CN114996633A - AI intelligent partial discharge detection method - Google Patents
AI intelligent partial discharge detection method Download PDFInfo
- Publication number
- CN114996633A CN114996633A CN202210729831.7A CN202210729831A CN114996633A CN 114996633 A CN114996633 A CN 114996633A CN 202210729831 A CN202210729831 A CN 202210729831A CN 114996633 A CN114996633 A CN 114996633A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- output
- electric
- electronic device
- equation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 90
- 230000004927 fusion Effects 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000013139 quantization Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 13
- 230000010355 oscillation Effects 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000013016 damping Methods 0.000 claims description 6
- 238000009413 insulation Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses an AI intelligent partial discharge detection method, which comprises the steps of establishing a pulse form change model for pulse data during partial discharge; establishing a controlled data constraint equation, a data gain equation and a data quantization equation; resolving the stability of the partial discharge output of the electric and electronic device to obtain a data output equation; establishing a stable data characteristic quantity equation of partial discharge output of the electric and electronic device and a fluctuation data characteristic quantity equation of partial discharge output; fusing local data; establishing a partial discharge data constraint equation, an output reliability characteristic quantity equation of partial discharge detection and a data fusion equation of partial discharge detection; carrying out characteristic extraction on partial discharge of the electric and electronic device; detecting partial discharge of the electric and electronic device by using a characteristic detection function; the method is based on the existing electrical theory, and can effectively solve the problems of poor anti-interference capability and high identification difficulty of partial discharge detection.
Description
Technical Field
The invention relates to the field of partial discharge and algorithm of electric and electronic devices, in particular to an AI intelligent partial discharge detection method.
Background
Partial discharge is one of the main causes of insulation degradation, and some critical parts in the power system need to be detected, such as transformers, GIS stations, cables, switch cabinets, and the like. When partial discharge occurs, the direct manifestation of charge transfer is the generation of high-frequency pulse currents, which are accompanied by interfering signals caused by factors such as ultrasound, electromagnetic radiation, optical or chemical reactions, and the like.
Partial discharge detection is an important link for detecting the state of the power equipment. Because the insulation defect of the power equipment is easy to generate partial discharge under the action of high voltage, the development of the partial discharge can cause further deterioration of insulation and finally cause insulation flashover, the partial discharge condition of the equipment is monitored, and the defect can be timely found and the early warning of the insulation flashover fault is facilitated.
According to the measurement condition, the partial discharge detection method can be divided into power failure detection, live detection and on-line monitoring, and among the three methods, the power failure detection is higher in detection cost because equipment needs to be accompanied and stopped, and is generally used only when leaving a factory for testing, overhauling or replacing the equipment. On-line monitoring theoretically can realize real-time monitoring of equipment, but the interference in the actual operation process is large, the reliability of the measurement result is not high, and the on-line monitoring is less adopted. The live detection does not need equipment to be stopped, has the function of temporarily creating more appropriate experimental conditions so as to improve the reliability of a detection result, is a compromised partial discharge detection method, and is most common in practical application.
The patent with publication number CN111562468A discloses a GIS partial discharge signal measurement system and a GIS partial discharge fault diagnosis method, which can synchronously and respectively obtain pulse current partial discharge signals and ultrahigh frequency partial discharge signals inside and outside a metal shielding box of a GIS. Based on the GIS partial discharge signal measurement system, the invention provides a GIS partial discharge fault diagnosis method, which determines the GIS partial discharge fault according to the obtained partial discharge signal and the preset partial discharge fault criterion. The invention adopts the suspension shielding measurement, so that the external interference can be effectively inhibited, and the measured pulse current partial discharge signal and the ultrahigh frequency partial discharge signal are more accurate; the characteristic values of the pulse current partial discharge signal and the ultrahigh frequency partial discharge signal are used as the basis for judging whether the GIS has the partial discharge defect, so that the method has the advantages of strong field operability, accurate judgment, sensitive response, quantitative judgment, easiness in implementation and the like, and can be widely applied to diagnosis of the GIS partial discharge fault.
However, the existing partial discharge detection methods only carry out partial discharge detection on a specific electric and electronic device, have poor anti-interference capability and high identification difficulty on the partial discharge detection, and do not form a set of detection methods with strong operability.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an AI intelligent partial discharge detection method.
The technical scheme adopted by the invention is that the method comprises the following steps:
step S1: carrying out data acquisition on the electric and electronic devices, and establishing a pulse form change model for partial discharge of pulse data;
because the discharge generating mechanism of different electric and electronic devices, the propagation and attenuation modes of signals during discharge and the discharge positions of different devices are different, a unified model cannot be adopted to describe pulse signals during discharge of all the electric and electronic devices, so that four types of pulse form change models during partial discharge are established, wherein the four types of pulse form change models are respectively as follows: single exponential decay, single exponential oscillation decay, double exponential decay, and double exponential oscillation decay models.
