CN117235447A - Building energy data management method and system - Google Patents
Building energy data management method and system Download PDFInfo
- Publication number
- CN117235447A CN117235447A CN202311490687.7A CN202311490687A CN117235447A CN 117235447 A CN117235447 A CN 117235447A CN 202311490687 A CN202311490687 A CN 202311490687A CN 117235447 A CN117235447 A CN 117235447A
- Authority
- CN
- China
- Prior art keywords
- curve
- data
- imf component
- data points
- degree
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000013523 data management Methods 0.000 title claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 192
- 238000010438 heat treatment Methods 0.000 claims abstract description 45
- 230000005856 abnormality Effects 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 239000000758 substrate Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009428 plumbing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010992 reflux Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a building energy data management method and system, comprising the following steps: collecting pressure data at the outlet of a heating pipeline valve in a building, and obtaining a component curve and a characteristic curve; acquiring suspected abnormal data points and normal data points according to the characteristic curve; acquiring the abnormality degree of the suspected abnormal data point according to the suspected abnormal data; according to the abnormality degree of the suspected abnormal data points, the similarity degree of the local range of the real suspected abnormal data points and the component curves is obtained, and the contribution degree of each component curve to the characteristic curve is finally obtained by combining the normal data points; acquiring all abnormal data points on the target curve according to the final contribution degree of each component curve to the characteristic curve; all outlier data points on the target curve are stored separately. The method and the device can remove noise from the building energy data, retain detailed information, and finally realize the purpose of accurately detecting abnormal data in the building energy data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a building energy data management method and system.
Background
The pressure data collected at the outlet of the heating pipeline valve in the building is used as building energy data, and because the special collection mode causes that a plurality of noise signals exist in the pressure data collected at the outlet of the heating pipeline valve in the building, and a plurality of noise signals in the pressure data collected at the outlet of the heating pipeline valve in the building influence the detection of abnormal data, a plurality of noise signals in the pressure data collected at the outlet of the heating pipeline valve in the building need to be removed.
But common data denoising methods are based onThe decomposition denoising algorithm does not consider the difference +.>The degree of contribution of the components, i.e. different +.>If the information content of the components is not considered for synthesis, partial detail information is definitely lost, so that deviation of pressure data occurs, data analysis of a system is affected, and abnormal data in building energy data cannot be accurately detected.
Disclosure of Invention
The invention provides a building energy data management method and system, which aim to solve the existing problems: when denoising is carried out on building energy data, partial detail information loss is caused to influence the detection of abnormal data.
The invention relates to a building energy data management method and a system, which adopt the following technical scheme:
one embodiment of the invention provides a building energy data management method, which comprises the following steps:
collecting pressure data at the outlet of a heating pipeline valve in a building, and obtaining a pressure curve according to the pressure data; acquiring an IMF component curve and a characteristic curve according to the pressure curve;
acquiring suspected abnormal data points and normal data points according to the characteristic curve; acquiring the abnormality degree of the suspected abnormal data points;
obtaining the similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve; obtaining the real similarity degree between the local range of the suspected abnormal data point and the IMF component curve according to the similarity degree between the local range of the suspected abnormal data point and the IMF component curve and the abnormality degree of the suspected abnormal data point;
obtaining the similarity degree of the normal data segment and the IMF component curve according to the normal data point; obtaining the contribution degree of the IMF component curve to the characteristic curve according to the similarity degree of the normal data segment and the IMF component curve and the similarity degree of the local range of the real suspected abnormal data point and the IMF component curve; acquiring the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve;
Acquiring a target curve according to the final contribution degree of each IMF component curve to the characteristic curve, and acquiring all abnormal data points on the target curve; all outlier data points on the target curve are stored separately.
Preferably, the pressure data at the outlet of the heating pipeline valve in the building is collected, and a pressure curve is obtained according to the pressure data; the IMF component curve and the characteristic curve are obtained according to the pressure curve, and the method comprises the following specific steps:
a pressure sensor is arranged at the outlet of a heating pipeline valve in the building, and the sampling interval of pressure data is acquired according to the preset pressure sensorCollecting pressure data;
constructing a rectangular coordinate system by taking time as an abscissa and pressure as an ordinate, and filling pressure data into the rectangular coordinate system; fitting the pressure data at the outlet of the heating pipeline valve in the building by using a least square method to obtain a pressure data curve at the outlet of the heating pipeline valve in the building, and recording the pressure data curve as a pressure curve;
and carrying out EMD decomposition on the pressure curve to obtain all IMF component curves of the pressure curve, eliminating the pressure curve after the baseline drift, and marking the pressure curve after the baseline drift is eliminated as a characteristic curve.
Preferably, the suspected abnormal data point and the normal data point are obtained according to the characteristic curve; the method for acquiring the abnormality degree of the suspected abnormal data point comprises the following specific steps:
taking the average value of all data points on the characteristic curve as a stable value of the characteristic curve; presetting a fluctuation thresholdThe method comprises the steps of carrying out a first treatment on the surface of the For the +.>Data points, if the first ∈>The difference between the data point and the steady value of the characteristic curve is greater than +.>The +.>The data points are suspected abnormal data points; if the +.>The difference between the data point and the steady value of the characteristic curve is less than or equal to +.>The +.>The data points are normal data points;
for the firstA suspected abnormal data point, the characteristic curve is associated with +.>The nearest extreme point of each suspected abnormal data point is taken as a target extreme point, two extreme points adjacent to the target extreme point are taken as intercepting extreme points, all data points between the two intercepting extreme points form a local range, the local range of the target extreme point in the local range is divided into two sections, one section is monotonously increased, the other section is monotonously decreased, and the first section is obtained through the slopes of all the data points in the two sections >The degree of abnormality of each suspected abnormal data point is calculated by the following specific formula:
in the method, in the process of the invention,indicate->Degree of abnormality of the individual suspected abnormal data points; />Is indicated at +.>The average value of the slopes of all data points in the 1 st interval in the local range of the suspected abnormal data points; />Is indicated at +.>The average of the slopes of all data points in interval 2, within the local range of the suspected outlier data points.
