CN117786371A - Temperature monitoring data optimization prediction analysis method and system - Google Patents
Temperature monitoring data optimization prediction analysis method and system Download PDFInfo
- Publication number
- CN117786371A CN117786371A CN202410211278.7A CN202410211278A CN117786371A CN 117786371 A CN117786371 A CN 117786371A CN 202410211278 A CN202410211278 A CN 202410211278A CN 117786371 A CN117786371 A CN 117786371A
- Authority
- CN
- China
- Prior art keywords
- temperature data
- data
- temperature
- local
- abnormal
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 title claims abstract description 26
- 238000005457 optimization Methods 0.000 title abstract description 13
- 238000005070 sampling Methods 0.000 claims abstract description 117
- 230000002159 abnormal effect Effects 0.000 claims abstract description 96
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000005856 abnormality Effects 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 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 temperature monitoring data optimization prediction analysis method and a system, wherein the method comprises the following steps: acquiring time sequence temperature data, setting each local section of each sampling time temperature data, acquiring the abnormal degree of each sampling time temperature data in each local section, acquiring the abnormal stability of each sampling time temperature data in each local section according to the abnormal degree, acquiring the abnormal reality of each sampling time temperature data according to the abnormal stability and the distribution of the temperature data in the local section, and acquiring the real abnormal degree of each sampling time temperature data by combining the abnormal reality and the abnormal degree to complete the predictive analysis of the temperature data. The invention aims to improve the denoising effect of the temperature monitoring data, improve the accuracy of temperature data prediction analysis and finish the accurate prediction of the temperature monitoring data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a temperature monitoring data optimization prediction analysis method and a system.
Background
Along with the continuous development of technology, the application range of temperature monitoring data is wider and wider, for example, in industries such as metallurgy, chemical industry, energy and the like, the temperature needs to be monitored in real time. However, temperature data often has noise and anomalies due to temperature being affected by a variety of factors, which makes temperature prediction and analysis difficult. Therefore, before the temperature data is predicted and analyzed, denoising correction is needed to be carried out on the temperature data, and the accuracy of temperature data acquisition is ensured.
For the temperature data monitored in time sequence, a certain trend is often shown in time sequence, so that the difference between single temperature data and the time sequence change trend can be utilized to reflect the abnormality of the temperature data, wherein the time sequence change trend often uses a local range with a fixed length as a unit, but because the temperature data change trend at different positions has obvious difference, only the temperature data in the local range with the fixed length is considered to easily cause information loss, the accuracy of the single temperature data is further reduced, and the predictive analysis of the temperature data is affected.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a temperature monitoring data optimization prediction analysis method and a system, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a temperature monitoring data optimization prediction analysis method, including the steps of:
collecting time sequence temperature data;
acquiring each local interval of temperature data at each sampling moment; obtaining the abnormality degree of the temperature data at each sampling time in each local section according to the trend deviation of the temperature data at each sampling time in the local section; obtaining abnormal stability of the temperature data at each sampling moment in each local section according to the abnormal degree and the difference of the trend deviation of the temperature data in different local sections; obtaining abnormal reality of the temperature data at each sampling moment in each local interval according to the abnormal stability and the distribution of the temperature data in the local interval; combining the abnormality reality and the abnormality degree to obtain the real abnormality degree of the temperature data at each sampling moment; acquiring abnormal data in the time sequence temperature data by utilizing the real abnormal degree; and eliminating the abnormal data, and completing temperature prediction according to the temperature data after eliminating the abnormal data.
Preferably, the acquiring each local section of the temperature data at each sampling time includes:
a plurality of search lengths are set for temperature data at each sampling time, and all temperature data included in each search length of temperature data at each sampling time is set as each local section of temperature data at each sampling time.
