CN115964649A - Indoor gas monitoring fault analysis model - Google Patents
Indoor gas monitoring fault analysis model Download PDFInfo
- Publication number
- CN115964649A CN115964649A CN202211611524.5A CN202211611524A CN115964649A CN 115964649 A CN115964649 A CN 115964649A CN 202211611524 A CN202211611524 A CN 202211611524A CN 115964649 A CN115964649 A CN 115964649A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- gas monitoring
- curve
- clustering
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an indoor gas monitoring fault analysis model, and particularly relates to the technical field of Internet of things. It includes: acquiring fault data of gas monitoring equipment, and extracting abnormal data in the fault data; performing feature extraction on the abnormal data to form an original fault feature set, and performing dimensionless processing on the extracted data features; performing cluster analysis on the extracted data characteristics respectively, and establishing a fault data set after classifying results; and inputting the data to be monitored into a fault data set for similarity matching, analyzing and classifying faults, and acquiring a distribution rule of equipment fault loss. The invention can effectively solve the problem that the prior art lacks the fault monitoring capability of the gas sensor, thereby causing economic property loss caused by failure report.
Description
Technical Field
The invention relates to the technical field of Internet of things, in particular to an indoor gas monitoring fault analysis model.
Background
The safety of indoor gas monitoring and gas utilization is the basic guarantee of industrial and commercial and household user life, and with the development of new technologies such as artificial intelligence, big data, internet of things and the like, the safety, reliability and stability of indoor gas monitoring equipment are of great importance. At present, the faults of the gas monitoring equipment mainly depend on manual door inspection. However, with the increasing awareness of the safety of gas consumption of residents and the increasing coverage rate of gas equipment, the pressure of the traditional mode is multiplied.
Meanwhile, the working environment of the gas monitoring equipment is complex, the conditions of indoor complex temperature, humidity and smoke dust and various factors enable the gas monitoring equipment to be prone to failure, so that the conditions of false alarm or missing report are caused, and if the conditions cannot be found in advance, property economic loss is easily caused.
The traditional method generally adopts a threshold limiting condition method for fault monitoring of the gas sensor. This method does not allow for effective diagnostic discrimination of possible faults below a threshold. Meanwhile, the monitoring capability for the distribution of the equipment fault area and the performance data characteristics is lacked, so that the distribution rule of the equipment loss is difficult to obtain in time.
Disclosure of Invention
In view of the defects of the prior art, the invention aims to disclose an indoor gas monitoring fault analysis model, which is used for solving the problem that the prior art lacks the monitoring capability of a gas sensor on faults, and further economic property loss is caused by failure report of the faults.
To achieve the above and other related objects, the present invention discloses an indoor gas monitoring fault analysis model, which includes:
acquiring fault data of gas monitoring equipment, and extracting abnormal data in the fault data;
performing feature extraction on the abnormal data to form an original fault feature set, and performing dimensionless processing on the extracted data features;
performing cluster analysis on the extracted data characteristics respectively, and establishing a fault data set after classifying results;
and inputting the data to be monitored into a fault data set for similarity matching, analyzing and classifying faults, and acquiring a distribution rule of equipment fault loss.
In an embodiment of the present invention, the exception data includes: temperature anomaly data, humidity anomaly data, and gas volume concentration anomaly data.
In an embodiment of the present invention, in the step of obtaining the fault data of the gas monitoring equipment and extracting the abnormal data in the fault data, the step includes:
marking fault types in the collected gas monitoring equipment data, and respectively extracting temperature abnormal data, humidity abnormal data and gas concentration abnormal data;
establishing a correlation curve of temperature and time, a correlation curve of humidity and temperature and a correlation curve of gas concentration and time;
the time parameter is processed so that the time interval is 0 to 10.
In an embodiment of the present invention, the step of performing feature extraction on the abnormal data to form an original fault feature set, and performing dimensionless processing on the extracted data features includes:
processing each obtained curve, wherein the processing comprises calculating the mean value, the variance, the maximum value, the minimum value, the maximum difference value and the fluctuation rate of the curve;
carrying out data standardization processing on the mean value, the variance, the maximum value, the minimum value, the maximum difference value and the fluctuation rate of each curve to form a characteristic vector of the curve;
according to the feature vectors formed by the three curves, three original fault data sets composed of the feature vectors are established.