Step S2: reading the collected data to establish a controlled data constraint equation, a data gain equation and a data quantization equation;
step S3: resolving the stability of the partial discharge output of the electric and electronic device by using the optimal solution of the partial discharge output of the electric and electronic device to obtain a data output equation;
step S4: establishing a stable data characteristic quantity equation of partial discharge output of the electric and electronic device and a fluctuation data characteristic quantity equation of partial discharge output by using a characteristic analysis method;
step S5: fusing local data of the electric and electronic device to obtain a partial discharge control output equation and a maximum power parameter equation of the electric and electronic device;
step S6: establishing a partial discharge data constraint equation, an output reliability characteristic quantity equation of partial discharge detection and a data fusion equation of partial discharge detection;
step S7: the method comprises the following steps of carrying out feature extraction on partial discharge of the electric and electronic device, wherein the extraction process comprises the following steps:
s7.1, establishing an oscillation characteristic constraint condition of partial discharge;
s7.2, establishing an output reliability fusion parameter analysis control model of partial discharge;
s7.3, establishing an object model for partial discharge detection;
s7.4, establishing different frequency detection output error models;
s7.5, establishing a partial discharge output constraint characteristic function;
s7.6, establishing an iterative function of feature extraction;
step S8: and detecting partial discharge of the electric and electronic device by utilizing a characteristic detection function, wherein the characteristic detection function comprises a partial discharge detection output function and a partial discharge fundamental wave component detection output function.
Further, the partial discharge clock pulse form change model has an expression:
A 1 (b)＝B 1 e -b/β
wherein A is 1 (b) Representing a single exponential decay function, B 1 Signal amplitude representing a single exponential decay, b represents time, e represents a natural constant, and β represents a decay coefficient;
A 2 (b)＝B 2 e -b /βsin(A c ×2πb)
wherein A is 2 (b) Representing a single exponential oscillation damping function, B 2 Signal amplitude, A, representing the mono-exponential oscillation decay c Represents the oscillation frequency;
wherein A is 3 (b) Representing a double exponential decay function, B 3 The signal amplitude representing the double exponential decay, f and g representing decay constants, determined according to the discharge scene;
wherein A is 4 (b) Representing a double exponential oscillation damping function, B 4 Representing the signal amplitude of the double exponential oscillation decay.
Further, the data constraint equation has the expression:
wherein D represents the constraint result, e represents a constant parameter, n represents a partial discharge signal harmonic parameter, m represents the total number of partial discharges, η represents the capacitance of the electrical and electronic device, and b represents the signal frequency of the partial discharges;
the data gain equation has the expression:
E＝ηε+σD
wherein E represents a gain equation, ε represents an input voltage of the electrical electronic device, and σ represents a resistance of the electrical electronic device;
the data quantization equation has the expression:
wherein F represents a quantization function, h 1 ，h 2 ，h 3 The discharge output balance constant of the electric and electronic device at different moments is shown, and s represents the number of partial discharge positions of the electric and electronic device.
Further, the expression of the optimal solution function of the partial discharge output is as follows:
where G represents the optimal solution of the output, h 1 ，h 2 ，h 3 The method comprises the steps of representing discharge output equilibrium constants of the electric and electronic device at different moments, b representing time, eta representing electric capacity of the electric and electronic device, F representing a quantization function, and H representing a constraint parameter of partial discharge;
the data output equation has the expression:
I＝G+ξ(b+1)ω
wherein, I represents the characteristic result of voltage output, ξ represents the output voltage, b represents the time, and ω represents the characteristic of partial discharge output of the electric and electronic device;
ω＝J+ξ 2
wherein, J electric and electronic device partial discharge output phase difference.
Further, the stable data characteristic quantity equation has an expression:
k represents a stable data characteristic quantity, omega represents the characteristic of partial discharge output of the electric and electronic device, I represents the characteristic result of voltage output, e represents a constant parameter, v represents determined disturbance noise, and J represents the partial discharge output phase difference of the electric and electronic device;
the expression of the fluctuation data characteristic quantity equation is as follows:
where L represents the fluctuation data characteristic quantity, η represents the capacitance of the electric and electronic device, and ∈ represents the input voltage of the electric and electronic device.
Further, the control output equation has an expression as follows:
wherein M denotes a control output, b denotes time, L denotes a parameter characteristic amount, ω denotes a characteristic of a partial discharge output of an electric electronic device, and ψ denotes a control output coefficient;
the expression of the maximum power parameter equation is as follows:
where N represents the maximum power parameter, M represents the control output, ξ represents the output voltage, G represents the optimal solution for the output, and b represents time.
