CN116398823A - Gas pipeline detection early warning system and method based on algorithm - Google Patents
Gas pipeline detection early warning system and method based on algorithm Download PDFInfo
- Publication number
- CN116398823A CN116398823A CN202310441460.7A CN202310441460A CN116398823A CN 116398823 A CN116398823 A CN 116398823A CN 202310441460 A CN202310441460 A CN 202310441460A CN 116398823 A CN116398823 A CN 116398823A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- abnormal
- real
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000002159 abnormal effect Effects 0.000 claims abstract description 100
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000002372 labelling Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 5
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 20
- 239000007789 gas Substances 0.000 description 18
- 239000003345 natural gas Substances 0.000 description 10
- 230000006870 function Effects 0.000 description 4
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- VUZPPFZMUPKLLV-UHFFFAOYSA-N methane;hydrate Chemical compound C.O VUZPPFZMUPKLLV-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/005—Protection or supervision of installations of gas pipelines, e.g. alarm
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D3/00—Arrangements for supervising or controlling working operations
- F17D3/01—Arrangements for supervising or controlling working operations for controlling, signalling, or supervising the conveyance of a product
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a gas pipeline detection early warning system and method based on an algorithm, wherein the system comprises the following steps: the prediction module is used for training the prediction model according to the operation data to generate prediction data; the comparison module is used for comparing the predicted data with the real-time data and judging whether the real-time data is abnormal data or not according to the comparison result; and the analysis module is used for analyzing the abnormal data to obtain the abnormal event type when the real-time data is the abnormal data. According to the invention, the pipeline running state can be monitored without relying on manpower, the prediction model is trained and iterated to generate the prediction data, the prediction data and the real-time data are compared, when a problem occurs, the deviation of the prediction data and the real-time data can be found in advance, and the type of an abnormal event can be determined by comparing the abnormal data with the data stored in the abnormal database in time, so that an accident cause is provided for operation and maintenance personnel.
Description
Technical Field
The invention relates to the technical field of signal transmission, in particular to a gas pipeline detection early warning system and method based on an algorithm.
Background
With the increase of global warming on world climate influence, the social demand for clean energy is further increased for achieving the purposes of energy conservation and emission reduction. Compared with coal-series petrochemical energy, natural gas is a relatively clean energy with low emission, and is different from other petrochemical energy, the combustion of natural gas only generates carbon dioxide and water, harmful substances such as sulfur dioxide and the like are not generated, and the natural gas is considered as the cleanest fossil energy. The natural gas can be mixed with air more fully due to the chemical property of the natural gas, so that the natural gas can be combusted more fully, and the energy utilization rate is higher.
Along with the increase of the length of the natural gas pipeline, in order to ensure the safety of gas transmission, the monitoring and detection of the natural gas pipeline become an important link for ensuring the operation of the natural gas pipeline network. Currently mainstream natural gas pipe network detection systems commonly adopt the internet of things technology, and the pressure and temperature are added on the pipe network, so that the flow sensors can acquire and store data in real time. However, the detection and monitoring of this mode is not prospective, and an alarm can be given only when a problem affecting the operation of the pipeline has occurred. Meanwhile, a large amount of accumulated historical data of pipe network equipment operation, pipe and valve maintenance and pipe network construction cannot be effectively supported for the current pipe network operation expectation.
Disclosure of Invention
The present invention has been made in view of the above problems, and it is an object of the present invention to provide an algorithm-based gas pipeline detection warning system and method that overcomes or at least partially solves the above problems.
In one aspect of the invention, an algorithm-based gas pipeline detection and early warning system is provided, the system comprises:
the prediction module is used for training the prediction model according to the operation data to generate prediction data;
the comparison module is used for comparing the predicted data with the real-time data and judging whether the real-time data is abnormal data or not according to the comparison result;
and the analysis module is used for analyzing the abnormal data to obtain the abnormal event type when the real-time data is the abnormal data.
In some alternative embodiments, the predictive model includes: a first prediction model, a second prediction model, and a third prediction model;
the prediction module is used for training the first prediction model, the second prediction model and the third prediction model according to the operation data in the database respectively to generate corresponding first prediction data, second prediction data and third prediction data.
