CN117663005A - Power plant pipe valve leakage inspection device and abnormal data analysis method thereof - Google Patents
Power plant pipe valve leakage inspection device and abnormal data analysis method thereof Download PDFInfo
- Publication number
- CN117663005A CN117663005A CN202311748896.7A CN202311748896A CN117663005A CN 117663005 A CN117663005 A CN 117663005A CN 202311748896 A CN202311748896 A CN 202311748896A CN 117663005 A CN117663005 A CN 117663005A
- Authority
- CN
- China
- Prior art keywords
- data
- temperature
- leakage
- pipe valve
- power plant
- 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.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 46
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000007405 data analysis Methods 0.000 title abstract description 11
- 239000000523 sample Substances 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000009529 body temperature measurement Methods 0.000 claims description 41
- 238000012544 monitoring process Methods 0.000 claims description 23
- 238000007621 cluster analysis Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000009191 jumping Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/005—Protection or supervision of installations of gas pipelines, e.g. alarm
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- 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
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0037—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the heat emitted by liquids
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Acoustics & Sound (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a power plant pipe valve leakage inspection device and an abnormal data analysis method thereof, the power plant pipe valve leakage inspection device comprises a handheld cylinder, a data processing terminal and a data acquisition component, wherein analysis software is arranged in the data processing terminal, the data acquisition component comprises an RFID card reader arranged on the side edge of the handheld cylinder, a temperature and humidity sensor and an infrared temperature measuring probe which are arranged on the top of the handheld cylinder, a left laser emitter and a right laser emitter which are arranged on the top of the handheld cylinder and respectively positioned on two sides of the infrared temperature measuring probe, an input key arranged on the side edge of the handheld cylinder and an RS485 bus switch module arranged in the handheld cylinder, and the invention can intervene and treat pipe valve leakage in advance to reduce pipe valve leakage expansion loss.
Description
Technical Field
The invention relates to the technical field of thermal inspection, in particular to a pipe valve leakage inspection device of a power plant and an abnormal data analysis method thereof.
Background
The thermal inspection data mainly comprises field meter data such as temperature, pressure and the like, indoor environment temperature and humidity data, rotating machine vibration data, important equipment shell temperature and pipe valve leakage side temperature values. The indoor environment temperature, the humidity data and the temperature value of the leakage side of the pipe valve are controlled, the filling data are limit value parameters and are divided into normal values and out-of-limit values, and the abnormal alarming of the data is relatively easy to handle.
The valve leakage side temperature value can form different filling data characteristics along with the changes of shutdown, startup, warm-up, high-low load operation and environmental temperature values. Parameter-filled miscut sources are mainly derived from sensor focus position errors.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description summary and in the title of the application, to avoid obscuring the purpose of this section, the description summary and the title of the invention, which should not be used to limit the scope of the invention.
Therefore, the invention aims to provide a pipe valve leakage inspection device of a power plant and an abnormal data analysis method thereof, wherein a temperature difference data sequence of temperature measurement areas and environmental temperature is established through a data acquisition system, abnormal judgment is carried out on temperature data of leakage inspection positions, so that inspection temperature data alignment states are checked, leakage inspection data input reliability analysis is formed, further pipe valve leakage states of the power plant are inspected and monitored through reliably input leakage inspection data, interference treatment is carried out on pipe valve leakage in advance, and pipe valve leakage expansion loss is reduced.
In order to solve the technical problems, according to one aspect of the present invention, the following technical solutions are provided:
a power plant pipe valve leak inspection device, comprising:
a hand-held cartridge;
the data processing terminal is internally provided with analysis software;
the data acquisition assembly comprises an RFID card reader arranged on the side edge of the handheld cylinder, a temperature and humidity sensor and an infrared temperature measuring probe arranged on the top of the handheld cylinder, a left laser transmitter and a right laser transmitter which are arranged on the top of the handheld cylinder and respectively positioned on two sides of the infrared temperature measuring probe, an input key arranged on the side edge of the handheld cylinder and an RS bus switch module arranged in the handheld cylinder;
the RFID card reader, the temperature and humidity sensor, the infrared temperature measuring probe and the RS bus switch module are electrically connected, and the RS485 bus switch module is electrically connected with the data processing terminal through a data line.
As an optimal scheme of the power plant pipe valve leakage inspection device, the data processing terminal is a tablet computer.
As a preferred embodiment of the power plant pipe valve leakage inspection device, the data acquisition assembly further comprises a storage battery for supplying power.
