CN117725397A - A method for extracting partial discharge characteristics of switch cabinets - Google Patents

Abstract

The invention discloses a method for extracting partial discharge characteristics of a switch cabinet. It collects electrical signals generated by the switch cabinet and performs filtering processing. Then it performs parameter analysis on the partial discharge coupling process of the switch cabinet, and constructs parameters according to parameter constraints during the operation of the switch cabinet. Identification model takes characteristic parameters and characteristic constants as the key to extracting partial discharge signals. By acquiring characteristic constants and identifying various characteristic parameters, the construction of fuzzy information analysis model is completed. The sand cat algorithm is introduced to process the processed information. The key information and features are further extracted; the extracted partial discharge signal characteristic signal is represented by the partial discharge characteristic function, and coupled processing is performed to realize the discharge characteristic detection of the switch cabinet. The present invention regards the partial discharge signal as the walking path of a "sand cat" (an animal), extracts the characteristics of the partial discharge signal by simulating the walking path of the sand cat, and evaluates the operating status of the switch cabinet.

Description

A method for extracting partial discharge characteristics of switch cabinets

Technical field

The invention relates to the technical field of signal feature extraction, and in particular to a partial discharge feature extraction method for switch cabinets.

Background technique

Feature extraction of switchgear partial discharge signals is one of the important technologies in power equipment condition monitoring. With the complexity of power equipment and the diversification of operating environments, traditional monitoring methods have been unable to meet the needs of modern power systems. Therefore, it is of great significance to develop new partial discharge monitoring technology and signal feature extraction methods.

Feature extraction of switch cabinet partial discharge signals refers to extracting characteristic information from partial discharge signals that can reflect the status of the equipment, such as discharge intensity, discharge frequency, discharge duration, etc. This characteristic information can provide strong support for equipment status assessment and fault diagnosis. There are many methods and technologies for feature extraction of partial discharge signals in switchgear. Among them, the time domain analysis method is the most commonly used one. This method analyzes the time domain waveform of the partial discharge signal and extracts the peak value, mean value, variance and other characteristic values of the discharge signal. In addition, the frequency domain analysis method is also a commonly used technology. It converts the partial discharge signal into a frequency domain signal and extracts its frequency components, energy distribution and other characteristics. In addition to time domain and frequency domain analysis methods, there are many other partial discharge signal feature extraction methods, such as wavelet transform, short-time Fourier transform, empirical mode decomposition, etc. Each of these methods has advantages and disadvantages and is suitable for different application scenarios and device types. In short, feature extraction of switchgear partial discharge signals is one of the key technologies for power equipment condition monitoring. By selecting appropriate feature extraction methods and processing technologies, feature information that reflects the status of the equipment can be effectively extracted, providing strong support for status assessment and fault diagnosis of power equipment.

Existing switch cabinet partial discharge signal feature extraction methods are prone to interference from obstacles, have insufficient convergence speed, and cannot adapt well to different path planning problems.

Contents of the invention

In view of the shortcomings of the existing technology, the present invention proposes a partial discharge feature extraction method for switch cabinets.

The present invention is implemented in this way. A partial discharge feature extraction method for switch cabinets, including the following steps:

Step 1: Collect the electrical signals generated by the switch cabinet and perform filtering processing, then perform parameter analysis on the partial discharge coupling process of the switch cabinet, build a parameter identification model based on the parameter constraints during the operation of the switch cabinet, and use the characteristic parameters and characteristic constants as partial discharge The key to signal extraction is to achieve effective acquisition of parameter signals through the acquisition of characteristic constants. After completing the extraction of the partial discharge signal, process it. During processing, the extracted feature information is constrained to obtain a partial discharge feature. information;

Step 2: In order to obtain more stable signal characteristic constants, the fuzzy information analysis model is constructed through the identification of various characteristic parameters, and the sand cat algorithm is introduced to further extract key information and features of the processed information. The extraction process is divided into There are four processes for initializing the population, searching for prey, secondary search and attacking prey;

Step 3: Represent the extracted partial discharge signal characteristic signal with the partial discharge characteristic function and perform coupling processing to generate a relatively complete parameter component that can be used to describe the characteristics of the discharge signal. Adjust the parameter component to achieve the discharge characteristics of the switch cabinet. detection.