In some alternative embodiments, the prediction module is further configured to iterate the first prediction model, the second prediction model, and the third prediction model respectively using incremental learning according to the normal data determined by the comparison module.
In some optional embodiments, the comparison module is configured to obtain weights corresponding to the first prediction data, the second prediction data, and the third prediction data according to the corresponding accuracies of the first prediction model, the second prediction model, and the third prediction model, obtain comparison data based on weighted summation, and compare the comparison data with real-time data acquired by a sensor;
if the comparison result is larger than a first preset threshold value, judging that the real-time data is abnormal data;
and if the comparison result is smaller than the first preset threshold value, judging that the real-time data is normal data.
In some optional embodiments, the comparing module is configured to compare the first prediction data, the second prediction data, and the third prediction data with real-time data collected by a sensor, respectively;
if the corresponding comparison result is larger than a second preset threshold value, acquiring a first comparison result number larger than the second preset threshold value;
if the corresponding comparison result is smaller than a second preset threshold value, obtaining a second comparison result number smaller than the second preset threshold value;
if the first comparison result number is larger than the second comparison result number, judging that the real-time data is abnormal data;
and if the number of the first comparison results is smaller than the number of the second comparison results, judging that the real-time data is normal data.
In some optional embodiments, the analysis module is configured to obtain at least one data attribute of the abnormal data when the real-time data is abnormal data, and determine a target data feature of the abnormal data, where the target data feature is formed by one or more data attributes;
calculating a hash value of the target data feature;
based on the consistency of the hash value, comparing the target data characteristics with stored data characteristics in an abnormal database which is obtained in advance and is subjected to data classification and labeling;
determining whether to update the abnormal database by utilizing the target data characteristics according to a third comparison result;
and determining the type of the abnormal event according to the data tag corresponding to the target data characteristic in the abnormal database.
In some optional embodiments, the analysis module is configured to obtain at least one data attribute of the abnormal data when the real-time data is abnormal data, and determine a target data feature of the abnormal data, where the target data feature is formed by one or more data attributes;
calculating a hash value of the target data feature;
based on the consistency of the hash value, comparing the target data characteristics with stored data characteristics in an abnormal database which is obtained in advance and is subjected to data classification and labeling;
if the target data characteristics are the same as the stored data characteristics in the abnormal database, determining that the abnormal database does not need to be updated;
if the target data characteristics are different from the stored data characteristics in the abnormal database, the target data characteristics are newly added in the abnormal database;
and determining the type of the abnormal event according to the data tag corresponding to the target data characteristic in the abnormal database.
The invention provides a gas pipeline detection early warning method based on an algorithm, which comprises the following steps:
training a prediction model according to the operation data to generate prediction data;
comparing the predicted data with the real-time data, and judging whether the real-time data is abnormal data or not according to a comparison result;
and when the real-time data is abnormal data, analyzing the abnormal data to obtain an abnormal event type.
In some alternative embodiments, the predictive model includes: a first prediction model, a second prediction model, and a third prediction model;
training the prediction model according to the operation data to generate prediction data, including: and training the first prediction model, the second prediction model and the third prediction model according to the operation data in the database respectively to generate corresponding first prediction data, second prediction data and third prediction data.
In some optional embodiments, the comparing the predicted data with the real-time data, and determining whether the real-time data is abnormal data according to the comparison result includes:
the first prediction data, the second prediction data and the weight corresponding to the third prediction data are obtained according to the precision corresponding to the first prediction model, the second prediction model and the third prediction model, comparison data are obtained based on weighted summation, and the comparison data are compared with real-time data acquired through a sensor;
if the comparison result is larger than a first preset threshold value, judging that the real-time data is abnormal data;
and if the comparison result is smaller than the first preset threshold value, judging that the real-time data is normal data.