Further, the data constraint equation has an expression as follows:
where eta represents the capacitance of the electric and electronic device, D represents the confinement result, psi represents the control output coefficient, h 1 ，h 2 ，h 3 The method comprises the steps of representing discharge output equilibrium constants of the electric and electronic devices at different moments, representing reliability characteristic components by tau, and representing maximum power parameters by N;
the expression of the output reliability characteristic quantity equation is as follows:
wherein P represents an output reliability feature quantity;
the data fusion equation has the expression:
wherein q (i) represents a result of parameter fusion, r (i) represents a target parameter function of partial discharge output of the electric and electronic device, i represents a target parameter of partial discharge of the electric and electronic device, u (i) represents an adjustment parameter, and w (i) represents a constraint condition of the parameter.
Further, the oscillation characteristic constraint condition is expressed as:
xQ(i)≥η(ψ-Q(i))
wherein x represents oscillation amplitude of partial discharge, q (i) represents result of parameter fusion, η represents capacitance of electric and electronic devices, ψ represents control output coefficient;
the output reliability is fused with a parameter analysis control model, and the expression is as follows:
wherein, R represents the parameter analysis control result, i represents the target parameter of the partial discharge of the electric and electronic device, pi represents the circumference ratio, and y represents the target total number of the partial discharge of the electric and electronic device;
the expression of the detected object model is as follows:
wherein U represents the detection result, minz 1 、maxz 2 Minimum and maximum values representing different control constraints;
the different frequency detection output error model has the expression:
wherein V represents the detection output error result, T a The detection statistical characteristic quantity of the partial discharge output of the electric and electronic device is represented, and A represents the multi-mode parameter characteristic of the partial discharge of the electric and electronic device.
The output constraint characteristic function has the expression:
wherein W represents the output constraint characteristic result, V represents the detection output error result, minz 1 、maxz 2 Expressing the minimum value and the maximum value of different control constraint conditions, wherein A represents the multi-mode parameter characteristic of partial discharge of the electric and electronic device;
the expression of the iterative function of the feature extraction is as follows:
wherein X represents the iteration result of the feature extraction, i represents the target parameter of the partial discharge of the electric and electronic device, Y represents the current characteristic quantity output by the partial discharge of the electric and electronic device, and Z 3 Representing a characteristic quantity of the disturbance between the output current and the voltage.
Further, the partial discharge detection output function has the expression:
wherein A is tc Indicating the output result of partial discharge detection, j indicating the discharge layer, r indicating the total number of discharge layers, o j Representing a quantified characteristic in the discharge layer,. pi.representing a circumferential ratio,. x representing an oscillation amplitude of a partial discharge,. z 2 Controlling the constraint condition;
the fundamental component detection output function of the partial discharge has the expression:
wherein, B fg The result of detection of the fundamental component, r (i) represents the office of electric and electronic devicesAnd partial discharge output as a function of the target parameter.
Has the advantages that:
the invention provides an AI intelligent partial discharge detection method, which comprises a plurality of mathematical models, and utilizes a computer to analyze collected data, establish the models and obtain results.
Drawings
FIG. 1 is a flow chart of the overall steps of the present invention;
FIG. 2 is a partial discharge pulse shape variation model according to the present invention;
fig. 3 is a flowchart of partial discharge data feature extraction according to the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments can be combined with each other without conflict, and the present application will be further described in detail with reference to the drawings and specific embodiments.
As shown in fig. 1, an AI intelligent partial discharge detection method includes the steps of:
step S1: carrying out data acquisition on the electric and electronic devices, and establishing a pulse form change model for partial discharge of pulse data;
as shown in fig. 2, because the discharge mechanism of different electrical and electronic devices, the propagation and attenuation modes of signals during discharge, and the discharge positions of different devices are different, it is impossible to describe pulse signals during discharge of all electrical and electronic devices by using a unified model, and therefore four types of pulse form change models during partial discharge are established, which are: single exponential decay, single exponential oscillation decay, double exponential decay and double exponential oscillation decay models.
Step S2: reading the acquired data to establish a controlled data constraint equation, a data gain equation and a data quantization equation;
after the four types of pulse form change models in partial discharge are established in step S1, the unused attenuation models need unified constraint, gain, and data quantization equations, which are preprocessing steps for partial discharge of the electrical and electronic device, and the controlled data constraint equation is a summation equation for discharge times, which can describe the amount of electric charge generated by all discharge times in unit time, and the data gain equation is a description of increase of discharge times in unit time, because some electrical and electronic devices do not exhibit regularity in partial discharge, the rule of partial discharge of the electrical and electronic device can be controlled by using the data gain equation, and the data quantization equation quantifies the number of partial discharge of the electrical and electronic device by combining the data gain equation, and the constraint, gain, and data quantization equations are hierarchical and supplement each other.
