CN117870016A - Real-time monitoring method and system for heating system based on Internet of things - Google Patents
Real-time monitoring method and system for heating system based on Internet of things Download PDFInfo
- Publication number
- CN117870016A CN117870016A CN202410282401.4A CN202410282401A CN117870016A CN 117870016 A CN117870016 A CN 117870016A CN 202410282401 A CN202410282401 A CN 202410282401A CN 117870016 A CN117870016 A CN 117870016A
- Authority
- CN
- China
- Prior art keywords
- data
- curve
- real
- temperature
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000010438 heat treatment Methods 0.000 title claims abstract description 68
- 238000012544 monitoring process Methods 0.000 title claims abstract description 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 230000000087 stabilizing effect Effects 0.000 claims abstract description 16
- 230000001174 ascending effect Effects 0.000 claims description 74
- 230000000630 rising effect Effects 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000005526 G1 to G0 transition Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to the technical field of data analysis, in particular to a heating system real-time monitoring method and system based on the Internet of things, comprising the following steps: real-time heating data and a plurality of historical heating data are collected. Acquiring a historical temperature curve according to historical temperature data in the historical heat supply data, and acquiring starting stage data, stable stage data and ending stage data in the historical temperature curve; acquiring a plurality of real-time temperature curve segments according to real-time temperature data in the real-time heat supply data, acquiring a sample set of the real-time temperature curve according to starting phase data, stabilizing phase data and ending phase data in the real-time temperature curve segments and the historical temperature curve, and detecting abnormality of the real-time temperature data. According to the invention, the historical temperature data is segmented by analyzing the historical temperature data, the sample set is obtained based on the historical temperature data, and the accuracy of identifying abnormal data is improved by reducing the difference between the data in the sample set.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a heating system real-time monitoring method and system based on the Internet of things.
Background
In the process of monitoring a heating system based on the Internet of things in real time, the acquired real-time heating data and historical heating data commonly form a heating data set, and then abnormality detection is carried out on the data in the set. However, when the heating system is started, various heating data are gradually increased and when the heating system is closed, various heating data are gradually reduced, namely, differences exist in the heating data in different time periods during the heating period, and if the complete historical heating data are directly used as a data set to screen a sample set of abnormal data in the real-time heating data, the abnormal data in the real-time heating data cannot be accurately identified due to large differences in the heating data in different stages.
Disclosure of Invention
The invention provides a heating system real-time monitoring method and system based on the Internet of things, which are used for solving the existing problems: the traditional anomaly detection algorithm can not accurately identify the anomaly data in the real-time heat supply data.
The invention discloses a heating system real-time monitoring method and a heating system real-time monitoring system based on the Internet of things, wherein the heating system real-time monitoring method and the heating system based on the Internet of things adopt the following technical scheme:
the embodiment of the invention provides a heating system real-time monitoring method based on the Internet of things, which comprises the following steps:
collecting real-time heat supply data and a plurality of historical heat supply data;
acquiring a historical temperature curve according to historical temperature data in the historical heat supply data; segmenting a historical temperature curve to obtain all ascending curve sections and all descending curve sections in the historical temperature curve; calculating the similarity between adjacent ascending curve sections and the similarity between adjacent descending curve sections in the historical temperature curve; obtaining a probability parameter of the ascending curve section and the descending curve section as critical curve sections according to the similarity between adjacent ascending curve sections and the similarity between adjacent descending curve sections in the historical temperature curve; acquiring a critical curve segment according to the probability parameters of the critical curve segment; acquiring starting phase data, stable phase data and termination phase data in a historical temperature curve according to the possibility parameters of the critical curve segment;
fitting according to real-time temperature data in the real-time heat supply data to obtain a real-time temperature curve segment, segmenting the real-time temperature curve segment to obtain a plurality of real-time temperature curve segments, and acquiring a sample set of the real-time temperature curve according to all data in the real-time temperature curve segment and combining start-up phase data, stable phase data and termination phase data in a historical temperature curve;
and carrying out anomaly detection on the real-time temperature data according to the sample set of the real-time temperature curve.
Preferably, the historical temperature curve is obtained according to the historical temperature data in the historical heat supply data; segmenting a historical temperature curve to obtain all ascending curve sections and all descending curve sections in the historical temperature curve; and calculating the similarity between adjacent ascending curve segments and the similarity between adjacent descending curve segments in the historical temperature curve, wherein the specific method comprises the following steps:
for the firstYear history temperature data, fitting by least square method to obtain +.>A year history temperature profile;
acquisition of the firstAll minimum and maximum points in the annual history temperature curve and as +.>Sectional point pair of annual history temperature curve +.>Segmenting a year history temperature curve to obtain a plurality of +.>A yearly historic temperature curve segment, monotonically increasing +.>The annual history temperature curve section is marked as an ascending curve section, and the monotonically decreasing +.>The annual history temperature curve segment is marked as a descending curve segment;
first, theThe rising curve section and->The specific calculation formula of the similarity degree between the ascending curve sections is as follows:
in the method, in the process of the invention,indicate->The rising curve section and->Degree of similarity between the ascending curve segments;indicate->The average value of all temperature data in the ascending curve sections; />Indicate->The average value of all temperature data in the ascending curve sections; />Indicate->First temperature data in a rising curve segment; />Indicate->First temperature data in a rising curve segment; />Indicate->Last temperature data in the ascending curve segment; />Indicate->Last temperature data in the ascending curve segment; />Representing an absolute value operation;
and obtaining the similarity degree between the adjacent descending curve sections.
Preferably, the obtaining the probability parameter that the ascending curve segment and the descending curve segment are critical curve segments according to the similarity degree between the adjacent ascending curve segments and the similarity degree between the adjacent descending curve segments in the historical temperature curve includes the following specific methods:
will be the firstThe rising curve section and->Degree of similarity between the ascending curve sections, and +.>The rising curve section and->Absolute value of difference between degrees of similarity between the ascending curve sections as +.>The probability parameters of the ascending curve segments being critical curve segments;
and obtaining the probability parameter of the falling curve segment as the critical curve segment.
Preferably, the method for obtaining the critical curve segment according to the probability parameter of the critical curve segment includes the following specific steps:
for the firstObtaining a stable initial curve segment No. 1 and a stable termination curve segment No. 1 according to the annual history temperature curve and the two ascending curve segments with the maximum probability parameters of the critical curve segment;
obtaining a No. 2 stable initial curve segment and a No. 2 stable termination curve segment according to two descending curve segments with maximum probability parameters of being critical curve segments;
obtaining critical curve segments of a starting stage and a stabilizing stage according to the acquisition time of first data in each of the stable initial curve segment No. 1 and the stable initial curve segment No. 2; and obtaining critical curve segments of the stable phase and the termination phase according to the acquisition time of the first data in the stable termination curve segment No. 1 and the stable termination curve segment No. 2.
Preferably, the method for obtaining the start phase data, the steady phase data and the end phase data in the historical temperature curve according to the probability parameters of the critical curve segment includes the following specific steps:
for the firstAnnual history temperature curve, will->First data in the annual history temperature profile, to +.>All data between the starting stage and the previous data of the critical curve segment of the stable stage in the annual history temperature curve are used as starting stage data; will be->First data in critical curve segments of start-up phase and steady-state phase in annual history temperature curve, to +.>All data between the last data in the critical curve segment of the stable phase and the termination phase in the annual history temperature curve are used as stable phase data; will be->All data after the last data in the critical curve segments of the stable phase and the termination phase in the annual history temperature curve are taken as termination phase data.
Preferably, the fitting is performed according to real-time temperature data in the real-time heat supply data to obtain a real-time temperature curve segment, and the real-time temperature curve segment is segmented to obtain a plurality of real-time temperature curve segments, which comprises the following specific methods:
constructing a rectangular coordinate system by taking temperature as a vertical axis and time as a horizontal axis, placing real-time temperature data in the rectangular coordinate system, and fitting data points in the rectangular coordinate system by using a least square method to obtain a real-time temperature curve; acquiring all extreme points in the real-time temperature curve, and segmenting the real-time temperature curve by taking all extreme points in the real-time temperature curve as real-time temperature curve segmentation points to obtain a plurality of real-time temperature curve segments.
Preferably, the method for obtaining the sample set of the real-time temperature curve according to all the data in the real-time temperature curve segment and combining the start phase data, the stable phase data and the stop phase data in the historical temperature curve includes the following specific steps:
calculating the slope average value and the amplitude average value of all data points in each real-time temperature curve segment to be used as the slope and the amplitude of each real-time temperature curve segment;
then, counting the quantity of the data in the starting stage, the data in the stabilizing stage and the data in the ending stage in each calendar history temperature curve; and calculating the number average of the data in the start-up phase in each calendar history temperature curve asNumber average of data in stationary phase in calendar history temperature curves +.>；
Counting the quantity of data in the real-time temperature data and comparing withIs->Comparing the sizes, and obtaining a reference set according to the comparison result and all data respectively positioned in a starting stage, a stabilizing stage and a terminating stage in each calendar history temperature curve; calculating the slope average value and the amplitude average value of all data points in each historical temperature curve segment in the reference set, and taking the slope average value and the amplitude average value as the slope and the amplitude of each historical temperature curve segment in the reference set; the specific process for acquiring the matching degree between the real-time temperature curve and the reference set by combining the slopes and the amplitudes of all the real-time temperature curve segments is as follows:
in the method, in the process of the invention,indicating the degree of matching between the real-time temperature profile and the reference set,/->Representing the slope average of all real-time temperature curve segments; />Representation houseThe amplitude average value of the real-time temperature curve segment is provided; />Representing the slope average of all historical temperature curve segments in the reference set; />Representing the average value of the amplitude values of all historical temperature curve segments in the reference set; />Representing an absolute value operation; />Representing preset super parameters;
and acquiring a sample set of the real-time temperature curve according to the matching degree between the real-time temperature curve and the reference set.
Preferably, the method for obtaining the sample set of the real-time temperature curve according to the matching degree between the real-time temperature curve and the reference set includes the following specific steps:
according to the quantity of data in the real-time temperature dataIs->Comparing the magnitude to obtain a comparison result, combining the matching degree between the real-time temperature curve and the reference set, and +.>The number of data in the annual history temperature profile in the start phase, the steady phase and the end phase, respectively, for +.>Data in the starting stage, the stabilizing stage and the terminating stage in the annual history temperature curve are selected to obtain the +.>Annual target historical temperature data; acquisition of annual meshHistorical temperature data is marked, and annual target historical temperature data is taken as a sample set of real-time temperature curves.
Preferably, the anomaly detection is performed on the real-time temperature data according to the sample set of the real-time temperature curve, including the following specific methods:
placing all real-time temperature data into a sample set of a real-time temperature curve, and then calculating local outlier factors of all real-time temperature data by using an LOF anomaly detection algorithm; obtaining local outlier factors of all real-time temperature data, and then presetting an abnormal threshold valueThe method comprises the steps of carrying out a first treatment on the surface of the All local outliers are greater than +.>The real-time temperature data of the temperature sensor is marked as abnormal data, and the abnormal data in the real-time temperature data are marked to realize real-time monitoring of the temperature data.
The invention also provides a heating system real-time monitoring system based on the Internet of things, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any heating system real-time monitoring method based on the Internet of things when executing the computer program.
The technical scheme of the invention has the beneficial effects that: according to the method, the historical heat supply data are analyzed to obtain a historical temperature curve, an ascending curve section and a descending curve section are obtained according to the historical temperature curve, the similarity between the adjacent ascending curve section and the adjacent descending curve section is obtained according to the ascending curve section and the descending curve section, a critical curve section is obtained according to the similarity between the adjacent ascending curve section and the adjacent descending curve section, starting stage data, stabilizing stage data and ending stage data in the historical temperature curve are obtained, data of each stage in the historical temperature curve are accurately obtained, the data in the historical temperature curve are selected to serve as a sample set of a real-time temperature curve, the difference between the data in the sample set of the real-time temperature curve is reduced, and the purpose of screening anomalies in the real-time temperature data can be achieved more accurately.
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 flow chart of steps of a real-time monitoring method of a heating system based on the Internet of things;
fig. 2 is a flowchart of acquiring abnormal data in real-time temperature data according to an embodiment.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of the specific implementation, structure, characteristics and effects of the real-time monitoring method and system for the heating system based on the internet of things according to the invention in combination with the accompanying drawings and the preferred embodiment. 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 one or more embodiments 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 invention provides a heating system real-time monitoring method and a heating system real-time monitoring system based on the Internet of things.
Referring to fig. 1, a flowchart of steps of a method for monitoring a heating system in real time based on internet of things according to an embodiment of the present invention is shown, where the method includes the following steps:
step S001: real-time heating data and a plurality of historical heating data are collected.
It should be noted that, the embodiment is used as a real-time monitoring method for a heating system based on the internet of things, which aims to monitor various heating data in the heating system, discover abnormal data in various heating data in the heating system in time, and can greatly improve the safety of the heating system.
Specifically, sensors such as a temperature sensor, a pressure sensor, a flow sensor and the like are arranged at a pipeline of the heating system, and heating data such as temperature data, pressure data, flow data and the like of the heating system at each moment in the year are collected; recording heat supply data such as temperature data, pressure data, flow data and the like of a heat supply system at each moment in the year as real-time heat supply data;
then, the latest is called from the databaseVarious heat supply data of the year are obtained>Annual history heat supply data, said->For a preset history range->The specific value of (2) can be set by combining with the actual situation, the hard requirement is not required in the embodiment, and +_ is adopted in the embodiment>Description will be made.
Thus, real-time heat supply data and a plurality of historical heat supply data are obtained.
Step S002: acquiring a historical temperature curve according to historical temperature data in the historical heat supply data; segmenting a historical temperature curve to obtain all ascending curve sections and all descending curve sections in the historical temperature curve; calculating the similarity between adjacent ascending curve sections and the similarity between adjacent descending curve sections in the historical temperature curve; obtaining a probability parameter of the ascending curve section and the descending curve section as critical curve sections according to the similarity between adjacent ascending curve sections and the similarity between adjacent descending curve sections in the historical temperature curve; acquiring a critical curve segment according to the probability parameters of the critical curve segment; and acquiring starting phase data, stabilizing phase data and ending phase data in the historical temperature curve according to the possibility parameters of the critical curve segment.
It should be noted that, since the heating system is started only for a period of time in one year, that is, the heating system needs to be started from a cooling state when the heating system is started, at this time, each heating data gradually rises until each heating data starts to be stable after rising to a certain extent, and at last, each heating data gradually decreases until the heating system is closed after being stable for a period of time; namely, three stages exist in the change of each heat supply data, the difference of the heat supply data in different stages is large, if the complete historical heat supply data is directly used as a data set to screen a sample set of abnormal data in the real-time heat supply data, the abnormal data in the real-time heat supply data cannot be accurately identified due to the large difference of the heat supply data in different stages. Therefore, the historical data needs to be segmented firstly to accurately detect the abnormal data in the real-time heat supply data, and the analysis logic of each heat supply data is the same as the specific process, so the analysis of the temperature data in the heat supply data is described as an example in the embodiment.
Specifically, for the firstThe annual history temperature data firstly takes the temperature vertical axis as the horizontal axis and takes the time as the horizontal axis to construct a rectangular coordinate system, and the +.>The annual history temperature data are placed in a rectangular coordinate system, and then the least square method is used for fitting data points in the rectangular coordinate system to obtain the +.>The annual history temperature profile, since the least square method is known as suchIn this embodiment, a detailed description is omitted.
Then obtain the firstAll minima points and maxima points in the annual history temperature curve will +.>All minima points and maxima points in the annual history temperature curve are taken as +.>Piecewise point of the annual history temperature curve according to +.>Sectional point pair of annual history temperature curve +.>Segmenting the annual history temperature curve to obtain a plurality of +.>A temperature curve segment of the year history and monotonically increasing +.>The annual history temperature curve section is marked as an ascending curve section, and the monotonically decreasing +.>The annual history temperature curve segment is marked as a descending curve segment; get->All ascending curve sections and descending curve sections in the annual history temperature curve.
For calculation of the firstThe rising curve section and->Degree of similarity between the ascending curve segments, headFirst obtain the firstMean value of all temperature data in the respective ascending curve section and +.>The average value of all temperature data in the rising curve sections is respectively marked as +.>And->Then obtain->First temperature data and last temperature data in a rising curve section +.>The first temperature data and the last temperature data in the rising curve section are respectively marked as +.>、/>、/>And +.>The method comprises the steps of carrying out a first treatment on the surface of the According to->、/>、/>、/>、/>And +.>Obtain->The rising curve section and->The degree of similarity between the ascending curve segments is as follows:
in the method, in the process of the invention,indicate->The rising curve section and->Degree of similarity between the ascending curve segments;indicate->The average value of all temperature data in the ascending curve sections; />Indicate->The average value of all temperature data in the ascending curve sections; />Indicate->First temperature data in a rising curve segment; />Indicate->First temperature data in a rising curve segment; />Indicate->Last temperature data in the ascending curve segment; />Indicate->Last temperature data in the ascending curve segment; />Representing an absolute value operation.
It should be noted that, since the difference in the heating data in the different stages is large, when the previous rising curve section and the next rising curve section of a rising curve section are not data in the same stage, the degree of similarity between the rising curve section and the previous rising curve section of the rising curve section and the degree of similarity between the rising curve section and the next rising curve section of the rising curve section are large, so that the probability parameter that each rising curve section is a critical curve section can be calculated from this.
Specifically, for the firstThe probability parameter of the rising curve segment being the critical curve segment is first obtained +.>The rising curve section and->Degree of similarity between the ascending curve sections +.>The rising curve section and->Degree of similarity between the ascending curve segments; according to->The rising curve section and->Degree of similarity between the ascending curve sections +.>The rising curve section and->The degree of similarity between the ascending curve segments is calculated +.>The probability that each ascending curve segment is a critical curve segment is calculated by the following specific formula:
in the method, in the process of the invention,indicate->The probability parameters of the ascending curve segments being critical curve segments; />Indicate->A rising curveSection and->Degree of similarity between the ascending curve segments; />Indicate->Ascending curve segment(s)Degree of similarity between the ascending curve segments; />Representing an absolute value operation.
It should be noted that, since the curve segments between the different stages may be not only ascending curve segments but also descending curve segments, the probability parameter of the descending curve segment being a critical curve segment needs to be calculated, and the probability parameter of the descending curve segment being a critical curve segment and the probability parameter of the ascending curve segment being a critical curve segment need to be calculated, so that the description is not repeated in the present embodiment.
Specifically, for the firstObtaining the annual history temperature curve +.>The probability parameter of all ascending curve segments in the annual history temperature curve being critical curve segments +.>The method comprises the steps of marking a target ascending curve section with a front time sequence as a No. 1 stable initial curve section and marking a target ascending curve section with a rear time sequence as a No. 1 stable termination curve section as a target ascending curve section, wherein the two ascending curve sections with the maximum possibility parameters of the critical curve sections in all ascending curve sections in the annual history temperature curve;
then, according to the method for obtaining the probability parameter of the ascending curve segment as the critical curve segment, obtaining the probability parameter of the descending curve segment as the critical curve segment;
next, for the firstObtaining the annual history temperature curve +.>The probability parameter of all falling curve segments in the annual history temperature curve being critical curve segments +.>The method comprises the steps of marking a target descent curve segment with a front time sequence as a No. 2 stable initial curve segment and marking a target descent curve segment with a rear time sequence as a No. 2 stable termination curve segment, wherein the two descent curve segments with the highest probability parameters are critical curve segments in all descent curve segments in a historical temperature curve;
acquiring the acquisition time of the first data in the stable initial curve section 1 and the stable initial curve section 2 respectively, wherein when the acquisition time of the first data in the stable initial curve section 1 is smaller than the acquisition time of the first data in the stable initial curve section 2, the stable initial curve section 1 is a critical curve section of a starting stage and a stable stage, and otherwise the stable initial curve section 2 is a critical curve section of the starting stage and the stable stage;
and acquiring the acquisition time of the first data in the No. 1 stable termination curve section and the No. 2 stable termination curve section respectively, wherein when the acquisition time of the first data in the No. 1 stable termination curve section is larger than the acquisition time of the first data in the No. 2 stable termination curve section, the No. 1 stable termination curve section is a critical curve section of a stable stage and a termination stage, and otherwise the No. 2 stable termination curve section is a critical curve section of the stable stage and the termination stage.
For the firstAnnual history temperature curve, will->First data in the annual history temperature profile, to +.>All data between the starting stage and the previous data of the critical curve segment of the stable stage in the annual history temperature curve are used as starting stage data; will be->First data in critical curve segments of start-up phase and steady-state phase in annual history temperature curve, to +.>All data between the last data in the critical curve segment of the stable phase and the termination phase in the annual history temperature curve are used as stable phase data; will be->All data after the last data in the critical curve segments of the stable phase and the termination phase in the annual history temperature curve are taken as termination phase data.
So far, the starting phase data, the stabilizing phase data and the ending phase data in all the historical temperature curves are obtained.
Step S003: fitting according to real-time temperature data in the real-time heat supply data to obtain a real-time temperature curve segment, segmenting the real-time temperature curve segment to obtain a plurality of real-time temperature curve segments, and acquiring a sample set of the real-time temperature curve according to all data in the real-time temperature curve segment and combining start-up phase data, stable phase data and termination phase data in the historical temperature curve.
It should be noted that, in step S002, starting phase data, stabilizing phase data and terminating phase data in all the historical temperature curves are obtained, and the real-time heat supply data can be analyzed according to the starting phase data, stabilizing phase data and terminating phase data in all the historical temperature curves.
Specifically, a rectangular coordinate system is constructed by taking the temperature vertical axis and the time as the horizontal axis, real-time temperature data are placed in the rectangular coordinate system, and then the data points in the rectangular coordinate system are fitted by using a least square method to obtain a real-time temperature curve, and the least square method is used as a well-known prior art, so that redundant description is omitted in the embodiment; acquiring all extreme points in the real-time temperature curve, segmenting the real-time temperature curve by taking all extreme points in the real-time temperature curve as real-time temperature curve segmentation points to obtain a plurality of real-time temperature curve segments, and calculating the slope average value and the amplitude average value of all data points in each real-time temperature curve segment to serve as the slope and the amplitude of each real-time temperature curve segment;
then, counting the quantity of the data in the starting stage, the data in the stabilizing stage and the data in the ending stage in each calendar history temperature curve; and calculating the number average of the data in the start-up phase in each calendar history temperature curve asNumber average of data in stationary phase in calendar history temperature curves +.>Number average of data in the expiration phase in the calendar history temperature curves +.>；
Then, counting the number of data in the real-time temperature data, when the number of data in the real-time temperature data is less than or equal toAll data in the start-up phase of each calendar history temperature curve are recorded as a reference set; calculating the slope average value and the amplitude average value of all data points in each historical temperature curve segment in the reference set, and taking the slope average value and the amplitude average value as the slope and the amplitude of each historical temperature curve segment in the reference set; from slopes and amplitudes of all historical temperature curve segments in a reference setThe value is combined with the slope and the amplitude of all the real-time temperature curve segments to obtain the matching degree between the real-time temperature curve and the reference set;
when the amount of data in the real-time temperature data is larger thanLess than or equal to->All data in the starting stage and the stable stage in each calendar history temperature curve are recorded as a reference set; calculating the slope average value and the amplitude average value of all data points in each historical temperature curve segment in the reference set, and taking the slope average value and the amplitude average value as the slope and the amplitude of each historical temperature curve segment in the reference set; according to the slope and the amplitude of all the historical temperature curve segments in the reference set, combining the slope and the amplitude of all the real-time temperature curve segments to obtain the matching degree between the real-time temperature curve and the reference set;
when the amount of data in the real-time temperature data is larger thanAll data in the starting stage, the stabilizing stage and the terminating stage of each calendar history temperature curve are recorded as reference sets to calculate the average value of the slope and the average value of the amplitude of all data points in each historical temperature curve segment in the reference sets, and the average value of the slope and the average value of the amplitude of each historical temperature curve segment in the reference sets are used as the slope and the amplitude of each historical temperature curve segment in the reference sets; according to the slope and the amplitude of all the historical temperature curve segments in the reference set, combining the slope and the amplitude of all the real-time temperature curve segments to obtain the matching degree between the real-time temperature curve and the reference set;
according to the slope and amplitude of all historical temperature curve segments in the reference set, combining the slope and amplitude of all real-time temperature curve segments to obtain a calculation formula of the matching degree between the real-time temperature curve and the reference set, wherein the calculation formula comprises the following steps:
in the method, in the process of the invention,indicating the degree of matching between the real-time temperature profile and the reference set,/->Representing the slope average of all real-time temperature curve segments; />Representing the average value of the amplitude values of all the real-time temperature curve segments; />Representing the slope average of all historical temperature curve segments in the reference set; />Representing the average value of the amplitude values of all historical temperature curve segments in the reference set; />Representing an absolute value operation; />Representing preset superparameter->The specific value of (2) can be set by the user according to the actual situation, in this embodiment +.>The calculation is performed with 1, the purpose of which is to avoid the occurrence of the situation that the denominator is zero during the process of performing the division operation.
Up to this, the degree of matching between the real-time temperature profile and the reference set is obtained.
After the matching degree between the real-time temperature curve and the reference set is obtained, part of data can be screened out from the reference set according to the matching degree between the real-time temperature curve and the reference set to be used as a sample set of the real-time temperature curve.
Specifically, when the amount of data in the real-time temperature data is less than or equal toFor->Annual history temperature data, based on the degree of matching between the real-time temperature profile and the reference set and +.>The number of data in the start-up phase in the annual history temperature profile, obtain +.>Number of data selections during the start-up phase of the year +.>The specific calculation formula is as follows:
in the method, in the process of the invention,indicate->The number of data selection in the annual starting stage; />Representing the degree of matching between the real-time temperature curve and the reference set; />Indicate->The amount of data in the start-up phase in the year history temperature profile; />Representing a downward valued function.
Will be the firstBefore in the start-up phase data in the annual history temperature profile>Data, recorded as->Annual target historical temperature data are obtained, and the annual target historical temperature data are used as a sample set of a real-time temperature curve;
when the amount of data in the real-time temperature data is larger thanLess than or equal to->For->Annual history temperature data, based on the degree of matching between the real-time temperature profile and the reference set and +.>The number of data in the stable phase in the annual history temperature profile, obtain +.>Number of data selections for the annual stationary phase +.>The specific calculation formula is as follows:
in the method, in the process of the invention,indicate->The number of data selection in the annual stable stage; />Representing the degree of matching between the real-time temperature curve and the reference set; />Indicate->The amount of data in the stable phase in the annual history temperature profile; />Representing a downward valued function.
Will be the firstAll data in the start-up phase in the annual history temperature profile and before in the stability phase data +.>Data, recorded as->Annual target historical temperature data are obtained, and the annual target historical temperature data are used as a sample set of a real-time temperature curve;
when the amount of data in the real-time temperature data is larger thanFor->Annual history temperature data, based on the degree of matching between the real-time temperature profile and the reference set and +.>The number of data in the termination phase in the annual history temperature profile, obtain +.>Number of data selections in the expiration phase of the year +.>The specific calculation formula is as follows:
in the method, in the process of the invention,indicate->The number of data selections in the ending stage of the year; />Representing the degree of matching between the real-time temperature curve and the reference set; />Indicate->The amount of data in the termination phase in the year history temperature profile; />Representing a downward valued function.