Further preferably, the parameter constraints are expressed as:

In formula (1): A represents the operating parameter constraints of the switch cabinet; e represents the control parameter. Normally, the value of e is a constant value; i represents the harmonics generated during the transmission of the partial discharge signal of the switch cabinet during operation. ; δ represents the electrical signal capacity of the equipment; t represents the frequency of locally generated electrical signals.

It is further preferred that the characteristic parameters and characteristic constants are used as the key to extract the partial discharge signal, and the effective acquisition of the parameter signal is achieved by acquiring the characteristic constants; the acquisition process is as follows:

In formula (2): G represents the electrical signal characteristics; F represents the electrical signal disturbance compensation; S represents the signal fluctuation amplitude, and the value of S is controlled between +1 and -1.

Further preferably, the extracted feature information is constrained to obtain a partial discharge feature information, and the control terminal discharge is expressed as:

In formula (3): H represents the control terminal discharge signal; ε represents parameter reliability; ρ represents the signal fuzzy characteristic constant. Fuse parameter features with the same performance to construct a new signal, output this signal, and complete the signal processing.

Further preferably, the specific process of step 2 is:

Step 2.1: Initialize the sand cat population,

X _i =LB+S _i ×(UB-LB) (5)

_In the _{formula :} In order to generate three coefficient values with a certain degree of randomness through chaotic mapping, S _i+1 is the mapping coefficient corresponding to the i+1 sand cat, X _i is the initial position of the i sand cat, UB and LB are variables respectively. the upper and lower boundaries;

Step 2.2: The prey search mechanism _of sand cats relies on low _- frequency noise emission; _{the solution for} each sand cat is expressed as The two-dimensional SCSO algorithm simulates the hearing ability of sand cats in low-frequency detection. Sand cats can perceive low frequencies below 2 kHz, assuming the general sensitivity range of sand cats. From 0 to 2kHz, in order to improve the search speed in the early iteration and the search accuracy in the later iteration, the general sensitivity range/> Non-linearly decreases from 2 to 0 as the iterative process proceeds to gradually get closer to the prey without losing or skipping;

Step 2.3: In order to search for prey, assume that the sensitivity range of the sand cat is 2kHz to 0; s _M is the simulated sand cat hearing characteristic parameter;

In formula (6): t is the current number of iterations, and T is the maximum number of iterations;

Step 2.4: The final and main parameter that controls the transition between the exploration and development phases is R, due to this adaptive strategy:

In formula (7): rand(0,1) is a random number between (0,1), R is the interval A random value in; the search space is randomly initialized between defined boundaries. During the search step, the position update of each current search agent is based on a random position; the search agent explores new spaces in the search space;

Step 2.5: In order to avoid falling into the local optimum, the sensitivity range of each sand cat is different, defined as:

In formula (8): is the sensitivity range for each cat; in addition,/> for exploration or exploitation phase operations, while/> Used to guide parameter R to transfer control between these stages;

Step 2.6: When ||R||＞1, Sand Cat performs the search task, based on the optimal solution position Pos _bc (t) and the current position Pos _c (t) and its sensitivity range Updates its position; enables the sand cat to find other possible best positions:

In formula (9): Pos(t+1) is the updated position of the sand cat;

Step 2.7: When the sand cat searches for prey, after updating the location information, it conducts a second search for the individual with the worst fitness value:

x＝r×cos(θ) y＝r×sin(θ) z＝r×θ r＝u×e ^θv (10)

Pos(t+1)＝Pos _bc (t)×x×y×z+Pos _c (t) (11)

In the formula: x, y, z are the three search directions of the three-dimensional space coordinates, Pos(t+1) is the updated position of the sand cat, r is the radius of the spiral, and θ is a random angle in the range of [0, 2π] ;u and v are constants related to the spiral shape, used to control the spiral radius;

Step 2.8: When |R|≤1, the sand cat attacks the prey:

Pos _rnd (t)＝|rand(0,1)·Pos _bc (t)-Pos _c (t)| (12)

In formula (12): Pos _rnd (t) is a random position generated by using the optimal solution position Pos _bc (t) and the current position Pos _c (t).

