Driving monitoring system based on friction-electromagnetic composite pedal motion sensor and machine learning

Abstract

The invention discloses a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning, and solves the problem of monitoring and recognition of driving behaviors and driving styles. The device comprises a gear rack, a rigid stepped shaft, a planetary gear set and an electromagnetic and friction nano-generator element. The mechanical structure and a machine learning related algorithm realize data identification and classification. The gear is connected with the rigid stepped shaft, the sun gear is connected with the stepped shaft through the one-way bearing, the stator and the rotor of the electromagnetic generator are connected with the stepped shaft, and the rack moves under driving force and then transmits the movement to the shaft so as to drive the rotor of the electromagnetic generator to move. The one-way bearing and the sun gear enable the planetary gear set to move to drive a rotor electrode cylinder of the friction nanometer generator to move, and the friction nanometer generator generates electric signals. The system has the advantages of being simple in structure, convenient to install and manufacture, low in cost and the like, can achieve the driving behavior monitoring and early warning function, and has wide application prospects in the field of intelligent traffic.

Description

Technical Field

[0001] The application of this invention patent is mainly used in the field of intelligent transportation for the identification and monitoring of driving behavior and driving style of automobile drivers. By combining the power generation technology of rack and pinion, planetary gear set, friction nanogenerator and electromagnetic generator with machine learning related algorithms, the rack and pinion can convert the linear motion of the accelerator pedal and brake pedal into the rotational motion of the sensor friction electric element and electromagnetic generating element. Through the electrical signals generated by the friction nanogenerator and electromagnetic generator, the relevant algorithms of machine learning are used to realize the monitoring and identification of driving behavior. This technology is of great significance to the development of intelligent transportation and traffic safety. Background Art

[0002] As the number of vehicles continues to grow, road safety issues are becoming increasingly serious. A survey shows that over 80% of road accidents are caused by drivers' aggressive driving styles and poor safety awareness. The prevalence of poor driving behaviors, such as rapid acceleration, rapid deceleration, and illegal overtaking, poses a significant threat to driving safety. Therefore, driver monitoring, including monitoring driving behavior and identifying driving styles, is crucial.

[0003] Triboelectric nanogenerators utilize the triboelectric effect and electrostatic induction to convert mechanical energy into electrical energy. Machine learning algorithms are used to classify and identify clustered electrical signal data. The driver's pedal control directly reflects their driving behavior and style, utilizing the high voltage of the triboelectric nanogenerator and the high current of the electromagnetic generator to monitor pedal movement. A transmission rack and pinion transmits the driver's pedaling action to the triboelectric nanogenerator and electromagnetic generator. Identification and analysis of the generated electrical signals further informs and monitors the driver's driving behavior.

[0004] A driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning has broad application prospects. A new sensor and monitoring system for monitoring and identifying driver behavior has been proposed. The system features a simple structure. By utilizing a friction nanogenerator, the monitoring system is self-powered, eliminating the need for an external power supply. The three-phase electrodes in each stator and rotor also improve the sensor's resolution. The monitoring system processes and classifies the acquired data using machine learning algorithms, categorizing the driver's driving style into three categories: conservative, moderate, and aggressive. The low cost, low energy consumption, and high precision of this system make it widely applicable and promising. This system provides solutions for the development of intelligent transportation and further advancements in traffic safety. Summary of the Invention

[0005] The purpose of this patent is to design a new sensor and intelligent driving monitoring system for monitoring and identifying driver pedal motion. For example, the system combines a mechanical structure with a triboelectric nanogenerator and an electromagnetic generator to convert the driver's pedaling behavior into the rotational motion of the corresponding structure in the sensor, thereby causing the triboelectric nanogenerator and the electromagnetic generator to generate electrical signals. The collected data is input into a SOM network to obtain clustered weights. K-means is then used for secondary clustering to ultimately determine three driving styles. The system has the advantages of self-powered operation, low energy consumption, and simple structure, providing new methods and technologies for monitoring and identifying driving behavior.