An abnormal data analysis method of a pipe valve leakage inspection device of a power plant comprises the following steps:
s1, identifying leakage points and learning the characteristics of the data of the leakage points;
s2, performing FCN temperature difference cluster analysis on the leakage points;
s3, identifying the leakage points and analyzing the leakage point data.
As a preferable scheme of the method for analyzing abnormal data of the power plant pipe valve leakage inspection device of the present invention, in the step S1, the steps of identifying the leakage point and learning the characteristics of the leakage point data are as follows:
s101, identifying a leakage data input point of a pipe valve of a power plant through an RFID card reader, and transmitting preset data of a tag point to a data processing terminal through a MODBUS RTU;
s102, accurately identifying whether the input position is normal or not according to temperature measurement points of the four areas A1, A2, A3 and A4 and environmental background temperature difference data.
As an optimal scheme of the abnormal data analysis method of the power plant pipe valve leakage inspection device, in the step S2, FCN temperature difference cluster analysis is performed on leakage points, and the method comprises the following steps:
s201, identifying an RFID temperature measurement tag and identifying a temperature measurement object;
s202, reading leakage monitoring temperature monitoring area values according to four areas A1, A2, A3 and A4 respectively, forming a difference value with the ambient background temperature, and forming a power plant pipe valve leakage monitoring point temperature difference deviation data 140 group according to a random distance of 7m-10m and a random temperature measurement angle;
s203, forming a fuzzy clustering array X from 140 groups of data, forming an X classification space, and selecting two dimensions (X i ,x i ) I=140, namely 140 rounds of inspection training data are taken as cluster analysis, and longitudinal and transverse temperature difference values are used for drawing a two-dimensional cluster map;
s204, setting initialization parameter values, including fuzzy weighting parameter values m and clustering numbers k, iteration times S and algorithm termination errors epsilon;
s205, randomizing the center C of the initialization cluster 0 ,t＝0；
S206, calculating a membership matrix
Wherein mu ij Representing data x i Belonging to class center c j M is the fuzzy weighting parameter, mu ij ∈[0,1]i＝1,2,…,n；j＝1,2,…,k；D ij Is X i To the j-th class center C j Is the euclidean distance of (2);
s207, iteratively calculating the center of the cluster
S208, checking U s+1 -U s If the I < epsilon is satisfied, ending the algorithm, otherwise, jumping to the step S203;
s209, clustering center values which can form four types of temperature difference data of A1, A2, A3 and A4 are respectively marked as FA1, FA2, FA3 and FA4.
As a preferable scheme of the method for analyzing abnormal data of the power plant pipe valve leakage inspection device of the present invention, in the step S3, the identifying of the leakage point and the analysis of the leakage point data include the storage of a data feature table, and the steps are as follows:
s301, identifying an RFID temperature measurement tag and identifying a temperature measurement object;
s302, reading leakage monitoring temperature monitoring area values according to A1, A2, A3 and A4 respectively, forming a difference value with the ambient background temperature, and forming 140 groups of power plant pipe valve leakage monitoring point temperature difference deviation data according to a random distance of 7m-10m and a random temperature measuring angle.
S303, forming a leakage monitoring area temperature difference deviation characteristic table of A1, A2, A3 and A4 for the 140 groups of temperature measurement data in the step S302, forming Max and Min value range data for each temperature measurement area data, and respectively marking the Max and Min value range data as A1Max, A1Min, A2Max, A2Min, A3Max, A3Min, A4Max and A4Min.
As a preferable scheme of the method for analyzing abnormal data of the power plant pipe valve leakage inspection device, in the step S3, the step of analyzing the leakage point data is as follows:
s304, acquiring a serial number of the temperature measuring equipment through an RFID card reader and acquiring temperature difference data TA4 (t) according to the A4 area, wherein the serial number is 7m-10m close to the temperature measuring area;
s305, searching A1Max, A1Min, A2Max, A2Min, A3Max, A3Min, A4Max and A4Min according to the sequence numbers of the temperature measuring devices;
s306, judging TA4 (t) > A4Min, and TA4 (t) < A4Max, if yes, preliminarily judging that the temperature measuring area is correct, and if not, turning to step S307;
s307, calculating DA 1= |TA4 (t) -FA1|, DA 2= |TA4 (t) -FA2|, DA 3= |TA4 (t) -FA3|, and selecting the minimum value DAj of DA1, DA2 and DA3 as a suspected temperature measurement alignment area, wherein j=1, 2 and 3;
s308, judging TA4 (t) > AjMin, and if the detection result is met, displaying and prompting a temperature measurement area to be wrong, prompting a patrol inspector to correct temperature measurement, judging TA4 (t) < A2Min-2, prompting an infrared temperature sensor to be faulty, prompting the patrol inspector to replace an infrared temperature measurement probe, judging TA4 (t) > A1Max+10, and prompting a leakage alarm if the detection result is met, and further detecting to prompt the infrared temperature measurement probe to be faulty.
