TECHNICAL FIELD OF THE INVENTION
The disclosure relates to monitoring electrical equipment, and, more specifically, to systems and methods for fault precursor detection in electrical equipment.
BACKGROUND OF THE INVENTION
Industrial electrical equipment, such as electrical motors, electrical generators, and transformers represent valuable assets for customers. During operation, the electrical equipment may experience failures. Some commonly observed failures may include a stator inter-turn fault, bearing fault, broken rotor bar, and so forth. The failures may lead to unexpected outages, repair, and replacement of the electrical equipment. Timely detection of failures or a fault precursor in the industrial electrical equipment may provide valuable insight into health of components of the electrical equipment to improve reliability and efficiency of the electrical equipment, increase production capacity of the components of the electrical equipment, and avoid unexpected costs in their maintenance. Conventional solutions for detection of faults in electrical equipment may include analyzing the signals representing operational parameters of the electrical equipment in a frequency domain. A Fast Fourier transform or a wavelet transformation can be used to transform the signal from a time domain into the frequency domain. Detection of faults may include monitoring amplitude of the signal in the frequency domain at certain frequency bands. However, conventional solutions require knowledge of frequency bands to be monitored for a specific failure of the electrical equipment. Furthermore, conventional solutions need to determine correspondence between a change in amplitude at the selected frequency and the specific failure.
BRIEF DESCRIPTION OF THE INVENTION
This disclosure relates to systems and methods for fault precursor detection in electrical equipment. Some embodiments of the disclosure may facilitate early

prediction of failures of the electrical equipment using signal representing an operational parameter, for example a current signal.
According to one embodiment of the disclosure, a system for fault precursor detection in electrical equipment is provided. The system may include electrical equipment. The system may further include a data acquisition device. The data acquisition device can be configured to acquire a sampled signal. The sampled signal may represent time series of at least one operational parameter associated with the electrical equipment. The system may further include an equipment controller communicatively coupled to the data acquisition device. The equipment controller may be configured to define an embedding dimension (D). The equipment controller may be further configured to generate, based on the D, permutation patterns. The equipment controller may be further configured to determine occurrences of the permutation patterns in a window of the sampled signal. The equipment controller may be further configured to calculate, based on the occurrences of permutation patterns, a permutation entropy for the window. The equipment controller may be further configured to determine that the permutation entropy exceeds a pre-defined normal value by a pre-determined threshold. The equipment controller may be further configured to provide, based on the determination, at least one message concerning at least one event associated with the electrical equipment.
In some embodiments of the disclosure, the equipment controller can be further configured to compute a set of permutations of D cardinal numbers. The equipment controller can be further configured to associate elements of the set of permutations with corresponding permutation patterns.
In some embodiments of the disclosure, the D can be defined based on a sampled rate of the sampled signal.
In some embodiments of the disclosure, the equipment controller can be further configured to determine a sum of occurrences of the permutation patterns. The equipment controller can be further configured to determine, based on the occurrences and the sum of occurrences, relative occurrences of the permutation

patterns. The equipment controller can be further configured to calculate, based
on the relative occurrences, the permutation entropy.
In some embodiments of the disclosure, the electrical equipment may include one
or more of the following: an electrical rotating machine, a transformer, a blower, a
compressor, a cooling tower, and a heat exchanger.
In some embodiments of the disclosure, at least one operational parameter may
include one or more of the following: a phase of a current, a phase of a voltage, a
power, speed data, and vibrational data.
In some embodiments of the disclosure, at least one event associated with the
electrical equipment may include one of an electrical fault or a mechanical fault
associated with the electrical equipment.
In some embodiments of the disclosure, the pre-determined normal value and the
pre-determined threshold can be determined based on historical data for
permutation entropy collected for the electrical equipment.
In some embodiments of the disclosure, the equipment controller, in response to
determination that the permutation entropy exceeds the pre-determined normal
value by the pre-determined threshold, can be further configured to analyze the
occurrences of permutation patterns to determine a distribution of the permutation
patterns. The equipment controller can be further configured to associate the
distribution of permutation patterns with at least one event associated with the
electrical equipment.
In some embodiments of the disclosure, the equipment controller, in response to
determination that the permutation entropy exceeds the pre-determined normal
value by the pre-determined threshold, can be further configured to determine at
least one first permutation pattern. The first permutation pattern may have a
maximum increase in occurrence from a first normal value. The equipment
controller can be further configured to determine at least one second permutation
pattern. The second permutation pattern having a maximum decrease in
occurrence from a second normal value. The equipment controller can be further
configured to associate at least one first permutation pattern and at least one
second pattern with at least one event associated with electrical equipment.