Preferably, the method for obtaining the similarity between the local range of the suspected abnormal data point and the IMF component curve according to the abnormal degree of the suspected abnormal data point and the IMF component curve includes the following specific steps:
for the firstA suspected abnormal data point, the->The time period corresponding to the local range of the suspected abnormal data point is marked as +.>A local time period of each suspected abnormal data point; obtaining the +.f. in IMF component curve>The number and amplitude of data points within the local time period of each suspected abnormal data point; according to the +.>Number, amplitude, and +.>The number of data, amplitude and number of extreme points in the local range of the suspected abnormal data points are calculated +.>The local range of each suspected abnormal data point is similar to the IMF component curve, and a specific calculation formula is as follows:
In the method, in the process of the invention,indicate->Amplitude weights for a local range of the suspected outlier data points; />Indicate->The average value of the amplitudes of all data points in the local range of each suspected abnormal data point; />Indicate->A number of data points within a local range of the suspected outlier data points; />Indicate->The number of extreme points within the local range of the suspected outlier data points; />Indicate->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Indicate->The (th) in the individual IMF component curves>Within a local time period of each suspected abnormal data pointAverage amplitude of all data points; />Indicate->The (th) in the individual IMF component curves>The number of data points within the local time period of the suspected abnormal data points; />Representation->The (th) in the individual IMF component curves>The number of extreme points in the local time period of each suspected abnormal data point.
Preferably, the method for obtaining the similarity degree between the local range of the true suspected abnormal data point and the IMF component curve includes the following specific steps:
and taking the product of the similarity between the local range of the suspected abnormal data point and the IMF component curve and the abnormality of the suspected abnormal data point as the real similarity between the local range of the suspected abnormal data point and the IMF component curve.
Preferably, the method for obtaining the similarity between the normal data segment and the IMF component curve according to the normal data point includes the following specific steps:
recording a data segment formed by all normal data points in the characteristic curve as a normal data segment, recording the time corresponding to all the data points in the normal data segment as normal time, acquiring the number and the amplitude of the data points in the normal time in the IMF component curve, and calculating the similarity degree between the normal data segment and the IMF component curve according to the number and the amplitude of the data points in the normal time in the IMF component curve and the number of the number, the amplitude and the extreme point of all the normal data points in the normal data segment, wherein a specific calculation formula is as follows:
in the method, in the process of the invention,amplitude weights representing normal data segments; />Representing the average of the amplitudes of all data points in a normal data segment; />Representing the number of all data points in a normal data segment; />Representing the number of all extreme points in the normal data segment; />Representing normal data segment and +>The degree of similarity of the IMF component curves; />Indicate->The average value of the amplitudes of all data points in normal time in the IMF component curves; />Indicate->The number of all data points in the normal time in the IMF component curves; / >Indicate->Positive in each IMF component curveNumber of all extreme points in a constant time.
Preferably, the acquiring the contribution degree of the IMF component curve to the characteristic curve includes the following specific calculation formula:
in the method, in the process of the invention,indicate->The contribution degree of the IMF component curves to the characteristic curve; />Representing the number of suspected outlier data points in the feature curve; />Indicating true->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Representing normal data segment and +>The degree of similarity of the IMF component curves; />An exponential function based on a natural constant is represented.
Preferably, the obtaining the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve includes the following specific calculation formula:
in the method, in the process of the invention,indicating the final->Personal->The degree of contribution of the component curve to the characteristic curve; />Indicate->The contribution degree of the IMF component curves to the characteristic curve; />The number of IMF component curves versus characteristic curves is represented.
Preferably, the method for obtaining the target curve according to the contribution degree of each IMF component curve to the characteristic curve, and obtaining all abnormal data points on the target curve includes the following specific steps:
First, for the firstThe IMF component curves will be final +.>The contribution degree of the IMF component curve to the characteristic curve, and +.>The product of the IMF component curves and the characteristic curve is new +.>The IMF component curves; obtaining all new IMF component curves;
then, carrying out signal reconstruction on all new IMF component curves to obtain a new curve which is recorded as a target curve;
finally, taking the average value of all data points on the target curve as a stable value of the target curve; presetting a fluctuation thresholdThe method comprises the steps of carrying out a first treatment on the surface of the For the +.>Data points, if the first ∈of the target curve>The difference between the data point and the stable value of the target curve is greater than +.>Then +.>The data points are outlier data points; if the +.>The difference between the data point and the steady value of the target curve is less than or equal to +.>Then +.>The data points are not outlier data points.
The embodiment of the invention provides a building energy data management system, which comprises a data acquisition module, a data screening module, a data analysis module, a data processing module and a data detection module, wherein:
the data acquisition module is used for acquiring pressure data at the outlet of a heating pipeline valve in a building and obtaining a pressure curve according to the pressure data; acquiring an IMF component curve and a characteristic curve according to the pressure curve;
The data screening module is used for acquiring suspected abnormal data points and normal data points according to the characteristic curve; acquiring the abnormality degree of the suspected abnormal data points;
the data analysis module is used for acquiring the similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve; obtaining the real similarity degree between the local range of the suspected abnormal data point and the IMF component curve according to the similarity degree between the local range of the suspected abnormal data point and the IMF component curve and the abnormality degree of the suspected abnormal data point;
the data processing module is used for acquiring the similarity degree between the normal data segment and the IMF component curve according to the normal data point; obtaining the contribution degree of the IMF component curve to the characteristic curve according to the similarity degree of the normal data segment and the IMF component curve and the similarity degree of the local range of the real suspected abnormal data point and the IMF component curve; acquiring the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve;
the data detection module is used for acquiring a target curve according to the contribution degree of each IMF component curve to the characteristic curve, and acquiring all abnormal data points on the target curve; all outlier data points on the target curve are stored separately.