Preferably, the obtaining the degree of abnormality of the temperature data at each sampling time in each local section according to the trend deviation of the temperature data at each sampling time in the local section includes:
acquiring a first fitting residual error and a second fitting residual error of each local interval;
calculating the difference value of the first fitting residual error and the second fitting residual error of each local interval, calculating the ratio of the difference value to the number of the temperature data contained in each local interval, and taking the normalized value of the ratio as the abnormal degree of the temperature data in each local interval at each sampling moment.
Preferably, the obtaining the first fitting residual and the second fitting residual of each local interval includes:
and calculating fitting residual errors of all temperature data in each local interval and all remaining temperature data except the central position temperature data in each local interval according to the temperature data at each sampling moment, and respectively marking the fitting residual errors as a first fitting residual error and a second fitting residual error.
Preferably, the abnormal stability of the temperature data at each sampling time in each local section is obtained according to the abnormal degree and the difference of the trend deviation of the temperature data in different local sections, and the expression is as follows:
in the method, in the process of the invention,representing abnormal stability of temperature data at the ith sampling time in the kth local zone, +.>Indicating the degree of abnormality of the temperature data at the ith sampling instant in the (k+v) th partial section, +.>Indicating the degree of abnormality of the temperature data at the ith sampling instant in the (k+v-1) th partial section,/>Representing a preset movement step.
Preferably, the abnormal reality of the temperature data at each sampling time in each local section is obtained according to the abnormal stability and the distribution of the temperature data in the local section, and the expression is as follows:
in the method, in the process of the invention,representing the abnormal authenticity of the temperature data at the ith sampling moment in the kth local interval, +.>Representing abnormal stability of temperature data at the ith sampling time in the kth local zone, +.>Fitting residuals of all temperature data in the kth local interval representing temperature data at the ith sampling instant,/>Fitting residuals of all temperature data in the (k-1) th local interval representing temperature data at the (i) th sampling instant,/and (ii)>The kth partial section representing the temperature data at the ith sampling instant contains the number of temperature data,/->The kth-1 th local section representing the temperature data at the ith sampling instant contains the number of temperature data,representing the normalization function.
Preferably, the obtaining the real abnormal degree of the temperature data at each sampling time by combining the abnormal reality and the abnormal degree includes:
and calculating the product of the abnormality degree and the abnormality authenticity of the temperature data at each sampling time in each local section, and taking the sum of the products of the temperature data at each sampling time in all local sections as the actual abnormality degree of the temperature data at each sampling time.
Preferably, the acquiring the abnormal data in the time-series temperature data by using the real abnormal degree includes: and a preset threshold value, wherein temperature data with a normalized value of the real abnormality degree being more than or equal to the preset threshold value is used as abnormal data.
Preferably, the temperature prediction is performed according to the temperature data after the abnormal data is removed, including:
and carrying out temperature interpolation on the temperature data with abnormal data removed by using a linear interpolation method, taking all the temperature data after interpolation as input of an autoregressive moving average model, and outputting the temperature data as a temperature predicted value at the next moment.
In a second aspect, an embodiment of the present invention further provides a temperature monitoring data optimization prediction analysis system, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of any one of the methods described above when executing the computer program.
The invention has at least the following beneficial effects:
according to the method, the trend change of the temperature data of each local section is obtained through the collected temperature monitoring data, the abnormal degree of the temperature data of each local section is constructed, the difference of the overall trend change of the temperature data of each sampling time and the local section is comprehensively considered, the noise interference degree of the temperature data of each sampling time is reflected, the abnormal stability of the temperature data of each sampling time in each local section is obtained according to the abnormal degree, the stability of the abnormal degree of the temperature data of each sampling time along with the change of the length of the local section is reflected, the trend change condition of a plurality of local sections is considered, the abnormal authenticity of the temperature data of each sampling time in each local section is obtained according to the abnormal stability, the abnormal stability of the temperature data in each local section and the fitting residual error of the temperature data in each local section are comprehensively considered, the reliability of the abnormal degree of the temperature data is improved, the real abnormal degree of the temperature data of each sampling time is further obtained, the abnormal data is removed by the real abnormal degree, and the optimal prediction analysis of the temperature data is completed. The method has the advantages of high temperature monitoring data fidelity, high temperature monitoring data prediction accuracy and high reliability.
