CN117436845A - Abnormal data monitoring method for intelligent district heating system - Google Patents
Abnormal data monitoring method for intelligent district heating system Download PDFInfo
- Publication number
- CN117436845A CN117436845A CN202311722925.2A CN202311722925A CN117436845A CN 117436845 A CN117436845 A CN 117436845A CN 202311722925 A CN202311722925 A CN 202311722925A CN 117436845 A CN117436845 A CN 117436845A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- heating
- data
- user
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 255
- 238000010438 heat treatment Methods 0.000 title claims abstract description 219
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 138
- 230000005856 abnormality Effects 0.000 claims abstract description 93
- 238000011156 evaluation Methods 0.000 claims abstract description 74
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 239000008236 heating water Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to the technical field of data processing, in particular to a method for monitoring abnormal data of a heat supply system of an intelligent community, which comprises the following steps: collecting water temperature data and water flow data of all users within the collecting time range; acquiring outlier factors of each user according to water temperature data and water flow data of each user, and further acquiring all abnormal users; obtaining first heating abnormality evaluation of each abnormal user according to water temperature data and water flow data; acquiring an update coefficient of each outlier factor according to the outlier factors of all abnormal users; obtaining a second heating abnormal evaluation of each abnormal user according to the first heating abnormal evaluation of each abnormal user and the update coefficient of the outlier factor; and carrying out abnormal overhaul on the heating system according to the second heating abnormal evaluation. The invention aims to solve the problem that the abnormal evaluation difference of a plurality of abnormal users caused by the same fault greatly affects the overhaul efficiency, thereby setting approximate overhaul priority for the same fault and improving the overhaul efficiency.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an abnormal data monitoring method for a heat supply system of an intelligent community.
Background
An intelligent district heating system is a method for improving the efficiency, comfort and manageability of a heating system by utilizing modern technology and automation control. The system integrates the internet of things, data analysis, automatic control and intelligent equipment to provide a more intelligent and sustainable district heating solution.
At present, abnormal data monitoring for heating is mainly to obtain abnormal evaluation by analyzing heating data distribution trend of users, and then heating maintenance sequence of abnormal users is set according to the size of the abnormal evaluation, however, heating abnormality of a plurality of users possibly occurs in the same fault, a plurality of different abnormal evaluations can be generated after the abnormal data monitoring is influenced by use environment, so that when an intelligent district heating system monitors abnormality and carries out maintenance, the abnormality of a plurality of users in the same fault can not be related, and maintenance efficiency is affected.
Disclosure of Invention
The invention provides an abnormal data monitoring method of a heat supply system of an intelligent community, which aims to solve the problem that the existing heating abnormality of a plurality of users possibly occurs in the same fault, and a plurality of different abnormal evaluations are generated after the heating abnormality is influenced by a use environment, so that the abnormality of the plurality of users in the same fault cannot be related when the heat supply system of the intelligent community monitors the abnormality and overhauls, and the overhauling efficiency is influenced.
The invention discloses an abnormal data monitoring method of a heat supply system of an intelligent community, which adopts the following technical scheme:
the embodiment of the invention provides a method for monitoring abnormal data of a heating system of an intelligent community, which comprises the following steps:
collecting water temperature data and water flow data of all users within the collecting time range;
mapping water temperature data and water flow data of each user at the current acquisition time to a two-dimensional sample space to obtain heating data points of each user; obtaining outlier factors of heating data points of each user at the current acquisition time by using a local outlier factor algorithm in a two-dimensional sample space; obtaining abnormal users in all users at the current collection time according to outlier factors of heating data points of each user at the current collection time; acquiring first heating abnormal evaluation of each abnormal user at the current acquisition time according to water temperature data and water flow data of each abnormal user in the acquisition time range; the outlier factors of all abnormal users at the current acquisition time are arranged to obtain outlier factor sequences of all abnormal users at the current acquisition time; acquiring an update coefficient of each outlier factor in the outlier factor sequence at the current acquisition time according to the outlier factor sequences of all abnormal users at the current acquisition time; obtaining a second heating abnormal evaluation of each abnormal user at the current acquisition time according to the first heating abnormal evaluation of each abnormal user at the current acquisition time and the update coefficient of the outlier factor;
and carrying out abnormal overhaul on the heating system according to the second heating abnormal evaluation of each abnormal user.
Further, the obtaining heating data points for each user includes:
and mapping the water temperature data and the water flow data of each user at the current acquisition time to a two-dimensional sample space to obtain heating data points of each user, wherein the horizontal axis of the heating data points represents the water temperature data, and the vertical axis of the heating data points represents the water flow data.
Further, the obtaining abnormal users in all users at the current acquisition time includes:
heating data points with outliers greater than 1 in all heating data points are marked as outlier data points, and users with heating data points of users belonging to outlier data points in all users are marked as abnormal users.