The technical scheme of the invention has the beneficial effects that: because the common data denoising method is based on a denoising algorithm of EMD decomposition, partial detail information is lost when building energy data is denoised, so that abnormal data detection is affected; therefore, the invention utilizes the change characteristics of pressure data when the valve is opened or closed, respectively analyzes the contribution degree of each IMF component and reconstructs the contribution degree on the basis of EMD decomposition, realizes denoising of building energy data, retains detail information, and finally realizes the purpose of accurately detecting abnormal data in the building energy data.
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 method for managing building energy data according to the present invention;
fig. 2 is a block diagram of a construction energy data management system according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of a building energy data management method and system according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of 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 following specifically describes a specific scheme of a building energy data management method and system provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for managing building energy data according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: collecting pressure data at the outlet of a heating pipeline valve in a building, and obtaining a pressure curve according to the pressure data; and acquiring an IMF component curve and a characteristic curve according to the pressure curve.
It should be noted that, the embodiment is used as a building energy data management method, and the application scenario is that according to the pressure data collected at the outlet of a heating pipeline valve in a building, abnormal data are accurately detected; therefore, firstly, pressure data at the outlet of a heating pipeline valve in a building needs to be collected; since the pressure experienced at the outlet of the plumbing valve in a building is typically relatively stable, a low sampling interval may be used to collect the pressure experienced at the outlet of the plumbing valve in a building.
Specifically, a pressure sensor is arranged at the outlet of a heating pipeline valve in a building, and the sampling interval of pressure data is acquired according to a preset pressure sensorCollecting pressure data, < > on>The specific size of (2) can be set according to the actual situation, the hard requirement is not made in the present embodiment, in the present embodiment +.>And (5) second, and obtaining pressure data at the outlet of a heating pipeline valve in the building.
It should be further noted that, in order to better analyze the pressure data at the outlet of the valve of the heating pipeline in the building, the pressure data curve at the outlet of the valve of the heating pipeline in the building needs to be obtained according to the pressure data at the outlet of the valve of the heating pipeline in the building.
Specifically, a rectangular coordinate system is constructed by taking time as an abscissa and pressure as an ordinate, and pressure data is filled into the rectangular coordinate system; and fitting the pressure data at the outlet of the heating pipeline valve in the building by using a least square method to obtain a pressure data curve at the outlet of the heating pipeline valve in the building, and recording the pressure data curve as a pressure curve.
Thus, a pressure curve is obtained.
It should be noted that, the present embodiment is used as a method for managing building energy data, and its final purpose is to accurately detect abnormal data in pressure data at the outlet of a heating pipeline valve in a building; however, due to certain friction between the water flow in the heating pipeline and the inner wall of the heating pipeline, reflux noise is generated, so that noise exists in the pressure curve, the subsequent detection of abnormal data is affected, and therefore denoising processing is needed for the pressure curve.
It should be further noted that, because the pressure data is also affected by external factors such as temperature change, the pressure curve has an overall change trend; the basis for analyzing whether the pressure data is abnormal data is that the change trend of the data in a local range, the characteristics such as frequency and amplitude and the like are analyzed instead of the overall change trend, so that the overall change trend, namely baseline drift, is required to be eliminated, the pressure curve is smoother and more stable, and the abnormal data is easy to detect.
Specifically, the EMD decomposition is performed on the pressure curve, where the EMD decomposition is a known technique, and therefore, in this embodiment, it is not repeated to obtain all IMF component curves of the pressure curve, and the pressure curve after the baseline drift is eliminated is recorded as the characteristic curve.
To this end, all IMF component curves and characteristic curves are passed.
Step S002: acquiring suspected abnormal data points and normal data points according to the characteristic curve; and obtaining the abnormality degree of the suspected abnormal data points.
It should be noted that, the present embodiment is used as a method for managing building energy data, and the final purpose of the method is to accurately detect abnormal data in pressure data at the outlet of a heating pipeline valve in a building, and the basis for analyzing whether one pressure data is abnormal data is that by analyzing the characteristics of the data such as a change trend in a local range, frequency and amplitude, etc., that is, the abnormal data changes severely in the local range; however, when the valve of the heating pipeline in the building is opened or closed, the pressure data of the valve also changes drastically, and at this time, normal data may be misjudged as abnormal data. Therefore, in the characteristic curve, all abnormal data points and partial normal data points exist in all data points with large fluctuation degree, and in order to obtain all abnormal data points, suspected abnormal data points in the characteristic curve are required to be acquired first.
Specifically, taking the average value of all data points on the characteristic curve as a stable value of the characteristic curve; presetting a fluctuation threshold，/>The specific size of (2) can be set according to the actual situation, and the present embodiment does not require rigidity in the present embodiment by +.>Description is made; for the +.>Data points, if the first ∈>The difference between the data point and the steady value of the characteristic curve is greater than +.>The +.>The data points are suspected abnormal data points; if the +.>The difference between the data point and the steady value of the characteristic curve is less than or equal to +.>The +.>The data points are normal data points.
So far, all suspected abnormal data points and normal data points in the characteristic curve are obtained.
It should be further noted that when the valve of the heating pipeline in the building is opened, the water flow rapidly gushes in, so that the pressure data in the local time is increased drastically, and then the pressure data is gradually reduced until a stable state is shown along with the stable flow rate of the water flow in the heating pipeline; on the contrary, when the valve of the heating pipeline in the building is closed, water flows forward, so that the pressure data is severely reduced in local time, and then the pressure data is gradually increased until a stable state is shown along with the stable flow rate of the water flow in the heating pipeline. Based on the change characteristics of the pressure data, the degree of abnormality can be obtained by analyzing the data change in the local range in the characteristic curve.