To further optimize, assume that the sensitivity range of sand cats is a circle, and use the roulette method to randomly select an angle θ for each sand cat,

Among them, the random position can ensure that the sand cat approaches its prey, and the random angle helps the algorithm jump out of the local optimum.

Further preferably, the specific process of step 3 is:

Step 3.1: Construct an information analysis model for switch cabinet partial discharge, and use the training data set to train and optimize the model; finally, apply the optimized information analysis model to the information analysis of actual partial discharge data to implement the information analysis model Real-time monitoring and prediction function; in the information analysis model, the discharge layer is represented as y, and the corresponding value of y is 1 to 0. The partial discharge characteristic function is output, and the function is represented as Z. The description of Z is represented by the following calculation formula :

In formula (14): Z represents the detection feature output function; ω _y represents the output quantity;

Step 3.2: Perform coupling processing on the output results of the partial discharge characteristic function. The processing process is as follows (15):

In formula (15): Represents the coupling processing result of the output signal; Q represents the fuzzy component; Q represents the detection axis; the detection results are output, and the coupling results are output, so that after fusion, a relatively complete parameter component can be used to describe the characteristics of the discharge signal, and the parameter components are adjusted , to realize the detection of discharge characteristics of the switch cabinet.

The sand cat algorithm is a method that can be used to detect and analyze partial discharge signals in switchgear. The core idea is to regard the partial discharge signal as the walking path of a "sand cat" (an animal), and extract the characteristics of the discharge signal by simulating the walking path of the sand cat. Specifically, the algorithm treats the partial discharge signal as a random process and uses the walking path of the sand cat to simulate this random process. By analyzing the sand cat's walking path, various characteristics of the discharge signal can be extracted, such as discharge intensity, discharge frequency, discharge duration, etc. These features can be used to identify and classify different types of partial discharge signals and evaluate the operating status of the switchgear.

The invention has the advantages of strong robustness, fast convergence speed, strong adaptability, etc. When solving path planning problems, the sand cat algorithm has strong robustness by simulating animal behavior. Even when the environment changes greatly or there are obstacles, the algorithm can still find a better path. The sandcat algorithm gradually optimizes the value of the objective function by continuously updating the candidate solutions of the path. This iterative approach allows the algorithm to converge to the optimal solution in a shorter time. The Sandcat algorithm can be adjusted and optimized according to different environments and task requirements. By adjusting the parameters and constraints in the algorithm, the algorithm can be better adapted to different path planning problems.

Description of the drawings

Figure 1 is a flow chart of the partial discharge feature extraction method of the switch cabinet of the present invention;

Figure 2 is the sandcat algorithm feature extraction flow chart.

Detailed ways

The present invention will be explained in further detail below with reference to the accompanying drawings.

Referring to Figure 1, a partial discharge feature extraction method for switch cabinets includes the following steps:

Step 1: Collect the electrical signals generated by the switch cabinet, mainly including ultrasonic waves, ground waves and other electrical signals. After simple filtering and other processing of these signals, perform parameter analysis on the partial discharge coupling process of the switch cabinet. According to the parameters during the operation of the switch cabinet Constraints build a parameter identification model, using characteristic parameters and characteristic constants as the key to extracting partial discharge signals. By obtaining characteristic constants, effective acquisition of parameter signals is achieved. After completing the extraction of partial discharge signals, they are processed. During processing, the extracted feature information is constrained to obtain a partial discharge feature information;