According to one embodiment of the disclosure, a method for fault precursor detection in electrical equipment is provided. An example method may include providing, by a data acquisition device communicatively coupled to an electrical equipment, a sampled signal. The sample signal may represent a time series of at least one operational parameter associated with the electrical equipment. The method may further include defining, by an equipment controller communicatively coupled to the data acquisition device, an embedding dimension (D). The method may further include generating, by the equipment controller and based on the D, permutation patterns. The method may further allow determining, by the equipment controller, occurrences of the permutation patterns in a window of the sampled signal. The method may further include calculating, by the equipment controller and based on the occurrences of permutation patterns, a permutation entropy for the window. The method may further include determining, by the equipment controller, that the permutation entropy exceeds a pre-defined normal value by a pre-determined threshold. The method may further include providing, by the equipment controller and based on the determination, at least one message concerning at least one event associated with the electrical equipment.
Other embodiments, systems, methods, features, and aspects will become apparent from the following description taken in conjunction with the following drawings.
BRIEF DESCRIPTION OF THE DRAWINGS OF THE INVENTION
FIG. 1 is a block diagram illustrating an example system in which certain methods
of fault precursor detection in electrical equipment can be implemented, according
to some embodiments of the disclosure.
FIG. 2A is a schematic showing a set of permutation patterns, according to certain
example embodiments of the disclosure.
FIG. 2B is a plot of a sampled signal, according to certain example embodiments
of the disclosure.
FIG. 3 is an example plot of permutation entropy, according to certain example
embodiments of the disclosure.

FIG. 4 is a flow chart of an example method of fault precursor detection in electrical equipment, according to certain example embodiments of the disclosure. FIG. 5 is a flow chart of an example method of fault precursor detection in electrical equipment, according to certain example embodiments of the disclosure. FIG. 6 is a block diagram illustrating an example controller for analyzing operational parameters of electrical equipment, according to certain example embodiments of the disclosure.
DETAILED DESCRIPTION
The following detailed description includes references to the accompanying drawings, which form part of the detailed description. The drawings depict illustrations, in accordance with example embodiments. These example embodiments, which are also referred to herein as "examples," are described in enough detail to enable those skilled in the art to practice the present subject matter. The example embodiments may be combined, other embodiments may be utilized, or structural, logical, and electrical changes may be made, without departing from the scope of the claimed subject matter. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope is defined by the appended claims and their equivalents.
Certain embodiments of the disclosure can include systems and methods for fault precursor detection in electrical equipment. The electrical equipment may include electrical motors, electrical generators, transformers, blowers, compressors, cooling towers, heat exchangers, and so forth. Some embodiments of the disclosure may be applied to any power plant, and more specifically to a combined cycle plant, wherein a number of electrical motors is significant as compared to a simple cycle plant.
The disclosed systems and methods may provide an automatic procedure for collecting and analyzing high speed operational data of electrical equipment. Some embodiments of the disclosure may facilitate early detection anomalies or failures in electrical equipment before the failure happens. Some embodiments of the disclosure utilize symbolic dynamics based algorithms to analyze the high speed

operational data to detect precursors to failure of electrical equipment, which may allow customers to take action with regard to the electrical equipment and prevent and/or minimize damage.
In some example embodiments of the disclosure, a method of fault precursor detection in electrical equipment may include providing, by a data acquisition device communicatively coupled to an electrical equipment, a sampled signal. The sample signal may represent a time series of at least one operational parameter associated with the electrical equipment. The method may further include defining, by an equipment controller communicatively coupled to the data acquisition device, an embedding dimension (D). The method may further include generating, by the equipment controller and based on the D, permutation patterns. The method may further allow determining, by the equipment controller, occurrences of the permutation patterns in a window of the sampled signal. The method may further include calculating, by the equipment controller and based on the occurrences of permutation patterns, a permutation entropy for the window. The method may further include determining, by the equipment controller, that the permutation entropy exceeds a pre-defined normal value by a pre-determined threshold. The method may further include providing, by the equipment controller and based on the determination, at least one message concerning at least one event associated with the electrical equipment.
Technical effects of certain embodiments of the disclosure may include eliminating a manual process of monitoring and diagnostics of electrical equipment. Further technical effects of certain embodiments of the disclosure may provide insight into one or more components of electrical equipment in order to improve reliability of the components. Further technical effects of certain embodiments of the disclosure may prevent and/or minimize physical damage of the electrical equipment and reduce maintenance costs. Yet further technical effects of certain embodiments of the disclosure may allow a reduction in unplanned shutdowns, forced outage time, and unplanned expenses.
The following provides a detailed description of various example embodiments related to systems and methods of fault precursor detection in electrical equipment.