Specifically, for the firstA suspected abnormal data point, the characteristic curve is associated with +.>The nearest extreme point of each suspected abnormal data point is taken as a target extreme point, two extreme points adjacent to the target extreme point are taken as intercepting extreme points, all data points between the two intercepting extreme points form a local range, the local range of the target extreme point in the local range is divided into two sections, one section is monotonously increased, the other section is monotonously decreased, and the first section is obtained through the slopes of all the data points in the two sections>The degree of abnormality of each suspected abnormal data point is calculated by the following specific formula:
in the method, in the process of the invention,indicate->Degree of abnormality of the individual suspected abnormal data points; />Is indicated at +.>Suspected abnormal dataThe average value of all data point slopes in the 1 st interval in the local range of the point; />Is indicated at +.>The average of the slopes of all data points in interval 2, within the local range of the suspected outlier data points.
It should be noted that the number of the substrates,the smaller the value of (2) indicates +.>The greater the difference between the rate of change of the data point in the first interval and the rate of change of the data point in the second interval, i.e. +. >The more likely a suspected abnormal data point is caused by the opening or closing of a heating pipeline valve in a building; thus->The greater the value of +.>The greater the likelihood that the suspected outlier is an outlier.
Thus, the degree of abnormality of all abnormal data points is obtained.
Step S003: obtaining the similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve; and obtaining the real similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the similarity degree of the local range of the suspected abnormal data point and the IMF component curve and the abnormality degree of the suspected abnormal data point.
It should be noted that, the more similar the frequency and amplitude of the IMF component curve are to the frequency and amplitude of the feature curve, the more accurately the IMF component curve can capture the local feature in the feature curve; therefore, the similarity degree can be obtained by the frequency and the amplitude between the characteristic curve and the IMF component curve in the local range of the suspected abnormal data points, and the higher the similarity degree is, the more noise information is contained in the IMF component curve, and the more noise information is contained in the IMF component curve, the lower the contribution degree of the IMF component curve to the characteristic curve is. The contribution degree of each IMF component curve to the characteristic curve can be obtained by the similarity degree of the data in the local range of each suspected abnormal data point and each IMF component curve. It is therefore first necessary to obtain the degree of similarity of the local range of suspected outlier data points to the IMF component curve.
Specifically, for the firstA suspected abnormal data point, the->The time period corresponding to the local range of the suspected abnormal data point is marked as +.>A local time period of each suspected abnormal data point; obtaining the +.f. in IMF component curve>The number and amplitude of data points within the local time period of each suspected abnormal data point; according to the +.>Number, amplitude, and +.>The number of data, amplitude and number of extreme points in the local range of the suspected abnormal data points are calculated +.>The local range of each suspected abnormal data point is similar to the IMF component curve, and a specific calculation formula is as follows:
in the method, in the process of the invention,indicate->Amplitude weights for a local range of the suspected outlier data points; />Indicate->The average value of the amplitudes of all data points in the local range of each suspected abnormal data point; />Indicate->A number of data points within a local range of the suspected outlier data points; />Indicate->The number of extreme points within the local range of the suspected outlier data points; />Indicate->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Indicate->The (th) in the individual IMF component curves >Average amplitudes of all data points within a local time period of the suspected outlier data points; />Indicate->The (th) in the individual IMF component curves>The number of data points within the local time period of the suspected abnormal data points; />Representation->The (th) in the individual IMF component curves>The number of extreme points in the local time period of each suspected abnormal data point.
It should be noted that the number of the substrates,indicating->Local extent of the suspected outlier data points +.>Fluctuation of data within the local range of each suspected abnormal data point and the similarity degree of the IMF component curve, and when +.>The more intense the fluctuation of the data in the local area of the respective suspected outlier data point is, the calculation of the +.>The greater the ratio of the degree of similarity between the degree of fluctuation when the local range of each suspected abnormal data point is similar to the degree of similarity of the IMF component curve; similarly, let->The greater the amplitude of the data in the local range of the suspected outlier data points, the greater the duty cycle of the degree of similarity between the amplitudes should be.
Further, the method comprises the steps of,indicating->Local extent of the suspected outlier data points, and +.>The (th) in the individual IMF component curves>The degree of similarity between the data point amplitudes within the local time period of the suspected abnormal data points; / >Indicating->Local extent of the suspected outlier data points, and +.>The (th) in the individual IMF component curves>The degree of similarity between the degree of fluctuation of the data points in the local time period of each suspected abnormal data point; therefore->The greater the value of +.>Local extent of suspected abnormal data points and +.>The higher the degree of similarity of the individual IMF component curves.
It should be further noted that, the present embodiment is a building energy data management method, which is finally aimed at accurately detecting abnormal data in pressure data at the outlet of a heating pipe valve in a building, and because false abnormal data points generated by opening or closing the heating pipe valve in the building exist in the suspected abnormal data points, but the abnormal degree of the false abnormal data points generated by opening or closing the heating pipe valve in the building is low, and the abnormal degree of the true abnormal data points is high, the similarity degree between the local range of the suspected abnormal data points and the IMF component curve can be corrected by the abnormal degree of the suspected abnormal data points, so as to obtain the real similarity degree between the local range of the suspected abnormal data points and the IMF component curve.
Specifically, according to the degree of abnormality of the suspected abnormal data point and the degree of similarity between the local range of the suspected abnormal data point and the IMF component curve, the true degree of similarity between the local range of the suspected abnormal data point and the IMF component curve is calculated, and a specific calculation formula is as follows:
In the method, in the process of the invention,indicating true->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Indicate->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Indicate->Degree of abnormality of each suspected abnormal data point.