Step S3: resolving the stability of the partial discharge output of the electric and electronic device by using the optimal solution of the partial discharge output of the electric and electronic device to obtain a data output equation;
the optimal solution of the partial discharge output of the electric and electronic device is a parameter equation obtained based on a data quantization equation and is related to a discharge output balance constant of the electric and electronic device, the optimal solution of the output is the optimal solution of the charge quantity, the data output equation outputs a characteristic result of voltage, and the output voltage of the electric and electronic device changes along with the change of the charge quantity.
Step S4: establishing a stable data characteristic quantity equation of partial discharge output of the electric and electronic device and a fluctuation data characteristic quantity equation of partial discharge output by using a characteristic analysis method;
the stable data characteristic quantity equation and the fluctuation data characteristic quantity equation which are used for establishing the partial discharge output of the electric and electronic device are different, because the change of the input voltage can generate different discharge characteristics, the partial discharge description of different components is facilitated, the stable data characteristic quantity equation is used for collecting the partial discharge output of the electric and electronic device within a period of time according to the regulation, and the fluctuation data characteristic quantity equation is obtained by analyzing fluctuation factors on the basis of the stable data characteristic quantity equation.
Step S5: fusing local data of the electric and electronic device to obtain a partial discharge control output equation and a maximum power parameter equation of the electric and electronic device;
the partial discharge control output equation is a description of the overall discharge of the electrical and electronic device, and is different from the description of the partial discharge of the component in the step S4, the equation is an overall quantity, the maximum power parameter equation of the electrical and electronic device is a description of the power consumed by the electrical and electronic device, the power consumed by different electrical and electronic devices is different, and the maximum power parameter equation of the electrical and electronic device is established to be capable of mastering the limit of the partial discharge of the electrical and electronic device.
Step S6: establishing a partial discharge data constraint equation, an output reliability characteristic quantity equation of partial discharge detection and a data fusion equation of partial discharge detection;
the left side of the equation is an equality constraint equation of 0, the equation is used for constraining control output parameters during partial discharge, the output reliability characteristic quantity equation is a sine function equation, the equation is used for evaluating the output reliability characteristic quantity, and the data fusion equation is used for fusing a target parameter function and adjusting parameters of partial discharge output of the electric and electronic device.
As shown in fig. 3, step S7: the method comprises the following steps of carrying out feature extraction on partial discharge of the electric and electronic device, wherein the extraction process comprises 6 steps in total:
steps S1 to S6 are preparatory work for partial discharge feature extraction.
S7.1, establishing an oscillation characteristic constraint condition of partial discharge;
s7.2, establishing an output reliability fusion parameter analysis control model of partial discharge;
s7.3, establishing an object model for partial discharge detection;
s7.4, establishing different frequency detection output error models;
s7.5, establishing a partial discharge output constraint characteristic function;
s7.6, establishing an iterative function of feature extraction;
step S8: and detecting partial discharge of the electric and electronic device by using a characteristic detection function, wherein the characteristic detection function comprises a partial discharge detection output function and a partial discharge fundamental component detection output function.
The partial discharge detection output function is a collection for detecting all the characteristic quantities, and the partial discharge fundamental component detection output function is a detection of the fundamental component.
Further, the partial discharge clock pulse form change model has the expression:
A 1 (b)＝B 1 e -b/β
wherein A is 1 (b) Representing a single exponential decay function, B 1 Signal amplitude representing a single exponential decay, b represents time, e represents a natural constant, and β represents a decay coefficient;
A 2 (b)＝B 2 e -b/β sin(A c ×2πb)
wherein A is 2 (b) Representing a single exponential oscillation damping function, B 2 Signal amplitude, A, representing the mono-exponential oscillation decay c Represents the oscillation frequency, b represents time, e represents a natural constant, and β represents an attenuation coefficient;
wherein A is 3 (b) Representing a double exponential decay function, B 3 The signal amplitude representing the double-exponential attenuation, f and g represent attenuation constants, b represents time, e represents a natural constant, and beta represents an attenuation coefficient, and is determined according to a discharge scene;
wherein, A 4 (b) Representing a double-exponential oscillation damping function, B 4 Signal amplitude representing the decay of a double-exponential oscillation, b represents timeE denotes a natural constant, β denotes an attenuation coefficient, A c Representing the oscillation frequency.
Further, the controlled data constraint equation has the expression:
wherein D represents the constraint result, e represents a constant parameter, n represents a partial discharge signal harmonic parameter, m represents the total number of partial discharges, η represents the capacitance of the electrical and electronic device, and b represents the signal frequency of the partial discharges;
the data gain equation has the expression:
E＝ηε+σD
wherein E represents a gain equation, ε represents an input voltage of the electrical and electronic device, σ represents a resistance of the electrical and electronic device, and D represents a constraint result;
the data quantization equation has the expression:
wherein F represents a quantization function, h 1 ，h 2 ，h 3 The method comprises the steps of representing discharge output balance constants of the electric and electronic device at different moments, s representing the number of partial discharge positions of the electric and electronic device, E representing a constant parameter, n representing a partial discharge signal harmonic parameter, m representing the total number of partial discharge, and E representing a gain equation.