[0006] The technical solution of the present invention to achieve the above purpose is:

[0007] The driving monitoring system based on the friction-electromagnetic composite pedal motion sensor and machine learning comprises a right transmission rack, a right transmission gear, a rigid stepped shaft, a fixed bearing, a sun gear, a planetary gear, a right planetary carrier gear ring, a structural shell, a copper coil base, a copper coil, a magnet, a magnet base, a left support plate, a left planetary carrier gear ring, a left transmission gear, a left transmission rack, a right support plate, a planetary gear bearing, a one-way bearing, an inner friction nanogenerator rotor, a middle friction nanogenerator stator, and an outer friction nanogenerator rotor; the transmission scheme of the self-powered pedal motion sensor based on the friction nanogenerator and the electromagnetic generator adopts a gear rack meshing transmission, and the sun gear of the planetary gear set is connected to the rigid stepped shaft through a one-way bearing. The shafts are fixed, enabling unidirectional torque transmission and unidirectional free rotation. The stator of the electromagnetic generator is connected to the middle stator of the triboelectric nanogenerator, while the rotor of the electromagnetic generator is bonded to the rigid stepped shaft. The inner rotor cylinder of the triboelectric nanogenerator is bonded to the left planetary carrier ring gear, while the outer rotor cylinder is bonded to the right planetary carrier ring gear. The transmission rack and pinion transmits the linear motion of the accelerator and brake pedals to the rotational motion of the planetary gear set, thereby converting the rotational motion of the electromagnetic generator and triboelectric nanogenerator into electrical signals. The electrical signal data samples generated by the generator are clustered into three categories to identify three different driving styles. This solution effectively transforms the driver's accelerator and brake pedal behavior data output by the sensor and performs calculations and classification to obtain different driving style data. It also demonstrates the advantages of the sensor and system, such as excellent sensing recognition accuracy and low energy consumption.

[0008] The structural features of the patent of this invention are:

[0009] The structural shell, copper coil base, and magnet base are all made of PLA by 3D printing. The inner, middle, and outer friction nanogenerator rotors and stator cylinders are all made of acrylic material and are connected by bonding to ensure the synchronization of their movement.

[0010] The distance between the rotor and the stator of the electromagnetic generator is as small as possible to ensure the power generation effect, and the distance can be less than 1 mm.

[0011] The friction-electromagnetic composite pedal motion sensor has the characteristics of simple structure, low manufacturing cost, low energy consumption, strong reproducibility, etc.

[0012] The two rotor cylinders of the friction nanogenerator are pasted onto the copper electrodes and then covered with polytetrafluoroethylene films to form the electrodes of the friction nanogenerator.

[0013] This invention utilizes a triboelectric nanogenerator and an electromagnetic generator, ingeniously transmitting the pedal's linear motion through a mechanical structure to the generator, generating an electrical signal that is then analyzed and calculated using an algorithm. This system accurately generates motion and performs precise cluster analysis on the data, enabling classification and monitoring of driving behavior. This sensor device boasts a simple structure, low manufacturing cost, high resolution, and a highly efficient monitoring and recognition system. Its accurate recognition makes it suitable for applications in intelligent transportation and intelligent driving, with broad potential. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The illustrated drawings are used to provide further understanding of the present invention and constitute a part of this application. The illustrative examples of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0015] Figure 1 The figure shows the overall structure of a frictionless nanogenerator cylinder in a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning.

[0016] Figure 2 The figure shows the overall structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0017] Figure 3 The figure shows a schematic diagram of the transmission gear structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0018] Figure 4 The figure shows a schematic diagram of the transmission rack structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0019] Figure 5 The figure shows a schematic diagram of a rigid stepped shaft structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0020] Figure 6Shown is a schematic diagram of the inner-layer triboelectric nanogenerator rotor structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0021] Figure 7 Shown is a schematic diagram of the outer layer triboelectric nanogenerator rotor structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0022] Figure 8 Figure 2 shows the schematic diagram of the intermediate triboelectric nanogenerator stator structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning.