Drawings
In order to more clearly illustrate the embodiments of the invention 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 invention, 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 illustrating a method for optimizing predictive analysis of temperature monitoring data according to one embodiment of the present invention;
fig. 2 is a flowchart for obtaining a temperature optimization prediction index.
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 temperature monitoring data optimization prediction analysis method and system according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the temperature monitoring data optimization prediction analysis method and system provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a temperature monitoring data optimizing prediction analysis method according to an embodiment of the invention is shown, and the method includes the following steps:
and S001, collecting time sequence temperature data and preprocessing.
In this embodiment, the power distribution cabinet is taken as an example, the temperature sensor is used to collect time sequence temperature data of the power distribution cabinet, so as to obtain temperature data of each sampling moment, the sampling interval in this embodiment is 5 seconds, and an implementer can set the temperature according to actual conditions, which is not limited in this embodiment. For all the collected temperature data, firstly, the temperature data is subjected to coarse denoising by using a wavelet denoising algorithm to obtain temperature data of each sampling moment after denoising, wherein the wavelet denoising algorithm is a prior known technology, and the embodiment is not described in detail herein.
Step S002, obtaining the abnormal degree of the temperature data at each sampling time in each local section, obtaining the abnormal stability of the temperature data at each sampling time in each local section according to the abnormal degree, obtaining the abnormal reality of the temperature data at each sampling time in each local section according to the abnormal stability, and obtaining the real abnormal degree of the temperature data at each sampling time.
Specifically, in this embodiment, time-series temperature data is first collected, each local section of each sampling time temperature data is set, the degree of abnormality of each sampling time temperature data in each local section is obtained, the abnormal stability of each sampling time temperature data in each local section is obtained according to the degree of abnormality, the abnormal authenticity of each sampling time temperature data is obtained according to the abnormal stability and the distribution of temperature data in the local section, the real degree of abnormality of each sampling time temperature data is obtained in combination with the abnormal authenticity and the degree of abnormality, the prediction analysis of the temperature data is completed, and a specific temperature optimization prediction index obtaining flowchart is shown in fig. 2. The construction process of the real abnormal degree of the temperature data at each sampling time comprises the following steps:
for the temperature data monitored by the time sequence, the time sequence has uniform trend change, if the trend of the single temperature data is different from that of the whole trend, the temperature data at the sampling moment on the surface is seriously affected by noise, and larger deviation occurs, and at the moment, the higher the damage degree of the single temperature data to the trend is, the larger the abnormal degree of the temperature data is. However, the temperature data at different sampling moments have certain trend differences, and the trend change of the temperature data depends on the local range in which the temperature data is located, so that the reality of the degree of abnormality of the single temperature data in the local ranges of different lengths is different.
For individual temperature data, the more stable the trend is in the process of increasing the local range length, the higher the authenticity of the abnormality degree of the temperature data is, and as the trend is more stable in the local range, the more stable the abnormality degree of the individual temperature data is. Therefore, the more stable the degree of abnormality of the temperature data is, the higher the authenticity is when the local range length is changed.
For temperature monitoring data, where the anomaly noise data is primarily represented as a disruption to local trends, the local trends of the temperature data tend to react with the fit of the temperature data over a local range.
For each temperature data, firstly selecting a plurality of adjacent temperature data in time sequence to form a local section, then fitting all the temperature data in the local section, taking the sampling time as the horizontal axis and the temperature data as the vertical axis to obtain a fitting curve of all the temperature data in the local section, and thenAnd then, rejecting the temperature data at the middle position in the local interval to obtain fitting curves of all the remaining temperature data, calculating fitting residual errors of the two fitting curves, and respectively marking the fitting residual errors as a first fitting residual error and a second fitting residual error, wherein the calculation of the fitting residual errors is a prior known technology, and the embodiment is not described in detail herein. In this embodiment, the temperature data corresponding to each sampling time are sequentially taken forward and backwardThe local section of each temperature data at each sampling time is denoted as the maximum local section, in this embodiment +.>The implementation can be set by the implementation personnel according to the actual situation, and the embodiment is not limited to this.
