CN116702045A - Power supply room safety monitoring method and device based on multi-sensor data - Google Patents
Power supply room safety monitoring method and device based on multi-sensor data Download PDFInfo
- Publication number
- CN116702045A CN116702045A CN202310897620.9A CN202310897620A CN116702045A CN 116702045 A CN116702045 A CN 116702045A CN 202310897620 A CN202310897620 A CN 202310897620A CN 116702045 A CN116702045 A CN 116702045A
- Authority
- CN
- China
- Prior art keywords
- data
- power supply
- supply room
- target
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 167
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007635 classification algorithm Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000012800 visualization Methods 0.000 claims abstract description 9
- 238000010586 diagram Methods 0.000 claims description 49
- 230000000007 visual effect Effects 0.000 claims description 42
- 238000005070 sampling Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000013139 quantization Methods 0.000 claims description 12
- 238000012806 monitoring device Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 11
- 238000001914 filtration Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Computer Security & Cryptography (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to the technical field of artificial intelligence, and discloses a power supply room safety monitoring method and device based on multi-sensor data, wherein the method comprises the following steps: acquiring power supply room data of a target power supply room, and generating a topological graph of the target power supply room according to the power supply room data; performing monitoring site configuration on the target power supply room by using the topological graph to obtain configuration sites of the target power supply room; monitoring parameter configuration is carried out on the configuration site to obtain a parameter site of the configuration site; acquiring multi-sensing data of the target power supply room according to the parameter sites to obtain multi-sensing data of the target power supply room; carrying out data classification on the multi-sensing data according to a preset multi-target classification algorithm to obtain classified data of the multi-sensing data; and performing interface visualization processing on the classified data to obtain visualized data of the classified data, and performing safety monitoring on the target power supply room according to a preset alarm threshold and the visualized data. The application can improve the efficiency of safety monitoring of the power supply room.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a power supply room safety monitoring method and device based on multi-sensor data.
Background
The power supply house is an important facility in industrial production and is responsible for providing stable power supply to factories. Because high-voltage equipment, complicated electric circuits and a large number of electric equipment exist in a power supply room, safety monitoring is particularly important, and once the power supply room fails, short circuits or electric leakage and other problems occur, fire, explosion and even casualties can be caused, meanwhile, the power supply room is a core link of industrial production, and stable power supply is important for the continuity and stability of production.
The traditional power supply room safety monitoring system has the problems of large manual inspection workload, lack of real-time monitoring, limited monitoring means, difficult data processing and analysis, difficult fault diagnosis and the like, and the problems limit the efficiency of the monitoring system, so that how to improve the power supply room safety monitoring efficiency becomes a problem to be solved urgently.
Disclosure of Invention
The application provides a power supply room safety monitoring method and device based on multi-sensor data, and mainly aims to solve the problem of low efficiency in power supply room safety monitoring based on the multi-sensor data.
In order to achieve the above purpose, the application provides a power supply room safety monitoring method based on multi-sensor data, comprising the following steps:
acquiring power supply room data of a target power supply room, and generating a topological graph of the target power supply room according to the power supply room data;
performing monitoring site configuration on the target power supply room by using the topological graph to obtain configuration sites of the target power supply room;
monitoring parameter configuration is carried out on the configuration site to obtain a parameter site of the configuration site;
acquiring multi-sensing data of the target power supply room according to the parameter locus to obtain multi-sensing data of the target power supply room;
performing data classification on the multi-sensing data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensing data, wherein the preset multi-target classification algorithm is as follows:
wherein alpha is i Is the Lagrangian multiplier of the ith target feature generated from the multi-sensor data, i and j are the feature identities of the target features, n is the feature total number of the target features, alpha j Is the Lagrangian multiplier, x of the j-th said target feature i ·x j Is the point multiplication of the ith target feature and the jth target feature, y i Feature tag, y, which is the i-th target feature j Feature tag, x, being the jth target feature i Is the ith target feature, x j Is the jth target feature, max is the maximum function;
and performing interface visualization processing on the classified data to obtain visualized data of the classified data, and performing safety monitoring on the target power supply room according to a preset alarm threshold and the visualized data.
Optionally, the generating the topology map of the target power supply room according to the power supply room data includes:
carrying out structural data screening on the power supply room data to obtain structural data of the power supply room data;
generating an association relation of the structural data, and generating a power supply room structure diagram of the target power supply room according to the structural data and the association relation;
and carrying out component identification on the power supply room structure diagram according to the component data in the power supply room data to obtain a power supply room identification diagram of the power supply room structure diagram, and determining the power supply room identification diagram of the power supply room structure diagram as the topological diagram of the target power supply room.
Optionally, the performing component identification on the power supply room structure diagram according to component data in the power supply room data to obtain a power supply room identification diagram of the power supply room structure diagram includes:
component data screening is carried out on the power supply room data one by one according to a preset component tag, so that component data in the power supply room data are obtained;
generating a label identification of the preset component label, and carrying out data identification on the component data by utilizing the label identification to obtain identification data of the component data;
and carrying out component configuration on the power supply room structure diagram by utilizing the identification data to obtain a power supply room identification diagram of the power supply room structure diagram.