Further, the expression of the optimal solution function of the partial discharge output is as follows:
where G represents the optimal solution of the output, h 1 ，h 2 ，h 3 Representing discharge output equilibrium constants of the electric and electronic device at different times, b representing time, and eta representing electric and electronic deviceThe capacitance of the element, F represents a quantization function, and H represents a constraint parameter of partial discharge;
the data output equation has the expression:
I＝G+ξ(b+1)ω
wherein, I represents the characteristic result of voltage output, G represents the optimal solution of output, xi represents output voltage, b represents time, and omega represents the characteristic of partial discharge output of the electric and electronic device;
ω＝J+ξ 2
wherein, J electric and electronic device partial discharge output phase difference, ξ represents the output voltage.
Further, the stable data characteristic quantity equation has an expression:
k represents a stable data characteristic quantity, omega represents the characteristic of partial discharge output of the electric and electronic device, I represents the characteristic result of voltage output, e represents a constant parameter, v represents determined disturbance noise, and J represents the partial discharge output phase difference of the electric and electronic device;
the expression of the fluctuation data characteristic quantity equation is as follows:
wherein L represents the fluctuation data characteristic quantity, K represents the stable data characteristic quantity, η represents the capacitance of the electric electronic device, ∈ represents the input voltage of the electric electronic device, H represents the constraint parameter of partial discharge, and K represents the stable data characteristic quantity.
Further, the control output equation has an expression as follows:
wherein M denotes a control output, b denotes time, L denotes a parameter characteristic amount, ω denotes a characteristic of a partial discharge output of the electric and electronic device, and ψ denotes a control output coefficient;
the expression of the maximum power parameter equation is as follows:
where N represents the maximum power parameter, M represents the control output, ξ represents the output voltage, G represents the optimal solution for the output, and b represents time.
Further, the data constraint equation has an expression as follows:
where eta represents the capacitance of the electric and electronic device, D represents the confinement result, psi represents the control output coefficient, h 1 ，h 2 ，h 3 The method comprises the steps of representing discharge output equilibrium constants of the electric and electronic devices at different moments, representing reliability characteristic components by tau, and representing maximum power parameters by N;
the expression of the output reliability characteristic quantity equation is as follows:
wherein P represents an output reliability characteristic quantity, N represents a maximum power parameter, τ represents a reliability characteristic component, η represents a capacitance of the electric/electronic device, and b represents time;
the expression of the data fusion equation is as follows:
wherein q (i) represents a result of parameter fusion, r (i) represents a target parameter function of partial discharge output of the electric and electronic device, i represents a target parameter of partial discharge of the electric and electronic device, u (i) represents an adjustment parameter, and w (i) represents a constraint condition of the parameter.
Further, the oscillation characteristic constraint condition is expressed as:
xQ(i)≥η(ψ-Q(i))
wherein x represents oscillation amplitude of partial discharge, q (i) represents result of parameter fusion, η represents capacitance of electric and electronic device, ψ represents control output coefficient;
the output reliability fusion parameter analysis control model has the following expression:
wherein, R represents the parameter analysis control result, i represents the target parameter of the partial discharge of the electric and electronic device, pi represents the circumferential rate, y represents the target total number of the partial discharge of the electric and electronic device, Q (i) represents the result of parameter fusion, psi represents the control output coefficient, and x represents the oscillation amplitude of the partial discharge;
the expression of the detected object model is as follows:
wherein U represents the detection result, minz 1 、maxz 2 Expressing the minimum value and the maximum value of different control constraint conditions, wherein R represents a parameter analysis control result, and eta represents the capacitance of the electric and electronic device;
the different frequency detection output error model has the expression:
wherein V represents the detection output error result, U represents the detection result, and T represents a The statistical characteristic quantity of the detection of partial discharge output of the electric and electronic device is represented, A represents partial discharge of the electric and electronic deviceElectrical multi-mode parameter characteristics.
The output constraint characteristic function has the expression:
wherein W represents the output constraint characteristic result, V represents the detection output error result, minz 1 、maxz 2 Expressing the minimum value and the maximum value of different control constraint conditions, wherein A represents the multi-mode parameter characteristic of partial discharge of the electric and electronic device;
the expression of the iterative function of the feature extraction is as follows:
wherein X represents the iteration result of the feature extraction, i represents the target parameter of the partial discharge of the electric and electronic device, Y represents the current characteristic quantity output by the partial discharge of the electric and electronic device, and Z 3 And W represents the output constraint characteristic result.