Further, the obtaining the first heating abnormality evaluation of each abnormal user at the current collection time according to the water temperature data and the water flow data of each abnormal user in the collection time range includes:
the method comprises the steps of obtaining a heating abnormality starting time of each user at the current collecting time, obtaining a first heating abnormality coefficient of each user at the current collecting time according to the heating abnormality starting time and combining the change of water temperature data and water flow data, normalizing the first heating abnormality coefficients of all users at the current collecting time by using a linear normalization function, and obtaining a first heating abnormality evaluation of each user at the current collecting time as a normalization result.
Further, the specific method for obtaining the heating abnormality starting time of each user at the current collection time comprises the following steps:
acquisition of the firstThe absolute value of the difference value of the water temperature data of adjacent collecting moments in all water temperature data of abnormal users is selected, and the collecting moment of the largest absolute value of the difference values is recorded as the +.>Abnormal starting time of water temperature data of abnormal users; get->The absolute value of the difference value of the water flow data at adjacent collecting moments in all water flow data of abnormal users is selected, and the collecting moment of the largest absolute value of the difference values is recorded as the +.>Abnormal starting time of water flow data of abnormal users; will be->The average value of the abnormal start time of the water temperature data of the individual abnormal user and the abnormal start time of the water flow data is recorded as +.>Heating abnormality start time of individual abnormal users.
Further, the obtaining the first heating abnormality coefficient of each user at the current collection time according to the heating abnormality start time and combining the change of the water temperature data and the water flow data includes:
the current acquisition time is marked as the firstMoment->The abnormal users are currently collectedFirst heating abnormality coefficient of time->The calculation mode of (a) is as follows:
wherein,for the +.>Heating abnormality starting time of individual abnormal users; />Is->Standard data preset by the heating data;
when (when)At the time->The heating data represent water temperature data, when +.>At the time->The individual heating data represent water flow data;
indicate->Person abnormal user->Acquisition of heating data at current acquisition timeMean value in time range, +.>Is->Person abnormal user->Maximum value of the individual heating data in the range of the current acquisition time, < >>Is->Person abnormal user->And the minimum value of the heating data in the collection time range of the current collection time.
Further, the obtaining the outlier factor sequences of all abnormal users at the current acquisition time includes:
and (3) carrying out ascending order arrangement on the outlier factors of all abnormal users at the current acquisition time to obtain an outlier factor sequence of all abnormal users at the current acquisition time.
Further, the obtaining the update coefficient of each outlier factor in the outlier factor sequence at the current acquisition time according to the outlier factor sequences of all abnormal users at the current acquisition time comprises:
the current acquisition time is marked as the firstMoment, the first +.in the outlier factor sequence at the current acquisition moment>The individual outlier factors were noted +.>First +.in the outlier factor sequence at the current acquisition time>Update coefficient of individual outlier factor +.>The calculation mode of (a) is as follows:
wherein,for the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>For the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>To the first in the sequence of outliers at the current acquisition timeIndividual outlier factors;
represents an exponential function based on natural constants, < ->Is an error parameter;
the value range of (2) is +.>，/>The number of abnormal users at the current acquisition time is represented.
Further, the obtaining the second heating abnormality evaluation of each abnormal user at the current collection time includes:
the current acquisition time is marked as the firstMoment of time, the first +.in the sequence of outliers at the current acquisition moment>Abnormal user corresponding to the individual outlier factor is marked as +.>Abnormal user, then->The updating coefficient of the outlier factor of the abnormal user at the current acquisition time is the +.>Update coefficient of individual outlier factor, will +.>The first heating abnormality evaluation of the individual abnormal users at the current acquisition time is recorded as +.>Will be in the sequence of outliers at the current acquisition instant +.>Abnormal user corresponding to the individual outlier factor is marked as +.>Abnormal user, will->The abnormal users are at the current acquisition timeThe first heating abnormality evaluation of (1) is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the Starting from an abnormal user corresponding to the 2 nd outlier factor in an outlier factor sequence at the current acquisition time, calculating the ++according to the order of the outlier factor sequence from small to large>Second heating abnormality evaluation by individual abnormality user at current acquisition time +.>The method comprises the following steps:
wherein,is->Updating coefficient of outlier factor of abnormal user at current acquisition time,/for each abnormal user>For the first +.in the sequence of outliers at the current acquisition instant>The corresponding +.>And the abnormal users evaluate the second heating abnormality at the current acquisition time.
Further, the performing the abnormal overhaul of the heating system according to the second heating abnormal evaluation of each abnormal user includes:
and arranging the second heating abnormal evaluations of all the abnormal users at the current acquisition time in descending order to obtain an overhaul priority sequence of all the abnormal users, wherein the overhaul priority of the abnormal users with the larger second heating abnormal evaluations in the overhaul priority sequence is higher, and overhaul of the heating equipment of each abnormal user is carried out according to the overhaul sequence of the abnormal users in the priority sequence.