As a preferable scheme of the abnormal data analysis method of the power plant pipe valve leakage inspection device, the temperature difference data TA4 (t) is obtained by subtracting the temperature measured by the temperature and humidity sensor from the temperature measured by the infrared temperature measuring probe.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, through the temperature difference clustering learning of the background temperature and the infrared temperature measurement temperature of the pipe valve leakage area, four typical leakage monitoring area temperature clustering centers of A1, A2, A3 and A4 are obtained, a temperature difference deviation characteristic table is formed, according to the deviation values of the background temperature and the infrared temperature measurement temperature of the pipe valve leakage area, the leakage characteristics of the pipe valve can be analyzed, whether the infrared temperature measurement probe has a temperature measurement fault or not can be analyzed, whether the infrared temperature measurement area is aligned or not and the like, the pipe valve leakage inspection data can be input, the accuracy of the input data can be further analyzed, the leakage alarm is realized, the error of the field thermal inspection data input can be reduced, and the field thermal inspection data input effectiveness is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following detailed description will be given with reference to the accompanying drawings and detailed embodiments, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without inventive faculty for a person skilled in the art. Wherein:
FIG. 1 is a schematic diagram of a power plant pipe valve leak inspection device according to the present invention;
FIG. 2 is a diagram of the internal structure of a handheld cartridge of the power plant pipe valve leak inspection device of the present invention;
FIG. 3 is a wiring diagram of an RFID card reader, a temperature and humidity sensor, an infrared temperature measuring probe and an RS485 bus switch module of the pipe valve leakage inspection device of the power plant;
FIG. 4 is a schematic view of a temperature measuring point area of a pipe valve provided by the invention.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to the appended drawings.
Next, the present invention will be described in detail with reference to the drawings, wherein the sectional view of the device structure is not partially enlarged to general scale for the convenience of description, and the drawings are only examples, which should not limit the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
The invention provides a power plant pipe valve leakage inspection device and an abnormal data analysis method thereof, wherein a temperature difference data sequence of temperature measuring area temperature and environmental temperature is established through a data acquisition system, and abnormal judgment is carried out on temperature data of a leakage inspection position, so that inspection temperature data alignment state is checked, leakage inspection data input reliability analysis is formed, further, the leakage state of the power plant pipe valve is inspected and monitored through reliably input leakage inspection data, and further, pipe valve leakage is interfered and treated in advance, and pipe valve leakage expansion loss is reduced.
Fig. 1 to 3 are schematic structural views of a power plant pipe valve leakage inspection device according to the present invention, and referring to fig. 1 to 3, a main body portion of the power plant pipe valve leakage inspection device includes a handheld barrel 100, a data processing terminal 200 and a data acquisition assembly 300.
The handheld cartridge 100 is used to mount a data acquisition assembly 300.
Preferably, the data processing terminal 200 is a tablet computer, and the analysis software is embedded in the data processing terminal 200.
The data acquisition assembly 300 comprises an RFID card reader 310 arranged on the side edge of the handheld cylinder 100, a temperature and humidity sensor 320 and an infrared temperature measuring probe 330 arranged on the top of the handheld cylinder 100, a left laser transmitter 340 and a right laser transmitter 350 which are arranged on the top of the handheld cylinder 100 and are respectively positioned on two sides of the infrared temperature measuring probe 330, an input key 360 arranged on the side edge of the handheld cylinder 100, and an RS485 bus switch module 370 arranged in the handheld cylinder 100, wherein the data acquisition assembly 300 further comprises a storage battery 380 for supplying power, the temperature and humidity sensor 320 is used for measuring environmental temperature and humidity of a pipe valve working scene, background temperature data of the infrared temperature measuring probe 330 are formed, the left laser transmitter 340 and the right laser transmitter 350 are aligned with a temperature measuring area, after the readings of the display area are stable, the input key 360 is pressed, namely the field temperature can be input through double-click of the input key 360, and the input data can be deleted.
