle tire has a long service life and encounters high temperature weather, the risk warning level will be upgraded. The warning coefficient of the first evaluation and warning model is obtained through the evaluation algorithms of the above two. Then, the second evaluation and warning model is calculated. When the driver's fatigue level is high, the risk warning level of the first evaluation and warning model is improved. Finally, the data of the first evaluation and warning model and the second evaluation and warning model are combined to obtain the final risk assessment and warning level. After that, it can be put into specific application. During the driving process of the vehicle, various data are transmitted to the cloud data processing platform in real time, and various data and models are analyzed and processed on the cloud platform. After the data is imported in real time, the risk rating is obtained by analysis, and the information is transmitted to the driver in real time to remind the driver in the form of voice broadcast.

[0053] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0054] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0055] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A vehicle status assessment and early warning method based on an intelligent networked vehicle control center, characterized in that: The following steps are involved: S1: Comprehensive data collection Conduct status assessment and early warning on vehicles equipped with monitoring equipment and data connection and transmission equipment, and collect vehicle data, driver data, road information data, and weather and environmental data; In step S1, the data connection transmission device is a wireless transmission device; the monitoring device includes a vehicle monitoring device and a driver status monitoring device; the driver status monitoring device includes an infrared thermometer, a camera and a posture sensor; In step S1, the driver data includes the driver's historical driving data of following, overtaking and lane changing behaviors, and the collected driver data is formed into a driver behavior feature database; S2: Building a data processing model The automobile data, road information data and weather environment data collected in step S1 are comprehensively processed to construct a direct evaluation model as a first evaluation and early warning model; the driver data collected in step S1 are used to construct a driver behavior processing model as a second evaluation and early warning model; In step S2, the method for constructing a data processing model further includes: processing relatively unstable driver data separately, combining historical data of the driver data for comprehensive processing, constructing a driver behavior processing model, and then training in combination with the vehicle behavior processing model to obtain a driver-to-vehicle behavior processing model as a second evaluation and warning model; S3: Building a risk assessment algorithm First, the first evaluation and warning model constructed in step S2 is calculated to obtain the warning coefficient of the first evaluation and warning model, and then the second evaluation and warning model constructed in step S2 is calculated to obtain the driver fatigue information, and finally the warning coefficient and the driver fatigue information are combined to obtain the final risk assessment warning level; In step S3, the method for obtaining the warning coefficient includes: firstly performing a single basic evaluation and warning on the automobile data, road information data and weather environment data in the first evaluation and warning model, and then combining different data to perform a combined evaluation and warning on the items that may cause danger, and obtaining the warning coefficient of the first evaluation and warning model through the evaluation and warning algorithms of the above two; In step S3, the method for obtaining the driver's fatigue level information includes: monitoring the driver's body temperature through an infrared thermometer, detecting the driver's body surface state through a camera, and monitoring and analyzing the driver's body behavior through a posture sensor to obtain the driver's fatigue level information; and combining the driver's historical driving data of following, overtaking and lane changing behaviors, when the driver's fatigue level is high, the risk warning level of the first assessment and warning model is increased; S4: Real-time data import and analysis During the driving process of the vehicle, various data are transmitted to the cloud data processing platform in real time, and the data and models are analyzed and processed on the cloud platform; S5: Real-time reminder after risk rating After the data is imported and analyzed in real time to obtain the risk rating, the information is transmitted to the driver in real time and the driver is reminded in the form of voice broadcast.

2. The vehicle status assessment and early warning method based on the intelligent networked vehicle control center according to claim 1 is characterized in that: In step S1, the vehicle data includes vehicle battery status, vehicle operating mode, vehicle speed, cumulative mileage, SOC, highest voltage battery subsystem number, highest battery cell voltage value, highest voltage battery cell code, lowest voltage battery cell code, lowest voltage battery subsystem number, lowest battery cell voltage value, tire condition and general alarm sign.

3. The vehicle status assessment and early warning method based on the intelligent networked vehicle control center according to claim 1 is characterized in that: In step S1, the road information data includes road name, width, number of lanes, traffic light conditions, maintenance conditions and real-time vehicle conditions.

4. The vehicle status assessment and early warning method based on the intelligent networked vehicle control center according to claim 1 is characterized in that: In step S1, the weather environment data includes temperature, humidity, amount of rain and snow, wind speed, dust conditions and fog level.

5. The vehicle status assessment and early warning method based on the intelligent networked vehicle control center according to claim 1 is characterized in that: In step S2, the method for constructing a data processing model includes: comprehensively processing three types of objective, stable and controllable data, that is, comprehensively processing vehicle data, road information data and weather environment data to construct a direct evaluation model as the first evaluation and warning model.

Images