Turning now to the drawings, FIG. 1 is a block diagram illustrating a system 100, in accordance with an example embodiment of the disclosure. The system 100 may include an electrical equipment 110, a data acquisition device 150, and an equipment controller 600. In an example embodiment of the disclosure, the equipment controller 600 is shown to as part of system 100. In other embodiments of the disclosure, the equipment controller 600 may be located remote with respect to the system 100.
In various embodiments of the disclosure, the electrical equipment 110 may include an electrical rotating machine, such as electrical generator or an electrical motor, a transformer, a blower, a compressor, a cooling tower, a heat exchanger, and so forth. In operation, the electrical equipment may experience electrical and mechanical faults. The faults may include short circuits, insulation breakdowns between winding and earth, insulation breakdown between different phases, cooling medium failure, tap changing fault, bearing faults, loose foundations, eccentricity of a rotating shaft, and misalignment of the rotating shaft, and so forth. In various embodiments of the disclosure, the data acquisition device 150 may be configured to receive and digitize at least one operational parameter associated with the electrical equipment 110. In some embodiments of the disclosure, the operational parameter may include a phase of an electrical current or a phase of voltage associated with the electrical equipment 110. In further embodiments of the disclosure, the operational parameter may include thermal data or electromechanical data associated with the electrical equipment 110. In certain embodiments of the disclosure, the operational parameter may include speed data and vibrational data associated with the electrical equipment 110. In various embodiments of the disclosure, equipment controller 600 may be configured to receive, via the data acquisition device 150, and analyze operational parameters associated with the electrical rotating machine 110. In some embodiments of the disclosure, the equipment controller 600 may be configured to detect, based at least on the operational data, one or more fault precursor in the electrical equipment 110. In certain embodiments, the equipment controller 600 may be further configured to provide, based on an identified fault precursor, alerts

concerning condition of the electrical equipment. In some embodiments of the disclosure, the equipment controller 600 may be also configured to generate commands (opening or closing) for protection relays and circuit breakers. In some embodiments of the disclosure, the equipment controller 600 may also be configured to facilitate operation of one or more components associated with operation of the electrical equipment.
In some embodiments of the disclosure, the equipment controller 600 may receive a sampled signal representing an operational parameter associated with the electrical equipment. The signal may be sampled at a pre-defined sampled rate. The equipment controller 600 may be configured to compute a permutation entropy for a window of the sampled signal. In certain embodiments, the length of the window is one second.
In some embodiments of the disclosure, the permutation entropy can be calculated based on occurrences of permutation patterns in the window of sampled signal. Each of the permutation patterns can be associated with relative positions of amplitudes corresponding to a pre-defined number (D) subsequent data points in the sampled signal. Total number of possible permutation patterns can be equal to a factorial of D (D!). The pre-defined number D, also referenced as an embedding dimension D, can be selected as a maximum X for which X! is less than a number of samples in the window of the sampled signal, the number of samples in the window being determined by the sampled rate of the sampled signal. FIG. 2A shows an example set 200A of permutation patterns, according to an example embodiment. In the example of FIG. 2A, the embedding dimension D is equal to three, resulting in a total of six permutation patterns. In the example of the first permutation pattern, (1, 2, 3) may correspond to those three subsequent data points in the sampled signal, wherein the amplitude of the first data point is less than the amplitude of the second data point, and the amplitude of the second data point is less than the amplitude of the third data point. Similarly, the second permutation pattern (1, 3, 2) may correspond to those three subsequent data points in the sampled signal, wherein the amplitude of the first data point is less than the amplitude of the second data point and amplitude of the third data point, but the