The RFID card reader 310, the temperature and humidity sensor 320, the infrared temperature measuring probe 330 and the RS485 bus switch module 370 are electrically connected, the RS485 bus switch module 370 is electrically connected with the data processing terminal 200 through a data line A, the infrared temperature measuring probe 330, the temperature and humidity sensor 320 and the RFID card reader 310 are assembled to the RS485 bus switch module 370 through an RS485 free protocol or a MODBUS RTU protocol, and data interaction is realized with built-in analysis software of the data processing terminal 200 through an RS485/USB data line 8.
The abnormal data analysis method of the power plant pipe valve leakage inspection device comprises the following steps:
1. leakage point identification and leakage point data feature learning
The RFID reader 310 is used for identifying the leakage data input points of the pipe valve of the power plant, such as a high-pressure pollution discharge valve 10078, a main steam regulating valve 10021, a feed water pump regulating valve 10156 and an auxiliary steam regulating valve 10043, and the RFID reader 310 is used for transmitting preset data of the label points, such as 10021, 10156 and 10043, through a MODBUS RTU. Is affected by start-up and shutdown, air temperature, ventilation condition and the like, and the characteristic correlation of temperature measurement point data is poor. The actual measurement research shows that the deviation of the temperature measurement point data and the environmental background temperature data has good association degree, and an association degree table can be formed. As shown in FIG. 4, the temperature measuring point areas are divided into four areas A1, A2, A3 and A4 respectively.
Taking 10078, 10021, 10156, 10043 as an example, table 1 is the data characteristics of different temperature measurement areas of the class 4 valve, and it is obvious that the A4 temperature difference has significant differences from A1, A2, A3. Whether the input position is normal or not can be accurately identified through temperature measurement points and environmental background temperature difference data.
TABLE 1 Power plant tube valve leakage monitoring area temperature differential deviation characterization table
2. FCM temperature difference cluster analysis of leakage points
The FCM algorithm is a clustering algorithm based on partitioning, and its idea is to maximize the similarity between objects partitioned into the same class, while minimizing the similarity between different classes. Assuming that the sample space X is to be divided into k classes, the class center set c= (C) 1 ,c 2 ,c 3 ,…,c k ) The objective function value of the following formula is minimized:
wherein:
μ ij ∈[0,1] i＝1,2,…,n；j＝1,2,…,k (3)
let U= (μ) ij ) Is a fuzzy membership matrix. Mu (mu) ij Representing data x i Belonging to class center c j Is a membership of (1). m is a fuzzy weighting parameter. Applying Lagrangian multiplication and based on the constraints described above, the following formula can be obtained:
wherein: i is more than or equal to 1 and less than or equal to c, j is more than or equal to 1 and less than or equal to N
Wherein D is ij Is X i To the j-th class center C j Is the Euclidean distance of (X) i -C j ||。
FCM fuzzy clustering algorithm flow
Step 1: identifying an RFID temperature measurement tag and identifying a temperature measurement object;
step 2: and respectively reading leakage monitoring temperature monitoring area values according to A1, A2, A3 and A4, forming a difference value with the ambient background temperature, and forming a power plant pipe valve leakage monitoring point temperature difference deviation data 140 group according to a random distance of 7m-10m and a random temperature measuring angle.
Step 3: and forming a fuzzy cluster array X from 140 groups of data to form an X classification space. Dimension selection in text two-dimensional (x i ,x i ) Where i=140, i.e. 140 rounds of training data were taken as cluster analysis. The longitudinal and transverse directions are temperature difference values and are used for drawing a two-dimensional cluster map.
Step 4: initialization parameter values are set, including fuzzy weighting parameter value m and cluster number k, and the number of iterations s and algorithm termination error epsilon.
Step 5: randomization initiates clustering center C 0 ,t＝0。
Step 6: calculating membership degree matrix U can calculate U through (4) s Obtaining the product.
Step 7: the center of the cluster is calculated according to the iteration of (5)
Step 8, checking U s+1 -U s If yes, ending the algorithm, otherwise, jumping to the step 3.
Step 9: and clustering center values which can form four types of temperature difference data of A1, A2, A3 and A4 are respectively marked as FA1, FA2, FA3 and FA4.