The technical scheme of the invention has the beneficial effects that: according to the invention, water temperature data and water flow data of each user in the acquisition time range are acquired, the water temperature data and the water flow data of the current acquisition time are mapped to a two-dimensional space, an outlier factor of each user is obtained by combining an LOF algorithm, a user corresponding to an outlier data point is extracted according to the outlier factor to serve as an abnormal user, and the user with the abnormality at the current acquisition time is screened out; obtaining a first heating abnormal evaluation of each user according to water temperature data and water flow change of each abnormal user in the acquisition time range, wherein the first heating abnormal evaluation represents the fault severity and fault characteristics of the abnormal user; and updating the first heating abnormal evaluation according to the relevance of the outlier factors of each abnormal user to obtain a second heating abnormal evaluation of each abnormal user, and updating the second heating abnormal evaluation of a plurality of users possibly belonging to the same fault to be an approximate value by utilizing the relevance of the outlier factors, so that when the maintenance priorities are arranged according to the second heating abnormal evaluation after updating, the abnormality possibly belonging to the same fault can be simultaneously maintained, and the purpose of improving the maintenance efficiency of the heating system is achieved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart showing the steps of a method for monitoring abnormal data of a heat supply system of an intelligent community.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of a method for monitoring abnormal data of a heat supply system of an intelligent district according to the present invention, which is specific to the implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of an embodiment may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the method for monitoring abnormal data of the intelligent district heating system provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for monitoring abnormal data of a heating system of an intelligent district according to an embodiment of the invention is shown, the method comprises the following steps:
and S001, collecting water temperature data and water flow data of each user in a collecting time range.
The purpose of this embodiment is to obtain the heating abnormality evaluation of each user by analyzing the heating data of each user, and then arrange the order of heating maintenance according to the heating abnormality evaluation; it is therefore first necessary to acquire water temperature data and water flow data for each user heating. Specifically, the heating condition of the user is directly expressed as the heating water temperature and the water flow, so that the water temperature data and the water flow data during heating are selected as the data basis for abnormal heating evaluation, the water temperature data and the water flow data are collected through the sensors arranged at the water inlet and the water outlet of each user side pipeline, the water temperature data and the water flow data are used as the heating data of each user, the collection interval of each collection is 1 minute, and the water temperature data and the water flow data at each collection moment collected by the sensors are stored into the database of the intelligent district heating system through the Internet of things; and recording a time interval from the current acquisition time of the previous day to the current acquisition time of the current day in the database as an acquisition time range, and taking water temperature data and water flow data of all users in the acquisition time range as a data base of the embodiment.
So far, the water temperature data and the water flow data of all users in the acquisition time range are obtained.
And S002, constructing a two-dimensional sample data space by using water temperature data and water flow data to obtain heating data points of each user, obtaining outlier factors of each heating data point by using an LOF algorithm, and obtaining outlier data points and abnormal users corresponding to each outlier data point according to the outlier factors of the heating data points.
It should be noted that, the heating abnormality is represented in that the heating water temperature and the water flow rate are greatly different compared with the normal condition, and the user with the heating abnormality at the user side becomes an individual phenomenon in all users, so that the water temperature data and the water flow rate data of the user with the heating abnormality are outliers compared with the user with the heating abnormality, therefore, the embodiment uses the water temperature data and the water flow rate data of all users to construct a two-dimensional sample space to obtain the heating data point of each user, uses the local outlier (Local Outlier Factor, LOF) algorithm to obtain the outlier of each heating data point, and further obtains the user belonging to the heating abnormality as the abnormal user.
Specifically, in the embodiment, water temperature data and water flow data of each user at the current acquisition time are mapped to a two-dimensional sample space to obtain heating data points of each user, wherein the horizontal axis of the heating data points represents the water temperature data, and the vertical axis of the heating data points represents the water flow data; obtaining outlier factors of each heating data point in a two-dimensional sample space by using an LOF algorithm, marking heating data points with outlier factors larger than 1 in all the heating data points as outlier data points, and marking users with heating data points of users belonging to the outlier data points in all the users as abnormal users; the LOF algorithm is a known technique, and the embodiment is not described in detail.
So far, all abnormal users and outliers of all abnormal users are obtained.
And step S003, obtaining first heating abnormality evaluation of each abnormal user according to water temperature data and water flow data of each abnormal user in the acquisition time range.