[0023] Figure 9 Shown is a schematic diagram of the copper coil base structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0024] Figure 10 A schematic diagram of the planetary carrier and ring gear structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning is shown;

[0025] Figure 11 The figure shows a schematic diagram of the planetary gear support plate structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0026] Figure 12 Shown is a schematic diagram of the structural shell structure of a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning;

[0027] Figure 13 The figure shows a schematic diagram of the SOM algorithm used in a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning. DETAILED DESCRIPTION

[0028] The following further describes the details of the present invention and its specific implementation methods with reference to the accompanying drawings.

[0029] The driving monitoring system based on the friction-electromagnetic composite pedal motion sensor and machine learning consists of a right transmission rack 1, a right transmission gear 2, a rigid stepped shaft 3, a fixed bearing 4, a sun gear 5, a planetary gear 6, a right planetary carrier gear ring 7, a structural shell 8, a copper coil base 9, a copper coil 10, a magnet 11, a magnet base 12, a left planetary gear support plate 13, a left planetary carrier gear ring 14, a left transmission gear 15, a left transmission rack 16, a right planetary gear support plate 17, a planetary gear bearing 18, a one-way bearing 19, an inner friction nanogenerator rotor 20, a middle friction nanogenerator stator 21, and an outer friction nanogenerator rotor 22; wherein the two sides The transmission gear rack is installed on the structural housing 8 through the guide grooves 8-1 on both sides thereof, the transmission gears 2 and 15 are installed on the rigid stepped shaft 3 through the bearings 4, and the sun gear 5 of the planetary gear set is connected to the rigid stepped shaft 3 through the one-way bearing 19, which can realize one-way torque transmission; the planetary gear 6 is connected to the short shafts 17-1, 17-3, and 17-4 on the support plates 13 and 17 through bearings, and the planetary gear 6 and the planetary ring gear 14 and 7 are engaged with each other through gears to form the power transmission route of the sensor; the stator component of the electromagnetic generator is fixed by six identical copper coils 10 on the copper coil base 9 with grooves by bonding, thereby forming a stator component of the electromagnetic generator. The electromagnetic stator is fixed to the middle friction nanogenerator stator cylinder 21 by bonding; the rotor component of the electromagnetic generator is composed of six identical magnets 11 fixed to the magnet base 12 by bonding, thereby forming the rotor part of the electromagnetic power generation, and the electromagnetic rotor is fixed to the rigid stepped shaft 3 by bonding; the friction nanogenerator includes two rotor cylinders and one stator cylinder, the inner friction nanogenerator rotor 20 is fixed to the left (brake) planetary carrier ring gear 14 by bonding to achieve synchronous rotation, and the inner rotor is composed of a copper electrode 22-1 fixed to the outer surface of the rotor cylinder by bonding; the outer friction The nanogenerator rotor 22 is fixed to the right (acceleration) planetary carrier ring gear 7 by bonding to achieve synchronous rotation. The outer rotor is composed of a copper electrode 20-2 bonded to the inner surface of the rotor cylinder. The middle friction nanogenerator stator 21 is fixed to the structural shell 8 by bonding to achieve the fixation of the middle stator cylinder and the structural shell 8. The middle stator is composed of copper electrodes 21-3 and 21-2 bonded to the inner and outer surfaces of the stator cylinder. The signal data generated by the sensor is processed and calculated and then input into the SOM network to obtain the clustered weight result. Then, K-means is used for secondary clustering to finally obtain three driving styles.

[0030] The transmission gear 2 and the transmission rack 1 cooperate with each other through gear meshing to form a driving component of the device. The transmission gear 2 is installed on the rigid stepped shaft 3 through a fixed bearing 4 to achieve power transmission.

[0031] The rotor magnet base 12 of the electromagnetic generator includes six identical grooves 12 - 1 and a middle through hole 12 - 1 . The rigid stepped shaft 3 passes through the rotor base 12 through the middle through hole and is fixed together by bonding.