The FCM algorithm requires two parameters, one being the number of clusters c and the other being the parameter m. Generally, c is much smaller than the total number of clustered samples, while ensuring that c > 1, a cluster parameter of 4 is selected herein. For m, it is a parameter that controls the flexibility of the algorithm, if m is too large, the clustering effect will be very small, and if m is too small, the algorithm will approach the K-means clustering algorithm.
And a step of identifying the leakage points and analyzing the leakage point data:
data profile reserves
Step 1: identifying an RFID temperature measurement tag and identifying a temperature measurement object;
step 2: and respectively reading leakage monitoring temperature monitoring area values according to A1, A2, A3 and A4, forming a difference value with the ambient background temperature, and forming 140 groups of power plant pipe valve leakage monitoring point temperature difference deviation data according to a random distance of 7m-10m and a random temperature measuring angle.
Step 3: and (3) forming a leakage monitoring area temperature difference deviation characteristic table of A1, A2, A3 and A4 for 140 groups of temperature measurement data in the step (2), and forming Max and Min value range data for each temperature measurement area data. Marked as A1Max (RFID tag number), A1Min (RFID tag number), A2Max (RFID tag number), A2Min (RFID tag number), A3Max (RFID tag number), A3Min (RFID tag number), A4Max (RFID tag number), and A4Min (RFID tag number), respectively.
Leakage point data analysis step
Step 1: adjacent to the temperature measuring areas 7m-10m, the serial numbers of the temperature measuring equipment are acquired through the RFID card reader 10, and temperature difference data TA4 (t) are acquired according to the area A4 (the infrared temperature measuring probe 6-the field temperature and humidity sensor 9).
Step 2: according to the temperature measuring equipment serial numbers, A1Max (RFID label serial number), A1Min (RFID label serial number), A2Max (RFID label serial number), A2Min (RFID label serial number), A3Max (RFID label serial number), A3Min (RFID label serial number), A4Max (RFID label serial number) and A4Min (RFID label serial number) are searched.
Step 3: judging TA4 (t) > A4Min (RFID label serial number), TA4 (t) < A4Max (RFID label serial number, if yes, it can be preliminarily judged that the temperature measuring area is correct, if not, the step is transferred to step 4.
Step 4: calculating DA 1= |TA4 (t) -FA1|, DA 2= |TA4 (t) -FA2|, DA 3= |TA4 (t) -FA3|,
and selecting the minimum value DAj of DA1, DA2 and DA3 as a suspected thermometric alignment area, wherein j=1, 2 and 3.
Step 5: judging TA4 (t) > AjMin (RFID label serial number), and if TA4 (t) < AjMax (RFID label serial number) is met, displaying and prompting that the temperature measuring area is wrong, and prompting an inspector to correct temperature measurement.
Step 6: and judging TA4 (t) < A2Min (RFID label serial number) -2, prompting the fault of the infrared temperature sensor, and prompting the inspector to replace the temperature measuring probe.
Step 7: judging TA4 (t) > A1Max (RFID label serial number) +10, and prompting leakage alarm if the judgment is satisfied, and further detecting.
Step 8: and prompting the fault of the infrared temperature sensor.
Although the invention has been described hereinabove with reference to embodiments, various modifications thereof may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the features of the disclosed embodiments may be combined with each other in any manner as long as there is no structural conflict, and the exhaustive description of these combinations is not given in this specification merely for the sake of omitting the descriptions and saving resources. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (9)
1. A power plant pipe valve leak inspection device, comprising:
a hand-held cartridge (100);
a data processing terminal (200) in which analysis software is built;
the data acquisition assembly (300) comprises an RFID card reader (310) arranged on the side edge of the handheld cylinder (100), a temperature and humidity sensor (320) and an infrared temperature measuring probe (330) arranged on the top of the handheld cylinder (100), a left laser transmitter (340) and a right laser transmitter (350) which are arranged on the top of the handheld cylinder (100) and respectively positioned on two sides of the infrared temperature measuring probe (330), an input key (360) arranged on the side edge of the handheld cylinder (100) and an RS485 bus switch module (370) arranged in the handheld cylinder (100);
the RFID card reader (310), the temperature and humidity sensor (320), the infrared temperature measuring probe (330) and the RS485 bus switch module (370) are electrically connected, and the RS485 bus switch module (370) is electrically connected with the data processing terminal (200) through a data line (A).
2. A power plant pipe valve leak inspection device according to claim 1, characterized in that the data processing terminal (200) is a tablet computer.