Further, the partial discharge detection output function has an expression:
wherein A is tc Indicating the output result of partial discharge detection, j indicating the discharge layer, r indicating the total number of discharge layers, o j Representing a quantitative feature in the discharge layer, pi representing the circumferential rate, x representing the amplitude of oscillation of the partial discharge, z 2 Controlling the constraint condition;
the fundamental component detection output function of the partial discharge has the expression:
wherein, B fg Fundamental component detection result, r (i) represents target parameter function of partial discharge output of electric and electronic device, W represents output constraint characteristic result, A tc And (4) representing a partial discharge detection output result, and X representing an iteration result of feature extraction.
The invention provides an AI intelligent partial discharge detection method, which comprises a plurality of mathematical models, and utilizes a computer to analyze collected data, establish the models and obtain results.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made herein without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims (9)
1. An AI intelligent partial discharge detection method is characterized by comprising the following steps:
step S1: carrying out data acquisition on the electric and electronic devices, and establishing a pulse form change model for partial discharge of pulse data;
step S2: reading the acquired data to establish a controlled data constraint equation, a data gain equation and a data quantization equation;
step S3: resolving the stability of the partial discharge output of the electric and electronic device by using the optimal solution of the partial discharge output of the electric and electronic device to obtain a data output equation;
step S4: establishing a stable data characteristic quantity equation of partial discharge output of the electric and electronic device and a fluctuation data characteristic quantity equation of partial discharge output by using a characteristic analysis method;
step S5: fusing local data of the electric and electronic device to obtain a partial discharge control output equation and a maximum power parameter equation of the electric and electronic device;
step S6: establishing a partial discharge data constraint equation, an output reliability characteristic quantity equation of partial discharge detection and a data fusion equation of partial discharge detection;
step S7: the method comprises the following steps of carrying out feature extraction on partial discharge of the electric and electronic device, wherein the extraction process comprises the following steps:
s7.1, establishing an oscillation characteristic constraint condition of partial discharge;
s7.2, establishing an output reliability fusion parameter analysis control model of partial discharge;
s7.3, establishing an object model for partial discharge detection;
s7.4, establishing different frequency detection output error models;
s7.5, establishing a partial discharge output constraint characteristic function;
s7.6, establishing an iterative function of feature extraction;
step S8: and detecting partial discharge of the electric and electronic device by using a characteristic detection function, wherein the characteristic detection function comprises a partial discharge detection output function and a partial discharge fundamental component detection output function.
2. The AI intelligent partial discharge detection method of claim 1, wherein the pulse shape change model for partial discharge has an expression:
A 1 (b)＝B 1 e -b/β
wherein A is 1 (b) Representing a single exponential decay function, B 1 Signal amplitude representing single exponential decay, b representing time, e representing a natural constant, and beta representing a decay coefficient;
A 2 (b)＝B 2 e -b/β sin(A c ×2πb)
wherein, A 2 (b) Representing a single exponential oscillation damping function, B 2 Signal amplitude, A, representing the mono-exponential oscillation decay c Represents the oscillation frequency;
wherein A is 3 (b) Representing a double exponential decay function, B 3 The signal amplitude representing the double exponential decay, f and g representing decay constants, determined according to the discharge scene;
wherein A is 4 (b) Representing a double-exponential oscillation damping function, B 4 Representing the signal amplitude of the double exponential oscillation decay.
3. The AI intelligent partial discharge detection method of claim 1, wherein the data constraint equation is expressed as:
wherein D represents the constraint result, e represents a constant parameter, n represents a partial discharge signal harmonic parameter, m represents the total number of partial discharges, η represents the capacitance of the electrical and electronic device, and b represents the signal frequency of the partial discharges;
the data gain equation has the expression:
E＝ηε+σd
wherein E represents a gain equation, ε represents an input voltage of the electrical electronic device, and σ represents a resistance of the electrical electronic device;
the data quantization equation has the expression:
wherein F represents a quantization function, h 1 ，h 2 ，h 3 S-table representing discharge output equalization constants of electric and electronic devices at different timesShowing the number of partial discharge positions of the electric and electronic device.
4. The AI intelligent partial discharge detection method of claim 1, wherein the optimal solution function of the partial discharge output is expressed as:
where G represents the optimal solution of the output, h 1 ，h 2 ，h 3 The method comprises the steps of representing discharge output equilibrium constants of the electric and electronic device at different moments, b representing time, eta representing electric capacity of the electric and electronic device, F representing a quantization function, and H representing a constraint parameter of partial discharge;
the data output equation has the expression:
I＝G+ξ(b+1)ω
wherein, I represents the characteristic result of voltage output, xi represents output voltage, b represents time, and omega represents the characteristic of partial discharge output of the electric and electronic device;
ω＝J+ξ 2
wherein, J electric and electronic device partial discharge output phase difference.