Step 2: In order to obtain more stable signal characteristic constants, the fuzzy information analysis model is constructed through the identification of various characteristic parameters, and the sand cat algorithm is introduced to further extract key information and features of the processed information. The extraction process is divided into In order to initialize the population, there are four processes: searching for prey (exploration), secondary search and attacking prey (exploitation);

Step 3: Represent the extracted partial discharge signal characteristic signal with the partial discharge characteristic function and perform coupling processing to generate a relatively complete parameter component that can be used to describe the characteristics of the discharge signal. Adjust the parameter component to achieve the discharge characteristics of the switch cabinet. detection.

The specific process of step 1 of the present invention is:

Step 1.1: Based on the load fluctuation, perform parameter analysis on the partial discharge coupling process of the switch cabinet, and construct a parameter identification model based on the parameter constraints during the operation of the switch cabinet. Under such conditions, the parameter constraints are expressed as the following calculation formula (1 ):

In formula (1): A represents the operating parameter constraints of the switch cabinet; e represents the control parameter. Normally, the value of e is a constant value; i represents the harmonics generated during the transmission of the partial discharge signal of the switch cabinet during operation. ; δ represents the electrical signal capacity of the equipment; t represents the frequency of locally generated electrical signals.

Step 1.2: Under these constraints, the characteristic parameters and characteristic constants are regarded as the key to partial discharge signal extraction. By obtaining the characteristic constants, the parameter signal can be effectively obtained. This acquisition process is shown in the following calculation formula (2):

In formula (2): G represents the electrical signal characteristics; F represents the electrical signal disturbance compensation; S represents the signal fluctuation amplitude, and the value of S is controlled between +1 and -1.

Step 1.3: Complete the effective acquisition of the characteristic parameters and process them. During processing, the extracted characteristic information is constrained. At this time, a partial discharge characteristic information can be obtained, and the control terminal discharge is expressed as the following calculation formula (3) :

In formula (3): H represents the control terminal discharge signal; ε represents parameter reliability; ρ represents the signal fuzzy characteristic constant. Fuse parameter features with the same performance to construct a new signal, output this signal, and complete the signal processing.

The specific process of step 2 of the present invention is:

Step 2.1: In the SCSO algorithm, the population is called a sand cat group, and each sand cat displays the value of the problem variable. In the switchgear partial discharge detection, the population is the brand-new signal output after processing in step 1, and each sand cat collects and obtains each signal. This algorithm is a population-based method, and the initial population positions are evenly distributed in the search space, which helps to enhance the global search capability of the algorithm and improve search efficiency. The standard sand cat swarm optimization algorithm randomly initializes the population, which risks reducing the diversity of the population. The chaotic sequence generated by chaos mapping has the characteristics of ergodicity, nonlinearity and unpredictability, and is often used to initialize the population instead of random sequence. Mapping has the advantages of simple parameters and uniform distribution. Initialize the sand cat population.

X _i =LB+S _i ×(UB-LB) (5)

_In the _{formula :} In order to generate three coefficient values with a certain degree of randomness through chaotic mapping, they are used to initialize the position of the sand cat group in the search space, making it random and more conducive to global search. S _i+1 is the mapping coefficient corresponding to the i+1 sand cat, _Xi is the initial position of the i sand cat, UB and LB are the upper and lower boundaries of the variable respectively.

Step 2.2: The sand cat's prey search mechanism relies on low-frequency noise emissions. The solution expression of each sand cat is X _i =[x _i1 ,x _i2 ,…,x _id ]. x _id is the d-th dimension of the i-th sand cat. The SCSO algorithm simulates the hearing ability of sand cats in low-frequency detection. Sand cats can perceive low frequencies below 2 kHz. Assuming the general sensitivity range of sand cats From 0 to 2kHz, in order to improve the search speed in the early iteration and the search accuracy in the later iteration, the general sensitivity range/> Non-linearly decreases from 2 to 0 as the iterative process proceeds to gradually get closer to the prey without losing or skipping.