3. The power plant pipe valve leak inspection device of claim 1, wherein the data acquisition assembly (300) further comprises a battery (380) for supplying power.
4. A method of analyzing anomaly data for a power plant pipe valve leak inspection device according to any one of claims 1 to 3, comprising the steps of:
s1, identifying leakage points and learning the characteristics of the data of the leakage points;
s2, performing FCN temperature difference cluster analysis on the leakage points;
s3, identifying the leakage points and analyzing the leakage point data.
5. The method for analyzing abnormal data of a power plant pipe valve leakage inspection device according to claim 4, wherein in the step S1, the steps of identifying the leakage point and learning the characteristics of the leakage point data are as follows:
s101, identifying a leakage data input point of a pipe valve of a power plant through an RFID card reader (310), and transmitting preset data of a tag point to a data processing terminal (200) through a MODBUS RTU;
s102, accurately identifying whether the input position is normal or not according to temperature measurement points of the four areas A1, A2, A3 and A4 and environmental background temperature difference data.
6. The method for analyzing abnormal data of a power plant pipe valve leakage inspection device according to claim 4, wherein in the step S2, the step of performing FCN temperature difference cluster analysis on the leakage points is as follows:
s201, identifying an RFID temperature measurement tag and identifying a temperature measurement object;
s202, reading leakage monitoring temperature monitoring area values according to four areas A1, A2, A3 and A4 respectively, forming a difference value with the ambient background temperature, and forming a power plant pipe valve leakage monitoring point temperature difference deviation data 140 group according to a random distance of 7m-10m and a random temperature measurement angle;
s203, forming a fuzzy clustering array X from 140 groups of data, forming an X classification space, and selecting two dimensions (X i ,x i ) I=140, namely 140 rounds of inspection training data are taken as cluster analysis, and longitudinal and transverse temperature difference values are used for drawing a two-dimensional cluster map;
s204, setting initialization parameter values, including fuzzy weighting parameter values m and clustering numbers k, iteration times S and algorithm termination errors epsilon;
s205, randomizing the center C of the initialization cluster 0 ,t＝0；
S206, calculating a membership matrix
Wherein mu ij Representing data x i Belonging to class center c j M is the fuzzy weighting parameter, mu ij ∈[0,1]i＝1,2,…,n；j＝1,2,…,k；D ij Is X i To the j-th class center C j Is the euclidean distance of (2);
s207, iteratively calculating the center of the cluster1≤i≤c；
S208, checking U s+1 -U s If the I < epsilon is satisfied, ending the algorithm, otherwise, jumping to the step S203;
s209, clustering center values which can form four types of temperature difference data of A1, A2, A3 and A4 are respectively marked as FA1, FA2, FA3 and FA4.
7. The method for analyzing abnormal data of a power plant pipe valve leakage inspection device according to claim 1, wherein in the step S3, the identifying of the leakage point and the analysis of the leakage point data include the storage of a data feature table, and the steps are as follows:
s301, identifying an RFID temperature measurement tag and identifying a temperature measurement object;
s302, reading leakage monitoring temperature monitoring area values according to A1, A2, A3 and A4 respectively, forming a difference value with the ambient background temperature, and forming 140 groups of power plant pipe valve leakage monitoring point temperature difference deviation data according to a random distance of 7m-10m and a random temperature measuring angle.
S303, forming a leakage monitoring area temperature difference deviation characteristic table of A1, A2, A3 and A4 for the 140 groups of temperature measurement data in the step S302, forming Max and Min value range data for each temperature measurement area data, and respectively marking the Max and Min value range data as A1Max, A1Min, A2Max, A2Min, A3Max, A3Min, A4Max and A4Min.