And constructing the degree of abnormality of the temperature data at each sampling moment according to the fitting residual error, wherein the expression is as follows:
in the method, in the process of the invention,indicating the degree of abnormality of the temperature data at the ith sampling instant in the maximum local zone, +.>A first fitting residual representing the temperature data at the ith sampling instant in the maximum local interval, +.>Second fitting residual representing temperature data at the ith sampling instant in the maximum local interval, +.>The number of data representing the maximum local interval containing temperature data,/->Representing the normalization function.
When the fitting residual error after the temperature data of the ith sampling moment is removed in the maximum local interval is bigger than the fitting residual error reduction degree of all the temperature data in the original maximum local interval, the trend deviation of the temperature data of the ith sampling moment in the local interval is bigger, namely the abnormality degree of the temperature data of the ith sampling moment is higher.
In order to accurately reflect the abnormal condition of the temperature data, the embodiment sets the local intervals with different lengths according to the temperature data at each sampling time, wherein the number of the local intervals containing the temperature data is as followsWherein->Indicates the number of searches, +.>Indicates the search direction, in this embodiment +.>，/>The values of (2), 3,4,5,6,7,8,9, 10, 11) are determined by 10 searches for the temperature data at each sampling instant, 10 local intervals of different lengths are determined by 10 searches, and +.>And->The value-taking implementation of (a) can be set according to the actual situation, and the embodiment is not limited to this.
And acquiring the abnormal degree of the temperature data in each local section at each sampling time by adopting a calculation method which is the same as the abnormal degree of the temperature data in the maximum local section.
When fitting the temperature data in the local section to reflect the trend change of the local section aiming at each local section of the temperature data at each sampling time, the change of the local section length influences the trend expression of the local section, and further influences the abnormality judgment of the temperature data.
For temperature data at the ith sampling moment, constructing abnormal stability in each local interval, wherein the expression is as follows:
in the method, in the process of the invention,representing abnormal stability of temperature data at the ith sampling time in the kth local zone, +.>Indicating the degree of abnormality of the temperature data at the ith sampling instant in the (k+v) th partial section, +.>Indicating the degree of abnormality of the temperature data at the ith sampling instant in the (k+v-1) th partial section,/>Representing preset moving step length, and taking the values of-1, 0, 1, < >>The value-taking implementation of (a) can be set according to the actual situation, and the embodiment is not limited to this.
As the length of the local section increases, the variation trend of the temperature data in the local section is more stable, the corresponding fitting residual is smaller, the variation of the abnormality degree of the temperature data is more stable, and the abnormality degree of the temperature data in the corresponding local section is more true.
Meanwhile, new noise may be introduced in the process of increasing the length of the local interval, so that the trend of the local interval is reduced, and the fitting residual error of the temperature data in the local interval is increased. Therefore, the greater the increase degree of the fitting residual error of the corresponding local interval, the greater the possibility of introducing new noise, and the less realistic the degree of abnormality of the temperature data reflected by the corresponding local interval. Meanwhile, along with the change of the length of the local interval, the higher the stability of the abnormal degree of the temperature data is, the more the abnormal degree of the temperature data is true.
And constructing abnormal reality of the temperature data at each sampling moment in each local interval according to the analysis, wherein the expression is as follows:
in the method, in the process of the invention,representing the abnormal authenticity of the temperature data at the ith sampling moment in the kth local interval, +.>Representing abnormal stability of temperature data at the ith sampling time in the kth local zone, +.>Fitting residuals of all temperature data in the kth local interval representing temperature data at the ith sampling instant,/>Fitting residuals of all temperature data in the (k-1) th local interval representing temperature data at the (i) th sampling instant,/and (ii)>The kth partial section representing the temperature data at the ith sampling instant contains the number of temperature data,/->The kth-1 th local section representing the temperature data at the ith sampling instant contains the number of temperature data,representing the normalization function.