Step 2.3: To search for prey, assume that the sand cat's sensitivity range is 2kHz to 0kHz. s _M is a simulated sand cat auditory characteristic parameter. Its value is inspired by the auditory characteristics of sand cats. It is assumed that its value is 2.

In formula (6): t is the current number of iterations, T is the maximum number of iterations, s _M =2.

Step 2.4: The final and main parameter that controls the transition between the exploration and exploitation phases is R. Due to this adaptive strategy, the transitions and possibilities of the two phases will be more balanced.

In formula (7): rand(0,1) is a random number between (0,1), R is the interval a random value in . The search space is randomly initialized between defined boundaries, and during the search step, each current search agent's position update is based on a random position. In this way, the search agent is able to explore new spaces in the search space.

Step 2.5: In order to avoid falling into the local optimum, the sensitivity range of each sand cat is different, defined as:

In formula (8): Sensitivity range for each cat. In addition,/> for exploration or exploitation phase operations, while/> Used to guide parameter R to transfer control between these stages.

Step 2.6: When |R|＞1, Sand Cat performs the search task, based on the optimal solution position Pos _bc (t) and the current position Pos _c (t) and its sensitivity range Update your location. Allowing the sand cat to find the best possible location elsewhere.

In formula (9): Pos(t+1) is the updated position of the sand cat. This formulation provides another opportunity for the algorithm to find new local optima in the search area. Therefore, the obtained position is between the current position and the prey position. Furthermore, this is achieved through randomness rather than precise methods. In this way, the search agent in the algorithm is beneficial to improve randomness. This makes the algorithm cost-effective to operate and efficient in terms of complexity.

Step 2.7: When searching for prey, sand cats may not be able to effectively converge to the optimal solution. Therefore, after updating the location information, a second search is performed on the individual with the worst fitness value to improve the search performance of the sand cat group optimization algorithm. .

x＝r×cos(θ) y＝r×sin(θ) z＝r×θ r＝u×e ^θv (10)

Pos(t+1)＝Pos _bc (t)×x×y×z+Pos _c (t) (11)

In equations (10) and (11): x, y, z are the three search directions of the three-dimensional space coordinates, Pos(t+1) is the updated position of the sand cat, r is the radius of the spiral, and θ is [0 ,2π] at random angles within the range. u and v are constants related to the spiral shape and are used to control the spiral radius, which is often taken as 1; e is the base of the natural logarithm.

Step 2.8: When |R|≤1, the sand cat attacks the prey.

Pos _rnd (t)＝|rand(0,1)·Pos _bc (t)-Pos _c (t)| (12)

In formula (12): Pos _rnd (t) is a random position generated by using the optimal solution position Pos _bc (t) and the current position Pos _c (t).

To further optimize, assume that the sensitivity range of sand cats is a circle, and use the roulette method to randomly select an angle θ for each sand cat,

Among them, the random position can ensure that the sand cat approaches its prey, and the random angle helps the algorithm jump out of the local optimum.

Further preferably, the specific process of step 3 is as follows

Step 3.1: Construct an information analysis model for switchgear partial discharge, and use the training data set to train and optimize the model. Finally, the optimized information analysis model is applied to the information analysis of actual partial discharge data to achieve real-time monitoring and prediction functions of the information analysis model. In this information analysis model, the discharge layer is represented as y, and the corresponding value of y is 1 to 0. The partial discharge characteristic function is output, and the function is represented as Z. The description of Z can be expressed by the following calculation formula:

In formula (14): Z represents the detection feature output function; ω _y represents the output quantity.

Step 3.2: Perform coupling processing on the output results of the partial discharge characteristic function. The processing process is as follows (15):

In formula (15): Represents the coupling processing result of the output signal; Q represents the fuzzy component; Q represents the detection axis. According to the above calculation formula, the detection results are output, and the coupling results are output, so that after fusion, a relatively complete parameter component that can be used to describe the characteristics of the discharge signal is generated. The parameter components are adjusted to realize the detection of the discharge characteristics of the switch cabinet.

