DESC:FIELD OF THE INVENTION
The present invention relates to a prediction system and method more particularly rider’s biological data and riding history based battery level prediction system and method using artificial intelligence.
BACKGROUND OF THE INVENTION
The global annual production of bicycles is roughly 100 million. At the present pandemic time, the industry seems to be experiencing sudden growth due to health awareness and social distancing.
In particular, electric bicycles, or e-bike usage worldwide also appears to be rapidly escalating as urban populations assess the environmental impact of fossil-fueled transportation and new regulations governing motorized transportation.
Conventional electric bicycles, or e-bikes, generally comprise an electric motor and a rechargeable battery pack, and can be separated into two categories:
1. Pedelec bicycles and
2. All-electric bicycles.
Pedelec bicycles generally comprise an electric motor that is activated based cyclist requirements. The most salient factor is that Pedelec lower the difficulty barrier for people to engage in meaningful, regular exercise. The actual benefit of the pedelec bicycles are support the rider by operating the bicycle via electric power when the rider is feeling fatigue, demanding assistance or relief. These kind of regular activities can translate into progressive changes to the rider’s habits, which could lead to better health outcomes for riders who ride pedelec bicycles.
Pedelec bicycles also provide seniors another option to extend their period of independence. Not only could Pedelec bicycle keeps them physically active.
The proposed system and method assisting the progressive health benefits of the rider, the proposed patent provides a smart facility to “alert the cyclist” based on “biological data and driving history” therefore the cyclist/rider can have a more confident about their regular rides without any hesitation or panic. This method can give a more confident about hassle free daily rides.
OBJECT OF THE INVENTION
An object of the invention is to provide an assisting system for motorized bicycle riders.
Another object of the invention is to provide a battery level alerting system for a cyclist based on rider’s biological and driving history data.
Yet another object of the invention is to allow the rider effortlessly enjoying the regular cycling.
Yet another object of the invention is to provide more confident to the rider/cyclist for their regular riding pattern.
Yet another object of the invention is to make the method capable to learn the rider’s cycling habit, biological data and riding pattern for alerting the rider about the battery level.
Yet another object of the invention is to acquire partial sensing inputs from the rider’s computing/mobile device and smart watch/physiological device.
Yet another object of the invention is to provide an artificial Intelligence based learning platform.
Further object of the invention is to allow the system to learn the charge required to complete the daily riding cycle and correspondingly prefer the route based on learned trip history and alert the rider about the battery percentage required to complete the trip.
SUMMARY OF THE INVENTION
The present invention is intended to present a solution to assisting system need as well as needs for having a smart battery level alerting method for e-bike or pedelec which remain in the relevant field of art.
As such, and for purposes of clarity in describing the operative features of many of the preferred embodiments, the present invention is directed to provide a smart facility via AI based learning platform to “alert the cyclist” based on “biological data and driving history”. Therefore, the system ensures a physical fitness of the rider and also supporting the rider in their emergency situations thereby providing hassle free riding experience. This method and system also indirectly supports the rider’s progressive health benefits and also assist to predict the battery powered bicycle’s present condition or maintenance requirements.
BRIEF DESCRIPTION OF DRAWINGS
S.NO PART NAME PART NO
1. Battery 1
2. Motor with drive unit 2
3. Control system 3
4. Sensors 4
5. Computing device/Mobile device 5
6. physiological device/Smart watch 6
7. Remote server 7

Figure 1 illustrates embodiment of the invention which shows the system configuration.
Figure 2 illustrates the embodiment of the invention which shows the basic flow chart of the invention.

The above figures and related written description are not intended to limit the scope of the inventive concepts in any manner. Rather, the figures and written description are provided to illustrate the inventive concepts to a person skilled in the art by reference to particular embodiments.

DETAILED DESCRIPTION OF THE INVENTION
One of the preferred embodiment of the invention discloses about a method being performed in a battery powered bicycle having a battery (1), motor with drive unit (2), control system (3), plurality of sensors (4), a computing device (5) and a physiological device(6), and a remote server (7). The method comprises the steps of, first pairing the control system (3), sensors (4), computing device (5), remote server (7) and physiological device (6) then allowing the rider by the control system (3) to feed the weight, height, age and health data through the computing device (5). Once the above said pairing action has been initiated, then the method is acquiring the body temperature and heart rate data in real time by means of a physiological device (6) as well as acquiring the GPS, terrain, gyro, weather and wind velocity data by means of a computing device (5). In the above similar way acquiring the speed, battery percentage, voltage and current data by means of plurality of sensors (4). The method is mainly characterized for calculating the real time drag force with respect to frontal area by means of above said manually updated and real time acquired data. Deriving the health statistics data with respect to real time acquired physiological data and manually entered rider data. Further, mapping the real time data, daily riding pattern, calculated and derived data of the rider with battery consumption rate. Wherein each riding cycle being tracked and stored in the remote server along with the above said real time data by the control system to enable a machine learning and AI based alert thereby learning the charge required to complete the daily riding cycle for correspondingly preferring the route, alerting the rider and optionally controlling the drive unit (2) with respect to available battery percentage.