The real abnormal degree of the temperature data at each sampling time in each local interval is constructed by combining the abnormal degree and the abnormal authenticity, and the expression is as follows:
in the method, in the process of the invention,indicating the true degree of abnormality of the temperature data at the i-th sampling instant,/->Representing the abnormal authenticity of the temperature data at the ith sampling moment in the kth local interval, +.>Indicating the degree of abnormality of the temperature data at the ith sampling instant in the kth local zone, +.>The number of local sections of the temperature data at the i-th sampling time is represented.
Based on the analysis, the real abnormal degree of the temperature data at all sampling moments of the temperature monitoring is obtained, and accordingly, all the temperature abnormal data are screened out.
First, for the real abnormal degree of the temperature data at all sampling momentsThe normalization processing is performed, specifically, a maximum-minimum normalization method is adopted, the maximum-minimum normalization method is a prior known technique, the detailed description is omitted here, and then the normalization result is greater than a threshold +.>Is determined as abnormal data, in this embodiment +.>The implementation can be set by the implementation personnel according to the actual situation, and the embodiment is not limited to this.
And step S003, completing the optimized predictive analysis of the temperature monitoring data according to the temperature monitoring data after the abnormal data are removed.
And firstly removing all abnormal data from all the monitored temperature data, and then carrying out temperature interpolation on the sampling moment of removing the temperature data by using a linear interpolation method so as to ensure the integrity of the monitored temperature data. And then taking all the interpolated temperature data as input, predicting the monitored temperature by using an autoregressive moving average model, and outputting the temperature predicted value as the temperature predicted value at the next moment. The linear interpolation method and the autoregressive moving average model are known in the art, and the embodiment is not described in detail herein.
Based on the same inventive concept as the above method, the embodiment of the invention further provides a temperature monitoring data optimization prediction analysis system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to realize the steps of any one of the above temperature monitoring data optimization prediction analysis methods.
In summary, the embodiment of the invention solves the problem of low prediction analysis accuracy caused by noise interference of the temperature monitoring data, eliminates abnormal data in the temperature monitoring data by analyzing the overall change trend of the time sequence temperature monitoring data, and improves the reliability of the prediction analysis of the temperature monitoring data.
It should be noted that: the sequence of the embodiments of the present invention 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 invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. The temperature monitoring data optimizing, predicting and analyzing method is characterized by comprising the following steps:
collecting time sequence temperature data;
acquiring each local interval of temperature data at each sampling moment; obtaining the abnormality degree of the temperature data at each sampling time in each local section according to the trend deviation of the temperature data at each sampling time in the local section; obtaining abnormal stability of the temperature data at each sampling moment in each local section according to the abnormal degree and the difference of the trend deviation of the temperature data in different local sections; obtaining abnormal reality of the temperature data at each sampling moment in each local interval according to the abnormal stability and the distribution of the temperature data in the local interval; combining the abnormality reality and the abnormality degree to obtain the real abnormality degree of the temperature data at each sampling moment; acquiring abnormal data in the time sequence temperature data by utilizing the real abnormal degree; and eliminating the abnormal data, and completing temperature prediction according to the temperature data after eliminating the abnormal data.
2. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the step of obtaining each local section of the temperature data at each sampling time comprises:
a plurality of search lengths are set for temperature data at each sampling time, and all temperature data included in each search length of temperature data at each sampling time is set as each local section of temperature data at each sampling time.
3. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the obtaining the abnormality degree of the temperature data at each sampling time in each local section according to the trend deviation of the temperature data at each sampling time in the local section comprises:
acquiring a first fitting residual error and a second fitting residual error of each local interval;
calculating the difference value of the first fitting residual error and the second fitting residual error of each local interval, calculating the ratio of the difference value to the number of the temperature data contained in each local interval, and taking the normalized value of the ratio as the abnormal degree of the temperature data in each local interval at each sampling moment.
4. The method for optimizing predictive analysis of temperature monitoring data according to claim 3, wherein the obtaining the first fit residual and the second fit residual of each local interval comprises:
and calculating fitting residual errors of all temperature data in each local interval and all remaining temperature data except the central position temperature data in each local interval according to the temperature data at each sampling moment, and respectively marking the fitting residual errors as a first fitting residual error and a second fitting residual error.
5. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the abnormal stability of the temperature data at each sampling time in each local section is obtained according to the abnormal degree and the difference of the trend deviation of the temperature data in different local sections, and the expression is:
in the method, in the process of the invention,representing abnormal stability of temperature data at the ith sampling time in the kth local zone, +.>Indicating that the temperature data at the ith sampling moment is in the (k+v) th local intervalDegree of abnormality of->Indicating the degree of abnormality of the temperature data at the ith sampling instant in the (k+v-1) th partial section,/>Representing a preset movement step.
6. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the abnormal reality of the temperature data at each sampling time in each local section is obtained according to the abnormal stability and the distribution of the temperature data in the local section, and the expression is:
in the method, in the process of the invention,representing the abnormal authenticity of the temperature data at the ith sampling moment in the kth local interval, +.>Representing abnormal stability of temperature data at the ith sampling time in the kth local zone, +.>Fitting residuals of all temperature data in the kth local interval representing temperature data at the ith sampling instant,/>Fitting residuals of all temperature data in the (k-1) th local interval representing temperature data at the (i) th sampling instant,/and (ii)>The kth local section representing the temperature data at the ith sampling instant contains the temperature dataNumber of (A)>The (k-1) th partial section representing the temperature data at the (i) th sampling time contains the number of temperature data,/therein>Representing the normalization function.
7. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the step of obtaining the true abnormality degree of the temperature data at each sampling time by combining the abnormality authenticity and the abnormality degree comprises the steps of:
and calculating the product of the abnormality degree and the abnormality authenticity of the temperature data at each sampling time in each local section, and taking the sum of the products of the temperature data at each sampling time in all local sections as the actual abnormality degree of the temperature data at each sampling time.
8. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the acquiring abnormal data in the time-series temperature data using the degree of real abnormality comprises: and a preset threshold value, wherein temperature data with a normalized value of the real abnormality degree being more than or equal to the preset threshold value is used as abnormal data.
9. The method for optimizing, predicting and analyzing temperature monitoring data according to claim 1, wherein the step of completing the temperature prediction based on the temperature data after the abnormal data is removed comprises the steps of:
and carrying out temperature interpolation on the temperature data with abnormal data removed by using a linear interpolation method, taking all the temperature data after interpolation as input of an autoregressive moving average model, and outputting the temperature data as a temperature predicted value at the next moment.