8. The method for analyzing abnormal data of a power plant pipe valve leakage inspection device according to claim 1, wherein in the step S3, the step of analyzing the leakage point data is as follows:
s304, 7m-10m of adjacent temperature measuring areas are obtained, the serial numbers of the temperature measuring equipment are obtained through the RFID card reader (310), and temperature difference data TA4 (t) are obtained according to the area A4;
s305, searching A1Max, A1Min, A2Max, A2Min, A3Max, A3Min, A4Max and A4Min according to the sequence numbers of the temperature measuring devices;
s306, judging TA4 (t) > A4Min, and TA4 (t) < A4Max, if yes, preliminarily judging that the temperature measuring area is correct, and if not, turning to step S307;
s307, calculating DA 1= |TA4 (t) -FA1|, DA 2= |TA4 (t) -FA2|, DA 3= |TA4 (t) -FA3|, and selecting the minimum value DAj of DA1, DA2 and DA3 as a suspected temperature measurement alignment area, wherein j=1, 2 and 3;
s308, judging TA4 (t) > AjMin, and TA4 (t) < AjMax, if the detection result is met, displaying and prompting a temperature measurement area to be wrong, prompting a patrol inspector to correct temperature measurement, judging TA4 (t) < A2Min-2, prompting an infrared temperature sensor to be faulty, prompting the patrol inspector to replace an infrared temperature measuring probe (330), judging TA4 (t) > A1Max+10, prompting a leakage alarm if the detection result is met, and further prompting the infrared temperature measuring probe (330) to be faulty.
9. The method for analyzing abnormal data of a power plant pipe valve leakage inspection device according to claim 1, wherein the temperature difference data TA4 (t) is obtained by subtracting the temperature measured by the temperature and humidity sensor (320) from the temperature measured by the infrared temperature measuring probe (330).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311748896.7A CN117663005A (en) | 2023-12-19 | 2023-12-19 | Power plant pipe valve leakage inspection device and abnormal data analysis method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311748896.7A CN117663005A (en) | 2023-12-19 | 2023-12-19 | Power plant pipe valve leakage inspection device and abnormal data analysis method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117663005A true CN117663005A (en) | 2024-03-08 |
Family
ID=90082537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311748896.7A Pending CN117663005A (en) | 2023-12-19 | 2023-12-19 | Power plant pipe valve leakage inspection device and abnormal data analysis method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117663005A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875946A (en) * | 2024-03-11 | 2024-04-12 | 国网安徽省电力有限公司合肥供电公司 | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment |
-
2023
- 2023-12-19 CN CN202311748896.7A patent/CN117663005A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875946A (en) * | 2024-03-11 | 2024-04-12 | 国网安徽省电力有限公司合肥供电公司 | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment |
| CN117875946B (en) * | 2024-03-11 | 2024-06-04 | 国网安徽省电力有限公司合肥供电公司 | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117663005A (en) | Power plant pipe valve leakage inspection device and abnormal data analysis method thereof | |
| CN110826642B (en) | Unsupervised anomaly detection method for sensor data | |
| CN111814740B (en) | Pointer instrument reading identification method, device, computer equipment and storage medium | |
| US20220082625A1 (en) | Data processor, data processing method, and computer program | |
| CN109670549B (en) | Data screening method and device for thermal power generating unit and computer equipment | |
| CN116881749B (en) | Pollution site construction monitoring method and system | |
| CN113591711B (en) | Granary hazard source safety monitoring method and system based on artificial intelligence | |
| CN103020689A (en) | Method for recognizing hole-shaped codes of articles on basis of geometric figures | |
| CN111767192B (en) | Business data detection method, device, equipment and medium based on artificial intelligence | |
| CN114994547B (en) | Battery pack safety state evaluation method based on deep learning and consistency detection | |
| CN110705540A (en) | Animal remedy production pointer instrument image identification method and device based on RFID and deep learning | |
| CN114461476B (en) | Memory bank fault detection method, device and system | |
| CN112525925A (en) | Keyboard detection method, system, electronic equipment and medium | |
| Xu et al. | Detection method of insulator based on single shot multibox detector | |
| Khalid et al. | Tropical wood species recognition system based on multi-feature extractors and classifiers | |
| CN114781520A (en) | Natural gas behavior abnormity detection method and system based on improved LOF model | |
| CN116228770B (en) | Method and system for identifying and monitoring pipeline leakage | |
| CN116310913B (en) | Natural resource investigation monitoring method and device based on unmanned aerial vehicle measurement technology | |
| CN110222814B (en) | Ethylene cracking furnace tube heavy tube identification method based on embedded DCNN | |
| Xiao et al. | Support evidence statistics for operation reliability assessment using running state information and its application to rolling bearing | |
| CN116011982A (en) | Online monitoring method and system for breakage of grinding roller of coal mill | |
| CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model | |
| CN116337377A (en) | Multi-sensor-based mining equipment fault state analysis method and device | |
| CN116051885A (en) | Processing and mesoscale vortex identification method for marine mesoscale vortex sample data | |
| CN109190717A (en) | A kind of Multiple Source Sensor fault detection method based on ICA and kNN |
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 |