5. The AI intelligent partial discharge detection method of claim 1, wherein the stable data characteristic quantity equation has an expression:
k represents a stable data characteristic quantity, omega represents the characteristic of partial discharge output of the electric and electronic device, I represents the characteristic result of voltage output, e represents a constant parameter, v represents determined disturbance noise, and J represents the partial discharge output phase difference of the electric and electronic device;
the expression of the fluctuation data characteristic quantity equation is as follows:
where L represents the fluctuation data characteristic quantity, η represents the capacitance of the electric and electronic device, and ∈ represents the input voltage of the electric and electronic device.
6. The AI intelligent partial discharge detection method of claim 1, wherein the control output equation has an expression:
wherein M denotes a control output, b denotes time, L denotes a parameter characteristic amount, ω denotes a characteristic of a partial discharge output of the electric and electronic device, and ψ denotes a control output coefficient;
the expression of the maximum power parameter equation is as follows:
where N represents the maximum power parameter, M represents the control output, ξ represents the output voltage, G represents the optimal solution for the output, and b represents time.
7. The AI intelligent partial discharge detection method of claim 1, wherein the data constraint equation is expressed as:
where eta represents the capacitance of the electric and electronic device, D represents the confinement result, psi represents the control output coefficient, h 1 ，h 2 ，h 3 Indicating discharge of electric or electronic devices at different timesOutputting an equilibrium constant, wherein tau represents a reliability characteristic component, and N represents a maximum power parameter;
the expression of the output reliability characteristic quantity equation is as follows:
wherein P represents an output reliability feature quantity;
the expression of the data fusion equation is as follows:
wherein, q (i) represents a result of parameter fusion, r (i) represents a target parameter function of partial discharge output of the electric and electronic device, i represents a target parameter of partial discharge of the electric and electronic device, u (i) represents an adjustment parameter, and w (i) represents a constraint condition of the parameter.
8. The AI intelligent partial discharge detection method of claim 1, wherein the oscillation characteristic constraint condition is expressed as:
xQ(i)≥η(ψ-Q(i))
wherein x represents oscillation amplitude of partial discharge, q (i) represents result of parameter fusion, η represents capacitance of electric and electronic device, ψ represents control output coefficient;
the output reliability fusion parameter analysis control model has the following expression:
wherein, R represents the parameter analysis control result, i represents the target parameter of the partial discharge of the electric and electronic device, pi represents the circumferential rate, and y represents the target total number of the partial discharge of the electric and electronic device;
the expression of the detected object model is as follows:
wherein U represents the detection result, minz 1 、maxz 2 Minimum and maximum values representing different control constraints;
the different frequency detection output error model has the expression:
wherein V represents the detection output error result, T a The detection statistical characteristic quantity of the partial discharge output of the electric and electronic device is represented, and A represents the multi-mode parameter characteristic of the partial discharge of the electric and electronic device;
the expression of the output constraint characteristic function is as follows:
wherein W represents the output constraint characteristic result, V represents the detection output error result, minz 1 、maxz 2 Expressing the minimum value and the maximum value of different control constraint conditions, wherein A represents the multi-mode parameter characteristic of partial discharge of the electric and electronic device;
the expression of the iterative function of the feature extraction is as follows:
wherein X represents the iteration result of the feature extraction, i represents the target parameter of the partial discharge of the electric and electronic device, Y represents the current characteristic quantity output by the partial discharge of the electric and electronic device, and Z 3 Representing a characteristic quantity of the disturbance between the output current and the voltage.