10. A temperature monitoring data optimized predictive analysis system comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method of any of claims 1-9 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410211278.7A CN117786371B (en) | 2024-02-27 | 2024-02-27 | Temperature monitoring data optimization prediction analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410211278.7A CN117786371B (en) | 2024-02-27 | 2024-02-27 | Temperature monitoring data optimization prediction analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117786371A true CN117786371A (en) | 2024-03-29 |
| CN117786371B CN117786371B (en) | 2024-05-10 |
Family
ID=90391383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410211278.7A Active CN117786371B (en) | 2024-02-27 | 2024-02-27 | Temperature monitoring data optimization prediction analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117786371B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118053127A (en) * | 2024-04-16 | 2024-05-17 | 山东瑞福锂业有限公司 | Industrial equipment state monitoring and management method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016058010A (en) * | 2014-09-12 | 2016-04-21 | 株式会社日立ハイテクノロジーズ | Abnormality tendency detection method and system |
| WO2016101690A1 (en) * | 2014-12-22 | 2016-06-30 | 国家电网公司 | Time sequence analysis-based state monitoring data cleaning method for power transmission and transformation device |
| JP2020047078A (en) * | 2018-09-20 | 2020-03-26 | 株式会社Ｓｃｒｅｅｎホールディングス | Data processing method, data processing device, and data processing program |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| WO2022141871A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Time sequence data anomaly detection method, apparatus and device, and storage medium |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116659589A (en) * | 2023-07-25 | 2023-08-29 | 澳润(山东)药业有限公司 | Donkey-hide gelatin cake preservation environment monitoring method based on data analysis |
| CN116756526A (en) * | 2023-08-17 | 2023-09-15 | 北京英沣特能源技术有限公司 | Full life cycle performance detection and analysis system of energy storage equipment |
| CN116757553A (en) * | 2023-08-11 | 2023-09-15 | 山东中新农业发展有限公司 | Agricultural organic waste resource utilization digital information management system |
| JP2023148972A (en) * | 2022-03-30 | 2023-10-13 | セコム株式会社 | Abnormality determination device, abnormality determination method, and abnormality determination program |
| CN117390562A (en) * | 2023-10-18 | 2024-01-12 | 国网山东省电力公司营销服务中心(计量中心) | Data transmission management method and system for distributed power generation system |
| CN117407827A (en) * | 2023-12-15 | 2024-01-16 | 湖南辉达净化工程有限公司 | Abnormal operation data detection method for purification engineering waste gas purification equipment |
| CN117421610A (en) * | 2023-12-19 | 2024-01-19 | 山东德源电力科技股份有限公司 | Data anomaly analysis method for electric energy meter running state early warning |
| CN117421687A (en) * | 2023-12-18 | 2024-01-19 | 圣道天德电气(山东)有限公司 | Method for monitoring running state of digital power ring main unit |
| CN117556714A (en) * | 2024-01-12 | 2024-02-13 | 济南海德热工有限公司 | Preheating pipeline temperature data anomaly analysis method for aluminum metal smelting |
-
2024
- 2024-02-27 CN CN202410211278.7A patent/CN117786371B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016058010A (en) * | 2014-09-12 | 2016-04-21 | 株式会社日立ハイテクノロジーズ | Abnormality tendency detection method and system |
| WO2016101690A1 (en) * | 2014-12-22 | 2016-06-30 | 国家电网公司 | Time sequence analysis-based state monitoring data cleaning method for power transmission and transformation device |
| JP2020047078A (en) * | 2018-09-20 | 2020-03-26 | 株式会社Ｓｃｒｅｅｎホールディングス | Data processing method, data processing device, and data processing program |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| WO2022141871A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Time sequence data anomaly detection method, apparatus and device, and storage medium |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| JP2023148972A (en) * | 2022-03-30 | 2023-10-13 | セコム株式会社 | Abnormality determination device, abnormality determination method, and abnormality determination program |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116659589A (en) * | 2023-07-25 | 2023-08-29 | 澳润(山东)药业有限公司 | Donkey-hide gelatin cake preservation environment monitoring method based on data analysis |
| CN116757553A (en) * | 2023-08-11 | 2023-09-15 | 山东中新农业发展有限公司 | Agricultural organic waste resource utilization digital information management system |