amplitude of the second data point is greater than the amplitude of the third data
point.
FIG. 2B shows a plot 200B of a sampled signal 202, according to an example
embodiment of the disclosure. The signal 202 may represent one of operational
parameters associated with the electrical equipment 110.
In FIG. 2B, X-axis represents a sample time. Y-axis represents the sampled signal
amplitude. Reference number 204 represents a sliding window. The length of the
sliding window 204 is characterized by the embedding dimension D. The sliding
window 204 can be used to select an array of data points from the sampled signal
202. In example of FIG. 2B, the sliding window 204 is characterized by a length
equal to an embedding dimension (D) of three samples. Accordingly, there are D!
or six possible patterns that may be generated with the three time stamps, as shown
in FIG. 2A.
When the sliding window 204 is placed at a first position 206 on the signal 202,
three subsequent data points 208, 210, 212 in a portion of the sampled signal 202
overlap the sliding window 204. In the example illustrated by FIG 2A, the data
points 208, 210, and 212 form the first permutation pattern (1, 2, 3) shown in FIG.
2A.
Thereafter, the sliding window 204 can be shifted by one data point to a subsequent
position 214. Three subsequent data points 210, 212, and 216 in a portion of the
signal 202 that overlap with the sliding window 204 positioned at the subsequent
position 214 may form the fourth pattern (2, 3, 1) shown in FIG 2A. The sliding
window 204 may be further shifted along the signal 204 until each data point of the
window of the signal 204 forms a part of at least one pattern.
In some embodiments of the disclosure, the occurrences of the permutation patterns
in a window of the sampled signal can be counted by performing some or all of the
following operations:
(1) determining, for an array of D subsequent points in the window of the sampled
signal, relative positions of amplitudes corresponding to the D subsequent points;
(2) matching the relative positions of amplitudes to a specific pattern from the
permutation patterns;

(3) increasing based on the matching, an occurrence of the specific pattern by one;
(4) continuously shifting the array of the D subsequent points by one point along
the window; and
(5) repeating the operations (1), (2), (3) and (4) until the end of the window is
reached.
After counting occurrences of the permutation patterns in the window, the equipment controller 600 can be configured to calculate relative occurrences of the permutation patterns. A relative occurrence of a permutation pattern can be defined as occurrence of the permutation pattern divided by a sum of occurrences of permutation patterns counted in the window.
In some embodiments of disclosure, the equipment controller 600 can be further configured to calculate a permutation entropy (PE) for the window of the sampled signal. In certain embodiments, the permutation entropy can be determined using a
Shannon formula PE = —ZL- , wherein p(n) is a relative occurrence of a
log2D! ' KV J
pattern n and D is the embedding dimension. In other embodiments, the permutation entropy can be calculated by other methods, such as the Renyi permutation entropy method and the permutation mini-entropy method. In some embodiments of the disclosure, the equipment controller 600 can be configured to determine a change in the permutation entropy value from a pre¬determined normal value. The change can be indicative of an impending fault of the electrical equipment 110. In some embodiments, the equipment controller 600 may be further configured to determine that the change exceeds a pre-determined threshold. If the change exceeds the pre-determined threshold, the equipment controller 600 can be configured to issue an alert message regarding the change in the permutation entropy, which may be indicative of a fault in the electrical equipment 110. In certain instances, the equipment controller 600 can be configured to facilitate operation of one or more components associated with electrical equipment, such as opening and/or closing any combination of protection relays and/or circuit breakers. The pre-determined normal value of the permutation

entropy and the pre-determined threshold can be determined based on historical data for permutation entropy collected for the electrical equipment. FIG. 3 is a plot 300 of permutation entropy 302, according to an example embodiment of the disclosure. The permutation entropy 302 is calculated based on a sample signal representing a current of an electrical motor. In the example shown in FIG. 3, the permutation entropy 302 changes sharply from value Pi to value P2 for a window of the sample signal located at 20th second of the sample time. The change may be indicative of a fault in the electrical motor. In some embodiments of the disclosure, if the change of permutation entropy exceeds the pre-determined threshold, the equipment controller 600 may be further configured to analyze the occurrences of permutation patterns. In some embodiments of the disclosure, a distribution of permutation patterns can be determined. The distribution of the occurrences of permutation patterns can be used to determine a type of impending fault in the electrical equipment 110. The specific distribution of occurrences of permutations associated with a specific fault in electrical equipment can be determined, preliminary, based on historical data of occurrences of permutation patterns collected for the electrical equipment. In some embodiments of the disclosure, the equipment controller 600 may be configured to track changes of occurrences of patterns when the permutation entropy deviates from the pre-determined normal value by the pre-determined threshold. The equipment controller 600 may be configured to determine patterns having a maximum increase of occurrence or patterns having a maximum decrease of occurrence from a normal value. In certain embodiments, a specific fault in the electrical equipment can be determined based on the patterns having the maximum increase or the maximum decrease of occurrence from a normal value. The specific fault can be associated, preliminary, with changes in occurrences of specific permutation patterns based on historical data of occurrences of permutation patterns collected for the electrical equipment. In the example illustrated by FIG. 3, the analysis of the patterns contributing to an increase or decrease in occurrences of the permutation patterns can confirm that the increase in the permutation entropy can be caused by an inter-turn fault in the winding of the electrical motor.

FIG. 4 is a flow chart illustrating an example method 400 for fault precursor
detection in electrical equipment, according to some embodiments of the disclosure.
The method 400 can be implemented, for example, by system 100 described above
with reference to FIG. 1.
In block 402, the method 400 may commence with providing, by a data acquisition
device 150 communicatively coupled to an electrical equipment 110, a sampled
signal. The sampled signal may represent a time series of at least one operational
parameter associated with the electrical equipment 110.
In block 404, the method 400 may include defining, by an equipment controller 600
communicatively coupled to the data acquisition device 150, an embedding
dimension (D). In some embodiments, D can be selected based on sample rate of
the sampled signal, which is a number in samples in one second window of the
sampled signal. In certain embodiments, D = max X, such that X! < N, wherein N
is the number of samples in one second window of the sampled signal.
In block 406, the method 400 may include generating, by the equipment controller
600 and based on the D, permutation patterns. In some embodiments, the
permutation patterns may include elements of a set of permutations of numbers
from 1 to D.
In block 408, the method 400 may include determining, by the equipment controller
600, occurrences of the permutation patterns in a window of the sampled signal. In
some embodiments, a permutation pattern may be found in the window of the
sampled signal if the permutation pattern matches relative position of amplitudes of
D subsequent data points in the window of the sampled signal.
In block 410, the method 400 may include calculating, by the equipment controller
600 and based on the occurrences of permutation patterns, a permutation entropy
for the window. In block 412, the method 400 may include determining, by the
equipment controller 600, that the permutation entropy exceeds a pre-defined
normal value by a pre-determined threshold. In block 414, the method 400 may
include providing, by the equipment controller 600 and based on the determination,
at least one message concerning at least one event associated with the electrical
equipment.

FIG. 5 is a flow chart illustrating an example method 500 for fault precursor detection in electrical equipment, according to some example embodiments of the disclosure. The method 500 may provide additional details for block 414 of the method 400. The blocks of the method 500 may be performed after determination that the permutation entropy exceeds the pre-defined normal value by the pre-defined threshold.
In block 502, the method 500 may include analyzing, by the equipment controller 600, occurrences of permutation patterns to determine a distribution of the permutation patterns. In block 504, the method 500 may include determining, by the equipment controller 600, at least one first permutation pattern having maximum increase of occurrence from a first normal value. In block 506, the method 500 may include determining, by the equipment controller 600, at least one second permutation pattern having a maximum decrease of concurrence with a second normal value.
In block 508, the method 500 may include associating, by the equipment controller 600, one of distribution of the permutation pattern, the first permutation pattern, or the least one second permutation pattern with the event associated with the electrical equipment. The event may include a specific fault of the electrical equipment 110. The specific fault may include an electrical fault or a mechanical fault.
FIG. 6 depicts a block diagram illustrating an example controller 600, in accordance with an embodiment of the disclosure. More specifically, the elements of the controller 600 may be used to collect and analyze operational parameters associated with the electrical equipment 110. The controller 600 may include a memory 610 that stores programmed logic 620 (e.g., software) and may store data 630, such as operational data associated with the equipment controller 110, the set of constants, and the like. The memory 610 also may include an operating system 640.
A processor 650 may utilize the operating system 640 to execute the programmed logic 620, and in doing so, may also utilize the data 630. A data bus 660 may provide communication between the memory 610 and the processor 650. Users