According to the gas pipeline detection early warning system and method based on the algorithm, provided by the embodiment of the invention, the pipeline running state can be monitored without relying on manpower, the prediction model is trained and iterated to generate the prediction data, the prediction data and the real-time data are compared, when a problem occurs, the deviation of the prediction data and the real-time data can be found in advance, and the abnormal event type can be determined by comparing the abnormal data with the data stored in the abnormal database in time, so that an accident cause is provided for operation and maintenance personnel.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a schematic diagram of a gas pipeline detection and early warning system based on an algorithm provided by an embodiment of the invention;
fig. 2 is a flowchart of a gas pipeline detection early warning method based on an algorithm provided by an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It will be understood by those skilled in the art that all terms (including 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 unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
FIG. 1 schematically illustrates a schematic diagram of an algorithm-based gas pipeline detection early warning system in accordance with one embodiment of the present invention.
Referring to fig. 1, the algorithm-based gas pipeline detection and early warning system in the embodiment of the invention specifically includes:
the prediction module 11 is used for training the prediction model according to the operation data to generate prediction data;
the comparison module 12 is configured to compare the predicted data with real-time data, and determine whether the real-time data is abnormal data according to a comparison result;
and the analysis module 13 is used for analyzing the abnormal data to obtain the abnormal event type when the real-time data is the abnormal data.
Further, the predictive model includes: a first prediction model, a second prediction model, and a third prediction model;
the prediction module 11 is configured to train the first prediction model, the second prediction model, and the third prediction model according to the operation data in the database, and generate corresponding first prediction data, second prediction data, and third prediction data.
In this embodiment, in order to ensure the accuracy of the predicted data, the prediction module 11 is composed of 3 independent prediction models, each of which uses the same data for training and iteration, and the 3 prediction models generate the corresponding predicted data independently of each other.
In this embodiment, the prediction model may be selected from the Seasonal Auto-regressive Integrated Moving Average model model, long Short-term Memory neural network, and Prophet model.
In this embodiment, the nature of the prediction model is a regression problem, regression is used to predict the relationship between the input variable and the output variable, and when the value of the input variable changes, the value of the output variable changes, and the prediction model represents a function mapped from the input variable to the output variable.
In this embodiment, the prediction model is trained according to the pipeline operation data in the database, prediction data in a preset time period is generated, and the pipeline operation state in a future preset period is estimated.
In this embodiment, the generated prediction data is stored in a database.
Further, the prediction module 11 is further configured to iterate the first prediction model, the second prediction model, and the third prediction model respectively by using incremental learning according to the normal data determined by the comparison module 12.
In this embodiment, the prediction model is iterated through normal data, so that error accumulation can be avoided, prediction accuracy of the prediction model can be maintained, and along with the increase of the operation duration of the gas pipeline detection and early warning system, the prediction model is adaptive to the pipeline in which the gas pipeline detection and early warning system operates.
In this embodiment, in the pipeline operation, new normal data is continuously generated to continuously iterate the prediction model, and the prediction model can generate more accurate prediction data. Incremental learning may be described as the incremental updating of a function by new information brought by new data on the basis of an original function, without the need to reconstruct an existing model function each time data is newly added. Incremental updates enable the ability of the predictive model to achieve some degree of adaptivity.
Further, the comparison module 12 is configured to obtain weights corresponding to the first prediction data, the second prediction data, and the third prediction data according to the accuracies corresponding to the first prediction model, the second prediction model, and the third prediction model, obtain comparison data based on weighted summation, and compare the comparison data with real-time data collected by a sensor;
if the comparison result is larger than a first preset threshold value, judging that the real-time data is abnormal data;
and if the comparison result is smaller than the first preset threshold value, judging that the real-time data is normal data.
Further, the comparison module 12 is configured to compare the first prediction data, the second prediction data, and the third prediction data with real-time data collected by a sensor, respectively;
if the corresponding comparison result is larger than a second preset threshold value, acquiring a first comparison result number larger than the second preset threshold value;
if the corresponding comparison result is smaller than a second preset threshold value, obtaining a second comparison result number smaller than the second preset threshold value;
if the first comparison result number is larger than the second comparison result number, judging that the real-time data is abnormal data;
and if the number of the first comparison results is smaller than the number of the second comparison results, judging that the real-time data is normal data.
In this embodiment, since 3 sets of prediction data are generated by the prediction module 11 at the same time sequence, a comparison logic is required to be set in the prediction module 11 to compare 3 sets of prediction data with 1 set of real-time data to generate the classification result.