| CN116756526A (en) * | 2023-08-17 | 2023-09-15 | 北京英沣特能源技术有限公司 | Full life cycle performance detection and analysis system of energy storage equipment |
| CN117390562A (en) * | 2023-10-18 | 2024-01-12 | 国网山东省电力公司营销服务中心(计量中心) | Data transmission management method and system for distributed power generation system |
| CN117407827A (en) * | 2023-12-15 | 2024-01-16 | 湖南辉达净化工程有限公司 | Abnormal operation data detection method for purification engineering waste gas purification equipment |
| CN117421687A (en) * | 2023-12-18 | 2024-01-19 | 圣道天德电气(山东)有限公司 | Method for monitoring running state of digital power ring main unit |
| CN117421610A (en) * | 2023-12-19 | 2024-01-19 | 山东德源电力科技股份有限公司 | Data anomaly analysis method for electric energy meter running state early warning |
| CN117556714A (en) * | 2024-01-12 | 2024-02-13 | 济南海德热工有限公司 | Preheating pipeline temperature data anomaly analysis method for aluminum metal smelting |
Non-Patent Citations (3)
| Title |
|---|
| C. NG;PANASONIC SINGAPORE LABS;F. ZHAO;UC DAVIS; M. WATARI; KDDI R AMP;AMP;AMP;D LABS;P. THUBERT; CISCO SYSTEMS;: "Network Mobility Route Optimization Solution Space Analysis", IETF, 31 July 2007 (2007-07-31) * |
| 孙鹏;李剑;寇晓适;吕中宾;姚德贵;王吉;王磊磊;滕卫军;: "采用预测模型与模糊理论的风电机组状态参数异常辨识方法", 电力自动化设备, no. 08, 10 August 2017 (2017-08-10) * |
| 张峰;薛惠锋;WANG WEI;宋晓娜;万毅;: "水资源监测异常数据模态分解-支持向量机重构方法", 农业机械学报, no. 11, 25 November 2017 (2017-11-25) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118053127A (en) * | 2024-04-16 | 2024-05-17 | 山东瑞福锂业有限公司 | Industrial equipment state monitoring and management method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117786371B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117786371B (en) | Temperature monitoring data optimization prediction analysis method and system | |
| CN111241744B (en) | Low-pressure casting machine time sequence data abnormity detection method based on bidirectional LSTM | |
| CN112101480B (en) | Multivariate clustering and fused time sequence combined prediction method | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN109446189A (en) | A kind of technological parameter outlier detection system and method | |
| CN112414694B (en) | Equipment multistage abnormal state identification method and device based on multivariate state estimation technology | |
| CN110569566A (en) | Method for predicting mechanical property of plate strip | |
| Guo et al. | A hybrid prognosis scheme for rolling bearings based on a novel health indicator and nonlinear Wiener process | |
| CN112559598B (en) | Telemetry time series data abnormity detection method and system based on graph neural network | |
| CN103488561A (en) | kNN (k-nearest neighbor) fault detection method for online upgrading master sample model | |
| CN115829157A (en) | Chemical water quality index prediction method based on variational modal decomposition and auto former model | |
| CN110084301B (en) | Hidden Markov model-based multi-working-condition process working condition identification method | |
| Meng et al. | A gear fault diagnosis method based on improved accommodative random weighting algorithm and BB-1D-TP | |
| Li et al. | A new fractional-order augmented quaternion-valued approach for degradation prognostics of bearings using generalized Hamilton-real calculus | |
| CN110543869A (en) | Ball screw service life prediction method and device, computer equipment and storage medium | |
| CN113469408A (en) | Running state trend prediction method and system for phase modulator | |
| CN112561161A (en) | Time series trend extraction and prediction method based on compressed sensing | |
| CN115310499B (en) | Industrial equipment fault diagnosis system and method based on data fusion | |
| CN117171713A (en) | Cross self-adaptive deep migration learning method and system based on bearing service life | |
| CN116226770A (en) | Time sequence data anomaly detection method and device | |
| CN117808271B (en) | Digital agricultural fertilizer data optimization management method and system | |
| CN118090078B (en) | Leakage online monitoring method for closed circulation water cooling system | |
| CN116756531B (en) | Method and device for monitoring hot continuous rolling process of strip steel for model interaction linkage | |
| CN117829822B (en) | Power transformer fault early warning method and system | |
| CN117951695B (en) | Industrial unknown threat detection method and system |
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 |