Will be the firstAll data in the start-up phase, all data in the steady-state phase and before in the end-state phase data in the annual history temperature profile>Data, recorded as->Annual target historical temperature data is obtained, and the annual target historical temperature data is taken as a sample set of a real-time temperature curve.
When the amount of data in the real-time temperature data is equal to or less thanThen the latest real-time temperature data is indicated to be in the start-up phase; when the number of data in the real-time temperature data is greater than +.>Less than or equal to->Then the latest real-time temperature data is indicated to be in a stable phase; when the number of data in the real-time temperature data is greater than +.>It is indicated that the most recent real-time temperature data is in the termination phase.
It should be further noted that,the matching degree between the real-time temperature curve and the reference set is formed by the data of the whole stage, so that the larger the matching degree between the real-time temperature curve and the reference set is, the closer the time sequence range of the real-time temperature curve is to the time sequence range of the stage in the reference set is, and the time sequence range of the real-time temperature curve is equal to the time sequence range of the stage in the reference set, so that the time sequence range is equal to the time sequence range of the stage in the reference set>The larger the data in the phase should be taken as data in the sample set of the real-time temperature profile.
Step S004: and carrying out anomaly detection on the real-time temperature data according to the sample set of the real-time temperature curve.
After the sample set of the real-time temperature curve is obtained in step S003, the anomaly detection can be performed on the real-time temperature data according to the sample set of the real-time temperature curve.
Specifically, all real-time temperature data are put into a sample set of a real-time temperature curve, and then all real-time temperature data are calculated by using an LOF abnormality detection algorithmThe specific process of calculating the local outlier factor by using the LOF anomaly detection algorithm is a well-known prior art, so that a detailed description is omitted in this embodiment; obtaining local outlier factors of all real-time temperature data, and then presetting an abnormal threshold value，/>The specific value of (2) can be set by combining with the actual situation, the hard requirement is not required in the embodiment, and +_ is adopted in the embodiment>Description is made; all local outliers are greater than +.>The real-time temperature data of the system is marked as abnormal data, and the abnormal data in the real-time temperature data are marked, so that the real-time monitoring of the temperature data is realized, and the safety of the heating system is greatly improved.
The flowchart of acquiring abnormal data in real-time temperature data according to the present embodiment is shown in fig. 2.
The embodiment provides a heating system real-time monitoring system based on the Internet of things, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the real-time monitoring method of the heating system based on the Internet of things in the steps S001 to S004 is realized when the processor executes the computer program.
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 real-time monitoring method for the heating system based on the Internet of things is characterized by comprising the following steps of:
collecting real-time heat supply data and a plurality of historical heat supply data;
acquiring a historical temperature curve according to historical temperature data in the historical heat supply data; segmenting a historical temperature curve to obtain all ascending curve sections and all descending curve sections in the historical temperature curve; calculating the similarity between adjacent ascending curve sections and the similarity between adjacent descending curve sections in the historical temperature curve; obtaining a probability parameter of the ascending curve section and the descending curve section as critical curve sections according to the similarity between adjacent ascending curve sections and the similarity between adjacent descending curve sections in the historical temperature curve; acquiring a critical curve segment according to the probability parameters of the critical curve segment; acquiring starting phase data, stable phase data and termination phase data in a historical temperature curve according to the possibility parameters of the critical curve segment;
fitting according to real-time temperature data in the real-time heat supply data to obtain a real-time temperature curve segment, segmenting the real-time temperature curve segment to obtain a plurality of real-time temperature curve segments, and acquiring a sample set of the real-time temperature curve according to all data in the real-time temperature curve segment and combining start-up phase data, stable phase data and termination phase data in a historical temperature curve;
and carrying out anomaly detection on the real-time temperature data according to the sample set of the real-time temperature curve.
2. The real-time monitoring method of a heating system based on the internet of things according to claim 1, wherein the historical temperature curve is obtained according to historical temperature data in the historical heating data; segmenting a historical temperature curve to obtain all ascending curve sections and all descending curve sections in the historical temperature curve; and calculating the similarity between adjacent ascending curve segments and the similarity between adjacent descending curve segments in the historical temperature curve, wherein the specific method comprises the following steps:
for the firstAnnual history temperature data, get the first through least square fitting/>A year history temperature profile;
acquisition of the firstAll minimum and maximum points in the annual history temperature curve and as +.>Sectional point pair of annual history temperature curve +.>Segmenting a year history temperature curve to obtain a plurality of +.>A yearly historic temperature curve segment, monotonically increasing +.>The annual history temperature curve section is marked as an ascending curve section, and the monotonically decreasing +.>The annual history temperature curve segment is marked as a descending curve segment;
first, theThe rising curve section and->The specific calculation formula of the similarity degree between the ascending curve sections is as follows:
in the method, in the process of the invention,indicate->The rising curve section and->Degree of similarity between the ascending curve segments; />Indicate->The average value of all temperature data in the ascending curve sections; />Indicate->The average value of all temperature data in the ascending curve sections; />Indicate->First temperature data in a rising curve segment; />Indicate->First temperature data in a rising curve segment; />Indicate->Last temperature data in the ascending curve segment; />Indicate->Last temperature data in the ascending curve segment; />Representing an absolute value operation;
and obtaining the similarity degree between the adjacent descending curve sections.