It should be further noted that, in the degree of similarity between the local range of the true suspected abnormal data point and the IMF component curve, the degree of similarity between the false abnormal data point and the IMF component curve is low, while the degree of similarity between the true abnormal data point and the IMF component curve is high.
Thus, the similarity degree between the local range of the real suspected abnormal data point and the IMF component curve is obtained.
Step S004: obtaining the similarity degree of the normal data segment and the IMF component curve according to the normal data point; obtaining the contribution degree of the IMF component curve to the characteristic curve according to the similarity degree of the normal data segment and the IMF component curve and the similarity degree of the local range of the real suspected abnormal data point and the IMF component curve; and acquiring the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve.
It should be noted that, the degree of similarity between the local range of the true suspected abnormal data point and the IMF component curve is obtained in step S003, and in order to obtain all the data points on the overall characteristic curve, the degree of similarity between all the normal data points on the characteristic curve and the IMF component curve is also required to be obtained. The similarity between the normal data segment and the IMF component curve can be calculated by calculating the similarity between the local range of the abnormal data point and the IMF component curve.
Specifically, a data segment formed by all normal data points in the characteristic curve is recorded as a normal data segment, the time corresponding to all the data points in the normal data segment is recorded as a normal time, the number and the amplitude of the data points in the normal time in the IMF component curve are obtained, and the similarity degree between the normal data segment and the IMF component curve is calculated according to the number and the amplitude of the data points in the normal time in the IMF component curve and the number, the amplitude and the number of extreme points of all the normal data points in the normal data segment, wherein a specific calculation formula is as follows:
in the method, in the process of the invention,amplitude weights representing normal data segments; />Representing the average of the amplitudes of all data points in a normal data segment; />Representing the number of all data points in a normal data segment; />Representing the number of all extreme points in the normal data segment; />Representing normal data segment and +>The degree of similarity of the IMF component curves; />Indicate->All data points in normal time in the IMF component curvesAmplitude average value; />Indicate->The number of all data points in the normal time in the IMF component curves; />Indicate->The number of all extreme points in the normal time in the IMF component curves.
It should be noted that the number of the substrates,the larger the value of (2) is, the normal data segment and +. >The more similar the IMF component curves.
It should be further noted that, the higher the similarity of the characteristic curve is, the more noise information is contained in the IMF component curve, and the more noise information is contained in the IMF component curve, the lower the contribution degree of the IMF component curve to the characteristic curve is, so the contribution degree of the IMF component curve to the characteristic curve can be obtained by the similarity between the normal data segment in the characteristic curve and the IMF component curve, and the similarity between the local range of the suspected abnormal data point and the IMF component curve, and the specific calculation formula is as follows:
in the method, in the process of the invention,indicate->The contribution degree of the IMF component curves to the characteristic curve; />Representing the number of suspected outlier data points in the feature curve; />Indicating true->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Representing normal data segment and +>The degree of similarity of the IMF component curves; />An exponential function based on a natural constant is represented.
It should be further noted that, in order to avoid scaling problem after the IMF component curves are reconstructed, the sum of the contribution degrees of all IMF component curves to the characteristic curve should be ensured to be 1; the contribution degree of all IMF component curves to the characteristic curve needs to be normalized, and the final contribution degree of each IMF component curve to the characteristic curve is obtained.
Specifically, a calculation formula for obtaining the contribution degree of each IMF component curve to the characteristic curve is as follows:
in the method, in the process of the invention,indicating the final->Personal->The degree of contribution of the component curve to the characteristic curve; />Indicate->The contribution degree of the IMF component curves to the characteristic curve; />The number of IMF component curves versus characteristic curves is represented.
It should be noted that,the greater the value of +.>Personal->The higher the contribution of the component curve to the characteristic curve.
So far, the final contribution degree of each IMF component curve to the characteristic curve is obtained.
Step S005: acquiring a target curve according to the final contribution degree of each IMF component curve to the characteristic curve, and acquiring all abnormal data points on the target curve; all outlier data points on the target curve are stored separately.
It should be noted that, the final contribution degree of each IMF component curve to the characteristic curve is obtained through step S004, that is, each new IMF component curve can be obtained through the final contribution degree of each IMF component curve to the characteristic curve and each IMF component curve, and because the new IMF classification curve is obtained after the false abnormal data points and noise information in the IMF component curves are removed through steps S003 and S004, a new curve can be obtained through all the new IMF classification curves, and the false abnormal data points and noise information do not exist in the curve, that is, the abnormal data in the pressure data at the outlet of the heating pipeline valve in the building can be accurately monitored through the new curve.
Specifically, for the firstThe IMF component curves will be final +.>The contribution degree of the IMF component curve to the characteristic curve, and +.>The product of the IMF component curves and the characteristic curve is new +.>Obtaining all new IMF component curves by the same method;
then, signal reconstruction is carried out on all new IMF component curves to obtain a new curve which is marked as a target curve, wherein the signal reconstruction is a known technology and is not repeated in the embodiment;
finally, taking the average value of all data points on the target curve as a stable value of the target curve; presetting a fluctuation threshold，/>The specific size of (2) can be set according to the actual situation, and the present embodiment does not require rigidity in the present embodiment by +.>Description is made; for the +.>Data points, if the first ∈of the target curve>Between data points and steady values of the target curveThe difference is greater than->Then +.>The data points are outlier data points; if the +.>The difference between the data point and the steady value of the target curve is less than or equal to +.>Then +.>The data points are not outlier data points.
The purpose of accurately detecting abnormal data in pressure data at the outlet of a heating pipeline valve in a building is achieved; because the abnormal data in the pressure data at the outlet of the heating pipeline valve in the building is more important than the normal data, the abnormal data in the pressure data at the outlet of the heating pipeline valve in the building is independently analyzed and stored, and the energy data management efficiency of the building can be greatly improved.