In an embodiment of the present invention, the method for calculating the fluctuation ratio includes: and averagely dividing the processed curve into ten equal parts, performing difference on ninety quantiles and ten quantiles in each data to obtain the fluctuation amplitude of the data, and taking the median of the fluctuation amplitudes of the ten fluctuation data as the fluctuation rate of the curve.
In an embodiment of the present invention, the step of performing cluster analysis on the extracted data features respectively, classifying the results, and then establishing the fault data set includes:
respectively applying a k-means + + clustering algorithm to the three original fault feature sets to perform clustering analysis;
marking the result obtained by the clustering analysis of each original fault feature set into different fault types, and respectively establishing fault data sets of temperature, humidity and gas concentration.
In an embodiment of the present invention, the step of performing cluster analysis on the three original fault feature sets by respectively applying a k-means + + clustering algorithm includes:
s311, each curve is represented by six features, and all the curves are taken as one point in a six-dimensional space to obtain a scatter diagram in the six-dimensional space;
s312, inputting a k value, wherein the k value is a preset number of desired fault classifications;
s313, randomly selecting a data point in a six-dimensional space as an initial clustering center;
s314, respectively calculating Euclidean distances D (x) of the rest data points to the initial clustering center;
s315, taking the relative size of the D (x) value of each point as the probability of selecting the next clustering center, and selecting the next clustering center by using a wheel disc selection method until k clustering centers are obtained;
s316, respectively calculating the Euclidean distance of each data point except the clustering center to each clustering center, and selecting the clustering center with the closest distance as a class;
s317, taking a median value of data point coordinates in each clustered class as a new clustering center of the class;
s318, repeating the step S316 and the step S317 until the new cluster center coordinates are not changed;
and S319, obtaining a final clustering result.
In an embodiment of the present invention, the step of inputting the data to be monitored into the fault data set for similarity matching, and performing fault analysis and classification includes:
carrying out feature extraction on data to be monitored to form an original fault feature set, and carrying out dimensionless processing on the extracted data features;
and when the Euclidean distance between the data point and a certain clustering center is close, obtaining the distribution rule of the equipment fault loss.
As described above, the invention discloses an indoor gas monitoring fault analysis model, which performs cluster analysis on data characteristics such as region distribution, model and the like of equipment faults through a k-means + + clustering algorithm to obtain a distribution rule of equipment fault loss. Based on the distribution rule of the equipment fault loss, the use state of the equipment can be predicted. The occurrence of related accidents can be effectively prevented, and the life and property safety of people can be guaranteed.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts
FIG. 1 is a schematic flow chart illustrating an exemplary method for analyzing a fault in an indoor gas monitoring system according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating the step S20 of the indoor gas monitoring fault analysis model according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating the step S30 of the indoor gas monitoring fault analysis model according to an embodiment of the present invention;
fig. 4 is a detailed flowchart of step S310 of an indoor gas monitoring fault analysis model according to an embodiment of the invention.
Detailed Description
The following embodiments of the present invention are provided by way of specific examples, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, amount and proportion of each component in actual implementation can be changed freely, and the layout of the components can be more complicated.
Referring to fig. 1, the invention discloses an indoor gas monitoring fault analysis model, which can be used for solving the problem that economic property loss is caused by failure report of faults due to the fact that the fault monitoring capability of a gas sensor is lacked in the prior art.
Specifically, the fault analysis model of the indoor gas monitoring equipment mainly monitors faults of the gas sensor through the following steps.
And S10, acquiring fault data of the gas monitoring equipment, and extracting abnormal data in the fault data. The abnormal data may include temperature abnormal data, humidity abnormal data and gas concentration abnormal data. It should be noted that it is permissible for the fault data to be acquired based on manual prior experience, or a threshold-defined method. Therefore, a related threshold value can be preset, and when the related data of the gas monitoring equipment does not meet the corresponding threshold value condition, the related data is judged to be abnormal data.
Specifically, the step S10 includes the steps of:
and S101, marking fault types in the collected gas monitoring equipment data, and respectively extracting temperature abnormal data, humidity abnormal data and gas concentration abnormal data.
S102, establishing a temperature and time correlation curve, a humidity and temperature correlation curve and a gas concentration and time correlation curve. Wherein, different time respectively corresponds to having temperature data, humidity data and gas concentration data.
And S103, processing the time parameter, and enabling the time interval to be 0-10. Since the durations of the three resulting curves may be different in step S102, the pass time parameter is set to a range of 1 to 10 to facilitate subsequent processing.
And executing the step S20, performing feature extraction on the abnormal data to form an original fault feature set, and performing dimensionless processing on the extracted data features. The abnormal data is subjected to feature extraction and non-dimensionalization processing, so that the abnormal data can be further analyzed.
Specifically, referring to fig. 2, in the process of executing step S20, it includes the steps of:
s201, processing each obtained curve, wherein the processing comprises calculating the mean value, the variance, the maximum value, the minimum value, the maximum difference value and the fluctuation rate of the curve. The calculation method of the fluctuation rate comprises the following steps: and averagely dividing the processed curve into ten equal parts, performing difference on ninety quantiles and ten quantiles in each data to obtain the fluctuation amplitude of the data, and taking the median of the fluctuation amplitudes of the ten fluctuation data as the fluctuation rate of the curve.
S202, carrying out data standardization processing on the mean value, the variance, the maximum value, the minimum value difference value and the fluctuation rate of each curve to form a characteristic vector of the curve.
And S203, establishing three original fault data sets consisting of the characteristic vectors according to the characteristic vectors formed by the three curves.
Therefore, by carrying out non-dimensionalization processing on the abnormal data, more detailed classification and analysis on the abnormal data are facilitated.
And step S30 is executed, the extracted data features are respectively subjected to clustering analysis, and a fault data set is established after results are classified. When performing cluster analysis on the extracted data features, the cluster analysis may be allowed to be performed by a k-means + + clustering algorithm. Specifically, the k-means + + clustering algorithm measures the relationship among all data in a data set by using a similarity measurement method, and divides data with close relationship into a set. The k-means + + clustering algorithm has the advantages of being easy to implement, simple in principle and high in clustering speed.
Referring to fig. 3 and 4, when performing cluster analysis on the extracted data features respectively, classifying the results, and then establishing a fault data set, the method may include the steps of:
s310, respectively applying a k-means + + clustering algorithm to the three original fault feature sets for clustering analysis. Specifically, when performing cluster analysis by a k-means + + clustering algorithm, the following steps may be included:
s311, each curve is represented by six features, and all the curves are taken as one point in a six-dimensional space to obtain a scatter diagram in the six-dimensional space;
s312, inputting a k value, wherein the k value is a preset number of desired fault classifications;
s313, randomly selecting a data point in a six-dimensional space as an initial clustering center;
s314, respectively calculating Euclidean distances D (x) of the rest data points to the initial clustering center;
s315, taking the relative size of the D (x) value of each point as the probability of selecting the next clustering center, and selecting the next clustering center by using a wheel disc selection method until k clustering centers are obtained;
s316, respectively calculating the Euclidean distance of each data point except the clustering center to each clustering center, and selecting the clustering center with the closest distance as a class;
s317, taking a median value from the data point coordinates in each clustered class as a new clustering center of the class;
s318, repeating the step S316 and the step S317 until the new cluster center coordinates do not change any more;
and S319, obtaining a final clustering result.
And S320, marking the result obtained by the clustering analysis of each original fault feature set into different fault types, and establishing a fault data set of temperature, humidity and gas concentration.
And finally, executing a step S40, inputting the data to be monitored into the fault data set for similarity matching, analyzing and classifying faults, and acquiring a distribution rule of equipment fault loss.
Specifically, after the monitoring data is obtained, feature extraction is performed on the data to be monitored to form an original fault feature set, and dimensionless processing is performed on the extracted data features. And then, inputting the data to be monitored into a fault data set for similarity matching, and analyzing and classifying the faults.
