CN116772285A - Intelligent building heating load safety real-time monitoring method - Google Patents
Intelligent building heating load safety real-time monitoring method Download PDFInfo
- Publication number
- CN116772285A CN116772285A CN202311082409.8A CN202311082409A CN116772285A CN 116772285 A CN116772285 A CN 116772285A CN 202311082409 A CN202311082409 A CN 202311082409A CN 116772285 A CN116772285 A CN 116772285A
- Authority
- CN
- China
- Prior art keywords
- candidate
- periodic sequence
- sequence
- segment
- sequence segment
- 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
- 238000010438 heat treatment Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 230000000737 periodic effect Effects 0.000 claims abstract description 106
- 230000002159 abnormal effect Effects 0.000 claims abstract description 94
- 230000005856 abnormality Effects 0.000 claims abstract description 65
- 230000003321 amplification Effects 0.000 claims description 34
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 34
- 230000000295 complement effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D19/00—Details
- F24D19/10—Arrangement or mounting of control or safety devices
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The application relates to the field of data processing, in particular to a method for monitoring the heating load safety of an intelligent building in real time, which comprises the following steps: acquiring an actual temperature sequence and a standard reference temperature of each region; obtaining a plurality of candidate periodic sequence segments according to the actual temperature sequence, and obtaining an extended periodic sequence segment according to the candidate periodic sequence segments; the abnormal degree of each candidate abnormal point is obtained according to each subsequence segment, and the abnormal degree of each region is obtained; and obtaining a heating temperature adjustment value of each region according to the abnormality degree of each region, and adjusting the heating temperature of each region, so that the heating abnormality condition of each region is accurately described, and the building heating adjustment precision is improved.
Description
Technical Field
The application relates to the field of data processing, in particular to a method for monitoring the heating load safety of an intelligent building in real time.
Background
Under building heating load safety real-time monitoring scene, current heating load safety monitoring is often through gathering heating relevant sensor data, for example temperature, through judging whether sensor data is the scope of predetermineeing, judges to be abnormal data when sensor data does not belong to the scope of predetermineeing, when there is abnormal data, sends the safety precaution. Meanwhile, due to various reasons for causing abnormality of the sensor data, such as heating temperature setting errors and sensor faults, the abnormal data is difficult to accurately locate only through the judgment of the pre-support range, so that error early warning occurs. Meanwhile, when abnormality occurs, heating parameters are manually adjusted, and heating load cannot be adaptively adjusted according to abnormal conditions of the heating load.
Disclosure of Invention
In order to solve the technical problems, the application provides a method for monitoring the heating load safety of an intelligent building in real time, which comprises the following steps:
acquiring all actual temperatures of each area, an actual temperature sequence formed by all the actual temperatures and a standard reference temperature;
obtaining a plurality of periodic sequence segments according to all actual temperatures, calculating the correlation of each periodic sequence segment, obtaining a plurality of candidate periodic sequence segments according to the correlation of each periodic sequence segment, calculating the amplification cycle number of each candidate periodic sequence segment, and carrying out expansion processing on each candidate periodic sequence segment according to the amplification cycle number to obtain an expansion periodic sequence segment;
obtaining a plurality of candidate abnormal points according to the extended period sequence segments, carrying out segmentation processing on each extended period sequence segment according to the candidate abnormal points to obtain a plurality of subsequence segments, obtaining the abnormal degree of each candidate abnormal point according to the variation condition of the subsequence segment where each candidate abnormal point is located, taking the candidate abnormal point with the abnormal degree larger than a preset abnormal degree threshold value as the abnormal point, and taking the maximum value of the abnormal degrees of all abnormal points of each region as the abnormal degree of each region;
obtaining a heating temperature adjustment value of each area according to the difference condition and the abnormality degree of the actual temperature sequence and the standard reference temperature, and adjusting the heating temperature of each area according to the heating temperature adjustment value of each area;
obtaining the degree of abnormality of each candidate abnormal point according to the variation condition of the subsequence segment where each candidate abnormal point is located, including the following specific steps:
wherein ,representing the variance of slope values of all actual temperatures within the sub-sequence segment where the z-th candidate outlier is located,indicating the degree of abnormality of the z-th candidate abnormal point, exp () indicates an exponential function based on a natural constant.
Preferably, the obtaining a plurality of periodic sequence segments according to all actual temperatures includes the following specific steps:
taking a sequence section formed by the actual temperature of one day as a periodic sequence section, and acquiring all the periodic sequence sections.
Preferably, the calculating the correlation of each periodic sequence segment includes the following specific steps:
the absolute value of the pearson correlation coefficient of each periodic sequence segment and the previous periodic sequence segment is taken as the correlation degree of each periodic sequence segment.
Preferably, the obtaining a plurality of candidate periodic sequence segments according to the correlation of each periodic sequence segment includes the following specific steps:
and taking the periodic sequence segment with the correlation degree smaller than the preset correlation degree threshold value as a candidate periodic sequence segment.
Preferably, the calculating the amplification cycle number of each candidate cycle sequence segment includes the following specific steps:
wherein ,indicating the degree of correlation of the j-th candidate periodic sequence segment,indicating the degree of correlation of the period sequence segment preceding the jth candidate period sequence segment,representing the degree of correlation of the left adjacent periodic sequence segments of the previous periodic sequence segment of the j-th candidate periodic sequence segment,the adjustment coefficient is amplified for a predetermined period,representing the amplification cycle number of the j-th candidate cycle sequence segment;
the left adjacent periodic sequence segment of the periodic sequence segment refers to: and arranging all the periodic sequence segments according to the time sequence, and then arranging the left adjacent periodic sequence segments of each periodic sequence segment.
Preferably, the expanding process is performed on each candidate periodic sequence segment according to the number of the expansion periods to obtain an expanded periodic sequence segment, which comprises the following specific steps:
for the jth candidate periodic sequence segment, acquiring the period sequence segment in the actual temperature sequenceThe periodic sequence segments are used as complementary sequences of the candidate periodic sequence segments, and the complementary sequences are spliced after the candidate periodic sequence segments to obtain amplified periodic sequence segments of the candidate periodic sequence segments;representing the amplification cycle number of the j-th candidate cycle sequence segment;
and obtaining an amplified periodic sequence segment of each candidate periodic sequence segment.
Preferably, the obtaining a plurality of candidate abnormal points according to the extended period sequence segment includes the specific steps of:
and obtaining extreme points of each amplification period sequence segment, and taking the extreme points of each amplification period sequence segment as candidate abnormal points.
Preferably, the heating temperature adjustment value of each area is obtained according to the difference condition and the abnormality degree of the actual temperature sequence and the standard reference temperature, and the specific steps include:
acquiring an integral value of a difference function of each region;
the method for obtaining the heating temperature adjustment amplitude of each area according to the integral value and the abnormality degree of the difference function comprises the following steps:
wherein ,an integrated value representing the difference function of each region,representing the maximum of all the actual temperatures for each zone,representing the minimum of all actual temperatures for each zone,the degree of abnormality of each zone is represented, and F represents the heating temperature adjustment amplitude of each zone;
when the integral value of the difference function is smaller than 0, F is taken as a heating temperature adjustment value;
when the integral value of the difference function is greater than 0, -F is taken as the heating temperature adjustment value.
Preferably, the step of obtaining the integral value of the difference function of each region includes the specific steps of:
for any region, fitting a fitting curve of an actual temperature sequence, setting a standard reference temperature sequence with the length of N, respectively taking standard reference temperatures of all elements in the standard reference temperature sequence, fitting a fitting straight line of the standard reference temperature sequence, fitting a function of the fitting curve of the actual temperature sequence of the region, fitting a function of the fitting straight line of the standard reference temperature sequence, subtracting the function of the fitting curve of the actual temperature sequence from the function of the fitting straight line of the standard reference temperature sequence to obtain a difference function, and obtaining an integral value of the difference function;
an integrated value of the difference function of each region is acquired.
The embodiment of the application has at least the following beneficial effects: the abnormal degree of the actual temperature of each area can better reflect the abnormal heating condition of each area, so that the abnormal degree of each area needs to be accurately obtained in order to more accurately adjust the heating temperature of each area in the building; in order to describe the degree of abnormality of each region more accurately, it is necessary to obtain the abnormality data corresponding to the abnormality time of each region accurately. The method comprises the steps of obtaining the actual temperature correlation in adjacent periods, obtaining the candidate periods according to the actual temperature correlation in the adjacent periods, and amplifying the candidate periods to obtain an amplified period sequence because the abnormal data are difficult to accurately locate due to the fact that the data of the candidate periods are less. For the reason that the abnormality is caused more, to reduce the difficulty of analysis, the amplification cycle sequence needs to be segmented to obtain a plurality of subsequence segments, the abnormality degree of each candidate abnormal data is calculated according to each subsequence segment, then the abnormal data is obtained, the abnormality degree of each region is obtained according to the abnormality degree of the abnormal data, the heating temperature adjustment value of each region is obtained by combining the abnormality degree of each region, and the heating temperature of each region is adjusted according to the heating temperature adjustment value, so that the heating temperature of each region is accurately adjusted.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for monitoring the safety of heating loads of intelligent buildings in real time;
fig. 2 is a schematic diagram showing actual temperature change at abnormal heating provided by the present application.
Detailed Description
In order to further explain the technical means and effects adopted by the application to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the intelligent building heating load safety real-time monitoring method according to the application 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 application belongs.
The application provides a specific scheme of an intelligent building heating load safety real-time monitoring method, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for monitoring the safety of a heating load of an intelligent building in real time according to an embodiment of the application is shown, the method includes the following steps:
step S001, obtaining standard reference temperature values of the whole building and actual temperature sequences of all areas.
In the traditional building heating load safety management method, heating load sensor data of the whole building are collected, the heating load sensor data are compared with a preset threshold range, when the heating load sensor data exceed the preset threshold range, the sensor data are judged to be abnormal sensor data, safety early warning is carried out when the abnormal sensor data exist, and meanwhile heating parameters are adjusted by manually analyzing the abnormal sensor data. In real life, there are various reasons for the presence of abnormal sensor data, for example, the collected sensor data is abnormal due to abnormal sensor, and the abnormal sensor data is caused by the problem of setting heating parameters, so that the abnormal sensor data is not accurately positioned only according to the threshold range, and then early warning errors and heating temperature adjustment errors are caused.
In order to realize more accurate building heating load management, sensor data of the whole building need to be acquired first, wherein the temperature data acquired by the temperature sensor can better reflect the heating condition of the building, and therefore the data are acquired by the temperature sensor.
Taking each household in a building as an area, arranging a temperature sensor in each area, acquiring actual temperatures every 30min, acquiring N times, and arranging N actual temperatures acquired by the temperature sensors in each area in time sequence to obtain an actual temperature sequence of each area;
and acquiring a standard reference temperature value set by the heating center.
Step S002, obtaining all candidate period sequence segments of each region according to the actual temperature sequence of each region, calculating the amplification cycle number of each candidate period of each region, and carrying out amplification treatment on each candidate period sequence segment according to the amplification cycle number to obtain a plurality of amplification period sequence segments of each region.
Since the heating temperature of each zone needs to be adjusted when there is an abnormality in the actual temperature values at all times of each zone, the heating abnormality time must be accurately located first, and the zone heating temperature needs to be adjusted according to the degree of abnormality in the actual temperature values at the heating abnormality time.
Because the factors causing the abnormality of the actual measured temperature of each area are more, it is difficult to directly locate the abnormal heating time of each area, so that some candidate periodic sequence segments containing abnormal time can be located first.
Acquiring all candidate periodic sequence segments of each region:
since the temperature changes of the adjacent two days of one region are similar in normal condition, the correlation of the temperature changes of the adjacent two days of one region is large, and thus the candidate period is acquired based on this.
Since the temperature change rule of a region takes one day as a period, the actual temperature sequence comprises actual temperature values of a plurality of days, the sequence formed by the actual temperature values of one day is taken as a period sequence section of one period, and the actual temperature sequence is divided into a plurality of period sequence sections.
Calculating the pearson correlation coefficient of the periodic sequence segment of each period and the periodic sequence segment of the previous period, taking the absolute value of the pearson correlation coefficient of each periodic sequence segment and the previous periodic sequence segment as the correlation degree of each periodic sequence segment, wherein the correlation degree of the periodic sequence segment is also the correlation degree of the corresponding period, and the correlation degree of the jth periodic sequence segment is recorded as. It should be noted that, since the distance between the first period and the current time is relatively long, the influence of temperature regulation at the current time is small, so that the correlation degree of the period sequence segment of the first period does not need to be obtained.
Since the period with small correlation degree is a period containing abnormal time, the probability is high that the correlation degree is smaller than the preset correlation degree threshold valueThe period of the cycle sequence corresponding to the candidate period is referred to as a candidate period sequence segment. In this embodiment, K is taken as an example of 0.8, and other values may be taken in other embodiments, which is not limited.
Calculating the amplification period number of each candidate period sequence segment:
since the data in each candidate period sequence segment is less, the reason for abnormality in the period cannot be accurately analyzed, and thus expansion processing is required for the candidate period sequence segment of each candidate period, and since the possibility of abnormality occurrence is different for each candidate period sequence segment, the analysis accuracy required for the candidate period with high possibility of abnormality occurrence is greater, and thus more data is required for locating the abnormality occurrence for the candidate period sequence segment with high possibility of abnormality occurrence, the number of amplification cycles for each candidate period sequence segment is determined based on this.
The method for determining the amplification cycle number of each candidate cycle sequence segment comprises the following steps:
wherein ,indicating the degree of correlation of the j-th candidate periodic sequence segment,indicating the degree of correlation of the period sequence segment preceding the jth candidate period sequence segment,representing the correlation degree of a left adjacent periodic sequence segment of a previous periodic sequence segment of the j candidate periodic sequence segment, wherein the left adjacent periodic sequence segment is a left adjacent periodic sequence segment;reflecting the variation of the degree of correlation of the jth candidate periodic sequence segment, the larger the value is, the greater the variation of the degree of correlation of the jth candidate periodic sequence segment is, and thus the greater the likelihood of the occurrence of an abnormal moment in the jth candidate period, and thus more data is required to accurately locate the abnormal moment, and thus the number of amplification cycles of the candidate periodic sequence segment is greater,for the preset period amplification adjustment coefficient, the embodiment usesBy taking 10 as a description, other values may be taken in other embodiments, which are not limiting,representing the jth candidateCycles of amplification of the periodic sequence segment.
Amplifying each candidate periodic sequence segment to obtain an amplified periodic sequence segment:
for the jth candidate periodic sequence segment of a region, after the candidate periodic sequence segment is acquired in the actual temperature sequenceAnd the periodic sequence segments are used as complementary sequences of the candidate periodic sequence segments, and the complementary sequences are spliced after the candidate periodic sequence segments to obtain amplified periodic sequence segments of the candidate periodic sequence segments.
When the amplification period sequence segments are obtained, candidate period sequence segments are obtained according to the fact that the correlation between two adjacent periods is high under normal conditions, and each candidate period sequence segment is amplified to obtain the amplification period sequence segments due to the fact that the data size of the candidate period sequence segments is small.
Step S003, carrying out segmentation processing on each amplification period sequence segment of each region to obtain a plurality of subsequence segments of each amplification period sequence segment of each region, and obtaining a plurality of abnormal points of each region and the degree of abnormality of each abnormal point according to the plurality of subsequence segments of each region.
There are various reasons for the abnormality of the actual temperature of each region: a. temperature abnormality due to heating temperature setting problem, b. false actual temperature is acquired due to sensor failure; and only the temperature abnormality caused by the heating temperature setting problem needs to adjust the heating temperature. Therefore, to realize accurate temperature adjustment, the disturbance of temperature abnormality caused by sensor fault needs to be removed, and accurate abnormal points are obtained, which comprises the following specific operations:
acquiring a plurality of subsequence segments and candidate outliers of each amplification cycle sequence segment:
the actual temperature has a plurality of reasons for abnormality, so that the analysis is difficult, and when the actual temperature has a variation rule, the probability of being interfered by one factor is high, so that the segmentation processing is required to be carried out on each amplification period sequence segment, the probability of the actual temperature in each segment being influenced by a single factor is high, and the analysis difficulty based on each segment is low.
Since there is a difference in the change law of the data on both sides of the extreme point, segmentation is performed based on the extreme point. The specific segmentation operation is as follows:
because the variation rules at the two sides of the extreme point have differences, the extreme point is highly likely to be an abnormal point, and therefore the extreme point of each amplification period sequence segment is taken as a candidate abnormal point.
And dividing the amplification period sequence segment into a plurality of subsequence segments by taking the candidate abnormal point as a dividing point. It should be noted that each sub-sequence segment contains the extreme point on the left.
Calculating the degree of abnormality of each candidate abnormal point:
each candidate outlier corresponds to one sub-sequence segment, and the outlier degree of each candidate outlier is calculated based on the variation characteristics of the sub-sequence segment corresponding to each candidate outlier.
Since the actual temperature will normally fluctuate within a certain range, and when there is an abnormality, the actual temperature will remain unchanged or continuously increase or decrease according to a certain slope, as shown in fig. 2, where the point a in fig. 2 is a candidate abnormal point, and the slope after the candidate abnormal point remains unchanged or changes according to a trend of increasing according to a certain slope, the abnormality degree of each candidate abnormal point is calculated based on this, specifically:
wherein ,the larger the variance of slope values of all actual temperatures in the subsequence segment where the z candidate abnormal point is located is, the larger the variance of slope change of the subsequence segment where the z candidate abnormal point is located is, the no abnormality exists in the subsequence segment, and therefore the degree of abnormality of the candidate abnormal point is small;represent the firstThe degree of abnormality of the z candidate outliers, exp () represents an exponential function based on a natural constant.
Thus, the degree of abnormality of each candidate abnormal point is calculated.
3. Obtaining abnormal points according to the abnormal degree:
the degree of abnormality is larger than a preset threshold value of degree of abnormalityIs used as the outlier, in the present embodimentTaking 0.8 as an example for description, other embodiments may take other values, and the present embodiment is not particularly limited.
Step S004, a heating temperature adjustment value of each area is obtained according to a plurality of abnormal points of each area and the abnormal degree of each abnormal point, and the heating temperature of each area is adjusted according to the heating temperature adjustment value of each area.
The standard reference temperature has been acquired in step S001, and the heating temperature of each zone is adjusted based on the standard reference temperature and the degree of abnormality of the plurality of abnormal points of each zone.
1. Determining a heating temperature adjustment value for each zone:
the maximum value of the degree of abnormality of all abnormal points in each region is taken as the degree of abnormality of each region. The value can accurately reflect the abnormal condition of each region. The degree of abnormality of each region is recorded as。
Normally, the actual temperature of each area should fluctuate around the standard reference temperature value, and when abnormality exists, the actual temperature of each area deviates from the standard reference temperature, wherein the greater the abnormality degree, the farther the actual temperature of each area deviates from the standard reference temperature, so that the heating temperature of each area can be adjusted in combination with the fluctuation condition of the actual temperature of each area around the standard reference temperature and the abnormality degree of each area.
For one ofAnd setting a standard reference temperature sequence with the length of N, respectively taking standard reference temperature from each element in the standard reference temperature sequence, fitting a fitting straight line of the standard reference temperature sequence, when the fitting curve of the actual temperature sequence is above the fitting straight line of the standard reference temperature sequence, indicating that the actual temperature value of the area is higher, and when the fitting curve of the actual temperature sequence is below the fitting straight line of the standard reference temperature sequence, indicating that the actual temperature value of the area is lower, so that the integral value of the difference function of the two fitting functions of the fitting curve of the actual temperature sequence and the fitting straight line of the standard reference temperature sequence can reflect the heating condition of the area, thereby fitting the function of the fitting curve of the actual temperature sequence of the area, wherein the function of the fitting curve of the actual temperature sequence is a polynomial of 5 times, fitting the function of the fitting straight line of the standard reference temperature sequence, subtracting the function of the fitting curve of the actual temperature sequence and the function of the straight line of the standard reference temperature sequence to obtain the difference function, and obtaining the integral value of the difference function. The integral value of the difference function of each region is recorded as。
Obtaining heating temperature adjustment amplitude of each region according to the integral value and the abnormality degree of the difference function of each region:
wherein ,an integral value representing the difference function for each zone, the greater the value indicating that the heating temperature for that zone is set too high, requiring downward adjustment,representing the maximum of all the actual temperatures for each zone,representing the minimum of all actual temperatures for each zone,the degree of abnormality for each region is indicated, and a larger value indicates that the heating temperature of the region is abnormal, and thus the heating temperature adjustment range for the region is larger, and F indicates the heating temperature adjustment range for each region.
When the integral value Mm of the difference function is smaller than 0, it is explained that the actual heating temperature of the zone is smaller than the standard reference temperature most of the time, that is, the heating temperature of the zone is not satisfied, and thus it is necessary to raise the heating temperature of the zone, and F is taken as the heating temperature adjustment value Ff of the zone.
When the integral value Mm of the difference function is greater than 0, it is explained that the actual heating temperature of the zone is greater than the standard reference temperature most of the time, that is, the heating temperature of the zone is not satisfied, and thus the heating temperature of the zone needs to be adjusted down, and-F is taken as the heating temperature adjustment value Ff of the zone.
2. Adjusting the heating temperature of each area according to the heating temperature adjustment amplitude and the adjustment direction of each area:
when an abnormal point exists in the area, an alarm is given, and the heating temperature of the area is increased by Ff. When there is no abnormal point in the area, no alarm is required, and no heating temperature adjustment is performed.
In summary, the embodiment of the application provides a method for monitoring the heating load safety of an intelligent building in real time, because the abnormal degree of the actual temperature of each area can better reflect the abnormal heating condition of each area, in order to more accurately adjust the heating temperature of each area in the building, the abnormal degree of each area needs to be accurately obtained; in order to describe the degree of abnormality of each region more accurately, it is necessary to obtain the abnormality data corresponding to the abnormality time of each region accurately. The method comprises the steps of obtaining the actual temperature correlation in adjacent periods, obtaining the candidate periods according to the actual temperature correlation in the adjacent periods, and amplifying the candidate periods to obtain an amplified period sequence because the abnormal data are difficult to accurately locate due to the fact that the data of the candidate periods are less. For the reason that the abnormality is caused more, to reduce the difficulty of analysis, the amplification cycle sequence needs to be segmented to obtain a plurality of subsequence segments, the abnormality degree of each candidate abnormal data is calculated according to each subsequence segment, then the abnormal data is obtained, the abnormality degree of each region is obtained according to the abnormality degree of the abnormal data, the heating temperature adjustment value of each region is obtained by combining the abnormality degree of each region, and the heating temperature of each region is adjusted according to the heating temperature adjustment value, so that the heating temperature of each region is accurately adjusted.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present application are intended to be included within the scope of the present application.
Claims (9)
1. The intelligent building heating load safety real-time monitoring method is characterized by comprising the following steps of:
acquiring all actual temperatures of each area, an actual temperature sequence formed by all the actual temperatures and a standard reference temperature;
obtaining a plurality of periodic sequence segments according to all actual temperatures, calculating the correlation of each periodic sequence segment, obtaining a plurality of candidate periodic sequence segments according to the correlation of each periodic sequence segment, calculating the amplification cycle number of each candidate periodic sequence segment, and carrying out expansion processing on each candidate periodic sequence segment according to the amplification cycle number to obtain an expansion periodic sequence segment;
obtaining a plurality of candidate abnormal points according to the extended period sequence segments, carrying out segmentation processing on each extended period sequence segment according to the candidate abnormal points to obtain a plurality of subsequence segments, obtaining the abnormal degree of each candidate abnormal point according to the variation condition of the subsequence segment where each candidate abnormal point is located, taking the candidate abnormal point with the abnormal degree larger than a preset abnormal degree threshold value as the abnormal point, and taking the maximum value of the abnormal degrees of all abnormal points of each region as the abnormal degree of each region;
obtaining a heating temperature adjustment value of each area according to the difference condition and the abnormality degree of the actual temperature sequence and the standard reference temperature, and adjusting the heating temperature of each area according to the heating temperature adjustment value of each area;
obtaining the degree of abnormality of each candidate abnormal point according to the variation condition of the subsequence segment where each candidate abnormal point is located, including the following specific steps:
wherein ,representing the variance of slope values of all actual temperatures within the sub-sequence segment where the z-th candidate outlier is located, +.>Indicating the degree of abnormality of the z-th candidate abnormal point, exp () indicates an exponential function based on a natural constant.
2. The method for monitoring the safety of heating loads of intelligent buildings in real time according to claim 1, wherein the steps of obtaining a plurality of periodic sequence segments according to all actual temperatures comprise the following specific steps:
taking a sequence section formed by the actual temperature of one day as a periodic sequence section, and acquiring all the periodic sequence sections.
3. The method for monitoring the safety of heating loads of intelligent buildings in real time according to claim 1, wherein the calculating of the correlation of each period sequence segment comprises the following specific steps:
the absolute value of the pearson correlation coefficient of each periodic sequence segment and the previous periodic sequence segment is taken as the correlation degree of each periodic sequence segment.
4. The method for monitoring the safety of the heating load of the intelligent building in real time according to claim 1, wherein the step of obtaining a plurality of candidate periodic sequence segments according to the correlation of each periodic sequence segment comprises the following specific steps:
and taking the periodic sequence segment with the correlation degree smaller than the preset correlation degree threshold value as a candidate periodic sequence segment.
5. The method for monitoring the safety of heating loads of intelligent buildings in real time according to claim 1, wherein the step of calculating the number of amplified cycles of each candidate cycle sequence segment comprises the following specific steps:
wherein ,indicating the degree of correlation of the j-th candidate periodic sequence segment,/->Indicating the degree of correlation of the segment of the periodic sequence preceding the j-th candidate segment of the periodic sequence, +.>Representing the degree of correlation of the left adjacent periodic sequence segments of the previous periodic sequence segment of the jth candidate periodic sequence segment,/for>For a preset period amplification adjustment factor, +.>Representing the amplification cycle number of the j-th candidate cycle sequence segment;
the left adjacent periodic sequence segment of the periodic sequence segment refers to: and arranging all the periodic sequence segments according to the time sequence, and then arranging the left adjacent periodic sequence segments of each periodic sequence segment.
6. The method for monitoring the safety of heating loads of intelligent buildings in real time according to claim 1, wherein the step of expanding each candidate periodic sequence segment according to the number of the expansion periods to obtain an expanded periodic sequence segment comprises the following specific steps:
for the jth candidate periodic sequence segment, acquiring the period sequence segment in the actual temperature sequenceThe periodic sequence segments are used as complementary sequences of the candidate periodic sequence segments, and the complementary sequences are spliced after the candidate periodic sequence segments to obtain amplified periodic sequence segments of the candidate periodic sequence segments; />Representing the amplification cycle number of the j-th candidate cycle sequence segment;
and obtaining an amplified periodic sequence segment of each candidate periodic sequence segment.
7. The method for monitoring the safety of heating loads of intelligent buildings in real time according to claim 1, wherein the step of obtaining a plurality of candidate abnormal points according to the extended period sequence segment comprises the following specific steps:
and obtaining extreme points of each amplification period sequence segment, and taking the extreme points of each amplification period sequence segment as candidate abnormal points.
8. The method for monitoring the heating load safety of the intelligent building in real time according to claim 1, wherein the heating temperature adjustment value of each area is obtained according to the difference condition and the abnormality degree of the actual temperature sequence and the standard reference temperature, comprises the following specific steps:
acquiring an integral value of a difference function of each region;
the method for obtaining the heating temperature adjustment amplitude of each area according to the integral value and the abnormality degree of the difference function comprises the following steps:
wherein ,integral value of the difference function representing each region, < ->Represents the maximum value of all the actual temperatures of each zone, +.>Representing the minimum value of all actual temperatures of each zone,/->The degree of abnormality of each zone is represented, and F represents the heating temperature adjustment amplitude of each zone;
when the integral value of the difference function is smaller than 0, F is taken as a heating temperature adjustment value;
when the integral value of the difference function is greater than 0, -F is taken as the heating temperature adjustment value.
9. The method for monitoring the safety of heating loads of intelligent buildings in real time according to claim 8, wherein the step of obtaining the integral value of the difference function of each area comprises the following specific steps:
for any region, fitting a fitting curve of an actual temperature sequence, setting a standard reference temperature sequence with the length of N, respectively taking standard reference temperatures of all elements in the standard reference temperature sequence, fitting a fitting straight line of the standard reference temperature sequence, fitting a function of the fitting curve of the actual temperature sequence of the region, fitting a function of the fitting straight line of the standard reference temperature sequence, subtracting the function of the fitting curve of the actual temperature sequence from the function of the fitting straight line of the standard reference temperature sequence to obtain a difference function, and obtaining an integral value of the difference function;
an integrated value of the difference function of each region is acquired.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311082409.8A CN116772285B (en) | 2023-08-28 | 2023-08-28 | Intelligent building heating load safety real-time monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311082409.8A CN116772285B (en) | 2023-08-28 | 2023-08-28 | Intelligent building heating load safety real-time monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116772285A true CN116772285A (en) | 2023-09-19 |
| CN116772285B CN116772285B (en) | 2023-11-07 |
Family
ID=87993492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311082409.8A Active CN116772285B (en) | 2023-08-28 | 2023-08-28 | Intelligent building heating load safety real-time monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116772285B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116974268A (en) * | 2023-09-20 | 2023-10-31 | 青岛朗兹环保科技有限公司 | Intelligent monitoring and early warning method for control system circuit |
| CN118117760A (en) * | 2024-04-25 | 2024-05-31 | 闽西职业技术学院 | Intelligent monitoring method and system for electrical load |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016078791A1 (en) * | 2014-11-21 | 2016-05-26 | Siemens Aktiengesellschaft | Method and assistance system for recognising a fault in a system |
| US20220065705A1 (en) * | 2020-08-27 | 2022-03-03 | Yokogawa Electric Corporation | Abnormal temperature detection device, abnormal temperature detection method, and storage medium |
| 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 |
| CN115018315A (en) * | 2022-05-31 | 2022-09-06 | 河北建筑工程学院 | Method and device for detecting abnormal heat supply, electronic equipment and storage medium |