Those of ordinary skill in the art can understand that the above are only preferred examples of the invention and are not intended to limit the invention. Although the invention has been described in detail with reference to the foregoing examples, those skilled in the art can still The technical solutions recorded in the foregoing examples are modified, or some of the technical features are equivalently replaced. All modifications, equivalent substitutions, etc. that are within the spirit and principle of the invention shall be included in the protection scope of the invention.

Claims (7)

1. The partial discharge characteristic extraction method of the switch cabinet is characterized by comprising the following steps of:

step 1, collecting an electric signal generated by a switch cabinet, performing filtering treatment, performing parameter analysis on a partial discharge coupling process of the switch cabinet, constructing a parameter identification model according to parameter constraint conditions in the operation process of the switch cabinet, taking characteristic parameters and characteristic constants as keys for extracting partial discharge signals, effectively acquiring the parameter signals through acquiring the characteristic constants, processing the partial discharge signals after the extraction of the partial discharge signals is completed, and constraining the extracted characteristic information during the processing to obtain partial discharge characteristic information;

step 2: in order to obtain a more stable signal characteristic constant, the construction of a fuzzy information analysis model is completed by identifying various characteristic parameters, a salsa algorithm is introduced to further extract key information and characteristics of the processed information, and the extraction process comprises four processes of initializing a population, searching hunting, searching for a second time and attacking hunting;

step 3: the extracted partial discharge signal characteristic signals are represented by partial discharge characteristic functions and are subjected to coupling processing, so that a relatively complete parameter component which can be used for describing the characteristics of the discharge signals is generated, and the parameter component is adjusted to realize the detection of the discharge characteristics of the switch cabinet.

2. The partial discharge feature extraction method of a switchgear cabinet according to claim 1, characterized in that the parameter constraints are expressed as:

in the formula (1): a represents a constraint condition of operation parameters of the switch cabinet; e represents a control parameter, and the value of e is a constant value in normal cases; i represents the harmonic wave generated by the partial discharge signal of the switch cabinet in operation in transmission; delta is expressed as the device electrical signal capacity; t is denoted as the frequency at which the electrical signal is locally generated.

3. The partial discharge characteristic extraction method of the switch cabinet according to claim 2, wherein the characteristic parameters and the characteristic constants are used as keys for extracting the partial discharge signals, and the parameter signals are effectively obtained through obtaining the characteristic constants; the acquisition process is as follows:

in the formula (2): g represents the characteristics of the electrical signal; f represents electric signal disturbance compensation; s represents the fluctuation amplitude of the signal, and the value of S is controlled between +1 and-1.

4. The method for extracting partial discharge characteristics of a switchgear according to claim 3, wherein the constraint on the extracted characteristic information obtains partial discharge characteristic information, and the control end discharge is expressed as:

in the formula (3): h represents a control end discharge signal; epsilon represents the reliability of the parameter; ρ represents a signal blur feature constant; and fusing the parameter characteristics with the same performance, constructing a brand new signal, outputting the signal, and finishing the signal processing.

5. The partial discharge characteristic extraction method of a switchgear according to claim 1, wherein the specific process of step 2 is:

step 2.1 initializing a sandcat population,

X _i ＝LB+S _i ×(UB-LB) (5)

wherein: x is X _i E (0.9,1.08), taking initial value S for S sequence ₁ ＝rand[0,1]，S _i For the mapping coefficient corresponding to the ith sand cat,s is three coefficient values generated by chaotic mapping _i+1 Mapping coefficient corresponding to ith+1st sand cat, X _i For the initial position of the ith cat, UB and LB are the upper and lower boundaries of the variable respectively;