The comparison can be completed by using various logics, different weights can be given to the prediction models according to the precision of the prediction models, comparison data is obtained based on weighted summation, the comparison data and real-time data acquired through a sensor are compared, the real-time data and the prediction data can be respectively compared, and the first comparison result number larger than a second preset threshold value and the second comparison result number smaller than the second preset threshold value are compared to generate comparison and classification results.
Further, the analysis module 13 is configured to obtain at least one data attribute of the abnormal data when the real-time data is abnormal data, and determine a target data feature of the abnormal data, where the target data feature is formed by one or more data attributes;
calculating a hash value of the target data feature;
based on the consistency of the hash value, comparing the target data characteristics with stored data characteristics in an abnormal database which is obtained in advance and is subjected to data classification and labeling;
determining whether to update the abnormal database by utilizing the target data characteristics according to a third comparison result;
and determining the type of the abnormal event according to the data tag corresponding to the target data characteristic in the abnormal database.
Further, the analysis module 13 is configured to obtain at least one data attribute of the abnormal data when the real-time data is abnormal data, and determine a target data feature of the abnormal data, where the target data feature is formed by one or more data attributes;
calculating a hash value of the target data feature;
based on the consistency of the hash value, comparing the target data characteristics with stored data characteristics in an abnormal database which is obtained in advance and is subjected to data classification and labeling;
if the target data characteristics are the same as the stored data characteristics in the abnormal database, determining that the abnormal database does not need to be updated;
if the target data characteristics are different from the stored data characteristics in the abnormal database, the target data characteristics are newly added in the abnormal database;
and determining the type of the abnormal event according to the data tag corresponding to the target data characteristic in the abnormal database.
In this embodiment, the analysis module 13 is configured to determine a cause of the data abnormality according to the abnormal data determined by the comparison module 12.
In this embodiment, the analysis module 13 may provide error recognition capability for the gas pipeline detection and early warning system.
In this embodiment, the abnormal data may be given a new data tag to update the abnormal database.
According to the gas pipeline detection early warning system based on the algorithm, provided by the embodiment of the invention, the operation state of the pipeline can be monitored without relying on manpower, the prediction model is trained and iterated to generate the prediction data, the prediction data and the real-time data are compared, when a problem occurs, the deviation of the prediction data and the real-time data can be found in advance, and the type of an abnormal event can be determined by comparing the abnormal data with the data stored in the abnormal database, so that an accident cause is provided for operation and maintenance personnel.
Fig. 2 is a flowchart of an algorithm-based gas pipeline detection and early warning method provided by an embodiment of the present invention, and referring to fig. 2, the algorithm-based gas pipeline detection and early warning method of an embodiment of the present invention specifically includes:
s21, training a prediction model according to the operation data to generate prediction data;
s22, comparing the predicted data with the real-time data, and judging whether the real-time data is abnormal data or not according to a comparison result;
s23, when the real-time data are abnormal data, analyzing the abnormal data to obtain the abnormal event type.
Further, the predictive model includes: a first prediction model, a second prediction model, and a third prediction model;
training the prediction model according to the operation data to generate prediction data, including: and training the first prediction model, the second prediction model and the third prediction model according to the operation data in the database respectively to generate corresponding first prediction data, second prediction data and third prediction data.
Further, the comparing the predicted data with the real-time data, and judging whether the real-time data is abnormal data according to the comparison result includes:
the first prediction data, the second prediction data and the weight corresponding to the third prediction data are obtained according to the precision corresponding to the first prediction model, the second prediction model and the third prediction model, comparison data are obtained based on weighted summation, and the comparison data are compared with real-time data acquired through a sensor;
if the comparison result is larger than a first preset threshold value, judging that the real-time data is abnormal data;
and if the comparison result is smaller than the first preset threshold value, judging that the real-time data is normal data.