| CN115289637A (en) * | 2022-07-13 | 2022-11-04 | 中国电信股份有限公司 | Temperature adjustment method, system, device, storage medium, and program product |
| US20230082012A1 (en) * | 2021-06-24 | 2023-03-16 | Tencent Technology (Shenzhen) Company Limited | Service data processing method and apparatus, computer device, and storage medium |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN115962551A (en) * | 2023-03-16 | 2023-04-14 | 深圳市森辉智能自控技术有限公司 | Intelligent air conditioner control system and method for building automatic control |
| CN116111727A (en) * | 2023-04-13 | 2023-05-12 | 盛锋电力科技有限公司 | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold |
| CN116183058A (en) * | 2023-04-21 | 2023-05-30 | 实德电气集团有限公司 | Monitoring method of intelligent capacitor |
-
2023
- 2023-08-28 CN CN202311082409.8A patent/CN116772285B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016078791A1 (en) * | 2014-11-21 | 2016-05-26 | Siemens Aktiengesellschaft | Method and assistance system for recognising a fault in a system |
| US20220065705A1 (en) * | 2020-08-27 | 2022-03-03 | Yokogawa Electric Corporation | Abnormal temperature detection device, abnormal temperature detection method, and storage medium |
| US20230082012A1 (en) * | 2021-06-24 | 2023-03-16 | Tencent Technology (Shenzhen) Company Limited | Service data processing method and apparatus, computer device, and storage medium |
| CN115018315A (en) * | 2022-05-31 | 2022-09-06 | 河北建筑工程学院 | Method and device for detecting abnormal heat supply, electronic equipment and storage medium |
| CN115289637A (en) * | 2022-07-13 | 2022-11-04 | 中国电信股份有限公司 | Temperature adjustment method, system, device, storage medium, and program product |
| 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 |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN115962551A (en) * | 2023-03-16 | 2023-04-14 | 深圳市森辉智能自控技术有限公司 | Intelligent air conditioner control system and method for building automatic control |
| CN116111727A (en) * | 2023-04-13 | 2023-05-12 | 盛锋电力科技有限公司 | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold |
| CN116183058A (en) * | 2023-04-21 | 2023-05-30 | 实德电气集团有限公司 | Monitoring method of intelligent capacitor |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116974268A (en) * | 2023-09-20 | 2023-10-31 | 青岛朗兹环保科技有限公司 | Intelligent monitoring and early warning method for control system circuit |
| CN116974268B (en) * | 2023-09-20 | 2023-12-15 | 青岛朗兹环保科技有限公司 | Intelligent monitoring and early warning method for control system circuit |
| CN118117760A (en) * | 2024-04-25 | 2024-05-31 | 闽西职业技术学院 | Intelligent monitoring method and system for electrical load |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116772285B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116772285B (en) | Intelligent building heating load safety real-time monitoring method | |
| US9146800B2 (en) | Method for detecting anomalies in a time series data with trajectory and stochastic components | |
| CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
| CN117076934B (en) | Monitoring data acquisition and analysis method based on Internet of things | |
| CN117193164B (en) | Fault monitoring method and system of numerical control machine tool | |
| CN107729985B (en) | Method for detecting process anomalies in a technical installation and corresponding diagnostic system | |
| CN116304958B (en) | Intelligent monitoring system and method for underground water treatment abnormality | |
| CN112148768A (en) | Index time series abnormity detection method, system and storage medium | |
| CN112418517B (en) | Prediction method for freeze injury short-term early warning | |
| CN117473350B (en) | Welded pipe welding production process monitoring method based on data processing | |
| KR20230125116A (en) | The method for fault detection without training data or diagnosis with prediction of remaining time until breakdown using clustering algorithm and statistical methods | |
| CN117235462B (en) | Intelligent fault prediction method for bag type packaging machine based on time sequence data analysis | |
| CN116796209B (en) | Data processing method for monitoring storage environment temperature of detection kit | |
| CN117313020A (en) | Data processing method of bearing type tension sensor | |
| US20220004154A1 (en) | Information processing apparatus | |
| KR101615345B1 (en) | Method for analyzing wafer yield rate using sensor data in semiconductor manufacturing process | |
| KR100340967B1 (en) | Method and apparatus for detecting fault using General Regression Neural Network | |
| CN117931897B (en) | Temperature data operation monitoring method for heating device | |
| Kim et al. | Fault detection method using inverse distance weight-based local outlier factor | |
| CN117970168B (en) | High-efficiency processing method for monitoring data of dual-power conversion device | |
| CN117870016B (en) | Real-time monitoring method and system for heating system based on Internet of things | |
| CN116757337B (en) | House construction progress prediction system based on artificial intelligence | |
| CN117554109B (en) | Intelligent monitoring method and system for fault data information of heat exchanger | |
| CN117129904B (en) | Industrial power supply rapid switching monitoring method based on data analysis | |
| CN117171517B (en) | Dynamic early warning method for operation fault risk of data center |
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 |