may interface with the controller 600 via at least one user interface device 670, such as a keyboard, mouse, control panel, or any other device capable of communicating data to and from the controller 600. The controller 600 may be in communication with the system 100 while operating via an input/output (I/O) interface 680. Additionally, it should be appreciated that other external devices or multiple other systems or intelligent electronic devices (TEDs) may be in communication with the controller 600 via the I/O interface 680. Further, the controller 600 and the programmed logic 620 implemented thereby may include software, hardware, firmware, or any combination thereof. It should also be appreciated that multiple controllers 600 may be used, whereby different features described herein may be executed on one or more different controllers 600. References are made to block diagrams of systems, methods, apparatuses, and computer program products, according to example embodiments of the disclosure. It will be understood that at least some of the blocks of the block diagrams, and combinations of blocks in the block diagrams, may be implemented at least partially by computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, special purpose hardware-based computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functionality of at least some of the blocks of the block diagrams, or combinations of blocks in the block diagrams discussed.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in the block or blocks. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operations and/or acts to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the

computer or other programmable apparatus provide operations and/or acts for implementing the functions specified in the block or blocks.
One or more components of the systems and one or more elements of the methods described herein may be implemented through an application program running on an operating system of a computer. They also may be practiced with other computer system configurations, including hand-held devices, multiprocessor systems, microprocessor based or programmable consumer electronics, mini-computers, mainframe computers, and the like.
Application programs that are components of the systems and methods described herein may include routines, programs, components, data structures, and so forth that implement certain abstract data types and perform certain tasks or actions. In a distributed computing environment, the application program (in whole or in part) may be located in local memory or in other storage. In addition, or alternatively, the application program (in whole or in part) may be located in remote memory or in storage to allow for circumstances where tasks are performed by remote processing devices linked through a communications network. Many modifications and other embodiments of the example descriptions set forth herein to which these descriptions pertain will come to mind having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Thus, it will be appreciated that the disclosure may be embodied in many forms and should not be limited to the example embodiments described above. Therefore, it is to be understood that the disclosure is not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

We claim:
1. A system comprising:
an electrical equipment;
a data acquisition device configured to acquire a sampled signal representing at least one operational parameter, the at least one operational parameter being associated with the electrical equipment; and
an equipment controller communicatively coupled to the data acquisition device, the equipment controller configured to:
define an embedding dimension (D);
generate, based on the D, permutation patterns;
determine occurrences of the permutation patterns in a window of the sampled signal;
calculate, based on the occurrences of permutation patterns, a permutation entropy for the window;
determine that the permutation entropy exceeds a pre-defined normal value by a pre-determined threshold; and
provide, based on the determination, at least one message concerning at least one event associated with the electrical equipment.
2. The system as claimed in claim 1, wherein the equipment controller
configured to generate permutation patterns is further configured to:
compute a set of permutations of D cardinal numbers; and associate elements of the set of permutations with corresponding permutation patterns.
3. The system as claimed in claim 1, wherein the D is defined based on a
sampled rate of the sampled signal.

4. The system as claimed in claim 1, wherein the equipment controller
configured to determine the permutation entropy is further configured to:
determine a sum of occurrences of the permutation patterns; determine, based on the occurrences and the sum of occurrences, relative occurrences of the permutation patterns; and
calculate, based on the relative occurrences, the permutation entropy.
5. The system as claimed in claim 1, wherein the electrical equipment
includes one or more of the following: an electrical rotating machine, a
transformer, a blower, a compressor, a cooling tower, and a heat exchanger.
6. The system as claimed in claim 1, wherein the at least one operational
parameter includes one or more of the following: a phase of a current, a phase of a
voltage, a power, speed data, and vibrational data.
7. The system as claimed in claim 1, wherein the at least one event includes
one of an electrical fault or a mechanical fault associated with the electrical
equipment.
8. The system o as claimed in claim 1, wherein the pre-determined normal
value and the pre-determined threshold are determined based on historical data for
permutation entropy collected for the electrical equipment.
9. The system as claimed in claim 1, wherein the equipment controller, in
response to determination that the permutation entropy exceeds the pre¬
determined normal value by the pre-determined threshold, is further configured to:
analyze the occurrences of permutation patterns to determine a distribution of the permutation patterns; and
associate the distribution of permutation patterns with the at least one event associated with the electrical equipment.