9. The AI intelligent partial discharge detection method of claim 1, wherein the partial discharge detection output function has an expression:
wherein A is tc Indicating the output result of partial discharge detection, j indicating the discharge layer, r indicating the total number of discharge layers, o j Representing a quantitative feature in the discharge layer, pi representing the circumferential rate, x representing the amplitude of oscillation of the partial discharge, z 2 Controlling the constraint condition;
the fundamental component detection output function of the partial discharge has the expression:
wherein, B fg The detection result of the fundamental component, r (i), represents the objective parameter function of the partial discharge output of the electric and electronic device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210729831.7A CN114996633B (en) | 2022-06-24 | 2022-06-24 | AI intelligent partial discharge detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210729831.7A CN114996633B (en) | 2022-06-24 | 2022-06-24 | AI intelligent partial discharge detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114996633A true CN114996633A (en) | 2022-09-02 |
| CN114996633B CN114996633B (en) | 2024-05-14 |
Family
ID=83036172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210729831.7A Active CN114996633B (en) | 2022-06-24 | 2022-06-24 | AI intelligent partial discharge detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114996633B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359683A (en) * | 2023-02-28 | 2023-06-30 | 四川大唐国际甘孜水电开发有限公司 | Partial discharge mode identification method and system based on information interaction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080246507A1 (en) * | 2003-07-25 | 2008-10-09 | Power Measurement Ltd. | Body Capacitance Electric Field Powered Device For High Voltage Lines |
| KR101553005B1 (en) * | 2015-04-20 | 2015-10-01 | 지투파워 (주) | A partial discharge monitoring and diagnosis system for power devices |
| CN109991520A (en) * | 2019-03-19 | 2019-07-09 | 中国电力科学研究院有限公司 | A kind of cable oscillation wave partial discharge detecting system velocity of wave New calculating method |
| CN114299308A (en) * | 2021-12-20 | 2022-04-08 | 中用科技有限公司 | Intelligent detection system and method for damaged road guardrail |
-
2022
- 2022-06-24 CN CN202210729831.7A patent/CN114996633B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080246507A1 (en) * | 2003-07-25 | 2008-10-09 | Power Measurement Ltd. | Body Capacitance Electric Field Powered Device For High Voltage Lines |
| KR101553005B1 (en) * | 2015-04-20 | 2015-10-01 | 지투파워 (주) | A partial discharge monitoring and diagnosis system for power devices |
| CN109991520A (en) * | 2019-03-19 | 2019-07-09 | 中国电力科学研究院有限公司 | A kind of cable oscillation wave partial discharge detecting system velocity of wave New calculating method |
| CN114299308A (en) * | 2021-12-20 | 2022-04-08 | 中用科技有限公司 | Intelligent detection system and method for damaged road guardrail |
Non-Patent Citations (1)
| Title |
|---|
| 张泓;董涛;张博;余光凯;胡泰山;: "电力电缆局放信号传播特性分析及仿真研究", 电线电缆, no. 04, 25 August 2016 (2016-08-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359683A (en) * | 2023-02-28 | 2023-06-30 | 四川大唐国际甘孜水电开发有限公司 | Partial discharge mode identification method and system based on information interaction |
| CN116359683B (en) * | 2023-02-28 | 2023-12-26 | 四川大唐国际甘孜水电开发有限公司 | Partial discharge mode identification method and system based on information interaction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114996633B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101574615B1 (en) | A partial discharge monitoring and diagnosis system for power devices by using signal detection based on statistical phase-angle patterns | |
| Zhang et al. | A Wiener process model with dynamic covariate for degradation modeling and remaining useful life prediction | |
| CN107807860B (en) | Power failure analysis method and system based on matrix decomposition | |
| CN109284933B (en) | Electronic transformer state evaluation system and method based on mathematical statistics | |
| Seri et al. | Modelling of supply voltage frequency effect on partial discharge repetition rate and charge amplitude from AC to DC at room temperature | |
| CN107103184A (en) | A kind of high-voltage cable joint temperature predicting method | |
| CN112180204A (en) | Power grid line fault diagnosis method based on electric quantity information | |
| CN114996633A (en) | AI intelligent partial discharge detection method | |
| CN114091231A (en) | Switch cabinet modeling method based on digital twin and error adaptive optimization | |
| Zhang et al. | Research on estimating method for the smart electric energy meter’s error based on parameter degradation model | |
| CN109613372B (en) | Power grid fault diagnosis method based on multi-element power grid database | |
| CN113919198A (en) | Electrical fire monitoring and early warning method based on generation of countermeasure network | |
| Yang et al. | Intelligent fault diagnosis method of capacitor voltage transformer based on recurrent neural network | |
| CN112014696A (en) | Dry-type air-core reactor fault diagnosis method and device based on partial discharge characteristics | |
| Xiao et al. | Remaining useful life prediction of lithium-ion battery based on unscented Kalman filter and back propagation neural network | |
| CN112464848B (en) | Information flow abnormal data monitoring method and device based on density space clustering | |
| Gopinath et al. | Insulation condition assessment of high‐voltage rotating machines using hybrid techniques | |
| Poluyanovich et al. | Evaluation of the Cable Line Resource From the Aaging Degree of Its Insulating Material | |
| CN114091322A (en) | High-voltage switch cabinet state prediction method based on digital model | |
| Huang et al. | The system of temperature rise monitoring and temperature prediction for power equipment | |
| CN114487643A (en) | On-spot handing-over of extra-high voltage GIL equipment is accepted and is synthesized test platform | |
| Estrada et al. | Magnetic Flux Entropy as a Tool to Predict Transformer's Failures | |
| Wang et al. | Insulation condition forewarning of form‐wound winding for electric aircraft propulsion based on partial discharge and deep learning neural network | |
| Wang et al. | Neural network modeling of distribution transformers with internal short circuit winding faults | |
| Xu et al. | Operating state evaluation of smart electricity meter based on data fusion method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |