CN110610254B - Multi-dimensional monitoring system and prediction evaluation method for pollution degree of equipment surface - Google Patents
Multi-dimensional monitoring system and prediction evaluation method for pollution degree of equipment surface Download PDFInfo
- Publication number
- CN110610254B CN110610254B CN201910691027.2A CN201910691027A CN110610254B CN 110610254 B CN110610254 B CN 110610254B CN 201910691027 A CN201910691027 A CN 201910691027A CN 110610254 B CN110610254 B CN 110610254B
- Authority
- CN
- China
- Prior art keywords
- equipment
- state quantity
- prediction
- pollution degree
- monitoring
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 75
- 238000011156 evaluation Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 230000005684 electric field Effects 0.000 claims abstract description 28
- 230000008859 change Effects 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 21
- 150000003839 salts Chemical class 0.000 claims abstract description 21
- 238000013139 quantization Methods 0.000 claims abstract description 20
- 239000013618 particulate matter Substances 0.000 claims abstract description 17
- 238000004891 communication Methods 0.000 claims abstract description 10
- 238000011002 quantification Methods 0.000 claims abstract description 6
- 230000003287 optical effect Effects 0.000 claims abstract description 5
- 238000011109 contamination Methods 0.000 claims description 17
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 239000002245 particle Substances 0.000 description 16
- 230000005540 biological transmission Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a multidimensional monitoring system and a predictive evaluation method for the pollution degree of the surface of equipment, relating to the field of security analysis of a power grid system; the monitoring system mainly comprises a main control unit, a temperature and humidity sensor, a particulate matter sensor, an optical sensing salt density sensor, an electric field intensity sensor and a wireless communication module; the prediction evaluation method comprises the following steps: acquiring multi-dimensional information of the pollution degree affecting the surface of the equipment in the valve hall; according to the acquired multi-dimensional information of the pollution degree of the surface of the equipment, establishing a prediction quantification index of abnormal fluctuation of the equipment based on a multi-dimensional state quantity time sequence trend analysis prediction method and a multi-dimensional state quantity transverse contrast analysis prediction method; evaluating the pollution degree of the surface of the equipment according to the prediction quantization index of the abnormal fluctuation of the equipment and a corresponding threshold value; and displaying the evaluation result. The invention can predict the equipment pollution degree change of the environment in the valve hall and ensure the safe and stable operation of the valve hall.
Description
Technical Field
The invention relates to the field of security analysis of a power grid system, in particular to a multi-dimensional monitoring system and a prediction evaluation method for the pollution degree of the surface of equipment.
Background
In recent years, the direct-current transmission technology is rapidly developed in China, and the advantages of the direct-current transmission technology in the aspects of long-distance transmission, cross-regional networking, flexible scheduling and the like are gradually shown. The converter valve is an important core electrical device of the converter station, and the function of the converter valve is to realize rectification and inversion. The converter valve is used as a core element for converting alternating current into direct current, the requirements on the operating environment are very strict, the operating environment temperature and humidity are strictly described, and the influence of the cleanliness of the whole valve hall on the converter valve and an auxiliary control unit of the converter valve is very large from the operation experience of the converter valve.
The equipment in the valve hall includes valves module and sleeve pipe class equipment, and the experience surface of operation, in the good operational environment in the valve hall, sleeve pipe class equipment is difficult for long-pending dirty, and TE board and TVM board card in the valves module are direct to be exposed in the valve hall environment, and no shell protection, the easy deposit of particulate matter is on equipment surface. In a dry environment, the particles exist in a solid state, and the insulation performance of the material is less influenced due to the larger resistance of the particles. However, in a humid environment, soluble substances in the dirt particles are gradually dissolved and ionized to form a conductive film, so that the surface conductivity of the equipment is increased, the equipment is switched on by mistake or the insulating property is reduced, and further accidents are caused. In ac and dc fields, the accumulation effect is mainly caused by the attraction force generated by the electric dipoles induced by the surrounding particles in the field. A large amount of suspended particles can induce out electric dipoles under the action of an external electric field, the electric dipoles generate an uneven electric field in the surrounding space, and the particles in the electric field are acted by polarized force, so that interaction is generated between the particles, and the particles are attracted mutually to accumulate.
The valve towers have different voltage grades at different heights, the voltage of the valve tower at the bottommost layer is 0V, and the voltage of the valve tower at the highest layer is 500kV or even higher. The valve group modules are distributed at different positions of the valve tower, and the voltage levels of the valve group modules at different heights are different, so that the equipment at different positions on the valve tower is different in dirt accumulation, and the treatment is difficult. A small amount of dust is brought when operation and maintenance personnel enter the valve hall, the dust is influenced by airflow and an electromagnetic field and is distributed at each position in the valve hall, and an effective valve hall equipment monitoring system and a surface pollution degree prediction and evaluation method are still lacking at present.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a multidimensional monitoring system and a prediction evaluation method for the pollution degree of the surface of equipment, which can predict the pollution degree change of the equipment in the environment of a valve hall and ensure the safe and stable operation of the valve hall.
In order to achieve the purpose, the invention provides a multi-dimensional monitoring system for the filthy degree of the surface of equipment, which comprises a main control unit, a temperature and humidity sensor, a particulate matter sensor, an optical sensing salt density sensor, an electric field intensity sensor and a wireless communication module, wherein the main control unit is used for controlling the temperature and humidity sensor; the temperature and humidity sensor is used for acquiring monitoring values of temperature and relative humidity in the valve hall, the particulate matter sensor is used for acquiring a particulate matter concentration monitoring value in the valve hall, the optical sensing salt density sensor is used for acquiring a salt density monitoring value of equipment in the valve hall, and the electric field intensity sensor is used for acquiring a monitoring value of electric field intensity in the valve hall; the main control unit is used for receiving monitoring values obtained by the temperature and humidity sensor, the particulate matter sensor, the light sensing salt density sensor and the electric field intensity sensor, carrying out prediction evaluation on equipment according to the monitoring values, and transmitting an evaluation result to an upper computer through the wireless communication module.
A multi-dimensional prediction evaluation method for the pollution degree of the surface of equipment comprises the following steps:
step 1: acquiring multi-dimensional information of the pollution degree affecting the surface of the equipment in the valve hall;
step 2: according to the acquired multi-dimensional information of the pollution degree of the surface of the equipment, establishing a prediction quantification index of abnormal fluctuation of the equipment based on a multi-dimensional state quantity time sequence trend analysis prediction method and a multi-dimensional state quantity transverse contrast analysis prediction method;
and step 3: evaluating the pollution degree of the surface of the equipment according to the prediction quantization index of the abnormal fluctuation of the equipment and a corresponding threshold value;
and 4, step 4: display the results of the evaluation
According to the multidimensional prediction and evaluation method for the pollution degree of the equipment surface, further, the state quantities of the pollution degree multidimensional information model comprise electric field intensity, particulate matters, temperature, relative humidity, salt density, surface energy, height and wind speed.
The multidimensional prediction and evaluation method for the pollution degree of the surface of the equipment further comprises the following steps of: the accumulated sum of the difference values of the monitoring values at the adjacent moments and the change rate of the monitoring values at the current moment are used as prediction quantization indexes; wherein the content of the first and second substances,
the accumulated sum of the difference values of the monitoring values at the adjacent moments is as follows:
Δx＝∑(xt-xt-1)
in the formula, xtIs the monitored value of the state quantity x at the current time t, xt-1Change rate x of monitored value x at present time which is monitored value of state quantity x at last time t-1Δ：
In the formula, xtIs the monitored value of the state quantity x at the current time t, x0A monitored value of a state quantity x at an initial time
The multi-dimensional prediction evaluation method for the surface pollution degree of the equipment further takes the surface pollution correlation coefficient of the three-phase equipment of the same type and the monitoring value deviation of the equipment of different types as prediction quantization indexes under the same environment and the same height.
The method for multi-dimensional prediction and evaluation of the surface pollution degree of the equipment further calculates the surface pollution correlation coefficient by a distance correlation method, wherein the distance correlation method comprises the following steps:
a state quantity of the same type of equipment is represented as a single variable sequence,
Xi＝[x1,x2,…xt]
in the formula, XiIs a single variable sequence of device i, xtIs the monitored value at time t.
And solving the correlation coefficient of the surface contamination of two devices of the same type in the same environment and at the same height:
in the formula, dcor is a surface pollution correlation coefficient, and S is expressed as a vector inner product; alpha is vector length, i, j is equipment identification of three-phase equipment out-of-phase
The method for multi-dimensional prediction and evaluation of the pollution degree of the surface of the equipment further comprises the following steps of 3:
the prediction quantization index established by the multi-dimensional state quantity time sequence trend analysis prediction method comprises the following steps: the absolute value | Delta x | of the sum of the differences of the monitoring values at adjacent times is summed with a sum threshold Delta xεComparing the change rates x of the monitored values at the current timeΔAnd a rate of change threshold xΔεComparing;
the prediction quantization index established by the transverse contrast analysis prediction method for the multidimensional state quantity comprises the following steps: comparing the surface contamination correlation coefficient dcor with a surface contamination correlation coefficient threshold epsilon, and comparing the deviation of the monitored value with a deviation threshold DEεAnd (6) comparing.
The method for multi-dimensional prediction and evaluation of the pollution degree of the surface of the equipment further comprises accumulating a sum threshold value delta xεThreshold value of rate of change xΔεAnd deviation threshold DEεAnd setting according to the operation experience and the equipment operation requirement.
According to the multi-dimensional prediction evaluation method for the surface pollution degree of the equipment, further, the surface pollution correlation coefficient threshold epsilon is obtained through a clustering algorithm.
Compared with the prior art, the invention has the beneficial effects that: the multi-dimensional monitoring system provided by the invention starts with factors influencing the pollution degree, adopts various sensors to monitor the environment of the valve hall, and provides an effective means for the comprehensive analysis of the running environment of the valve hall of the converter station. The multi-dimensional information of the pollution degree related to the prediction and evaluation method provided by the invention covers main factors influencing environmental equipment in the valve hall, a prediction model of abnormal fluctuation of the equipment is established based on a multi-dimensional state quantity time sequence trend analysis and prediction method and a multi-dimensional state quantity transverse comparison analysis and prediction method, so that the change of the pollution degree of the equipment in the valve hall can be predicted, the established pollution degree evaluation standard can effectively judge whether the pollution degree of the equipment is abnormal or not, the equipment operation failure caused by the pollution degree is avoided, and the safe and stable operation of each equipment in the valve hall is ensured.
Drawings
FIG. 1 is a schematic diagram of a multi-dimensional monitoring system for the filthy degree on the surface of equipment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method provided by an embodiment of the present invention;
fig. 3 is a schematic diagram of a converter station valve hall in an application scenario of the present invention.
Wherein: 1. a main control unit; 2. a temperature and humidity sensor; 3. an electric field intensity sensor; 4. a light sensing salt deposit density sensor; 5. a particulate matter sensor; 6. a wireless communication module; 7. a power supply; 8. a crystal oscillator circuit; 9. a reset circuit; 10. and (4) an upper computer.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and detailed description.
Example (b):
referring to fig. 1, a multi-dimensional monitoring system for the filthy degree on the surface of equipment comprises a main control unit 1, a temperature and humidity sensor 2, a particulate matter sensor 5, a light sensing salt density sensor 4, an electric field intensity sensor 3 and a wireless communication module 6; the temperature and humidity sensor 2 is used for acquiring monitoring values of temperature and relative humidity in the valve hall, the particulate matter sensor 5 is used for acquiring a particulate matter concentration monitoring value in the valve hall, the optical sensing salt density sensor 4 is used for acquiring a salt density monitoring value of equipment in the valve hall, and the electric field intensity sensor 3 is used for acquiring a monitoring value of electric field intensity in the valve hall; the main control unit 1 is configured to receive monitoring values obtained by the temperature and humidity sensor 2, the particulate matter sensor 5, the light sensing salt density sensor 4, and the electric field intensity sensor 3, perform predictive evaluation on the device according to the monitoring values, and transmit a result of the predictive evaluation to the upper computer 1010 through the wireless communication module 6.
In specific implementation, the main control unit 1 adopts an STM32F103 series chip, which is mainly used for receiving monitoring values of each sensor and performing prediction evaluation on the monitoring values based on a set algorithm. The temperature and humidity sensor 2 is used for collecting the temperature of the operating environment and is communicated with the main control unit 1 through an I2C interface; the particulate matter sensor 5 is used for collecting particulate matters PM2.5 and PM10.0 in the environment and is communicated with the main control unit 1 through a USART serial port; the light sensing salt density sensor 4 is used for collecting the salt density and the ash density of the environment where the equipment is located and communicating with the main control unit 1 through a USART serial port. The electric field intensity sensor 3 is used for collecting the electric field intensity of a space where the equipment is located, and the main control unit 1 acquires electric field intensity data through an RS485 interface. The wireless communication module 6 adopts a zigbee wireless transmission module, data is transmitted to a zigbee collecting unit at the door of the valve hall through zigbee wireless transmission, the zigbee collecting unit is forwarded to the upper computer 1010 through 4G, the upper computer 1010 can be a main control computer, a server or monitoring display equipment, and operation and maintenance personnel can check monitoring information of equipment in the valve hall through the upper computer 1010. In addition, the main control unit 1 is provided with a crystal oscillator circuit 8 for providing clock information, a power supply 7 for supplying power, and a reset circuit 9 for restoring the circuit to an initial state.
Referring to fig. 2, a method for multi-dimensional prediction and evaluation of the pollution degree of the surface of equipment includes the following steps:
step 1: and acquiring multi-dimensional information of the pollution degree affecting the surface of the equipment in the valve hall.
The equipment in the valve hall comprises a valve group module and sleeve equipment, as shown in figure 3, the dirt accumulation process of dirt particles on the surface of the equipment is mainly determined by two aspects of stress: one is the force that moves the particles to the surface of the equipment; the other is the force that enables the particles to deposit on the surface of the equipment without falling off. The forces of the two aspects provide power for the movement of the filthy particles, so that the filthy particles are promoted to collide with the surface of the equipment and then adhere and deposit. Factors in the valve hall that cause the particles to move to the surface of the equipment include air flow and electric field action; factors that the particles deposit on the surface of the equipment without falling off include: the particles themselves gravity, humidity and surface energy.
In the analysis of the pollution factors on the surface of the equipment, the factors influencing the pollution on the surface of the equipment in the valve hall, namely the state quantities which need to be monitored and measured in the method are determined, and as shown in table 1, the multidimensional information influencing the pollution degree on the surface of the equipment in the valve hall is obtained through each sensor in the multidimensional monitoring system for the pollution degree on the surface of the equipment.
TABLE 1
Step 2: and establishing a prediction quantification index of abnormal fluctuation of the equipment based on a multi-dimensional state quantity time sequence trend analysis prediction method and a multi-dimensional state quantity transverse contrast analysis prediction method according to the acquired multi-dimensional information of the pollution degree of the surface of the equipment.
The main control unit 1 establishes a prediction quantization index of abnormal fluctuation of the equipment for the monitoring value based on a multi-dimensional state quantity time sequence trend analysis prediction method and a multi-dimensional state quantity transverse comparison analysis prediction method according to the acquired multi-dimensional information of the pollution degree of the surface of the equipment, namely the monitoring value of the state quantity acquired by each sensor.
The method for establishing the prediction quantification index of the abnormal fluctuation of the equipment comprises a multi-dimensional state quantity time sequence trend analysis and prediction method and a multi-dimensional state quantity transverse comparison analysis and prediction method, wherein the monitoring state quantity refers to the state quantity obtained by taking a data source as a monitoring means, namely the state quantity of a numerical value can be acquired in real time through a sensor, and the numerical value of the monitoring state quantity is a monitoring value. Similarly, the measured state quantity refers to a state quantity obtained by a data source through an artificial measurement means, the measured state quantity is an environment constant, the numerical value of the measured state quantity is not easy to fluctuate generally, the monitored state quantity is updated in real time, and the evaluation of the pollution degree of the equipment is greatly influenced, so that a prediction model of abnormal fluctuation of the equipment is established on the basis of the monitored state quantity.
Shape of multiple dimensionsThe method for analyzing and predicting the state quantity time sequence trend comprises the following steps: accumulating the difference of the monitoring values at the adjacent moments, and calculating the sum delta x and the change rate x of the monitoring values at the current momentΔAs a predictive quantitative index for trend analysis, Δ x represents the cumulative amount of change in the monitored value of the state quantity, xΔAn instantaneous rate of change of the monitored value representing the state quantity. It should be noted that the monitored state quantities include temperature, humidity, particulate matters (PM2.5, PM10.0, etc.), salt density, and the electric field intensity is influenced by the current passing through the equipment, so that the numerical fluctuation of the electric field intensity is large, and therefore, the electric field intensity is used as a parameter of the multi-dimensional state quantity transverse contrast analysis prediction method.
The accumulated sum of the difference values of the monitoring values at the adjacent moments is as follows:
Δx＝∑(xt-xt-1)
in the formula, xtIs the monitored value of the state quantity x at the current time t, xt-1Is the monitored value of the state quantity x at the last time t-1.
Rate of change x of monitored value at present timeΔ：
In the formula, xtIs the monitored value of the state quantity x at the current time t, x0Is the monitored value of the state quantity x at the initial time.
Wherein the accumulated sum threshold value Deltax of the monitoring state quantityεAnd a rate of change threshold xΔεThe setting is performed according to the operation experience and the equipment operation requirement, and the preferable values in this embodiment are as shown in table 2.
TABLE 2
The multi-dimensional state quantity transverse contrast analysis and prediction method comprises the following steps: and the surface pollution correlation coefficient of the three-phase equipment of the same type and the monitoring value deviation of the equipment of different types are used as prediction quantization indexes. The monitoring state quantity comprises temperature T, humidity RH, electric field intensity E, particulate matters PM and salt density D.
The method is characterized in that multiple three-phase devices such as a line sleeve, a lightning arrester, a converter transformer incoming line sleeve and the like exist in a converter station valve hall, the three-phase devices of the same type run in the same environment and at the same height, monitoring values of all points and change characteristics of the monitoring values are basically consistent under the condition that the pollution degree of the devices is normal, and the surface pollution correlation coefficient dcor among the three-phase devices of the same type at any moment is calculated to identify abnormality. Wherein, the same environment refers to being in the valve hall in the present embodiment; the voltage level is related to the height of the equipment, and the same height represents the same voltage level; the method is realized by solving the surface pollution correlation coefficient dcor of two and three-phase equipment of the same type in the same environment and at the same height, and taking the surface pollution correlation coefficient dcor as a prediction quantization index for evaluating the pollution degree of the equipment surface.
Distance correlation method: taking A, B, C phase valve tower equipment as an example:
XA＝[xA1，xA2，...xAt]
XB＝[xB1，xB2，...xBt]
XC＝[xC1，xC2，...xCt]
in the formula: xA，XB，XCRespectively, A, B, C phase valve towers.
The correlation coefficient of the surface dirt of A, B, C phase valve tower equipment in the same environment and at the same height is obtained:
wherein S is expressed as the vector inner product; α is the vector length, dcorAB、dcorBC、dcorACAnd respectively the related coefficients of the surface dirt of AB phase valve tower equipment, BC phase valve tower equipment and AC phase valve tower equipment.
In addition, x isAt、xBt、xBtRefers to the monitored value of the same state quantity at the time T, wherein the state quantity comprises the temperature T, the humidity RH, the electric field intensity E, the particulate matter PM and the salt deposit density D.
The determination of the threshold value of the correlation coefficient of the surface contamination is realized by a clustering algorithm, the distribution position of the data with the maximum density in the index under the normal condition is analyzed by adopting a Mean Shift method, the method arbitrarily selects a sample value x as a reference point in a sample, and the offset vector of the reference point x is (x)i-x), calculating the mean of the shifts of the current point x according to a formula, the resulting value representing the weight of each sample point.
In the formula: g (| | (x-x)i)/h||2Is a kernel function, h is the size of the kernel
If m (x) is > ε', move the point to
Then, taking the value as a new starting point, calculating the offset mean value, wherein epsilon' is a set value and is taken as 0.01 in the invention. After moving n times, when m (x)n) When | | < epsilon', the point value is considered to be moved to the place where the data is the most dense, and the point value is obtained, and the value is the solved correlation coefficient threshold epsilon.
Different types of equipment run in the same environment and at the same height, and the monitoring values and the change characteristics of the monitoring values of all points are kept within a certain fluctuation range under the condition that the pollution degree of the equipment is normal, wherein the different types of equipment can be embodied into different monitoring positions.
Deviation of monitoring values for different types of devices:
Dt＝xi-xj
wherein D is x at time tiAnd xjRespectively the monitoring values of the same state quantity x in the devices i and j
In the present embodiment, the surface contamination correlation coefficient threshold e is set to 0.9, and the deviation threshold DE is set toεAnd setting according to the operation experience and the equipment operation requirement.
And step 3: and evaluating the pollution degree of the surface of the equipment according to the prediction quantization index of the abnormal fluctuation of the equipment and a corresponding threshold value.
TABLE 3
As shown in table 3, the state quantities are divided into general state quantities and important state quantities by monitoring data and measurement data, and the main control unit 1 compares the prediction quantization index of the abnormal fluctuation of the device with the corresponding threshold value and generates an evaluation result; in the table, the characters used in the judgment logic of the multidimensional state quantity time sequence trend analysis are integrated.
(1) General State quantity evaluation criterion
The general state quantity has little influence on the surface pollution degree of the equipment, the state quantity is an environment constant in a valve hall, and the measured value is not easy to fluctuate.
(2) Evaluation criterion of important state quantity
The evaluation standard of the method is that a prediction quantification index established by comprehensively using a multi-dimensional state quantity time sequence trend analysis and prediction method and a multi-dimensional state quantity transverse contrast analysis and prediction method is used for monitoring and evaluating the important state quantity, when any one of the two analysis methods is judged to be abnormal, the pollution degree of the surface of the equipment in the valve hall is abnormal, otherwise, the pollution degree of the surface of the equipment is normal.
1) The judgment logic of the prediction quantization index established by the multi-dimensional state quantity time sequence trend analysis prediction method is as follows:
to monitor the cumulative sum threshold deltax of the state quantitiesεAnd a rate of change threshold xΔεThe values are respectively used as prediction quantization indexes, when the sum and the change rate are required to be simultaneously judged to be normal, the pollution degree of the surface of the equipment is judged to be normal:
the absolute value | delta x | of the accumulated sum of the difference values of the monitoring values at the adjacent time points and the accumulated sum threshold delta xεBy comparison, when | Δ x | < Δ xεWhen the dirt degree on the surface of the equipment is judged to be normal, and when | delta x | ≧ delta x |, the dirt degree on the surface of the equipment is judged to be normalεIn the meantime, the degree of contamination on the surface of the apparatus is judged to be abnormal.
Secondly, changing the change rate x of the monitoring value at the current momentΔAnd a rate of change threshold xΔεComparison, when xΔ＜xΔεWhen the contamination degree on the surface of the equipment is judged to be normal, when x isΔ＞xΔεIn the meantime, the degree of contamination on the surface of the apparatus is judged to be abnormal.
2) The judgment logic of the prediction quantization index established by the multi-dimensional state quantity transverse contrast analysis prediction method is as follows:
when the surface contamination correlation coefficient dcor of the same type of three-phase equipment and the monitoring value deviation D of different types of equipment are used as prediction quantization indexes and the surface contamination correlation coefficient and the monitoring value deviation are simultaneously judged to be normal, the contamination degree of the surface of the equipment is judged to be normal:
comparing a surface pollution correlation coefficient dcor with a surface pollution correlation coefficient threshold epsilon, when the surface pollution correlation coefficient dcor is less than epsilon, indicating that the surface pollution of certain two devices is greatly different, judging that the pollution degree on the surface of the device is abnormal, otherwise, judging that the pollution degree on the surface of the device is normal if the surface pollution correlation coefficient dcor is more than or equal to epsilon.
② deviation D and deviation threshold DE of monitoring values of different types of equipmentεBy comparison, when D < DEεWhen the contamination degree on the surface of the equipment is judged to be normal, when D is more than DEεAnd judging the dirt degree on the surface of the equipment to be abnormal.
And 4, step 4: display the results of the evaluation
The main control unit 1 transmits the evaluation result to the upper computer 10 through the wireless communication module 6, the upper computer 10 displays alarm information on the equipment which is judged to be abnormal in pollution degree, and operation and maintenance personnel take measures such as key monitoring, equipment running stopping, maintenance and the like according to the alarm information.
The above embodiments are only for illustrating the technical concept and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention accordingly, and not to limit the protection scope of the present invention accordingly. All equivalent changes or modifications made in accordance with the spirit of the present disclosure are intended to be covered by the scope of the present disclosure.
Claims (2)
1. A multidimensional prediction and evaluation method for the pollution degree of the surface of equipment is realized based on a multidimensional monitoring system for the pollution degree of the surface of the equipment, wherein the multidimensional monitoring system for the pollution degree of the surface of the equipment comprises a main control unit (1), a temperature and humidity sensor (2), a particulate matter sensor (5), an optical sensing salt density sensor (4), an electric field intensity sensor (3) and a wireless communication module (6); the temperature and humidity sensor (2) is used for acquiring monitoring values of temperature and relative humidity in the valve hall, the particulate matter sensor (5) is used for acquiring a particulate matter concentration monitoring value in the valve hall, the light sensing salt density sensor (4) is used for acquiring a salt density monitoring value of equipment in the valve hall, and the electric field intensity sensor (3) is used for acquiring a monitoring value of electric field intensity in the valve hall; the main control unit (1) is used for receiving monitoring values obtained by the temperature and humidity sensor (2), the particulate matter sensor (5), the light sensing salt density sensor (4) and the electric field intensity sensor (3), carrying out prediction evaluation on equipment according to the monitoring values, and transmitting an evaluation result to the upper computer (10) through the wireless communication module (6), and is characterized by comprising the following steps:
step 1: acquiring multi-dimensional information of the pollution degree affecting the surface of the equipment in the valve hall;
step 2: according to the acquired multi-dimensional information of the pollution degree of the surface of the equipment, establishing a prediction quantification index of abnormal fluctuation of the equipment based on a multi-dimensional state quantity time sequence trend analysis prediction method and a multi-dimensional state quantity transverse contrast analysis prediction method;
analyzing the time sequence trend of the multidimensional state quantity: the accumulated sum of the difference values of the monitoring values at the adjacent moments and the change rate of the monitoring values at the current moment are used as prediction quantization indexes; wherein the content of the first and second substances,
the accumulated sum of the difference values of the monitoring values at the adjacent moments is as follows:
Δx＝∑(xt-xt-1)
in the formula, xtIs the monitored value of the state quantity x at the current time t, xt-1Change rate x of monitored value x at present time which is monitored value of state quantity x at last time t-1Δ：
In the formula, xtIs the monitored value of the state quantity x at the current time t, x0The monitoring value of the state quantity x at the initial moment;
the multi-dimensional state quantity transverse contrast analysis prediction method comprises the following steps: under the same environment and the same height, the surface pollution correlation coefficient of the three-phase equipment of the same type and the deviation of the monitoring values of the equipment of different types are used as the prediction quantization index;
calculating the surface contamination correlation coefficient by a distance correlation method, wherein the distance correlation method comprises the following steps:
a state quantity of three-phase devices of the same type is represented as a single variable sequence,
Xi＝[x1,x2,…xt]
in the formula, XiIs a single variable sequence of device i, xtThe monitoring value of the same state quantity x at the moment t;
and solving the correlation coefficient of the surface contamination of two and three-phase devices of the same type in the same environment and at the same height:
in the formula, dcor is a surface pollution correlation coefficient, and S is expressed as a vector inner product; alpha is the vector length, i, j is the equipment identification of the different phases of the three-phase equipment;
and step 3: evaluating the pollution degree of the surface of the equipment according to the prediction quantization index of the abnormal fluctuation of the equipment and a corresponding threshold value;
the prediction quantization index established by the multi-dimensional state quantity time sequence trend analysis prediction method comprises the following steps: the absolute value | Delta x | of the sum of the differences of the monitoring values at adjacent times is summed with a sum threshold Delta xεComparing the change rates x of the monitored values at the current timeΔAnd a rate of change threshold xΔεComparing;
the prediction quantization index established by the transverse contrast analysis prediction method for the multidimensional state quantity comprises the following steps: comparing the surface contamination correlation coefficient dcor with a surface contamination correlation coefficient threshold epsilon, and comparing the deviation of the monitored value with a deviation threshold DEεComparing;
cumulative sum threshold Δ xεThreshold value of rate of change xΔεAnd deviation threshold DEεSetting according to operation experience and equipment operation requirements;
the surface contamination correlation coefficient threshold epsilon is obtained through a clustering algorithm;
and 4, step 4: and displaying the evaluation result.
2. The method for multi-dimensional prediction and evaluation of the pollution degree of the equipment surface according to claim 1, wherein the multi-dimensional information of the pollution degree comprises electric field intensity, particulate matters, temperature, relative humidity, salt density, surface energy, height and wind speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910691027.2A CN110610254B (en) | 2019-07-29 | 2019-07-29 | Multi-dimensional monitoring system and prediction evaluation method for pollution degree of equipment surface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910691027.2A CN110610254B (en) | 2019-07-29 | 2019-07-29 | Multi-dimensional monitoring system and prediction evaluation method for pollution degree of equipment surface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110610254A CN110610254A (en) | 2019-12-24 |
| CN110610254B true CN110610254B (en) | 2021-02-02 |
Family
ID=68891009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910691027.2A Active CN110610254B (en) | 2019-07-29 | 2019-07-29 | Multi-dimensional monitoring system and prediction evaluation method for pollution degree of equipment surface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610254B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992322B (en) * | 2023-09-25 | 2024-01-16 | 广东申创光电科技有限公司 | Smart city data center management system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101614645A (en) * | 2008-06-23 | 2009-12-30 | 广东电网公司东莞供电局 | A kind of method of measuring accumulation of external insulation pollution of electric transmission and transformation equipment |
| CN104459489A (en) * | 2014-12-05 | 2015-03-25 | 深圳供电局有限公司 | Post insulator contamination degree recognition method |
| CN105067043A (en) * | 2015-08-28 | 2015-11-18 | 国家电网公司 | Power transmission and transformation equipment accumulated dirt growth rate prediction apparatus |
| CN105510525A (en) * | 2015-07-23 | 2016-04-20 | 深圳供电局有限公司 | Electric-transmission-line dirt monitoring apparatus and method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4901524B2 (en) * | 2007-02-22 | 2012-03-21 | 株式会社東芝 | Paper sheet contamination degree determination apparatus and contamination degree determination method |
| CN104316851A (en) * | 2014-10-30 | 2015-01-28 | 国网上海市电力公司 | Method and device for automatically monitoring pollution of line insulators |
-
2019
- 2019-07-29 CN CN201910691027.2A patent/CN110610254B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101614645A (en) * | 2008-06-23 | 2009-12-30 | 广东电网公司东莞供电局 | A kind of method of measuring accumulation of external insulation pollution of electric transmission and transformation equipment |
| CN104459489A (en) * | 2014-12-05 | 2015-03-25 | 深圳供电局有限公司 | Post insulator contamination degree recognition method |
| CN105510525A (en) * | 2015-07-23 | 2016-04-20 | 深圳供电局有限公司 | Electric-transmission-line dirt monitoring apparatus and method |
| CN105067043A (en) * | 2015-08-28 | 2015-11-18 | 国家电网公司 | Power transmission and transformation equipment accumulated dirt growth rate prediction apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 基于距离相关系数和支持向量机回归的PM2.5浓度滚动统计预报方案;王黎明 等;《环境科学学报》;20170406;第37卷(第4期);第1268-1276页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110610254A (en) | 2019-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106199305A (en) | Underground coal mine electric power system dry-type transformer insulation health state evaluation method | |
| CN101650404B (en) | Method for detecting and identifying constructional deficiencies of high-voltage and supervoltage cables and cable sets | |
| CN109102171A (en) | A kind of substation equipment condition intelligent evaluation system and method based on big data | |
| CN108256559A (en) | A kind of low pressure stealing method for positioning user based on the local outlier factor | |
| CN110210701A (en) | A kind of grid equipment risk perceptions method | |
| CN114966467A (en) | Power transmission line state evaluation method based on digital twinning | |
| CN111256876B (en) | High-voltage switch cabinet temperature monitoring system and method | |
| CN105139158A (en) | Power grid abnormal information intelligent alarming and assistant decision-making method | |
| CN110019098A (en) | Electrical energy measurement big data analysis system based on Hadoop frame | |
| CN111525697A (en) | Medium and low voltage power distribution network electricity larceny prevention method and system based on current monitoring and line topology analysis | |
| CN110610254B (en) | Multi-dimensional monitoring system and prediction evaluation method for pollution degree of equipment surface | |
| CN105391168B (en) | Transformer load real-time control method | |
| CN108376194A (en) | Insulator contamination prediction technique based on atmospheric environmental parameters | |
| CN109387779A (en) | A kind of omnipotent breaker operation attachment method for predicting residual useful life based on statistical data driving | |
| CN104316851A (en) | Method and device for automatically monitoring pollution of line insulators | |
| CN107884646B (en) | Emergency warning method for transformer substation online monitoring system | |
| CN108459269A (en) | A kind of 10kV pvs (pole-mounted vacuum switch)s state on-line evaluation method and apparatus | |
| CN114959716A (en) | Stray current interference test probe for cathode protection pipeline and intelligent monitoring system | |
| CN103400308A (en) | Online detection method and online detection system for running state of GIS (gas insulated switchgear) equipment | |
| CN103389427A (en) | Online detection method and system for GIS (gas insulated switchgear) operational condition | |
| CN114034997A (en) | Insulator degradation degree prediction method and system based on multiple parameters | |
| CN110907731A (en) | Transformer substation thermal state evaluation method and system based on temperature sensing | |
| CN108604821A (en) | Energy expenditure alarm method, energy expenditure alarm system and platform | |
| CN103472297A (en) | Electricity subentry measurement method | |
| CN111668926B (en) | Method for monitoring service microenvironment of distribution network equipment ring network unit in hot and humid climate |
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 |