[0032] The right (left side omitted) planetary gear support plate 17 includes a middle through hole 17-2 and three planetary gear mounting shafts 17-1, 17-3, and 17-4. The rigid stepped shaft 3 passes through the right support plate 17 through the middle through hole 17-2, and the planetary gear 6 is mounted on the support plate mounting shafts 17-1, 17-3, and 17-4 through bearings.

[0033] The inner rotor component of the friction nanogenerator includes a rotor cylinder 20-1 and a three-phase copper electrode 20-2. Each phase of the three-phase copper electrode 20-2 includes fifty copper units and is fixed to the outer surface of the rotor cylinder 20-1 by gluing to achieve synchronous movement of the copper electrode 20-2 and the rotor cylinder 20-1.

[0034] The outer rotor component of the friction nanogenerator includes a three-phase copper electrode 22-1 and a rotor cylinder 22-2. Each phase of the three-phase copper electrode 22-1 includes fifty copper units and is fixed to the inner surface of the rotor cylinder 22-2 by gluing to achieve synchronous movement of the copper electrode 22-1 and the rotor cylinder 22-2.

[0035] The intermediate stator component of the friction nanogenerator includes a stator cylinder 21-1, an outer three-phase interdigitated copper electrode 22-2 and an inner three-phase interdigitated copper electrode 21-3. Each phase includes fifty copper units. The outer three-phase interdigitated copper electrode 22-2 and the inner three-phase interdigitated copper electrode 21-3 are fixed to the outer and inner surfaces of the stator cylinder 21-1 by gluing to form stator electrodes.

[0036] The surface of the three-phase copper electrode 20-2 of the inner rotor of the friction nanogenerator is covered with a layer of polytetrafluoroethylene film, forming the electrode of the inner friction nanogenerator; similarly, the three-phase copper electrode 22-1 of the outer rotor of the friction nanogenerator is covered with a layer of polytetrafluoroethylene film, forming the electrode of the outer friction nanogenerator.

[0037] The sensor generates data outputs, which are clustered into three styles using a clustering method. The SOM network is used to perform cluster analysis effectively. The SOM clustering results are then divided into multiple categories, and the K-means algorithm is used to further cluster the classification results into three categories. How it works

[0038] This invention combines a triboelectric nanogenerator, an electromagnetic generator, a planetary gearset, and a rack-and-pinion transmission. Through ingenious design, it forms a sensor driven by the driver's pedaling action, converting the linear motion of the driver's pedaling action into the rotational motion of the generator. The invention cleverly utilizes the torque transmission characteristics of a one-way bearing to differentiate the motion of two planetary gearsets connected on the same shaft based on different mounting methods. After the generator outputs the relevant data from the electrical signal machine, a machine learning algorithm is introduced to calculate, cluster, and analyze the data collected by the sensor, ultimately identifying three different driving styles. The data is clustered into three styles using a clustering method. A SOM network is employed to effectively implement the cluster analysis. The SOM clustering results are then divided into multiple categories. The K-means algorithm is then used to further cluster the classification results into three categories: conservative, moderate, and aggressive.

[0039] In summary, the present invention uses a triboelectric nanogenerator, an electromagnetic generator, and related mechanical structures to form a sensor, and combines them with relevant algorithms to design a new driver behavior monitoring and identification system. At the same time, the present invention has the advantages of simple structure, low manufacturing cost, self-power supply and high recognition accuracy, which can promote the further development of intelligent transportation and intelligent driving.

Claims

1. A driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning, characterized in that: It includes (1) a right transmission rack, (2) a right transmission gear, (3) a rigid stepped shaft, (4) a fixed bearing, (5) a sun gear, (6) a planetary gear, (7) a right planetary carrier gear ring, (8) a structural housing, (9) a copper coil base, (10) a copper coil, (11) a magnet, (12) a magnet base, (13) a left planetary gear support plate, (14) a left planetary carrier gear ring, (15) a left transmission gear, (16) a left transmission rack, (17) a right planetary gear support plate, (18) a planetary gear bearing, (19) a one-way bearing, (20) an inner friction nanogenerator rotor, (21) an intermediate friction nanogenerator stator, and (22) an outer friction nanogenerator rotor.

