BACKGROUND
[0001] Embodiments of the present disclosure relate to predictive maintenance of an object and more particularly to system and method for a predictive failure of a rotating object.
[0002] Predictive failure is a technique which is designed to determine a condition of an object such as a motor, in order to predict a maintenance requirement for the object. Further, the predictive failure method is used to allow a scheduling of corrective maintenance for the object which helps in preventing unexpected failure of the object.
[0003] One approach to predict a failure of the object in a machine is through manual inspection and testing of the object with parameters such as winding resistance, direct current (DC) step response, surge or the like. Further, the inspection and testing of the object is done by disconnecting or removing a load from the object. Moreover, in such an approach, the object has to be inspected and tested at every pre-defined time interval by a user. Also, such system obstructs the continuous functioning of the object even when the object is functioning in a good condition and limits the functioning of the system. Hence such limitation leads to interference in the continuous functioning of the object and further reduces an efficiency of the object. Furthermore, due to involvement of the user, such system adds an additional cost to an organization and is prone to manual error.
[0004] In another type of approach, a predictive failure method is used to diagnose and maintain the object in a machine, in such system, a plurality of inputs is received from the object at different time intervals, which are used by a predictive failure system to detect a condition of the object when the object is in an early degradation stage. Further, on detecting condition of the object, steps can be taken to maintain the object from further degrading. However, in such systems, the degradation of the object is not in sync with the condition which was detected based on the plurality of inputs received as there is a delay between a current degradation of the object with the condition detected, which leads to inefficiency in the system. Further, such inefficiencies cause uncertainty in the system.
[0005] Hence there is a need of an improved system and method for a predictive failure of a rotating object to address the aforementioned issues.

BRIEF DESCRIPTION
[0006] In accordance with one embodiment of the disclosure, a method for predicting a failure of a rotating object is provided. The method includes obtaining at least two signals representative of at least two parameters measured by corresponding at least two sensors. The method also includes extracting one or more features from the at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters. The method further includes computing a health value representative of the one or more features. The method further includes computing an overall health of the rotating object based on a computed health value representative of the one or more features. The method further includes representing a computed overall health of the rotating object in a predefined zone on a display device. The method further includes predicting a failure time of the rotating object based on the computed overall health.
[0007] In accordance with another embodiment of the disclosure, a system for a predictive failure of a rotating object is provided. The system includes a first processing subsystem. The first processing subsystem is configured to obtain at least two signals representative of at least two parameters measured by corresponding at least two sensors. The first processing subsystem is also configured to extract one or more features from at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters. The system also includes a second processing subsystem operatively coupled to the first processing subsystem. The second processing subsystem is configured to compute a health value representative of the one or more features. The second processing subsystem is also configured to compute an overall health of the rotating object based on a computed health value representative of the one or more features. The second processing subsystem is further configured to represent a computed overall health of the rotating object in a predefined zone on a display device. The second processing subsystem is further configured to predict a failure time of the rotating object based on the computed overall health.
[0008] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered 1 irm^ngin scope. Jhe-jdisdqsuxe^ and detail with the appended figures.

BRIEF DESCRIPTION OF THE DRAWINGS
The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0009] FIG. 1 is a flow chart representing steps involved in a;method for predicting a failure of a rotating object in accordance with an embodiment of the present disclosure;
[0010] FIG. 2 is a block diagram representation of a system for a predictive failure of a rotating object in accordance with an embodiment of the present disclosure; and
[0011] FIG. 3 is a block diagram representation of an exemplary embodiment of system for a predictive failure of a rotating object of FIG. 2 for predicting a maintenance of a motor in accordance with an embodiment of the present disclosure.
[0012] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0013] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0014] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or

structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems., additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0016] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms "a", "an", and "the" include plural references unless the context clearly dictates otherwise.
[0017] Embodiments of the present disclosure relate to a system and method for a predictive failure of a rotating object. The method includes obtaining at least two signals representative of at least two parameters measured by corresponding at least two sensors. The method also includes extracting one or more features from the at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters. The method further includes computing a health value representative of the one or more features. The method further includes computing an overall health of the rotating object based on a computed health value representative of the one or more features. The method further includes representing a computed overall health of the rotating object in a predefined zone on a display device. The method further includes predicting a failure time of the rotating object based on the computed overall health.
[0018] FIG. 1 is a flow chart representing steps involved in a method (10) for predicting a
failure of a rotating object in accordance with an embodiment of the present disclosure. The
method (10) includes obtaining at least two signals representative of at least two parameters
measured by corresponding at least two sensors in step 20. In one embodiment, obtaining the
at least two signals representative of the at least two parameters measured by the corresponding
at least two sensors may include obtaining a combination of the at least two parameters of
rfl"rcW&ffe^^

[0019] In one embodiment, obtaining the at least two signals representative of the at least two parameters may include obtaining the at least two signals representative of the at least two parameters in a frequency domain. As used herein, the frequency domain refers to analysis of a mathematical function or a signal with respect to frequency. In one embodiment, obtaining the at least two signals may also include obtaining a corresponding at least two analog signals in a time domain. In another embodiment, a spectral analysis method is applied on the at least two signals representative of the at least two parameters obtained in the time domain to convert the at least two signals in the time domain to corresponding at least two signals representative of the at least two parameters in a frequency domain.
[0020] Furthermore, the method (10) includes extracting one or more features from the at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters in step 30. As used herein, feature extraction is a process of building derived values from an initial set of measured values. As used herein, the machine learning model is an application of artificial intelligence which provides an ability for a computer system to progressively learn with data without being explicitly programmed by a user. In one embodiment, the one or more features may be used to expand a signature library which may be based on active and incremental learning of the machine learning model.
[0021] In one embodiment, extracting the one or more features from the at least two signals may include extracting the one or more features from the at least two signals representative of the at least two parameters. In one embodiment, extracting the one or more features from the at least two signals representative of the at least two parameters may include extracting the one or more features of overload count, overheat count, high vibrational count, high pressure count, high current count, high rotational count or weighted vibration anomaly count from the at least two signals.
[0022] As used herein, the overload count defines a count which exceeds a predefined load count of the rotational object. Further, the overheat count is defined as a count of heat produced within the rotational object, wherein the count of the heat exceeds a pre-defined heat count. Also, the high vibrational count is defined as a vibrational count when the vibrations of the rotating object increases than a pre-defined vibrational count.
[0023] Furthermore, the high-pressure count is defined as a count of pressure exerted by the ' rotational object.wherein the_countof„the_pressure_exceeds-anre=definedJpressure-level-leading--

to the high pressure count. Also, the high current count is defined as a count of flow of current through the rotating object when the count of the current exceeds a pre-defined current count. Further, the high rotational count is defined as a count of number of rotations exerted by the rotating object when the count of the number of rotations exceeds a pre-defined rotational count. Furthermore, the weighted vibration anomaly count is defined as a count of a combination of a total frequency and the overall health of the rotating object when the combination exceeds a pre-defined weighted vibration anomaly.
[0024] The method (10) further includes computing a health value representative of the one or more features in step 40. In one embodiment, computing the health value representative of the one or more features may include generating the health value for the rotating object based on the one or more extracted features corresponding to the at least two signals representative of the at least two parameters. In one embodiment, the health value may represent a working condition of the rotating object which may be determined based on the at least two parameters.
[0025] Furthermore, the method (10) includes computing an overall health of the rotating object based on a computed health value representative of the one or more features in step 50. As used herein, the overall health of the rotating object or any machine is a level of functioning or efficiency of the machine to work in a desired manner.
[0026] in one embodiment, computing the overall health of the rotating object based on the computed health value representative of the one or more features may include computing a degradation state of the rotating object based on the computed health value representative of the one or more features. As used herein, degradation state of the rotating object is an act of lowering a performance or a condition of the rotating object.
[0027] The method (10) further includes representing a computed overall health of the rotating object in a predefined zone on a display device in step 60. In one embodiment, representing the computed overall health of the rotating objectiin the predefined zone on the display device may include representing the computed overall health of the rotating object in a predefined colour zone in an ascending order of the degradation of the rotating object. The predefined colour zone may depict a corresponding computed overall health of the rotating object.