After carrying out dimensionless processing on the data to be monitored, judging whether the data point is close to the Euclidean distance of a certain clustering center: if so, obtaining the distribution rule of the equipment fault loss. And then effectively solve and lack the monitoring capability to the gas sensor to the trouble among the prior art, and then lead to because the problem of economic property loss that the failure was reported and is brought.
Therefore, the general distribution regularity of the equipment fault loss is accurately judged through the related algorithm, the occurrence of related accidents is effectively prevented, and the life and property safety of people is guaranteed.
In summary, the invention discloses an indoor gas monitoring fault analysis model, which performs cluster analysis on data characteristics such as region distribution, model and the like of equipment faults through a k-means + + clustering algorithm to obtain a distribution rule of equipment fault loss. Based on the distribution rule of the equipment fault loss, the use state of the equipment can be predicted. The occurrence of related accidents can be effectively prevented, and the life and property safety of people can be guaranteed. Therefore, the problem that the monitoring capability of the gas sensor on faults is lacked in the prior art, and economic property loss is caused by failure report of the faults is further solved.
Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (8)
1. An indoor gas monitoring fault analysis model, comprising:
acquiring fault data of gas monitoring equipment, and extracting abnormal data in the fault data;
performing feature extraction on the abnormal data to form an original fault feature set, and performing dimensionless processing on the extracted data features;
performing cluster analysis on the extracted data characteristics respectively, and establishing a fault data set after classifying results;
and inputting the data to be monitored into a fault data set for similarity matching, analyzing and classifying faults, and acquiring a distribution rule of equipment fault loss.
2. The indoor gas monitoring fault analysis model of claim 1, wherein the anomaly data comprises: temperature anomaly data, humidity anomaly data and gas-volumetric concentration anomaly data.
3. The indoor gas monitoring fault analysis model according to claim 1, wherein in the step of obtaining fault data of the gas monitoring equipment and extracting abnormal data in the fault data, the method comprises the following steps:
marking fault types in the collected gas monitoring equipment data, and respectively extracting temperature abnormal data, humidity abnormal data and gas concentration abnormal data;
establishing a correlation curve of temperature and time, a correlation curve of humidity and temperature and a correlation curve of gas concentration and time;
the time parameter is processed and the time interval is made 0 to 10.
4. The indoor gas monitoring fault analysis model according to claim 1, wherein the step of performing feature extraction on the abnormal data to form an original fault feature set, and performing dimensionless processing on the extracted data features comprises:
processing each obtained curve, wherein the processing comprises calculating the mean value, the variance, the maximum value, the minimum value, the maximum difference value and the fluctuation rate of the curve;
carrying out data standardization processing on the mean value, the variance, the maximum value, the minimum value, the maximum difference value and the fluctuation rate of each curve to form a characteristic vector of the curve;
according to the feature vectors formed by the three curves, three original fault data sets consisting of the feature vectors are established.
5. The indoor gas monitoring fault analysis model of claim 4, wherein the calculation method of the fluctuation rate comprises:
and averagely dividing the processed curve into ten equal parts, performing difference on ninety quantiles and ten quantiles in each data to obtain the fluctuation amplitude of the data, and taking the median of the fluctuation amplitudes of the ten fluctuation data as the fluctuation rate of the curve.
6. The indoor gas monitoring and fault analyzing model of claim 1, wherein in the step of performing cluster analysis on the extracted data features respectively, classifying the results and then establishing a fault data set, the method comprises the following steps:
respectively applying a k-means + + clustering algorithm to the three original fault feature sets to perform clustering analysis;
and marking the result obtained by the clustering analysis of each original fault feature set into different fault types, and respectively establishing fault data sets of temperature, humidity and gas concentration.
7. The indoor gas monitoring fault analysis model according to claim 6, wherein the step of performing cluster analysis on the three original fault feature sets by respectively applying a k-means + + clustering algorithm comprises:
s311, each curve is represented by six features, and all the curves are taken as one point in a six-dimensional space to obtain a scatter diagram in the six-dimensional space;
s312, inputting a k value, wherein the k value is a preset number of desired fault classifications;
s313, randomly selecting a data point in a six-dimensional space as an initial clustering center;
s314, respectively calculating Euclidean distances D (x) of the rest data points to the initial clustering center;
s315, taking the relative size of the D (x) value of each point as the probability of selecting the next clustering center, and selecting the next clustering center by using a wheel disc selection method until k clustering centers are obtained;
s316, respectively calculating the Euclidean distance of each data point except the clustering center to each clustering center, and selecting the clustering center with the closest distance to be classified as one type;
s317, taking a median value of data point coordinates in each clustered class as a new clustering center of the class;
s318, repeating the step S316 and the step S317 until the coordinates of the new cluster center do not change;
and S319, obtaining a final clustering result.