Another embodiment of the invention discloses about a physiological device (6) is a smart watch or wearable device.

Yet another embodiment of the invention discloses about the way the method alerts the user. The method is having a multiple options, one is computing device (5), and another one is physiological device (6). In some cases, the alerting can be performed via light indication or display unit provided in the handle bar of the battery powered bicycle.

Yet another embodiment of the invention discloses about the control system (3). In one embodiment the control system (3) capable of being a micro controller.

Yet another embodiment of the invention discloses about the calculated user data capable of being a BMI, frontal area and aerobic/anaerobic respiration. The above calculation being performed based on manually entered height, weight and health details of the user.

Yet another embodiment of the invention discloses about the optional prediction option available in the method. In this method, can calculate the vehicle data capable of being chain life, preferred torque input from the rider, preferred electric assistance.

Yet another embodiment of the invention discloses about the method is capable of being a smart mode operation to understand the casual or fitness related ride and accordingly enable the electric assist.

Yet another embodiment of the invention discloses about the system for predicting and alerting the status of battery power of a battery-operated bicycle having a battery (1), motor with drive unit (2), control system (3), plurality of sensors (4), a computing device (5) and a physiological device(6) and a remote server (7). The system configured to pair with the control system (3), sensors (4), computing device (5), remote server (7) and physiological device (6). The system acquires the manually updated weight, height, age and health data through the computing device (5), and also acquire the body temperature and heart rate data in real time by means of a physiological device (6). The system acquires GPS, terrain, gyro, weather and wind velocity data by means of a computing device (5) and also acquire the speed, battery percentage, voltage and current data by means of plurality of sensors (4),
The system mainly characterized to calculate the real time drag force with respect to frontal area by means of above said manually updated and real time acquired data. Wherein the system is characterized to derive the health statistics data with respect to real time acquired physiological data and manually entered rider data. Wherein the system is characterized to map the real time data, daily riding pattern, calculated and derived data of the rider with battery consumption rate. Wherein each riding cycle being tracked and stored in the remote server along with the above said real time data by the control system to enable a machine learning and AI based alert thereby learning the charge required to complete the daily riding cycle for correspondingly preferring the route, alerting the rider and optionally controlling the drive unit (2) with respect to available battery percentage.

Yet another embodiment of the invention discloses about the method and system acquires the wind velocity to calculate the impacts of drag force while riding.

Yet another embodiment of the invention discloses about system developed in this embodiment determines the ability to predict the range of battery fitted on an electric bicycle equipped with Pedal Assisted System (PAS)/Throttle Assisted System (TAS) or both PAS and TAS for a predetermined route, or for given State of Charge (SOC) based on machine learning using various data points.

Yet another embodiment of the invention discloses about the data points which can be broadly classified as,
1. Vehicular data,
2. Environmental data,
3. Traffic data,
4. Rider history and
5. Biological data.

The historical data coupled with the raw real time data are fed into the self-learning algorithm programmed into a micro controller to assess the battery range.

Yet another embodiment of the invention discloses about the manual and smart mode operation of the proposed invention. The mode can be determined the battery range for a predetermined route or for a given SOC (State of Charge). Based on the riders’ historical riding pattern. In the smart mode embodiment, the battery range is estimated by optimization on the riders past riding pattern, endurance, terrain data and the level of electric assist.
The output suggests the range for the existing battery as well as provides the rider with the information on:
1. The number of batteries required in the current capacity to complete the trip

2. The battery capacity required for completing the trip

In both modes the battery SOC is taken as the rule of measure.
The manual mode embodiment focuses on the performance of the rider while the smart mode embodiment focuses on comfort.

Yet another embodiment of the invention discloses about some of the input, output and calculated data for the proposed method. Below table shows the some of the sensing information to determines the overall performance of the proposed method and system.

INPUT DATA OUTPUT
Terrain 1. Range of battery
2. Optimal battery usage
3. Riding preference based on trip
Environmental
Rider Info
Battery status
Route Info
Vehicular Info

Yet another embodiment of the invention discloses about the input information that includes, rider heart rate, BMI, age, weight, height, aerobic respiration range, number of discharge cycles of the battery, motor run hours, chain life, preferred torque input from rider, preferred electric assistance. While majority of them are fed into the self-learning platform on a dynamic basis, some are fed manually while setting up the bicycles and are used to estimate the optimum range from which the range assessment is done in both the manual as well as smart mode.