According to the gas pipeline detection early warning method based on the algorithm, provided by the embodiment of the invention, the operation state of the pipeline can be monitored without relying on manpower, the prediction model is trained and iterated to generate the prediction data, the prediction data and the real-time data are compared, when a problem occurs, the deviation of the prediction data and the real-time data can be found in advance, and the type of an abnormal event can be determined by comparing the abnormal data with the stored data in the abnormal database, so that an accident cause is provided for operation and maintenance personnel.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, any of the claimed embodiments can be used in any combination.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An algorithm-based gas pipeline detection and early warning system, which is characterized by comprising:
the prediction module is used for training the prediction model according to the operation data to generate prediction data;
the comparison module is used for comparing the predicted data with the real-time data and judging whether the real-time data is abnormal data or not according to the comparison result;
and the analysis module is used for analyzing the abnormal data to obtain the abnormal event type when the real-time data is the abnormal data.
2. The system of claim 1, wherein the system further comprises a controller configured to control the controller,
the predictive model includes: a first prediction model, a second prediction model, and a third prediction model;
the prediction module is used for training the first prediction model, the second prediction model and the third prediction model according to the operation data in the database respectively to generate corresponding first prediction data, second prediction data and third prediction data.
3. The system of claim 2, wherein the prediction module is further configured to iterate the first prediction model, the second prediction model, and the third prediction model using incremental learning based on the normal data determined by the comparison module, respectively.
4. The system according to claim 2, wherein the comparison module is configured to obtain the comparison data based on weighted summation of weights corresponding to the first prediction data, the second prediction data, and the third prediction data according to the accuracy corresponding to the first prediction model, the second prediction model, and the third prediction model, and compare the comparison data with real-time data acquired by the sensor;
if the comparison result is larger than a first preset threshold value, judging that the real-time data is abnormal data;
and if the comparison result is smaller than the first preset threshold value, judging that the real-time data is normal data.
5. The system of claim 2, wherein the comparison module is configured to compare the first, second, and third prediction data with real-time data collected by a sensor, respectively;
if the corresponding comparison result is larger than a second preset threshold value, acquiring a first comparison result number larger than the second preset threshold value;
if the corresponding comparison result is smaller than a second preset threshold value, obtaining a second comparison result number smaller than the second preset threshold value;
if the first comparison result number is larger than the second comparison result number, judging that the real-time data is abnormal data;
and if the number of the first comparison results is smaller than the number of the second comparison results, judging that the real-time data is normal data.
6. The system of claim 1, wherein the analysis module is configured to obtain at least one data attribute of the anomaly data when the real-time data is anomaly data, determine a target data characteristic of the anomaly data, the target data characteristic being comprised of one or more data attributes;
calculating a hash value of the target data feature;
based on the consistency of the hash value, comparing the target data characteristics with stored data characteristics in an abnormal database which is obtained in advance and is subjected to data classification and labeling;
determining whether to update the abnormal database by utilizing the target data characteristics according to a third comparison result;
and determining the type of the abnormal event according to the data tag corresponding to the target data characteristic in the abnormal database.
7. The system of claim 6, wherein the analysis module is configured to obtain at least one data attribute of the anomaly data when the real-time data is anomaly data, determine a target data characteristic of the anomaly data, the target data characteristic being comprised of one or more data attributes;
calculating a hash value of the target data feature;
based on the consistency of the hash value, comparing the target data characteristics with stored data characteristics in an abnormal database which is obtained in advance and is subjected to data classification and labeling;
if the target data characteristics are the same as the stored data characteristics in the abnormal database, determining that the abnormal database does not need to be updated;
if the target data characteristics are different from the stored data characteristics in the abnormal database, the target data characteristics are newly added in the abnormal database;
and determining the type of the abnormal event according to the data tag corresponding to the target data characteristic in the abnormal database.
8. The gas pipeline detection early warning method based on the algorithm is characterized by comprising the following steps of:
training a prediction model according to the operation data to generate prediction data;
comparing the predicted data with the real-time data, and judging whether the real-time data is abnormal data or not according to a comparison result;
and when the real-time data is abnormal data, analyzing the abnormal data to obtain an abnormal event type.
9. The method of claim 8, wherein the predictive model comprises: a first prediction model, a second prediction model, and a third prediction model;
training the prediction model according to the operation data to generate prediction data, including: and training the first prediction model, the second prediction model and the third prediction model according to the operation data in the database respectively to generate corresponding first prediction data, second prediction data and third prediction data.