3. The method for monitoring a heating system in real time based on the internet of things according to claim 2, wherein the obtaining the probability parameter that the ascending curve segment and the descending curve segment are critical curve segments according to the similarity between the adjacent ascending curve segments and the similarity between the adjacent descending curve segments in the historical temperature curve comprises the following specific steps:
will be the firstThe rising curve section and->Degree of similarity between the ascending curve sections, and +.>The rising curve section and->Absolute value of difference between degrees of similarity between the ascending curve sections as +.>The probability parameters of the ascending curve segments being critical curve segments;
and obtaining the probability parameter of the falling curve segment as the critical curve segment.
4. The method for monitoring the heating system in real time based on the internet of things according to claim 1, wherein the obtaining the critical curve segment according to the probability parameter of the critical curve segment comprises the following specific steps:
for the firstObtaining a stable initial curve segment No. 1 and a stable termination curve segment No. 1 according to the annual history temperature curve and the two ascending curve segments with the maximum probability parameters of the critical curve segment;
obtaining a No. 2 stable initial curve segment and a No. 2 stable termination curve segment according to two descending curve segments with maximum probability parameters of being critical curve segments;
obtaining critical curve segments of a starting stage and a stabilizing stage according to the acquisition time of first data in each of the stable initial curve segment No. 1 and the stable initial curve segment No. 2; and obtaining critical curve segments of the stable phase and the termination phase according to the acquisition time of the first data in the stable termination curve segment No. 1 and the stable termination curve segment No. 2.
5. The method for monitoring a heating system in real time based on the internet of things according to claim 1, wherein the method for acquiring the start phase data, the steady phase data and the end phase data in the historical temperature curve according to the probability parameter of the critical curve segment comprises the following specific steps:
for the firstAnnual history temperature curve, will->First data in the annual history temperature profile, to +.>Data of previous critical curve segment of starting phase and stable phase in annual history temperature curveAll data in between are used as starting stage data; will be->First data in critical curve segments of start-up phase and steady-state phase in annual history temperature curve, to +.>All data between the last data in the critical curve segment of the stable phase and the termination phase in the annual history temperature curve are used as stable phase data; will be->All data after the last data in the critical curve segments of the stable phase and the termination phase in the annual history temperature curve are taken as termination phase data.
6. The real-time monitoring method of a heating system based on the internet of things according to claim 1, wherein the fitting is performed according to real-time temperature data in real-time heating data to obtain a real-time temperature curve segment, and the real-time temperature curve segment is segmented to obtain a plurality of real-time temperature curve segments, comprising the following specific steps:
constructing a rectangular coordinate system by taking temperature as a vertical axis and time as a horizontal axis, placing real-time temperature data in the rectangular coordinate system, and fitting data points in the rectangular coordinate system by using a least square method to obtain a real-time temperature curve; acquiring all extreme points in the real-time temperature curve, and segmenting the real-time temperature curve by taking all extreme points in the real-time temperature curve as real-time temperature curve segmentation points to obtain a plurality of real-time temperature curve segments.
7. The method for monitoring the heating system in real time based on the internet of things according to claim 1, wherein the method for acquiring the sample set of the real-time temperature curve according to all the data in the real-time temperature curve section and combining the start phase data, the stable phase data and the stop phase data in the historical temperature curve comprises the following specific steps:
calculating the slope average value and the amplitude average value of all data points in each real-time temperature curve segment to be used as the slope and the amplitude of each real-time temperature curve segment;
then, counting the quantity of the data in the starting stage, the data in the stabilizing stage and the data in the ending stage in each calendar history temperature curve; and calculating the number average of the data in the start-up phase in each calendar history temperature curve asNumber average of data in stationary phase in calendar history temperature curves +.>；
Counting the quantity of data in the real-time temperature data and comparing withIs->Comparing the sizes, and obtaining a reference set according to the comparison result and all data respectively positioned in a starting stage, a stabilizing stage and a terminating stage in each calendar history temperature curve; calculating the slope average value and the amplitude average value of all data points in each historical temperature curve segment in the reference set, and taking the slope average value and the amplitude average value as the slope and the amplitude of each historical temperature curve segment in the reference set; the specific process for acquiring the matching degree between the real-time temperature curve and the reference set by combining the slopes and the amplitudes of all the real-time temperature curve segments is as follows:
in the method, in the process of the invention,indicating the degree of matching between the real-time temperature profile and the reference set,/->Representing the slope average of all real-time temperature curve segments; />Representing the average value of the amplitude values of all the real-time temperature curve segments; />Representing the slope average of all historical temperature curve segments in the reference set; />Representing the average value of the amplitude values of all historical temperature curve segments in the reference set; />Representing an absolute value operation; />Representing preset super parameters;
and acquiring a sample set of the real-time temperature curve according to the matching degree between the real-time temperature curve and the reference set.
8. The method for real-time monitoring of a heating system based on internet of things according to claim 7, wherein the method for obtaining the sample set of the real-time temperature curve according to the matching degree between the real-time temperature curve and the reference set comprises the following specific steps:
according to the quantity of data in the real-time temperature dataIs->Comparing the magnitude to obtain a comparison result, combining the matching degree between the real-time temperature curve and the reference set, and +.>The number of data in the annual history temperature profile in the start phase, the steady phase and the end phase, respectively, for +.>Data in the starting stage, the stabilizing stage and the terminating stage in the annual history temperature curve are selected to obtain the +.>Annual target historical temperature data; annual target historical temperature data is acquired and taken as a sample set of real-time temperature profiles.
9. The real-time monitoring method of the heating system based on the internet of things according to claim 1, wherein the anomaly detection is performed on the real-time temperature data according to the sample set of the real-time temperature curve, and the specific method comprises the following steps:
placing all real-time temperature data into a sample set of a real-time temperature curve, and then calculating local outlier factors of all real-time temperature data by using an LOF anomaly detection algorithm; obtaining local outlier factors of all real-time temperature data, and then presetting an abnormal threshold valueThe method comprises the steps of carrying out a first treatment on the surface of the All local outliers are greater than +.>The real-time temperature data of the temperature sensor is marked as abnormal data, and the abnormal data in the real-time temperature data are marked to realize real-time monitoring of the temperature data.