It should be noted that, in the formula of the present embodiment, there may be a case where the denominator is 0, and in order to avoid this, in the present embodiment, the denominator is added with 0.001 in the formula calculation, which is not described in detail in the present embodiment.
This embodiment is completed.
Referring to fig. 2, a block diagram of a building energy data management system according to an embodiment of the present invention is shown, where the system includes the following modules:
the data acquisition module is used for acquiring pressure data at the outlet of a heating pipeline valve in a building and obtaining a pressure curve according to the pressure data; acquiring an IMF component curve and a characteristic curve according to the pressure curve;
the data screening module is used for acquiring suspected abnormal data points and normal data points according to the characteristic curve; acquiring the abnormality degree of the suspected abnormal data points;
the data analysis module is used for acquiring the similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve; obtaining the real similarity degree between the local range of the suspected abnormal data point and the IMF component curve according to the similarity degree between the local range of the suspected abnormal data point and the IMF component curve and the abnormality degree of the suspected abnormal data point;
The data processing module is used for acquiring the similarity degree between the normal data segment and the IMF component curve according to the normal data point; obtaining the contribution degree of the IMF component curve to the characteristic curve according to the similarity degree of the normal data segment and the IMF component curve and the similarity degree of the local range of the real suspected abnormal data point and the IMF component curve; acquiring the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve;
the data detection module is used for acquiring a target curve according to the contribution degree of each IMF component curve to the characteristic curve, and acquiring all abnormal data points on the target curve; all outlier data points on the target curve are stored separately.
Because the common data denoising method is based on a denoising algorithm of EMD decomposition, partial detail information is lost when building energy data is denoised, so that abnormal data detection is affected; therefore, the invention utilizes the change characteristics of pressure data when the valve is opened or closed, respectively analyzes the contribution degree of each IMF component and reconstructs the contribution degree on the basis of EMD decomposition, realizes denoising of building energy data, retains detail information, and finally realizes the purpose of accurately detecting abnormal data in the building energy data.
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. A method for managing building energy data, the method comprising the steps of:
collecting pressure data at the outlet of a heating pipeline valve in a building, and obtaining a pressure curve according to the pressure data; acquiring an IMF component curve and a characteristic curve according to the pressure curve;
acquiring suspected abnormal data points and normal data points according to the characteristic curve; acquiring the abnormality degree of the suspected abnormal data points;
obtaining the similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve; obtaining the real similarity degree between the local range of the suspected abnormal data point and the IMF component curve according to the similarity degree between the local range of the suspected abnormal data point and the IMF component curve and the abnormality degree of the suspected abnormal data point;
obtaining the similarity degree of the normal data segment and the IMF component curve according to the normal data point; obtaining the contribution degree of the IMF component curve to the characteristic curve according to the similarity degree of the normal data segment and the IMF component curve and the similarity degree of the local range of the real suspected abnormal data point and the IMF component curve; acquiring the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve;
Acquiring a target curve according to the final contribution degree of each IMF component curve to the characteristic curve, and acquiring all abnormal data points on the target curve; all outlier data points on the target curve are stored separately.
2. The method for managing building energy data according to claim 1, wherein the method is characterized in that pressure data at an outlet of a heating pipeline valve in a building are collected, and a pressure curve is obtained according to the pressure data; the IMF component curve and the characteristic curve are obtained according to the pressure curve, and the method comprises the following specific steps:
a pressure sensor is arranged at the outlet of a heating pipeline valve in the building, and the sampling interval of pressure data is acquired according to the preset pressure sensorCollecting pressure data;
constructing a rectangular coordinate system by taking time as an abscissa and pressure as an ordinate, and filling pressure data into the rectangular coordinate system; fitting the pressure data at the outlet of the heating pipeline valve in the building by using a least square method to obtain a pressure data curve at the outlet of the heating pipeline valve in the building, and recording the pressure data curve as a pressure curve;
and carrying out EMD decomposition on the pressure curve to obtain all IMF component curves of the pressure curve, eliminating the pressure curve after the baseline drift, and marking the pressure curve after the baseline drift is eliminated as a characteristic curve.
3. The method for managing building energy data according to claim 1, wherein the suspected abnormal data points and normal data points are obtained according to a characteristic curve; the method for acquiring the abnormality degree of the suspected abnormal data point comprises the following specific steps:
taking the average value of all data points on the characteristic curve as a stable value of the characteristic curve; presetting a fluctuation thresholdThe method comprises the steps of carrying out a first treatment on the surface of the For the +.>Data points, if the first ∈>The difference between the data point and the steady value of the characteristic curve is greater than +.>The +.>The data points are suspected abnormal data points; if the +.>The difference between the data point and the steady value of the characteristic curve is less than or equal to +.>The +.>The data points are normal data points;
for the firstA suspected abnormal data point, the characteristic curve is associated with +.>The nearest extreme point of each suspected abnormal data point is taken as a target extreme point, two extreme points adjacent to the target extreme point are taken as intercepting extreme points, all data points between the two intercepting extreme points form a local range, the local range of the target extreme point in the local range is divided into two sections, one section is monotonously increased, the other section is monotonously decreased, and the first section is obtained through the slopes of all the data points in the two sections >The degree of abnormality of each suspected abnormal data point is calculated by the following specific formula:
in the method, in the process of the invention,indicate->Degree of abnormality of the individual suspected abnormal data points; />Is indicated at +.>The average value of the slopes of all data points in the 1 st interval in the local range of the suspected abnormal data points; />Is indicated at +.>The average of the slopes of all data points in interval 2, within the local range of the suspected outlier data points.
4. The method for managing building energy data according to claim 3, wherein the step of obtaining the similarity between the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve comprises the following specific steps:
for the firstA suspected abnormal data point, the->The time period corresponding to the local range of each suspected abnormal data point is recorded as the firstA local time period of each suspected abnormal data point; obtaining the +.f. in IMF component curve>The number and amplitude of data points within the local time period of each suspected abnormal data point; according to the +.>The number and amplitude of the data points in the local time period of each suspected abnormal data point are calculated byFirst->The number of data, amplitude and number of extreme points in the local range of the suspected abnormal data points are calculated +. >The local range of each suspected abnormal data point is similar to the IMF component curve, and a specific calculation formula is as follows:
in the method, in the process of the invention,indicate->Amplitude weights for a local range of the suspected outlier data points; />Indicate->The average value of the amplitudes of all data points in the local range of each suspected abnormal data point; />Indicate->A number of data points within a local range of the suspected outlier data points; />Indicate->Local range of suspected outlier data pointsThe number of extreme points within the enclosure; />Indicate->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Indicate->The (th) in the individual IMF component curves>Average amplitudes of all data points within a local time period of the suspected outlier data points; />Indicate->The first IMF component curveThe number of data points within the local time period of the suspected abnormal data points; />Representation->The (th) in the individual IMF component curves>The number of extreme points in the local time period of each suspected abnormal data point.
5. The method for managing building energy data according to claim 1, wherein the step of obtaining the similarity between the local range of the true suspected abnormal data point and the IMF component curve comprises the following specific steps:
And taking the product of the similarity between the local range of the suspected abnormal data point and the IMF component curve and the abnormality of the suspected abnormal data point as the real similarity between the local range of the suspected abnormal data point and the IMF component curve.
6. The method for managing building energy data according to claim 1, wherein the step of obtaining the similarity between the normal data segment and the IMF component curve according to the normal data point comprises the following specific steps:
recording a data segment formed by all normal data points in the characteristic curve as a normal data segment, recording the time corresponding to all the data points in the normal data segment as normal time, acquiring the number and the amplitude of the data points in the normal time in the IMF component curve, and calculating the similarity degree between the normal data segment and the IMF component curve according to the number and the amplitude of the data points in the normal time in the IMF component curve and the number of the number, the amplitude and the extreme point of all the normal data points in the normal data segment, wherein a specific calculation formula is as follows:
in the method, in the process of the invention,amplitude weights representing normal data segments; />Representing the average of the amplitudes of all data points in a normal data segment; />Representing normal data segmentsThe number of all data points in the database; / >Representing the number of all extreme points in the normal data segment; />Representing normal data segment and +>The degree of similarity of the IMF component curves; />Indicate->The average value of the amplitudes of all data points in normal time in the IMF component curves; />Indicate->The number of all data points in the normal time in the IMF component curves; />Indicate->The number of all extreme points in the normal time in the IMF component curves.
7. The method for managing building energy data according to claim 1, wherein the obtaining the contribution degree of the IMF component curve to the characteristic curve includes the following specific calculation formula:
in the method, in the process of the invention,indicate->The contribution degree of the IMF component curves to the characteristic curve; />Representing the number of suspected outlier data points in the feature curve; />Indicating true->Local extent of suspected abnormal data points and +.>The degree of similarity of the IMF component curves; />Representing normal data segment and +>The degree of similarity of the IMF component curves; />An exponential function based on a natural constant is represented.
8. The method for managing building energy data according to claim 1, wherein the step of obtaining the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve comprises the following specific calculation formula:
In the method, in the process of the invention,indicating the final->Personal->The degree of contribution of the component curve to the characteristic curve; />Indicate->The contribution degree of the IMF component curves to the characteristic curve; />The number of IMF component curves versus characteristic curves is represented.
9. The method for managing building energy data according to claim 1, wherein the step of obtaining the target curve according to the contribution degree of each IMF component curve to the characteristic curve, and obtaining all abnormal data points on the target curve comprises the following specific steps:
first, for the firstThe IMF component curves will be final +.>The contribution degree of the IMF component curve to the characteristic curve, and +.>The product of the IMF component curves and the characteristic curve is new +.>The IMF component curves; obtaining all new IMF component curves;
then, carrying out signal reconstruction on all new IMF component curves to obtain a new curve which is recorded as a target curve;
finally, taking the average value of all data points on the target curve as a stable value of the target curve; presetting a fluctuation thresholdThe method comprises the steps of carrying out a first treatment on the surface of the For the +.>Data points, if the first ∈of the target curve>The difference between the data point and the stable value of the target curve is greater than +. >Then +.>The data points are outlier data points; if the +.>The difference between the data point and the steady value of the target curve is less than or equal to +.>Then +.>The data points are not outlier data points.