[0028] In one embodiment, the health value may be a health index value. The health index value may be obtained by computing the one or more features with the at least two parameters. In such embodiment, the health index value may be calculated based on a relation given below:
Health Index value
= 1 - {(overload count + overheat count + high vibrational count. + high pressure count + high current count + high rotational count + weighted vibration anomaly count)/(total current observations + total temperature observations + total vibration observations + total pressure observations + total load weight observations + total rotations per minute observations)}
Wherein, weighted vibrational count = Z^oC^zone.i * nWd,()> wzone.i~ weight associated witS t0e predefined zone = l,
nvib,i
= number of observations of every frequency belonging to t(He predefined zone
= L
[0029] The method (10) further includes, predicting a failure time of the rotating object based on the computed overall health. In.one embodiment, predicting the failure time of the rotating object based on the computed overall health may include predicting the failure time of the rotating object based on the predefined colour zone which may be represented in the ascending order of the degradation of the rotating object.
[0030] Moreover, in one specific embodiment, the method (10) may include predicting a mean time to repair (MTTR) the rotating object and a mean time between failures (MTBF) of the rotating object based on a predicted failure time of the rotating object. As used herein, the mean time to repair is a measure of an average time required to repair a failed component or a failed device. Further, the mean time to failure is an expected time for an object to fail or degrade completely.
[0031 ] In another embodiment, the method (10) may also include predicting a maintenance of the rotating object based on the predicted failure time. In such embodiment, predicting the maintenance of the^^atjng^bjest basedo^—

a time at which the rotating object may require the maintenance to further operate in a healthy condition. In yet another embodiment, the method (10) may further include displaying the computed overall health and a predicted failure time as one or more graphs or one or more insights.
[0032] FIG. 2 is a block diagram representation of a system (80) for a predictive failure of a rotating object in accordance with an embodiment of the present disclosure. As used herein, the rotating object (90) is a kind of object which rotates in a circular movement around an axis or a centre of rotation of the object. In one embodiment, the rotating object (90) may be an induction motor, a servo motor, a turbine or a rotating shaft. Furthermore, the system (80) includes a first processing subsystem (100). The first processing subsystem (100) is configured to obtain at least two signals representative of at least two parameters measured by corresponding at least two sensors (110).
[0033] In one embodiment, the first processing subsystem (100) may be configured to obtain the at least two signals in the frequency domain. In another embodiment, the first processing subsystem (100) is configured to obtain the at least two signals representative of the at least two parameters in a time domain. Furthermore, the at least two signals may be transformed into a corresponding at least two signals in the frequency domain by applying a spectral analysis method on the at least two signals in the time domain. In one specific embodiment, the spectral analysis method may be applied on at least two signals representative of the vibrations caused in the rotating object to obtain one or more vibrational spectral quantities such as harmonics of acceleration of the rotating object, velocity of the rotating object and displacement of the rotating object.
[0034] In one embodiment, the at least two sensors (110) may include a combination of at least two of a current sensor, a temperature sensor, a vibration sensor, a pressure sensor, weight sensors or an accelerometer sensor, where the current sensor is configured to measure a current value, a temperature sensor is configured to measure a temperature value, a vibration sensor is configured to measure vibrations in the rotating object, the pressure sensor is configured to measure a pressure, the weight sensor is configured to measure a load weight, and the accelerometer configured to measure rotations per minute of the rotating object. In one embodiment, the at least two sensors (110) may be operatively coupled to one or more critical positions of the rotating object (90). As used herein, the one or more critical positions may be