Yet another embodiment of the invention discloses about the self-learning platform will take in real time data as well as the historic data and extrapolate the physical fitness of the rider and map it over the predefined route available on the bike. The smart mode embodiment will understand the type of trip viz. casual or fitness related and determined the battery range. Accordingly, the electric assist is provided to the rider to maintain the optimal pedal torque/heart rate required to be maintained during riding the bicycle so that the rider does not get fatigued by the end of the ride.

Yet another embodiment of the invention discloses about the difference types of inputs acquired from manual input and real time data.
Input acquired from 1. Input parameters 2. Calculated data 3. Overall calculation
User input 4. Age,
5. Height,
6. Weight,
Physical condition or health condition Health statistics
Frontal area

7.

• Range analysis
• Automated assist level
• Energy demand
physiological device Heart rate
Body temperature
8. Health statistics

Computing device Real time traffic
Weather condition
Wind data
Terrain data Drag force
Sensors Battery sensor
Voltage/current
Rpm sensor

Yet another embodiment of the invention discloses about the way of considering the environmental data to determine the battery level consumption. The impact of variable wind velocity will affect the riding behavior as well as battery percentage.

The ability to complete a trip start with the aerodynamic drag force is defined as:
Fad = 1 • ? • Af ront • Cd × (V -Vw), (1)
Where, ? is the density of air, Af ront is the frontal area, V the vehicle velocity of the vehicle and Vw is the wind velocity obtained from the weather information.
The rolling resistance is defined as:

Frr = M • g • Crr cos?, (2)
Where, M is the mass of the vehicle along with the mass of the rider, and g is the acceleration due to gravity and ? the angle of inclination is based on the terrain data obtained. The total force due to acceleration is defined as:
Fla + F?a = Fm × M • Acc, (3)
Where Acc is the acceleration. Finally, the traction power is defined as:
Fte = Fad + Frr + Fhc + F?a + Fla (4) Pte = Fte × V, (5)
The traction power Pte which is linked to the traction force Fte includes the manual power input along with the electric motor assist. The level of assist is based on both the requirement for the trip as well as considering the needs of the rider.
Yet another embodiment of the invention discloses about the control system will be able to predict the total energy required, human as well as electrical to complete the trip. Accordingly all the collected data being mapped to determine the battery level to complete the trip.

The non-connected embodiment, will have preset conditions in terms of electrical assist. This will determine in a given instant the electrical discharge at a fixed rate. This will in turn be used to determine the total battery capacity and the capability. Based on the cycle information and the rider information, the processor will maintain the optimum gain ratio range. This will be the optimum functioning range for the rider. This is applicable in the non-motor assisted embodiment also. There will be no contribution form the electric power aspect. The total traction power will 100% be linked to human power. This embodiment can be based on a smart as well as a non-smart platform.

In the connected embodiment, the controller along with cloud connectivity will be available. This version will be completely on the smart platform. The optimal gain ratio will not only be computed but constantly changing with each ride. This is because the smart platform will learn and predict the development of the rider and understand their need intuitively for any trip.

Power assistance provided is directly linked to the state of discharge of the battery. The real time tracking of the state of charge coupled with the historical data of number of cycles of discharge enables accurate extrapolation to determine the requirements for the required trip.

Traffic data accounts for the number of starts and stops which also links to the power requirement in the embodiment. This environment data includes the terrain data along with the weather info. The terrain data includes the slopes travelled, while the weather data determines the aerodynamic drag.

Yet another embodiment of the invention discloses about the possible speed range assisted by the proposed system. The proposed system can provide assist upto 25 km/hr and further capability to meet S-Pedelecs going upto 45km/hr.
Further embodiment of the invention discloses about an alerting system for a battery powered bicycle consisting of a battery (1), motor with drive unit (2), control system (3), plurality of sensors (4), a computing device (5) having a Gyro sensor, GPS and GSM, and a physiological device(6), and a remote server (7), the system configured to pair the control system, sensors, computing device, remote server and physiological device allowing the rider by the control system to feed the user data through the computing device. The system configured to acquire real time GPS, terrain, environmental and user data through the plurality of sensors or computing device or physiological device or combination thereof thereby acquiring the daily riding pattern and biological data of the rider, and mapping the same with battery consumption rate each riding cycle being tracked and stored in the remote server along with acquired inputs by the control system to enable machine learning and AI based alert thereby learning the charge required to complete the daily riding cycle for correspondingly preferring the route and alerting the rider with respect to available battery percentage.