10. The system as claimed in claim 1, wherein the equipment controller, in
response to determination that the permutation entropy exceeds the pre¬
determined normal value by the pre-determined threshold, is further configured to:
determine at least one first permutation pattern, the at least one first permutation pattern having a maximum increase in occurrence from a first normal value;
determine at least one second permutation pattern, the at least one second permutation pattern having a maximum decrease in occurrence from a second normal value; and
associate the at least one first permutation pattern and the at least one second pattern with the at least one event.
11. A method for fault precursor detection, the method comprising:
providing, by a data acquisition device communicatively coupled to an
electrical equipment, a sampled signal representing a time series of at least one operational parameter associated with the electrical equipment;
defining, by an equipment controller communicatively coupled to the data acquisition device, an embedding dimension (D);
generating, by the equipment controller and based on the D, permutation patterns;
determining, by the equipment controller, occurrences of the permutation patterns in a window of the sampled signal;
calculating, by the equipment controller and based on the occurrences of permutation patterns, a permutation entropy for the window;
determining, by the equipment controller, that the permutation entropy exceeds a pre-defined normal value by a pre-determined threshold; and
providing, by the equipment controller and based on the determination, at least one message concerning at least one event associated with the electrical equipment.

12. The method as claimed in claim 11, wherein generating the permutation
patterns includes:
computing, by the equipment controller, a set of permutations of D cardinal numbers; and
associating, by the equipment controller, elements of the set of permutations with corresponding permutation patterns.
13. The method as claimed in claim 11, wherein the D is defined based on a
sampled rate of the sampled signal.
14. The method as claimed in claim 11, wherein the determining of the
permutation includes:
determining, by the equipment controller, a sum of occurrences of the permutation patterns;
determining, by the equipment controller and based on the occurrences and the sum of occurrences, relative occurrences of the permutation patterns; and
calculating, by the equipment controller and based on the relative occurrences, the permutation entropy.
15. The method as claimed in claim 11, wherein the electrical equipment
includes one or more of the following: an electrical rotating machine, a
transformer, a blower, a compressor, a cooling tower, and a heat exchanger.
16. The method as claimed in claim 11, wherein the at least one operational
parameter includes one or more of the following: a phase of a current, a power,
speed data, and vibrational data.
17. The method as claimed in claim 11, wherein the at least one event includes
one of an electrical fault or a mechanical fault associated with the electrical
equipment.

18. The method as claimed in claim 11, wherein the pre-determined normal
value and the pre-determined threshold are determined based on historical data for
permutation entropy collected for the electrical equipment.
19. The method as claimed in claim 1, further comprising in response to the
determination that the permutation entropy exceeds the pre-determined normal
value by the pre-determined threshold:
analyzing, by the equipment controller, the occurrences of permutation patterns to determine a distribution of the permutation patterns; and
associating, by the equipment controller, the distribution of permutation patterns with the at least one event associated with the electrical equipment.
20. A system for fault precursor detection, the system comprising:
an electrical equipment;
a data acquisition device configured to acquire a sampled signal representing a time series of at least one operational parameter, the at least one operational parameter being associated with the electrical equipment; and
an equipment controller communicatively coupled to the data acquisition device, the equipment controller being configured to:
define, based on a rate of the sampled signal, an embedding dimension (D);
generate, based on the D, permutation patterns, wherein the permutation patterns are elements of set of permutations of D cardinal numbers;
determine occurrences of the permutation patterns in a window of the sampled signal by matching the permutation patterns to relative positions of amplitudes corresponding to D subsequent points in the window;
determine a sum of the occurrences;
determine, based on the occurrences and the sum of occurrences, relative occurrences of the permutation patterns;

calculate, based on the occurrences of permutation patterns, a permutation entropy;
determine that the permutation entropy exceeds a pre-defined normal value by a pre-determined threshold; and
in response of the determination that the permutation entropy exceeds the pre-defined normal value by the pre-determined threshold:
provide at least one message concerning at least one event
associated with the electrical equipment;
analyze the occurrences of permutation patterns to
determine a distribution of the permutation patterns, at least one
first pattern having maximum increase in occurrence, and at least
one second pattern having maximum decrease in occurrence; and associate at least one of the distribution of the permutation
patterns, the first permutation pattern, or the second permutation
pattern with the at least one event associated with the electrical
equipment.