defined as one or more locations on the rotating object (90) that provides most accurate measurements of the rotating objects (90).
[0035] Furthermore, the first processing subsystem (100) is also configured to extract one or more features from at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters. In one embodiment, the one or more features may include one or more of overload count, overheat count, high vibrational count, high pressure count, high current count, high rotational count or weighted vibration anomaly count. In such embodiment, the one or more features may be configured in a frequency domain.
[0036] In an exemplary embodiment, the first processing subsystem (100) may be operatively coupled to the rotating object through an edge gateway module. As used herein, the edge gateway is a virtual router configured to provide network services. Furthermore, the one or more features may be pre-processed in the edge gateway module and the one or more pre-processed features may be transmitted to a server. In one embodiment, the server may be a local server. In another embodiment, the server may be a remote server such as a cloud server.
[0037] Moreover, in one embodiment, the edge gateway module may detect one or more faults in the rotating object (90) and one or more detected faults may be displayed on the edge gateway module through a plurality of light emitting diodes (LEDs) which may be operatively coupled to the first processing subsystem (100). The LEDs may be configured to blink with a predefined frequency based on a level of one or more faults detected in the rotating object (90). The frequency of blinking of the LEDs may be employed to detect the one or more faults in the rotating object (90).
[0038] The system (80) also includes a second processing subsystem (120) operatively coupled to the first processing subsystem (100). In one embodiment, the second processing subsystem (120) may be communicatively coupled to the first processing subsystem (100) through a communication medium. In one embodiment, the communication medium may be a wired communication medium such as an Ethernet local area network (LAN). In another embodiment, the communication medium may be a wireless communication medium such as a wireless fidelity (Wi-Fi) medium, a Bluetooth medium or a Bluetooth low energy (BLE) medium.
[0039] Furthermore, the second processing subsystem (120) is conriyured-to-compute-a--g^e^lh^^'ue^ripreBentative^i^me' one or more features. In one embodiment, the second

processing subsystem (120) may generate a health value for the rotating object (90) which may be based on the one or more features. In one embodiment, the one or more features may be one or more of overload count, overheat count, high vibrational count, high pressure count, high current count, high rotational count or weighted vibration anomaly count in the frequency domain. In one embodiment, the health value may be a health index value. The health index value may be utilised to compute an overall health of the rotating object (90).
[0040] The second processing subsystem (120) is also configured to compute the overall health of the rotating object (90) based on a computed health value representative of the one or more features. In one embodiment, the overall health of the rotating object (90) may be a degradation state of the rotating object (90) which may be based on a based on a computed overall health of the rotating object (90).
[0041] The second processing subsystem (120) is further configured to represent the computed overall health of the rotating object (90) in a predefined zone on a display device (130). In one embodiment, the computed overall health of the rotating (90) object may be represented in a predefined colour zone depicting a corresponding computed overall health of the rotating object (90). In one embodiment, the predefined colour zone may be represented on at least one light emitting diode (LED), wherein the LED may be operatively coupled to the second processing subsystem (120). In one specific embodiment, the predefined colour zone may include a green zone, a yellow zone, an orange zone and a red zone representing a degradation value of the rotating object (120) in an ascending order of the degradation value respectively. More specifically, the green zone may represent a least degradation value of the rotating object (90) or may represent that the rotating object (90) is in good working condition. Furthermore, the red zone may represent a highest degradation value of the rotating object (90) or may represent that the rotating object (90) is in bad working condition. In such embodiment, the degradation value of rotating object (90) may not descent from the red zone to the green zone until the rotating object (90) undergoes maintenance.
[0042] The second processing subsystem (120) is further configured to predict a failure time of the rotating object (90) based on the computed overall health. In one embodiment, the second processing subsystem (120) may also be configured to predict predicting a mean time to repair (MTTR) for the rotating object (90) based on a predicted failure time and the predicted overall ^health^oLthe^rcaagn
(120) may further be configured to predict a mean time between failures (MTBF) of the rotating