ADVANTAGES
1. The predictive range analysis would intimate the user if there is enough battery capacity for a pre-determined trip.
2. The range analysis predicts the rider’s ability to complete a pre-determined trip based on the historical data.
3. The rider can select the route based on available battery percentage.
4. The smart mode embodiment assesses the stamina of the rider based on the riding pattern. This will also estimate the rider’s capability and the improvement over time with using this system.

So that the manner in which the features, advantages and objects of the invention, as well as others which will become apparent, may be understood in more detail, more particular description of the invention briefly summarized above may be had by reference to the embodiment thereof which is illustrated in the appended drawings, which form a part of this specification. It is to be noted, however, that the
drawing illustrate only a preferred embodiment of the invention and is therefore not to be considered limiting of the invention’s scope as it may admit to other equally effective embodiments.
,CLAIMS:WE CLAIM
1. A method being performed in a battery powered bicycle having a battery (1), motor with drive unit (2), control system (3), plurality of sensors (4), a computing device (5) and a physiological device(6), and a remote server (7), the method comprises the steps of;
a. pairing the control system (3), sensors (4), computing device (5), remote server (7) and physiological device (6) ,
b. allowing the rider by the control system (3) to feed the weight, height, age and health data through the computing device (5),
c. acquiring the body temperature and heart rate data in real time by means of a physiological device (6),
d. acquiring GPS, terrain, gyro, weather and wind velocity data by means of a computing device (5),
e. acquiring the speed, battery percentage, voltage and current data by means of plurality of sensors (4),
characterized in that
f. calculating the real time drag force with respect to frontal area by means of above said manually updated and real time acquired data,
g. deriving the health statistics data with respect to real time acquired physiological data and manually entered rider data,
h. mapping the real time data, daily riding pattern, calculated and derived data of the rider with battery consumption rate,
i. wherein each riding cycle being tracked and stored in the remote server along with the above said real time data by the control system to enable a machine learning and AI based alert thereby learning the charge required to complete the daily riding cycle for correspondingly preferring the route, alerting the rider and optionally controlling the drive unit (2) with respect to available battery percentage.

2. The method as claimed in claim 1, wherein the physiological device (6) is a smart watch or wearable device.

3. The method as claimed in claim 1, wherein the method alerts the user via computing device (5) or physiological device (6) or light indication or display unit provided in the handle bar or combination thereof.

4. The method as claimed in claim, wherein the control system (3) capable of being a micro controller.

5. The method as claimed in claim 1, wherein the calculated user data capable of being a BMI, frontal area and aerobic/anaerobic respiration.

6. The method as claimed in claim 1, wherein the calculated vehicle data capable of being chain life, preferred torque input from the rider, preferred electric assistance.

7. The method as claim in claim 1, wherein the method is capable of being a smart mode operation to understand the casual or fitness related ride and accordingly enable the electric assist.

8. A system for predicting and alerting the status of battery power of a battery-operated bicycle having a battery (1), motor with drive unit (2), control system (3), plurality of sensors (4), a computing device (5) and a physiological device(6) and a remote server (7),
a. Wherein the system configured to pair with the control system (3), sensors (4), computing device (5), remote server (7) and physiological device (6),
b. Wherein the system acquires the manually updated weight, height, age and health data through the computing device (5), and also acquire the body temperature and heart rate data in real time by means of a physiological device (6),
c. Wherein the system acquires GPS, terrain, gyro, weather and wind velocity data by means of a computing device (5) and also acquire the speed, battery percentage, voltage and current data by means of plurality of sensors (4),
characterized in that
d. wherein the system is characterized to calculate the real time drag force with respect to frontal area by means of above said manually updated and real time acquired data,
e. wherein the system is characterized to derive the health statistics data with respect to real time acquired physiological data and manually entered rider data,
f. wherein the system is characterized to map the real time data, daily riding pattern, calculated and derived data of the rider with battery consumption rate,
g. wherein each riding cycle being tracked and stored in the remote server along with the above said real time data by the control system to enable a machine learning and AI based alert thereby learning the charge required to complete the daily riding cycle for correspondingly preferring the route, alerting the rider and optionally controlling the drive unit (2) with respect to available battery percentage.

9. The system as claimed in claim 8, wherein the physiological device (6) is a smart watch or wearable device.

10. The system as claimed in claim 8, wherein the system alerts the user via computing device (5) or physiological device (6) or light indication or optional display unit provided in the handle bar or combination thereof.

11. The system as claimed in claim 8, wherein the control system (3) capable of being a micro controller.

12. The system as claimed in claim 8, wherein the calculated user data by the control system (3) capable of being a BMI, frontal area and aerobic/anaerobic respiration.

13. The system as claimed in claim 8, wherein the calculated vehicle data capable of being chain life, preferred torque input from the rider, preferred electric assistance.

14. The system as claim in claim 8, wherein the system is configured to understand the casual or fitness ride accordingly enable the electric assist.