The present invention relates to a system for predicting the distance covered in remaining energy of the battery. More particularly, the present invention provides a system for predicting the distance covered in remaining energy of the battery and the method of using thereof which involves the use of the instantaneous power being delivered per km and divide the total energy stored by this instantaneous power to calculate the total range.
BACKGROUND OF THE INVENTION:
The energy stored in a Lithium-ion battery is difficult to estimate. The voltage of the battery decreases non-linearly with energy remaining, with the voltage profile having a plateau for a range. Hence, measuring the voltage does not give an accurate idea for the energy remaining. The battery cut off voltage is characterized by the weakest cell. The overall voltage of the battery is not indicative of the cut-off voltage as it may vary.
The voltage vs. time profile of a cell dynamically depends on the temperature and the current drawn from it. The instantaneous current causes an instantaneous drop in the voltage which then gradually rises back to its natural voltage. But in a quick environment like a battery in use, the voltage is often not allowed to go back to its natural level. The voltage vs. time profile of each cell is unique and therefore can be generalized only to a certain extent. As the number of discharge cycles increases, individual cells develop significantly different profiles. The cell capacity reduces with cycles. Essentially, the voltage profile changes with the cycles, and this change is also unique to each cell. Coulomb-count based methods are unreliable as the total coulomb count varies over each discharge cycle. The speed profile of the user heavily affects the power consumed per Km. Typically, the aerodynamic drag is high at high speeds, and the drivetrain loss is high at low speeds. Additionally, a high number of accelerations and decelerations contribute to higher energy losses. The load, i.e., the weight of the rider(s) is a contributing factor to the power consumed. Higher loads will require more energy for the same distance. The power being delivered by the battery is not constant throughout the discharge cycle.
Therefore, there is need of a solution which can estimate the remaining distance that can be covered by the rider on the remaining energy of the battery and the calculated range/distance remain constant as the time and cycles passes.

The present invention involves the use of the instantaneous power being delivered per km and divide the total energy stored by this instantaneous power to calculate the total range. The present invention provides a system wherein the range estimation can be adapted to fit the immediate conditions of the battery and vehicle and the estimated range will remain constant as time and cycles proceed.
OBJECT OF THE INVENTION:
The primary objective of the present invention is to disclose a system for predicting the distance covered in remaining energy of the battery and the method of using thereof.
Another objective of the present invention is to disclose the system for predicting the distance covered in remaining energy of the battery which involves the use of the instantaneous power being delivered per km and divide the total energy stored by the said instantaneous power to calculate the total range.
Another objective of the present invention is to disclose a system for predicting the distance covered in remaining energy of the battery and the method of using thereof wherein the estimated range remain constant as time and cycles passes.
Yet another objective of the present invention is to disclose a system wherein the range estimation can be adapted to fit the immediate conditions of the battery and vehicle
Other objects and advantages of the present invention will become apparent from the following description taken in connection with the accompanying drawings, wherein, by way of illustration and example, the aspects of the present invention are disclosed.
SUMMARY OF THE INVENTION:
In accordance with the main embodiment of present invention, a system for predicting the distance covered in remaining energy of the battery comprising: a device with a microcontroller; a computing unit, comprises: a plurality of input and output ports; a set of data; a battery; and a plurality of key performance indicators for predicting state of charge of the said battery; and the method comprising the steps of: collecting, a plurality of data by means of battery management system (BMS) for recording the data on drive cycles of the two wheelers; recognizing, a driving pattern for categorizing the user between a number of classes; selecting, a plurality of parameters for the classification; using, a regression method based on the plurality of factors; and predicting, the remaining range of the said two wheelers; wherein

the driving pattern classification can be done, but is not limited to be done, by using the neural networks or other classification algorithms.
Other objects and advantages of the present invention will become apparent from the following description taken in connection with the accompanying drawings, wherein, by way of illustration and example, the aspects of the present invention are disclosed.
BRIEF DESCRIPTION OF DRAWINGS:
The present invention will be better understood after reading the following detailed description of the presently preferred aspects thereof with reference to the appended drawings, in which features, other aspects and advantages of certain exemplary embodiments of the invention will be more apparent from the accompanying drawings in which:
Figure 1 illustrates an architecture of working of the system.
Figure 2 illustrates a graph of the range left predicted vs actual via Linear Regression.
Figure 3 illustrates a graph of the range left predicted vs actual via Random Forest.
Figure 4 illustrates a graph of the range left predicted vs actual via Long Short-Term Memory (LSTM).
Figure 5 illustrates a graph of the range left predicted vs actual via Attention Long Short-Term Memory (LSTM).
DETAILED DESCRIPTION:
The following description describes various features and functions of the disclosed device and methods with reference to the accompanying figures. In the figures, similar symbols identify similar components, unless context dictates otherwise. The illustrative aspects described herein are not meant to be limiting. It may be readily understood that certain aspects of the disclosed system, method and apparatus can be arranged and combined in a wide variety of different configurations, all of which are contemplated herein.
These and other features and advantages of the present invention may be incorporated into certain embodiments of the invention and will become more fully apparent from the following