object (90) based on a predicted failure time of the rotating object (90) based on the predicted failure time and the predicted overall health of the rotating object (90). In one specific embodiment, the processing subsystem (120) may be configured to predict a maintenance of the rotating object (90) based on the predicted failure time of the rotating object (90).
[0043] Moreover, in one specific embodiment, the system (80) may include a display module which may be operatively coupled to the second processing subsystem (120). The display module may be configured to display the computed overall health and a predicted failure time as one or more insights or one or more graphs. In one embodiment, the display module may be a visualisation engine, which may be operatively coupled to the second processing subsystem (120). The visualisation engine may be configured to display a plurality of quantities such as the overall health, the one or more detected faults, the at least two parameters in real-time.
[0044] FIG. 3 is a block diagram representation of an exemplary embodiment of system for a predictive failure of a rotating object of FIG. 2 for predicting a maintenance of a motor in accordance with an embodiment of the present disclosure. The motor (140) is operatively coupled with a plurality of sensors (145) configured to sense a plurality of parameters, wherein the plurality of sensors (145) includes a current sensor (150) configured to sense current flow in the motor (140), a temperature sensor (160) configured to sense temperature generated by the motor (140) and a vibrational sensor (170) configured to sense vibrations generated by the motor (140). Further, the plurality of sensors (145) is substantially similar to at least two sensors (110) of FIG.2. Further, the plurality of sensors (145) is operatively coupled to one or more critical positions of the motor (140) to monitor functioning of the motor (140) and to predict a failure time of the motor (140).
[0045] Moreover, the plurality of signals sensed by the corresponding plurality of sensors (145) is analogue signals which are converted to digital signal by a processor. Further, a plurality of digital signals is transmitted to a system (180) for further processing and prediction of failure time of the motor (140), wherein the system (180) is substantially similar to a system (80) of FIG. 2. Further, the system (180) includes an edge gateway module (190), wherein the edge gateway module (190) includes a first processing subsystem (200). The edge gateway module (190) is communicatively coupled to a cloud server (220) through a communication
wherein the first processing subsystem (200) and the second processing subsystem (230) are

substantially similar to a first processing subsystem (100) and a second processing subsystem (120) of FIG. 2 respectively.
[0046] Furthermore, the plurality of digital signals is pre-processed by a first processing subsystem (200). In some embodiments, the plurality of digital signals obtained is in a time domain. Such plurality of digital signals in the time domain are converted to a corresponding plurality of digital signals in a frequency domain by applying a spectral analysis method on the plurality of digital signals in time domain. Further, the plurality of digital signals in the frequency domain is transmitted to a cloud server (220) for analysing the plurality of signals to predict a failure time of the motor (140).
[0047] Furthermore, the first processing subsystem (200) may detect a fault in the motor (140) which may need an immediate attention by an operator. In such a condition, a plurality of light emitting diodes (LEDs) which is operatively coupled to the edge gateway module (190) starts blinking in order to grab the operator's attention. In one embodiment, the edge gateway module (190) may be operatively coupled with an alarm along with the LED's to generate an alert notification to the operator regarding the fault which was detected by the first processing subsystem (200).
[0048] Further, the plurality of signals in frequency domain is subjected to feature extraction method. Further, one or more features are extracted from the plurality of signals using machine learning model, wherein the one or more features include total current observations, total temperature observations and total vibration weights. Further, the one or more features extracted are computed by the second processing subsystem to determine a health index value representative of the one or more features. The health index value is determined using a relation as shown below:

[0049] Furthermore, based on the health index value of the motor (140), an overall health of the motor (140) is predicted by the second processing subsystem (230). Further, the overall health of the motor (140) is represented on a visualization device (240) in a predefined colour zone. If the overall health of the motor (140) was found to be maximum degraded, the overall health of the motor (140) is represented on a red zone on the visualization engine (240). Further, if the overall health of the motor (140) is found to be least degraded, the overall health of the motor (140) is represented on a green zone on the visualization engine (240).
[0050] Also, the second processing subsystem (230) predicts the failure time of the motor (140) based on the predicted overall health of the motor (140). Further, the second processing subsystem (240) predicts a maintenance time for the motor (140) based on the predicted failure time of the motor (140). Moreover, based on the overall health of the motor (140) and a predicted failure time of the motor (140), a mean time to repair (MTTR) for the motor (140) and a mean time between failures (MTBF) of the motor (140) is predicted. Also, a predicted MTTR, the MTBF, the failure time and the maintenance for the motor (140) is displayed on the visualization engine (240) in real-time in a form of a graph or an insight.
[0051] Various embodiments of the system for a predictive failure of a rotating object enable the system to predict an overall health of the rotating object in real time and hence predicts the time of failure of the rotating object without obstructing the functioning of the rotating object. Hence the efficiency of the system is well maintained. Since the system works on real time, examination of the rotating object by an operator is not required, hence saves the time of the operator and makes the system cost effective.
[0052] Also, the failure time of the rotating object detected by the system is in sync with the degradation level of the rotating object. Henceforth reducing the delay between the failure prediction time and the degradation time of the rotating object. Further, the system helps to enable effective plan and conduct maintenance of the rotating object well ahead of time before the actual failure of the rotating object.
[0053] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0054] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependant on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