step 2.2 search for hunting of a Sai catThe cable mechanism relies on low frequency noise emissions; solution expression of each sand cat is X _i ＝[x _i1 ,x _i2 ,…,x _id ]；x _id SCSO algorithm for the d dimension of the ith cat simulates the hearing ability of the cat in terms of low frequency detection, the cat perceives low frequencies below 2kHz, assuming the general sensitivity range of the catFrom 0 to 2kHz, to improve the searching speed in the initial stage of iteration and the searching precision in the later stage of iteration, the general sensitivity range is +.>Non-linearly decreasing from 2 to 0 as the iterative process proceeds to gradually approach the prey without losing or skipping;

step 2.3, in order to search for prey, assume that the sensitivity range of the sand cat is 2kHz to 0; s is(s) _M Simulating acoustic characteristic parameters of the sand cat;

in formula (6): t is the current iteration number, and T is the maximum iteration number;

step 2.4. The final and main parameters of the control exploration and development phase transition are R, due to this adaptive strategy:

in the formula (7): rand (0, 1) is a random number between (0, 1), R is the intervalA random value of (a) is determined; randomly initializing search spaces between defined boundaries, wherein in the step of searching, the location update of each current search agent is based on a random location; search agentExploring new space in the search space;

step 2.5 to avoid trapping in local optima, the sensitivity range is different for each sand cat, defined as:

in formula (8):sensitivity ranges for each cat; furthermore, the->For exploring or utilizing the operation of the phase, but +.>For steering the parameter R to achieve transfer control between these phases;

step 2.6, when the I R I is more than 1, the salsa executes a search task according to the optimal solution position Pos _bc (t) and the current position Pos _c (t) sensitivity RangeUpdating the position of the user; enabling the sandcat to find other best possible locations:

in the formula (9): pos (t+1) is the updated position of the salsa;

step 2.7, when the sand cat searches for the prey, after updating the position information, performing secondary search on the individual with the worst fitness value:

x＝r×cos(θ) y＝r×sin(θ) z＝r×θ r＝u×e ^θv (10)

Pos(t+1)＝Pos _bc (t)×x×y×z+Pos _c (t) (11)

wherein: x, y, z are three search directions of three-dimensional space coordinates, pos (t+1) is the updated position of the sand cat, r is the radius of the spiral, and θ is a random angle in the range of [0,2 pi ]; u and v are constants related to the spiral shape for controlling the spiral radius;

step 2.8: when |R| is less than or equal to 1, the sand cat carries out attack hunting:

Pos _rnd (t)＝|rand(0,1)·Pos _bc (t)-Pos _c (t)| (12)

in the formula (12): pos _rnd (t) is to use the optimal solution position Pos _bc (t) and the current position Pos _c (t) random positions of production.

6. The method of claim 5, wherein assuming that the sensitivity range of the cat is a circle, randomly selecting an angle θ for each cat using roulette,

the random positions can ensure that the sand cat approaches to the prey, and the random angles are helpful for the algorithm to jump out of local optimum.

7. The partial discharge characteristic extraction method of a switchgear according to claim 1, wherein the specific process of step 3 is:

step 3.1: constructing an information analysis model aiming at the partial discharge of the switch cabinet, and training and optimizing the model by using a training data set; finally, the optimized information analysis model is applied to information analysis of actual partial discharge data, so that the functions of real-time monitoring and prediction of the information analysis model are realized; the discharge layer in the information analysis model is expressed as y, the value of the corresponding y is 1-0, a partial discharge characteristic function is output, the function is expressed as Z, and the description of Z is expressed by the following calculation formula:

in formula (14): z represents a detection feature output function; omega _y Representing the output quantity;

step 3.2: and (3) coupling the partial discharge characteristic function output result, wherein the processing process is as follows (15):

in formula (15):representing the coupling processing result of the output signal; q represents a blurring component; q represents a detection axis; and outputting the detection result, outputting the coupling result, and generating a relatively complete parameter component which can be used for describing the characteristics of the discharge signal after the coupling result is fused, and adjusting the parameter component to realize the detection of the discharge characteristics of the switch cabinet.