10. A building energy data management system, comprising the following modules:
the data acquisition module is used for acquiring pressure data at the outlet of a heating pipeline valve in a building and obtaining a pressure curve according to the pressure data; acquiring an IMF component curve and a characteristic curve according to the pressure curve;
the data screening module is used for acquiring suspected abnormal data points and normal data points according to the characteristic curve; acquiring the abnormality degree of the suspected abnormal data points;
the data analysis module is used for acquiring the similarity degree of the local range of the suspected abnormal data point and the IMF component curve according to the abnormality degree of the suspected abnormal data point and the IMF component curve; obtaining the real similarity degree between the local range of the suspected abnormal data point and the IMF component curve according to the similarity degree between the local range of the suspected abnormal data point and the IMF component curve and the abnormality degree of the suspected abnormal data point;
the data processing module is used for acquiring the similarity degree between the normal data segment and the IMF component curve according to the normal data point; obtaining the contribution degree of the IMF component curve to the characteristic curve according to the similarity degree of the normal data segment and the IMF component curve and the similarity degree of the local range of the real suspected abnormal data point and the IMF component curve; acquiring the final contribution degree of each IMF component curve to the characteristic curve according to the contribution degree of the IMF component curve to the characteristic curve;
The data detection module is used for acquiring a target curve according to the contribution degree of each IMF component curve to the characteristic curve, and acquiring all abnormal data points on the target curve; all outlier data points on the target curve are stored separately.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311490687.7A CN117235447A (en) | 2023-11-10 | 2023-11-10 | Building energy data management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311490687.7A CN117235447A (en) | 2023-11-10 | 2023-11-10 | Building energy data management method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117235447A true CN117235447A (en) | 2023-12-15 |
Family
ID=89088324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311490687.7A Withdrawn CN117235447A (en) | 2023-11-10 | 2023-11-10 | Building energy data management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117235447A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117421689A (en) * | 2023-12-18 | 2024-01-19 | 杭州湘亭科技有限公司 | Uranium radioactivity pollution measurement transmission system based on pipeline robot |
| CN117555761A (en) * | 2024-01-11 | 2024-02-13 | 深圳市蓝智电子有限公司 | Mobile hard disk operation monitoring system based on Internet of things |
| CN117574102A (en) * | 2024-01-17 | 2024-02-20 | 山东华中重钢有限公司 | Steel structure fatigue life prediction method based on big data analysis |
| CN117828408A (en) * | 2024-03-04 | 2024-04-05 | 新风光电子科技股份有限公司 | Energy storage capacity data processing method and system |
| CN117870943A (en) * | 2024-01-22 | 2024-04-12 | 中国三峡建工(集团)有限公司 | Multi-sensor-based data optimization acquisition system in grouting process |
| CN117972314A (en) * | 2024-03-29 | 2024-05-03 | 山东华立供水设备有限公司 | Cloud platform monitoring method and system based on digital twinning |
-
2023
- 2023-11-10 CN CN202311490687.7A patent/CN117235447A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117421689A (en) * | 2023-12-18 | 2024-01-19 | 杭州湘亭科技有限公司 | Uranium radioactivity pollution measurement transmission system based on pipeline robot |
| CN117421689B (en) * | 2023-12-18 | 2024-03-12 | 杭州湘亭科技有限公司 | Uranium radioactivity pollution measurement transmission system based on pipeline robot |
| CN117555761A (en) * | 2024-01-11 | 2024-02-13 | 深圳市蓝智电子有限公司 | Mobile hard disk operation monitoring system based on Internet of things |
| CN117555761B (en) * | 2024-01-11 | 2024-04-02 | 深圳市蓝智电子有限公司 | Mobile hard disk operation monitoring system based on Internet of things |
| CN117574102A (en) * | 2024-01-17 | 2024-02-20 | 山东华中重钢有限公司 | Steel structure fatigue life prediction method based on big data analysis |
| CN117574102B (en) * | 2024-01-17 | 2024-04-05 | 山东华中重钢有限公司 | Steel structure fatigue life prediction method based on big data analysis |
| CN117870943A (en) * | 2024-01-22 | 2024-04-12 | 中国三峡建工(集团)有限公司 | Multi-sensor-based data optimization acquisition system in grouting process |
| CN117828408A (en) * | 2024-03-04 | 2024-04-05 | 新风光电子科技股份有限公司 | Energy storage capacity data processing method and system |
| CN117828408B (en) * | 2024-03-04 | 2024-05-14 | 新风光电子科技股份有限公司 | Energy storage capacity data processing method and system |
| CN117972314A (en) * | 2024-03-29 | 2024-05-03 | 山东华立供水设备有限公司 | Cloud platform monitoring method and system based on digital twinning |
| CN117972314B (en) * | 2024-03-29 | 2024-06-04 | 山东华立供水设备有限公司 | Cloud platform monitoring method and system based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117235447A (en) | Building energy data management method and system | |
| US10565699B2 (en) | Apparatus and method for detecting anomaly in plant pipe using multiple meta-learning | |
| CN110598851A (en) | Time series data abnormity detection method fusing LSTM and GAN | |
| CN111853555B (en) | Water supply pipe network blind leakage identification method based on dynamic process | |
| CN105574855B (en) | Infrared small target detection method under cloud background based on template convolution and false alarm rejection | |
| CN103761748A (en) | Method and device for detecting abnormal behaviors | |
| CN116756493B (en) | Data management method for security and fire control finger collecting platform | |
| CN109061591B (en) | Time-frequency line spectrum detection method based on sequential clustering | |
| CN116933044B (en) | Intelligent processing method and system for power supply data | |
| WO2020246944A1 (en) | Method and system for attack detection in a sensor network of a networked control system | |
| Hwang et al. | Detection and correction method of erroneous data using quantile pattern and LSTM | |
| CN110879927A (en) | Sea clutter amplitude statistical distribution field modeling method for sea target detection | |
| CN106594526A (en) | Water supply network condition monitoring method and water supply network condition monitoring device based on water pressure sampling data | |
| Vaghefi et al. | A comparison among data mining algorithms for outlier detection using flow pattern experiments | |
| CN114673246A (en) | Anti-blocking measurement method and measurement system for sewage pipeline | |
| CN116609440A (en) | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation | |
| Meng et al. | A gear fault diagnosis method based on improved accommodative random weighting algorithm and BB-1D-TP | |
| CN109214318A (en) | A method of finding the faint spike of unstable state time series | |
| CN111881929B (en) | Method and device for detecting large-period state of Duffing system based on chaotic image pixel identification | |
| CN114842280A (en) | Automatic micro-seismic signal identification algorithm based on convolutional neural network | |
| CN106574748A (en) | Fluctuation and phase-based method for detection of plugged impulse lines | |
| CN117172601A (en) | Non-invasive load monitoring method based on residual total convolution neural network | |
| Hamid et al. | Automatic detection and analysis of boiler tube leakage system | |
| CN115270843A (en) | Fault diagnosis method and device for floating platform reciprocating compressor | |
| KR102673168B1 (en) | Method for classifying appliance using non intrusive load monitoring and system thereof |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231215 |
|
| WW01 | Invention patent application withdrawn after publication |