We Claim:
1. A method (10) for predicting a failure of a rotating object comprising:
obtaining at least two signals representative of at least two parameters measured by corresponding at least two sensors; (20)
extracting one or more features from the at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters; (30)
computing a health value representative of the one or more features; (40)
computing an overall health of the rotating object based on a computed health value representative of the one or more features; (50)
representing a computed overall health of the rotating object in a predefined zone on a display device; and (60)
predicting a failure time of the rotating object based on the computed overall health. (70)
2. The method (10) as claimed in claim 1, wherein obtaining the at least two signals representative of the at least two parameters measured by the corresponding at least two sensors (in step 20) comprises obtaining a combination of the at least two parameters of current, temperature, vibration, pressure, load weight, or rotations per minute.
3. The method (10) as claimed in claim 1, wherein obtaining the at least two signals representative of the at least two parameters measured by the corresponding at least two sensors (in step 20) comprises obtaining the at least two signals representative of the at least two parameters in a frequency domain.
4. The method (10) as claimed in claim 3, wherein obtaining the at least two signals representative of the at least two parameters in a frequency domain further comprises:
obtaining at least two signals representative of the at least two parameters in a time domain;

applying a spectral analysis method on the at least two signals representative of the at least two parameters of the time domain;
generating a corresponding at least two signals representative of the at least two parameters in a frequency domain;
applying feature extraction method on at least two generated signals representative of the at least two parameters in the frequency domain; and
extracting one or more features from the at least two signals representative of the at least two parameters in the frequency domain based on the machine learning model.
5. The method (10) as claimed in claim 4, wherein extracting the one or more features from the at least two signals representative of the at least two parameters in the frequency domain based on the machine learning model comprises extracting the one or more features of overload count, overheat count, high vibrational count, high pressure count, high current count, high rotational count or weighted vibration anomaly count in the frequency domain.
6. The method (10) as claimed in claim 1, wherein computing the overall health of the rotating object based on the computed health value representative of the one or more features (in step 50) comprises computing a degradation state of the rotating object based on the computed health value representative of the one or more features.
7. The method (10) as claimed in claim t, wherein representing the computed overall health of the rotating object in the predefined zone on the display device (in step 60) comprises representing the computed overall health of the rotating object in a predefined colour zone depicting a corresponding computed overall health of the rotating object.
8. The method (10) as claimed in claim 1, further comprises predicting a mean time to repair (MTTR) for the rotating object and a mean time between failures (MTBF) of the rotating object based on a predicted failure time of the rotating object.
9. The method (10) as claimed in claim 1, further comprises predicting a maintenance of the rotating object based on the predicted failure time.
10. A system (80) for a predictive failure of a rotating object (90) comprising:
a first processing subsystem (100) configured to:

obtain at least two signals representative of at least two parameters measured by corresponding at least two sensors (110);
extract one or more features from at least two signals based on a machine learning model from the at least two signals representative of the at least two parameters;
a second processing subsystem (120) operatively coupled to the first processing subsystem, and configured to:
compute a health value representative of the one or more features;
compute an overall health of the rotating object (90) based on a computed health value representative of the one or more features;
represent a computed overall health of the rotating object (90) in a predefined zone on a display device (130); and
predict a failure time of the rotating object (90) based on the computed overall health.