When a user with heating abnormality is subjected to fault maintenance, an maintenance sequence is required to be set according to the degree of heating abnormality of each user, and then maintenance of heating faults is performed according to the maintenance sequence of each user, so that the degree of heating abnormality is influenced mainly by the duration of abnormality, the difference between the actual heating water temperature and the standard water temperature and the difference between the actual heating water flow and the standard water flow, and the longer the duration of abnormality, the larger the difference between the actual heating water temperature and the water flow compared with the standard water temperature and the water flow, the more likely the faults exist, therefore, the embodiment obtains the starting time of detecting heating abnormality of each abnormal user according to the change of water temperature data and water flow data of each abnormal user in the acquisition time range, and obtains the first heating abnormality evaluation of each abnormal user according to the duration of heating abnormality of each abnormal user to the current acquisition time combined with the water temperature and water flow change degree.
Specifically, when heating is normal, fluctuation of water temperature data and water flow data is small, when a user side has heating faults, for example, pipeline blockage, pipeline water leakage and the like, water flow passing through the user side is reduced, water temperature is reduced, and the moment when the faults occur is the moment when the water flow and the water temperature change greatly; based on the logic, the embodiment marks the time at which the acquisition time range starts as the 0 th time, and the current acquisition time is the maximum value of the acquisition time.
Further, obtain the firstThe absolute value of the difference value of the water temperature data of adjacent collecting moments in all water temperature data of abnormal users is selected, and the collecting moment of the largest absolute value of the difference values is recorded as the +.>Abnormal starting time of water temperature data of abnormal users; similarly, get->The absolute value of the difference value of the water flow data at adjacent collecting moments in all water flow data of abnormal users is selected, and the collecting moment when the largest absolute value of the difference values appears is recorded as the first momentThe abnormal start time of the water flow data of the abnormal user will be at +.>The average value of the abnormal start time of the water temperature data of the individual abnormal user and the abnormal start time of the water flow data is recorded as +.>Heating abnormality start time of individual abnormal users.
Further, it should be noted that after a heating fault occurs, the water temperature and the water flow change caused by the fault are all the descending trends, that is, the characteristics of abnormal appearance of the water temperature and the water flow are similar, so that the first heating abnormality evaluation of each abnormal user is obtained according to the water temperature and the water flow data change from the heating abnormality starting moment to the current collecting moment of each abnormal user.
Specifically, the current acquisition time is recorded as the firstMoment->The calculation mode of the first heating abnormal evaluation of the abnormal users at the current acquisition time is as follows:
wherein,is->Individual abnormal user presenceFirst heating abnormal coefficient of current acquisition time, < ->For the +.>Heating abnormality starting time of individual abnormal users; />Is->Standard data preset by the heating data; when (when)At the time->The heating data represent water temperature data, when +.>At the time->The individual heating data represent water flow data; />Indicate->Person abnormal user->Mean value of the individual heating data in the range of the current acquisition time, and +>Is->Person abnormal user->Maximum value of the individual heating data in the range of the current acquisition time, < >>Is->Person abnormal user->And the minimum value of the heating data in the collection time range of the current collection time.
The larger the value is, the more->The longer the time interval from the heating abnormality start time of the individual abnormal users to the current acquisition time is, the longer the time to failure is, the more the trouble is required to be repaired, so the first heating abnormality coefficient +>The larger the value is; />Indicate->Person abnormal user->The overall trend of the individual heating data is compared to +.>Standard data of the individual heating data differ by more than one, which means +.>The farther the individual heating data is from the standard data, the more likely it is that there is a failure and therefore the first heating abnormality coefficient +.>The larger the value is; />Indicate->Person abnormal user->Fluctuation range of the individual heating data, the larger the fluctuation range is, the more +.>Person abnormal user->The more unstable the individual heating data, the more likely there is a large failure, so the first heating abnormality coefficient +.>The larger the value is. The method comprises the steps of obtaining a heating abnormality starting time of each user at the current collecting time, obtaining a first heating abnormality coefficient of each user at the current collecting time according to the heating abnormality starting time and the change of water temperature and water flow data, normalizing the first heating abnormality coefficients of all users at the current collecting time by using a linear normalization function, and obtaining a first heating abnormality evaluation of each user at the current collecting time as a normalization result.
So far, the first heating abnormality evaluation of each user at the current acquisition time is obtained.
And S004, obtaining a second heating abnormality evaluation of each abnormal user according to the outlier factor and the first heating abnormality evaluation of each abnormal user.
It should be noted that, because of a connected circulation system during the heating system, when the heating system of a user side fails, similar outliers of water temperature and water flow data of other users may occur at the current collection time, but the users with passive anomalies do not have the same water temperature and water flow variation within the collection time range, so that the first heating evaluation of each abnormal user is corrected by using the correlation of outlier factors of each abnormal user at the current collection time to obtain the second heating anomaly evaluation of each abnormal user at the current collection time.
Specifically, the outlier factors of all the abnormal users at the current collection time are arranged in an ascending order to obtain an outlier factor sequence of all the abnormal users at the current collection time, the closer the distance between the two outlier factors in the outlier factor sequence is, the more similar the water temperatures and water flows of the two abnormal users corresponding to the two outlier factors show, the more likely that the two abnormal users are caused by the same fault, so that the first heating abnormal evaluation of each abnormal user is updated through the outlier factor difference in the outlier factor sequence at the current collection time, and the second heating abnormal evaluation of each abnormal user at the current collection time is obtained.
Specifically, the first of the outlier factor sequences of all abnormal users at the current acquisition timeThe individual outlier factors were noted +.>Then in the sequence of outliers at the current acquisition instant +.>Update coefficient of individual outlier factor +.>The calculation mode of (a) is as follows:
wherein,for the first +.in the sequence of outliers at the current acquisition instant>Update coefficients of individual outliers, +.>For the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>For the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>For the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>For the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>Represents an exponential function based on natural constants, < ->For error parameters, the preset value is +.>Wherein->The value range of (2) is +.>，/>The number of abnormal users at the current acquisition time is represented. />The smaller the value of the difference value of the adjacent outlier factors in the outlier factor sequence representing the current acquisition time is, the more similar the faults of the abnormal users represented by the adjacent outlier factors are, and the more approximate the heating data points in the two-dimensional sample space are, the overhaul sequence of the two abnormal users should be set to be approximate when in fault overhaul so as to be capable of being overhauled simultaneously.
Note that, the update coefficient of the first outlier in the outlier sequence at the current acquisition time is recorded as 1.
Further, the first outlier factor sequence at the current acquisition timeAbnormal user corresponding to the individual outlier factor is marked as +.>Abnormal user, then->The updating coefficient of the outlier factor of the abnormal user at the current acquisition time is the +.>Update coefficient of individual outlier factor, will +.>The first heating abnormality evaluation of the individual abnormal users at the current acquisition time is recorded as +.>Will be in the sequence of outliers at the current acquisition instant +.>Abnormal user corresponding to the individual outlier factor is marked as +.>Abnormal user, will->The first heating abnormality evaluation of the individual abnormal users at the current acquisition time is recorded as +.>Starting from an abnormal user corresponding to the 2 nd outlier factor in an outlier factor sequence at the current acquisition time, calculating the ++according to the sequence from small to large of the outlier factor sequence>Second heating abnormality evaluation by individual abnormality user at current acquisition time +.>The method comprises the following steps:
wherein,is->Second heating abnormality evaluation by individual abnormality user at current acquisition time,/>Is->First heating abnormality evaluation of individual abnormal users at current acquisition time,/>Is->Outlier factor update coefficient of individual abnormal user at current acquisition time, +.>For the first +.in the sequence of outliers at the current acquisition instant>The corresponding +.>And the abnormal users evaluate the second heating abnormality at the current acquisition time.
Heating abnormality evaluation difference value for abnormal users corresponding to adjacent outliers in the outlier sequence is equal to +.>First->When the outlier factor updating coefficient of the current acquisition time is larger, the more likely that the faults of two adjacent outlier users of the outlier factors are similar, the +.>First heating abnormality evaluation of individual abnormal users ∈>Adding the update coefficient as the difference of the weights such that +.>First heating abnormality evaluation of individual abnormal users ∈>The more approaching the%>Second heating abnormality evaluation by abnormal user, again because of +.>The second heating abnormality evaluation of the abnormal users at the current acquisition time is updated already, and thus serves as an updated criterion.
Note that, the first heating abnormality evaluation of the first outlier in the outlier sequence at the current acquisition time is referred to as the second heating abnormality evaluation.
And similarly, starting from the first outlier factor in the outlier factor sequence at the current acquisition time, acquiring second heating abnormality evaluation of all the abnormal users corresponding to the first outlier factor in the outlier factor sequence at the current acquisition time.
So far, the second heating abnormal evaluation of all abnormal users at the current acquisition time is obtained.
And step S005, carrying out abnormal maintenance on the heating system according to the second heating abnormal evaluation of each abnormal user.
The second heating abnormality evaluation value of each abnormal user indicates the severity and the characteristics of the fault of the user, and when the heating of a plurality of users caused by one fault is abnormal, the plurality of users are used for reflecting the approximation of the severity and the characteristics of the fault because the variation of the water temperature and the water flow are approximated, so that in order to make the overhaul more accurate and efficient, the second heating abnormality evaluation of all abnormal users at the current acquisition time is arranged according to the descending order to obtain an overhaul priority sequence of all abnormal users, and the overhaul priority of the abnormal user with the larger second heating abnormality evaluation in the overhaul priority sequence is higher, and the overhaul of the heating equipment of each abnormal user is carried out according to the overhaul sequence of the abnormal user in the priority sequence.
The following examples were usedThe model only represents the negative correlation and the result of the constraint model output is +.>Within the interval>For the input of the model, other models with the same purpose can be replaced in the implementation, and the embodiment is only to +.>The model is described as an example, and is not particularly limited.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The abnormal data monitoring method for the intelligent district heating system is characterized by comprising the following steps:
collecting water temperature data and water flow data of all users within the collecting time range;
mapping water temperature data and water flow data of each user at the current acquisition time to a two-dimensional sample space to obtain heating data points of each user; obtaining outlier factors of heating data points of each user at the current acquisition time by using a local outlier factor algorithm in a two-dimensional sample space; obtaining abnormal users in all users at the current collection time according to outlier factors of heating data points of each user at the current collection time; acquiring first heating abnormal evaluation of each abnormal user at the current acquisition time according to water temperature data and water flow data of each abnormal user in the acquisition time range; the outlier factors of all abnormal users at the current acquisition time are arranged to obtain outlier factor sequences of all abnormal users at the current acquisition time; acquiring an update coefficient of each outlier factor in the outlier factor sequence at the current acquisition time according to the outlier factor sequences of all abnormal users at the current acquisition time; obtaining a second heating abnormal evaluation of each abnormal user at the current acquisition time according to the first heating abnormal evaluation of each abnormal user at the current acquisition time and the update coefficient of the outlier factor;
and carrying out abnormal overhaul on the heating system according to the second heating abnormal evaluation of each abnormal user.
2. The method for monitoring abnormal data of a heating system of a smart cell according to claim 1, wherein the obtaining heating data points of each user comprises:
and mapping the water temperature data and the water flow data of each user at the current acquisition time to a two-dimensional sample space to obtain heating data points of each user, wherein the horizontal axis of the heating data points represents the water temperature data, and the vertical axis of the heating data points represents the water flow data.
3. The method for monitoring abnormal data of a heating system of an intelligent community according to claim 1, wherein the obtaining abnormal users among all users at the current collection time comprises:
heating data points with outliers greater than 1 in all heating data points are marked as outlier data points, and users with heating data points of users belonging to outlier data points in all users are marked as abnormal users.
4. The method for monitoring abnormal data of a heating system of a smart district according to claim 1, wherein the obtaining the first heating abnormal evaluation of each abnormal user at the current collection time according to the water temperature data and the water flow data of each abnormal user in the collection time range comprises:
the method comprises the steps of obtaining a heating abnormality starting time of each user at the current collecting time, obtaining a first heating abnormality coefficient of each user at the current collecting time according to the heating abnormality starting time and combining the change of water temperature data and water flow data, normalizing the first heating abnormality coefficients of all users at the current collecting time by using a linear normalization function, and obtaining a first heating abnormality evaluation of each user at the current collecting time as a normalization result.
5. The method for monitoring abnormal data of a heating system of an intelligent community according to claim 4, wherein the specific method for acquiring the heating abnormal starting time of each user at the current acquisition time comprises the following steps:
acquisition of the firstThe absolute value of the difference value of the water temperature data of adjacent collecting moments in all water temperature data of abnormal users is selected, and the collecting moment of the largest absolute value of the difference values is recorded as the +.>Abnormal starting time of water temperature data of abnormal users; get->The absolute value of the difference value of the water flow data at adjacent collecting moments in all water flow data of abnormal users is selected, and the collecting moment of the largest absolute value of the difference values is recorded as the +.>Abnormal starting time of water flow data of abnormal users; will be->The average value of the abnormal start time of the water temperature data of the individual abnormal user and the abnormal start time of the water flow data is recorded as +.>Heating abnormality start time of individual abnormal users.
6. The method for monitoring abnormal data of a heating system of a smart district according to claim 4, wherein the obtaining the first heating abnormal coefficient of each user at the current collection time according to the heating abnormal start time in combination with the change of the water temperature data and the water flow data comprises:
recording the current acquisition timeIs the firstMoment->First heating abnormal coefficient of abnormal user at current collection timeThe calculation mode of (a) is as follows:
wherein,for the +.>Heating abnormality starting time of individual abnormal users; />Is->Standard data preset by the heating data;
when (when)At the time->The heating data represent water temperature data, when +.>At the time->The individual heating data represent water flow data;
indicate->Person abnormal user->The average value of the individual heating data in the acquisition time range of the current acquisition time,is->Person abnormal user->The maximum value of the individual heating data in the acquisition time range of the current acquisition time,is->Person abnormal user->And the minimum value of the heating data in the collection time range of the current collection time.
7. The method for monitoring abnormal data of a heating system of an intelligent community according to claim 1, wherein the obtaining the outlier factor sequence of all abnormal users at the current collection time comprises:
and (3) carrying out ascending order arrangement on the outlier factors of all abnormal users at the current acquisition time to obtain an outlier factor sequence of all abnormal users at the current acquisition time.
8. The method for monitoring abnormal data of a heating system of an intelligent community according to claim 1, wherein the step of obtaining the update coefficient of each outlier factor in the outlier factor sequence at the current collection time according to the outlier factor sequence of all abnormal users at the current collection time comprises the steps of:
the current acquisition time is marked as the firstMoment, the first +.in the outlier factor sequence at the current acquisition moment>The individual outlier factors are noted asFirst +.in the outlier factor sequence at the current acquisition time>Update coefficient of individual outlier factor +.>The calculation mode of (a) is as follows:
wherein,for the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>For the first +.in the sequence of outliers at the current acquisition instant>Individual outlier factors, < >>To the first in the sequence of outliers at the current acquisition timeIndividual outlier factors;
represents an exponential function based on natural constants, < ->Is an error parameter;
the value range of (2) is +.>，/>The number of abnormal users at the current acquisition time is represented.
9. The method for monitoring abnormal data of a heating system of a smart cell according to claim 1, wherein the obtaining the second heating abnormality evaluation of each abnormal user at the current collection time comprises:
the current acquisition time is marked as the firstMoment of time, the first +.in the sequence of outliers at the current acquisition moment>Abnormal user corresponding to the individual outlier factor is marked as +.>Abnormal user, then->The updating coefficient of the outlier factor of the abnormal user at the current acquisition time is the +.>Update coefficient of individual outlier factor, will +.>The first heating abnormality evaluation of the individual abnormal users at the current acquisition time is recorded as +.>Will be in the outlier factor sequence at the current acquisition timeAbnormal user corresponding to the individual outlier factor is marked as +.>Abnormal user, will->The first heating abnormality evaluation of the individual abnormal users at the current acquisition time is recorded as +.>The method comprises the steps of carrying out a first treatment on the surface of the Starting from an abnormal user corresponding to the 2 nd outlier factor in an outlier factor sequence at the current acquisition time, calculating the ++according to the order of the outlier factor sequence from small to large>Second heating abnormality evaluation by individual abnormality user at current acquisition time +.>The method comprises the following steps:
wherein,is->Updating coefficient of outlier factor of abnormal user at current acquisition time,/for each abnormal user>For the first +.in the sequence of outliers at the current acquisition instant>The corresponding +.>And the abnormal users evaluate the second heating abnormality at the current acquisition time.
10. The method for monitoring abnormal data of a heating system of a smart district according to claim 1, wherein the performing abnormal maintenance of the heating system according to the second heating abnormality evaluation of each abnormal user comprises:
and arranging the second heating abnormal evaluations of all the abnormal users at the current acquisition time in descending order to obtain an overhaul priority sequence of all the abnormal users, wherein the overhaul priority of the abnormal users with the larger second heating abnormal evaluations in the overhaul priority sequence is higher, and overhaul of the heating equipment of each abnormal user is carried out according to the overhaul sequence of the abnormal users in the priority sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311722925.2A CN117436845B (en) | 2023-12-15 | 2023-12-15 | Abnormal data monitoring method for intelligent district heating system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311722925.2A CN117436845B (en) | 2023-12-15 | 2023-12-15 | Abnormal data monitoring method for intelligent district heating system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117436845A true CN117436845A (en) | 2024-01-23 |
| CN117436845B CN117436845B (en) | 2024-04-09 |
Family
ID=89546386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311722925.2A Active CN117436845B (en) | 2023-12-15 | 2023-12-15 | Abnormal data monitoring method for intelligent district heating system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117436845B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668844A (en) * | 2024-01-30 | 2024-03-08 | 浙江御安信息技术有限公司 | Threat file detection system based on information security |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006285389A (en) * | 2005-03-31 | 2006-10-19 | Yokohama National Univ | Device, program and method for specifying conduit fracture position |
| CN107676634A (en) * | 2017-10-19 | 2018-02-09 | 郑州尚润电子科技有限公司 | Water supply network soil's rigidity analysis method, apparatus and system |
| CN110285330A (en) * | 2019-07-11 | 2019-09-27 | 重庆大学 | A kind of water utilities net pipe burst detection method based on the local factor that peels off |
| US20200104651A1 (en) * | 2018-09-28 | 2020-04-02 | Hartford Steam Boiler Inspection & Insurance Compa | Dynamic outlier bias reduction system and method |
| US20220164592A1 (en) * | 2021-02-04 | 2022-05-26 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and systems for detecting detection devices located at energy metering points of natural gas |