description and claims or may be learned by the practice of the invention as set forth hereinafter.
Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
The terms and words used in the following description and claims are not limited to the bibliographical meanings, but, are merely used to enable a clear and consistent understanding of the invention. Accordingly, it should be apparent to those skilled in the art that the following description of exemplary embodiments of the present invention are provided for illustration purpose only and not for the purpose of limiting the invention.
It is to be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.
It should be emphasized that the term "comprises/comprising" when used in this specification is taken to specify the presence of stated features, integers, steps or components but does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof.
In accordance with the present invention, a system for predicting the distance covered in remaining energy of the battery is disclosed, comprising: a device with a microcontroller; a computing unit, comprises: a plurality of input and output ports; a set of data; a battery; and a plurality of key performance indicators for predicting state of charge of the said battery; wherein the said collected data is fed to the said device by means of the said plurality of input ports to determine the historical and statistical features of the classes; transfers the data inputs to the neural network model which finally produces the output data received by means of the said plurality of output ports to estimate the said range; wherein the said types of collected data are: the detailed drive cycle data and the charging data from two wheelers; and the simulated data generated from the simulation model following manufactured driving patterns.
As per Figure 1 of the present invention, a method for predicting the distance covered in remaining energy of the battery is disclosed, comprising the steps of: collecting, a plurality of data by means of battery management system (BMS) for recording the data on drive cycles of the two wheelers; recognizing, a driving pattern for categorizing the user between a number of

classes; selecting, a plurality of parameters for the classification; using, a regression method based on the plurality of factors; and predicting, the remaining range of the said two wheelers; wherein the driving pattern classification can be done, but is not limited to be done, by using the neural networks or other classification algorithms.
As per Figure 2 of the present invention the graph of the range left predicted vs actual via Linear Regression is displayed in which the Linear Regression mean absolute error is 5.937946520744549.
As per Figure 3 of the present invention the graph of the range left predicted vs actual via Random Forest is displayed in which the Random Forest mean absolute error is 4.530999748188052.
As per Figure 4 of the present invention the graph of the range left predicted vs actual via Long Short-Term Memory (LSTM) is displayed in which the LSTM mean absolute error is 3.9772256768544514.
As per Figure 5 of the present invention the graph of the range left predicted vs actual via Long Short-Term Memory (LSTM) is displayed in which the Attention LSTM absolute error is 3.2600760440826417.

We Claim:

1. A system for predicting the distance covered in remaining energy of the battery, comprising:
a. a device with a microcontroller;
b. a computing unit, comprises:
i. a plurality of input and output ports;
c. a set of data;
d. a battery; and
e. a plurality of key performance indicators for predicting state of charge of the said
battery;
wherein the said collected data is fed to the said device by means of the said plurality of input ports to determine the historical and statistical features of the classes; transfers the data inputs to the neural network model which finally produces the output data received by means of the said plurality of output ports to estimate the said range;
wherein the said collected data can also determine the weakest cell in the battery and the driver behaviour by calculating the statistics of the user speed and acceleration.
2. The system for predicting the distance covered in remaining energy of the battery as claimed in claim 1, wherein the said types of collected data are: the detailed drive cycle data and the charging data from two wheelers; and the simulated data generated from the simulation model following manufactured driving patterns.
3. The system for predicting the distance covered in remaining energy of the battery as claimed in claim 1, wherein the battery used has a configuration of 13S10P which represent 13 cells in series and 10 cells in parallel with a nominal capacity of 2.6 Ah and voltage of 3.7 V.
4. The system for predicting the distance covered in remaining energy of the battery as claimed in claim 1, wherein the said collected data includes: the instantaneous voltage of cell, voltage, temperature and time.
5. The system for predicting the distance covered in remaining energy of the battery as claimed in claim 1, wherein the plurality of key performance indicators is the maximum error and the average error.

6. The system for predicting the distance covered in remaining energy of the battery as claimed in claim 1, wherein Possible regression algorithms can be, but are not limited to, Random Forest, Bonsai or Decision Tree.
7. A method for predicting the distance covered in remaining energy of the battery, the steps comprising of:
i. collecting, a plurality of data by means of battery management system (BMS) for recording the data on drive cycles of the two wheelers;
ii. recognizing, a driving pattern for categorizing the user between a number of classes;
iii. selecting, a plurality of parameters for the classification;
iv. using, a regression method based on the plurality of factors; and
v. predicting, the remaining range of the said two wheelers.
wherein the driving pattern classification can be done, by using the neural networks or other classification algorithms.
8. The method for predicting the distance covered in remaining energy of the battery as claimed in claim 7, wherein the driver is provided with Markov chain probabilities to switch between classes at every specific time interval based on the historical data and a probability distribution of classes can be computed on the basis of the historical data.
9. The method for predicting the distance covered in remaining energy of the battery as claimed in claim 7, wherein the training and the prediction steps can be carried out locally or remotely.