10. The method according to claim 8, wherein comparing the predicted data with real-time data, and determining whether the real-time data is abnormal data according to the comparison result, comprises:
the first prediction data, the second prediction data and the weight corresponding to the third prediction data are obtained according to the precision corresponding to the first prediction model, the second prediction model and the third prediction model, comparison data are obtained based on weighted summation, and the comparison data are compared with real-time data acquired through a sensor;
if the comparison result is larger than a first preset threshold value, judging that the real-time data is abnormal data;
and if the comparison result is smaller than the first preset threshold value, judging that the real-time data is normal data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310441460.7A CN116398823A (en) | 2023-04-23 | 2023-04-23 | Gas pipeline detection early warning system and method based on algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310441460.7A CN116398823A (en) | 2023-04-23 | 2023-04-23 | Gas pipeline detection early warning system and method based on algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116398823A true CN116398823A (en) | 2023-07-07 |
Family
ID=87014133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310441460.7A Pending CN116398823A (en) | 2023-04-23 | 2023-04-23 | Gas pipeline detection early warning system and method based on algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116398823A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688438A (en) * | 2023-11-13 | 2024-03-12 | 江苏盛伟燃气科技有限公司 | Public integrated facility gas supply safety monitoring and early warning system and method |
-
2023
- 2023-04-23 CN CN202310441460.7A patent/CN116398823A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688438A (en) * | 2023-11-13 | 2024-03-12 | 江苏盛伟燃气科技有限公司 | Public integrated facility gas supply safety monitoring and early warning system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3809220B1 (en) | Method and system for semi-supervised deep anomaly detection for large-scale industrial monitoring systems based on time-series data utilizing digital twin simulation data | |
| Marugán et al. | Reliability analysis of detecting false alarms that employ neural networks: A real case study on wind turbines | |
| Chen et al. | Anomaly detection for wind turbines based on the reconstruction of condition parameters using stacked denoising autoencoders | |
| US20200371491A1 (en) | Determining Operating State from Complex Sensor Data | |
| Peng et al. | A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction | |
| Es-Sakali et al. | Review of predictive maintenance algorithms applied to HVAC systems | |
| CN109977624A (en) | Photovoltaic plant soft fault monitoring method based on deep neural network | |
| Caraka et al. | Hybrid vector autoregression feedforward neural network with genetic algorithm model for forecasting space-time pollution data | |
| Mathew et al. | Regression kernel for prognostics with support vector machines | |
| Pattison et al. | Intelligent integrated maintenance for wind power generation | |
| CN116398823A (en) | Gas pipeline detection early warning system and method based on algorithm | |
| JP2021193557A (en) | Method for executing predicted soundness analysis for asset and computing system | |
| Zhang et al. | A data-driven maintenance framework under imperfect inspections for deteriorating systems using multitask learning-based status prognostics | |
| Zhou et al. | A hidden fault prediction model based on the belief rule base with power set and considering attribute reliability | |
| Jiang et al. | A timeseries supervised learning framework for fault prediction in chiller systems | |
| CN117523793A (en) | Power plant equipment fault early warning method and computer equipment | |
| CN116453292A (en) | Chemical enterprise production safety risk classification and early warning method | |
| Arabgol et al. | Artificial neural network and ewma-based fault prediction in wind turbines | |
| CN114692738A (en) | Lightweight real-time series anomaly detection method | |
| Aggarwal et al. | Automation of Water Distribution System by Prediction of Water Consumption and Leakage Detection Using Machine Learning and IoT | |
| Wang et al. | Maintenance decision based on data fusion of aero engines | |
| Mounce et al. | Development of artificial intelligence systems for analysis of water supply system data | |
| CN116095704B (en) | 5G base station intelligent inspection method and system | |
| Belhaj Salem et al. | Prognostic and Classification of the Dynamic Degradation in a Mechanical System Using Variance Gamma Process. Mathematics 2021, 9, 254 | |
| CN115456168B (en) | Training method of reinforcement learning model, energy consumption determining method and device |
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 |