| CN115013865A (en) * | 2022-08-08 | 2022-09-06 | 南通金立电气工程有限公司 | Heating supply abnormity identification method based on industrial big data |
| CN116257809A (en) * | 2023-03-09 | 2023-06-13 | 浙江浙能电力股份有限公司台州发电厂 | Heat supply pipe network abnormality diagnosis method based on machine learning algorithm |
| CN117073056A (en) * | 2023-07-11 | 2023-11-17 | 青岛海尔空调器有限总公司 | Water flow abnormality judgment method for heating system and heating system |
| CN117081909A (en) * | 2023-10-18 | 2023-11-17 | 联通在线信息科技有限公司 | Abnormal broadband correction method, device, electronic equipment and storage medium |
-
2023
- 2023-12-15 CN CN202311722925.2A patent/CN117436845B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006285389A (en) * | 2005-03-31 | 2006-10-19 | Yokohama National Univ | Device, program and method for specifying conduit fracture position |
| CN107676634A (en) * | 2017-10-19 | 2018-02-09 | 郑州尚润电子科技有限公司 | Water supply network soil's rigidity analysis method, apparatus and system |
| US20200104651A1 (en) * | 2018-09-28 | 2020-04-02 | Hartford Steam Boiler Inspection & Insurance Compa | Dynamic outlier bias reduction system and method |
| CN110285330A (en) * | 2019-07-11 | 2019-09-27 | 重庆大学 | A kind of water utilities net pipe burst detection method based on the local factor that peels off |
| US20220164592A1 (en) * | 2021-02-04 | 2022-05-26 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and systems for detecting detection devices located at energy metering points of natural gas |
| CN115013865A (en) * | 2022-08-08 | 2022-09-06 | 南通金立电气工程有限公司 | Heating supply abnormity identification method based on industrial big data |
| CN116257809A (en) * | 2023-03-09 | 2023-06-13 | 浙江浙能电力股份有限公司台州发电厂 | Heat supply pipe network abnormality diagnosis method based on machine learning algorithm |
| CN117073056A (en) * | 2023-07-11 | 2023-11-17 | 青岛海尔空调器有限总公司 | Water flow abnormality judgment method for heating system and heating system |
| CN117081909A (en) * | 2023-10-18 | 2023-11-17 | 联通在线信息科技有限公司 | Abnormal broadband correction method, device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 毛莺池;齐海;接青;王龙宝;: "M-TAEDA:多变量水质参数时序数据异常事件检测算法", 计算机应用, no. 01, 10 January 2017 (2017-01-10), pages 138 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668844A (en) * | 2024-01-30 | 2024-03-08 | 浙江御安信息技术有限公司 | Threat file detection system based on information security |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117436845B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117436845B (en) | Abnormal data monitoring method for intelligent district heating system | |
| CN111159844B (en) | Abnormity detection method for exhaust temperature of gas turbine of power station | |
| CN110220602A (en) | A kind of switchgear overheating fault recognition methods | |
| CN108388922A (en) | A kind of recognition methods and system for the major-minor equipment state exception of fired power generating unit | |
| CN109858125B (en) | Thermal power unit power supply coal consumption calculation method based on radial basis function neural network | |
| CN113722906B (en) | Digital twinning-based data center air conditioning system reliability assessment method | |
| CN111178602A (en) | Circulating water loss prediction method based on support vector machine and neural network | |
| CN105870913B (en) | Consider the sequential Monte Carlo simulation reliability estimation method and system of heating constraint | |
| CN109869198B (en) | Method for monitoring efficiency of steam turbine full-life high-pressure cylinder based on valve position correction | |
| CN111443602B (en) | Hidden Markov-based valve health degree estimation and life prediction method | |
| CN114861810A (en) | Coal gasification device process diagnosis method and system | |
| KR100752765B1 (en) | A real-time calculation system and method on performance impact of controllable operation parameters for combined-cycle power plant | |
| CN116628289B (en) | Heating system operation data processing method and strategy optimization system | |
| CN115434878B (en) | Wind generating set temperature cluster control method, device, equipment and medium | |
| CN115808944B (en) | Stator temperature rise test control method | |
| CN111581787A (en) | Method and system for screening heat consumption rate analysis data of steam turbine in real time | |
| KR102406994B1 (en) | Bigdata based system and method for diagnose and analyze abnormalities in facility | |
| CN109670243A (en) | A kind of life-span prediction method based on lebesgue space model | |
| CN117459073B (en) | Intelligent management method for heat pump system operation data | |
| CN117452989B (en) | BP neural network-based temperature regulation and control valve performance regulation and test method | |
| CN117272704B (en) | Digital twin-drive data processing system for multi-source heterogeneous data | |
| CN116500898B (en) | Thermal power generating unit AGC load control system based on characteristic flow identification | |
| CN109492855B (en) | Condenser type steam turbine exhaust temperature prediction method based on data model | |
| CN117117981A (en) | Unit operation management method and system based on low-pressure cylinder zero power | |
| CN117556193A (en) | Pretreatment method for efficiency monitoring and diagnosis data of gas turbine combined cycle unit |
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 |