2. A driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 1, characterized in that (1) The right transmission rack is installed at a corresponding position on the (8) structural housing; (2) The right transmission gear is engaged with (1) the right transmission rack to form the input drive device on the right side of the entire structure; (2) The right transmission gear is installed on (3) the rigid stepped shaft by cooperating with the bearing, and (3) the rigid stepped shaft is installed on the (8) structural housing by cooperating with (4) the fixed bearing.

3. The driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 1 is characterized in that The (5) sun gear of the planetary gear set is matched with the (3) rigid stepped shaft through the (19) one-way bearing, and the three (6) planetary gears are installed on the (13) left and (17) right support plates through bearings, and are respectively engaged with the (5) sun gear and the (7) and (14) planetary gear rings to form an integral planetary gear set to transmit torque and movement; the (22) outer friction nanogenerator rotor is connected to the (7) right planetary gear ring by bonding to achieve synchronous movement with the (7) right planetary gear ring, the (20) inner friction nanogenerator rotor is connected to the (14) left planetary gear ring by bonding to achieve synchronous movement with the (14) left planetary gear ring, and the (21) middle friction nanogenerator stator is connected to the (8) structural shell by bonding to form a stator.

4. The driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 1, characterized in that The stator of the electromagnetic power generation element is composed of six (10) copper coils of the same size connected to a (9) copper coil base with grooves by bonding to form an electromagnetic power generation stator. The rotor of the electromagnetic power generation has six (11) magnet blocks of the same size connected to a (12) magnet base with (12-2) grooves by bonding to form an electromagnetic power generation rotor. The electromagnetic power generation rotor formed by the connection of the (11) magnets and the (12) magnet base is fixed on the (3) rigid stepped shaft to achieve synchronous movement with it to realize the rotor function.

5. The driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 3 is characterized in that (20) The outer surface of the inner friction nanogenerator rotor tube is affixed with (20-2) three-phase electrodes by bonding, with 50 units per phase electrode; (22) The inner surface of the outer friction nanogenerator rotor tube is affixed with (22-1) three-phase electrodes by bonding, with 50 units per phase electrode; (21) The inner and outer surfaces of the middle friction nanogenerator stator tube are affixed with (21-3), (21-2) inner and outer three-phase electrodes by bonding, with 50 units per phase electrode.

6. The driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 4, characterized in that The six identical (11) magnets are of the same size as the six (10) copper coils, and the angle difference between adjacent (11) magnets is 60°. The polarities of two adjacent (11) magnets are opposite, and the distance between the (11) magnets and the (10) copper coils is one millimeter.

7. The driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 1, characterized in that The ratio of the pitch circle linear speeds of (15) the left transmission gear, (2) the right transmission gear, and (14) the left planetary carrier ring gear, and (7) the right planetary carrier ring gear is 50:76, ​​and the gear ratio of (14) the left planetary carrier ring gear, (7) the right planetary carrier ring gear, and (5) the sun gear is 30:

76.

8. The driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning according to claim 3 is characterized in that (19) The one-way bearing transmits torque in one direction and rotational motion in the other direction. When installing, the left and right sides are installed in opposite directions to ensure that the one-way bearing on one side (19) transmits torque and the one-way bearing on the other side (19) is not subjected to force.

9. According to claim 1, a driving monitoring system based on a friction-electromagnetic composite pedal motion sensor and machine learning, when the transmission rack is linearly driven, it drives the gear to rotate, thereby converting the rotational motion into friction nanogenerator and electromagnetic power generation. The data is then identified and classified according to the machine learning-related SOM algorithm and K-means algorithm to meet the needs of detecting and identifying the driver's driving behavior.

Images