10. The real-time monitoring system of the heating system based on the internet of things, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, characterized in that the computer program, when executed by the processor, realizes the steps of the real-time monitoring method of the heating system based on the internet of things as claimed in any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410282401.4A CN117870016A (en) | 2024-03-13 | 2024-03-13 | Real-time monitoring method and system for heating system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410282401.4A CN117870016A (en) | 2024-03-13 | 2024-03-13 | Real-time monitoring method and system for heating system based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117870016A true CN117870016A (en) | 2024-04-12 |
Family
ID=90584994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410282401.4A Pending CN117870016A (en) | 2024-03-13 | 2024-03-13 | Real-time monitoring method and system for heating system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117870016A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0056670A2 (en) * | 1981-01-16 | 1982-07-28 | Nederlandse Energie Ontwikkeling Maatschappij (NEOM) B.V. | Assembly comprising a heat recovery device |
| JPH11254537A (en) * | 1998-03-09 | 1999-09-21 | Kubota Corp | Method and apparatus for detecting abnormality in electric welding |
| KR101782893B1 (en) * | 2016-07-28 | 2017-09-29 | 린나이코리아 주식회사 | Multi-automatic setting of the boiler thermostat |
| CN111811567A (en) * | 2020-07-21 | 2020-10-23 | 北京中科五极数据科技有限公司 | Equipment detection method based on curve inflection point comparison and related device |
| WO2021169109A1 (en) * | 2020-02-26 | 2021-09-02 | 杰马科技（中山）有限公司 | Temperature control method and apparatus for air conditioner, and air conditioner |
| CN116595426A (en) * | 2023-07-17 | 2023-08-15 | 济南大陆机电股份有限公司 | Industrial Internet of things data intelligent acquisition management system |
| CN117433058A (en) * | 2023-09-27 | 2024-01-23 | 青岛海尔科技有限公司 | Thermal energy management method, device, equipment and medium for heat supply equipment |
-
2024
- 2024-03-13 CN CN202410282401.4A patent/CN117870016A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0056670A2 (en) * | 1981-01-16 | 1982-07-28 | Nederlandse Energie Ontwikkeling Maatschappij (NEOM) B.V. | Assembly comprising a heat recovery device |
| JPH11254537A (en) * | 1998-03-09 | 1999-09-21 | Kubota Corp | Method and apparatus for detecting abnormality in electric welding |
| KR101782893B1 (en) * | 2016-07-28 | 2017-09-29 | 린나이코리아 주식회사 | Multi-automatic setting of the boiler thermostat |
| WO2021169109A1 (en) * | 2020-02-26 | 2021-09-02 | 杰马科技（中山）有限公司 | Temperature control method and apparatus for air conditioner, and air conditioner |
| CN111811567A (en) * | 2020-07-21 | 2020-10-23 | 北京中科五极数据科技有限公司 | Equipment detection method based on curve inflection point comparison and related device |
| CN116595426A (en) * | 2023-07-17 | 2023-08-15 | 济南大陆机电股份有限公司 | Industrial Internet of things data intelligent acquisition management system |
| CN117433058A (en) * | 2023-09-27 | 2024-01-23 | 青岛海尔科技有限公司 | Thermal energy management method, device, equipment and medium for heat supply equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110018670B (en) | Industrial process abnormal working condition prediction method based on dynamic association rule mining | |
| CN108959778B (en) | Method for predicting residual life of aircraft engine based on consistency of degradation modes | |
| CN108038044B (en) | Anomaly detection method for continuous monitored object | |
| CN116111727B (en) | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold | |
| CN117238058B (en) | Starter monitoring method for automobile based on data analysis | |
| CN116756493B (en) | Data management method for security and fire control finger collecting platform | |
| EP4280088A1 (en) | Time series data trend feature extraction method based on dynamic grid division | |
| CN117167903B (en) | Artificial intelligence-based foreign matter fault detection method for heating ventilation equipment | |
| CN116308963B (en) | Government affair data analysis method and system | |
| CN117235462B (en) | Intelligent fault prediction method for bag type packaging machine based on time sequence data analysis | |
| CN117093947B (en) | Power generation diesel engine operation abnormity monitoring method and system | |
| CN116796209B (en) | Data processing method for monitoring storage environment temperature of detection kit | |
| CN116772285B (en) | Intelligent building heating load safety real-time monitoring method | |
| CN117870016A (en) | Real-time monitoring method and system for heating system based on Internet of things | |
| CN117313020A (en) | Data processing method of bearing type tension sensor | |
| CN116448263B (en) | Method for detecting running state of boehmite production equipment | |
| JP2009258879A (en) | Design support device | |
| CN110288021B (en) | Segmentation method of multi-element industrial time series data | |
| CN112149833B (en) | Prediction method, device, equipment and storage medium based on machine learning | |
| CN110083804B (en) | Wind power plant SCADA data missing intelligent repairing method based on condition distribution regression | |
| CN110162853B (en) | Mechanical experiment data preprocessing method based on mechanical model | |
| CN112700039A (en) | Steady state detection and extraction method for load operation data of thermal power plant | |
| CN117931897B (en) | Temperature data operation monitoring method for heating device | |
| CN116595338B (en) | Engineering information acquisition and processing system based on Internet of things | |
| CN117556386B (en) | Temperature data monitoring method in furnace refining process |
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 |