8. The indoor gas monitoring fault analysis model of claim 1, wherein in the step of performing similarity matching, fault analysis and classification on the data to be monitored which are also input into the fault data set, the method comprises the following steps:
performing feature extraction on data to be monitored to form an original fault feature set, and performing dimensionless processing on the extracted data features;
and when the Euclidean distance between the data point and a certain clustering center is close, obtaining the distribution rule of the equipment fault loss.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211611524.5A CN115964649A (en) | 2022-12-13 | 2022-12-13 | Indoor gas monitoring fault analysis model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211611524.5A CN115964649A (en) | 2022-12-13 | 2022-12-13 | Indoor gas monitoring fault analysis model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115964649A true CN115964649A (en) | 2023-04-14 |
Family
ID=87359132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211611524.5A Pending CN115964649A (en) | 2022-12-13 | 2022-12-13 | Indoor gas monitoring fault analysis model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115964649A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805065A (en) * | 2023-08-25 | 2023-09-26 | 山东荣信集团有限公司 | Intelligent management method for monitoring data of coal powder heating furnace burner |
-
2022
- 2022-12-13 CN CN202211611524.5A patent/CN115964649A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805065A (en) * | 2023-08-25 | 2023-09-26 | 山东荣信集团有限公司 | Intelligent management method for monitoring data of coal powder heating furnace burner |
| CN116805065B (en) * | 2023-08-25 | 2023-11-14 | 山东荣信集团有限公司 | Intelligent management method for monitoring data of coal powder heating furnace burner |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112580749B (en) | Intelligent fire detection method based on machine olfaction technology | |
| CN101738998B (en) | System and method for monitoring industrial process based on local discriminatory analysis | |
| CN116304766A (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
| CN113537321B (en) | Network flow anomaly detection method based on isolated forest and X mean value | |
| CN112966879A (en) | Environmental test chamber fault prediction method and device, computer equipment and storage medium | |
| CN115964649A (en) | Indoor gas monitoring fault analysis model | |
| CN110910615A (en) | Building fire alarm classification method and system | |
| CN109947815B (en) | Power theft identification method based on outlier algorithm | |
| US11331024B2 (en) | Calibration method for critical point of mental fatigue based on self-organized criticality | |
| CN113570200A (en) | Power grid operation state monitoring method and system based on multidimensional information | |
| Radja et al. | Performance evaluation of supervised machine learning algorithms using different data set sizes for diabetes prediction | |
| CN112906738A (en) | Water quality detection and treatment method | |
| CN113810792B (en) | Edge data acquisition and analysis system based on cloud computing | |
| Bo et al. | Recognition of control chart patterns in auto-correlated process based on random forest | |
| CN107704818A (en) | A kind of fire detection system based on video image | |
| CN110837953A (en) | Automatic abnormal entity positioning analysis method | |
| CN115659195A (en) | Online atmospheric pollution identification method | |
| CN111680572B (en) | Dynamic judgment method and system for power grid operation scene | |
| CN111523576B (en) | Density peak clustering outlier detection method suitable for electron quality detection | |
| Huang et al. | Outlier detection method based on improved two-step clustering algorithm and synthetic hypothesis testing | |
| CN113780354A (en) | Telemetry data anomaly identification method and device for dispatching automation master station system | |
| CN112422505A (en) | Network malicious traffic identification method based on high-dimensional extended key feature vector | |
| CN103440537A (en) | System state real-time evaluation method based on sample similarity ordering modeling | |
| CN117391458B (en) | Safety production risk detection and early warning method and system based on data analysis | |
| CN115237739B (en) | Analysis method, device and equipment for board card running environment and readable storage medium |
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 |