Optionally, the configuring the monitoring site for the target power supply room by using the topological graph to obtain the configuration site of the target power supply room includes:
performing monitoring position analysis on the topological graph according to a preset monitoring requirement to obtain a monitoring position of the topological graph;
and configuring the monitoring sites of the target power supply room according to the monitoring positions to obtain the configuration sites of the target power supply room.
Optionally, the monitoring parameter configuration is performed on the configuration site to obtain a parameter site of the configuration site, including:
determining a sensor type of the target power supply room according to the configuration site, and generating sensor parameters of the configuration site according to the sensor type;
and carrying out monitoring parameter configuration on the configuration sites one by one according to the sensor parameters to obtain the parameter sites of the configuration sites.
Optionally, the multi-sensor data acquisition is performed on the target power supply room according to the parameter site to obtain multi-sensor data of the target power supply room, including:
acquiring site data of the parameter sites one by using a preset sensor, and performing data sampling on the site data to obtain sampling data of the site data;
carrying out quantization processing on the sampling data to obtain quantized data of the sampling data;
and carrying out data encoding on the quantized data by using a preset encoding algorithm to obtain encoded data of the quantized data, wherein the preset encoding algorithm is as follows:
wherein T is the encoded data of the quantized data, round is a rounding function for converting floating point numbers into integers, p is the sampled data, V min Is the minimum sampling value, V max Is the maximum sampling value, N is the quantization grade number of the quantized data;
and determining the coded data as digital signals of the site data, and collecting the digital signals as multi-sensing data of the target power supply room.
Optionally, the classifying the multi-sensing data according to a preset multi-target classification algorithm to obtain classified data of the multi-sensing data includes:
carrying out data denoising on the multi-sensing data to obtain denoising data of the multi-sensing data;
carrying out vectorization conversion on the denoising data to obtain a data vector of the denoising data;
performing feature selection on the denoising data according to the data vector to obtain target features of the denoising data;
and carrying out feature classification on the target features by using a preset multi-target classification algorithm to obtain classification features of the target features, and generating classification data of the multi-sensor data according to the classification features.
Optionally, the performing interface visualization processing on the classification data to obtain visualized data of the classification data includes:
according to the time labels of the classified data, carrying out data sorting on the classified data to obtain a data sequence table of the classified data;
generating a data line graph of the classified data according to the data sequence table;
and carrying out visual display on the data line graph to obtain visual data of the classified data.
Optionally, the safety monitoring of the target power supply room according to a preset alarm threshold and the visual data includes:
setting a threshold line of a preset alarm threshold value on a visual interface of the visual data;
and generating a safety value of the target power supply room according to the threshold line and the data point of the visual data, and carrying out safety analysis on the target power supply room according to the safety value.
In order to solve the above problems, the present application further provides a power supply room safety monitoring device based on multi-sensor data, the device comprising:
the topological graph generation module is used for acquiring power supply room data of a target power supply room and generating a topological graph of the target power supply room according to the power supply room data;
the monitoring site configuration module is used for configuring the monitoring site of the target power supply room by utilizing the topological graph to obtain the configuration site of the target power supply room;
the monitoring parameter configuration module is used for carrying out monitoring parameter configuration on the configuration site to obtain a parameter site of the configuration site;
the multi-sensing data acquisition module is used for acquiring multi-sensing data of the target power supply room according to the parameter sites to obtain multi-sensing data of the target power supply room;
the multi-sensing data classification module is used for carrying out data classification on the multi-sensing data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensing data, wherein the preset multi-target classification algorithm is as follows:
wherein alpha is i Is the Lagrangian multiplier of the ith target feature generated from the multi-sensor data, i and j are the feature identities of the target features, n is the feature total number of the target features, alpha j Is the Lagrangian multiplier, x of the j-th said target feature i ·x j Is the point multiplication of the ith target feature and the jth target feature, y i Feature tag, y, which is the i-th target feature j Feature tag, x, being the jth target feature i Is the ith target feature, x j Is the jth target feature, max is the maximum function;
and the visual monitoring module is used for carrying out interface visual processing on the classified data to obtain visual data of the classified data, and carrying out safety monitoring on the target power supply room according to a preset alarm threshold and the visual data.
The embodiment of the application can clearly show the arrangement and interconnection relation of the devices in the power supply room by acquiring the power supply room data of the target power supply room and generating the topological graph according to the data, thus helping monitoring personnel to comprehensively understand the structure of the power supply room, leading the monitoring arrangement to be more reasonable and efficient, reducing the monitoring blind area, improving the monitoring efficiency, utilizing the generated topological graph, carrying out monitoring site configuration on the target power supply room, namely determining the proper position to install the monitoring device, covering a wider area by reasonably configuring the monitoring site, improving the comprehensiveness and accuracy of monitoring, reducing the situation of missing report and misinformation, carrying out monitoring parameter configuration on the configuration site, namely setting proper monitoring parameters, adjusting the accuracy and sensitivity of monitoring to the optimal state, leading different devices and monitoring requirements to possibly needing different parameter configuration, leading the configuration module to meet different monitoring requirements, acquiring multiple sensing data to provide more information and indexes, providing more reliable basis for subsequent judgment and analysis, carrying out automatic acquisition of multiple sensing data according to preset multiple target algorithms, leading the multiple sensing data and automatic acquisition data to be more efficient, leading the power supply information to be more visual, leading the monitoring risk to be more important to the safety of the monitoring information, filtering the monitoring information, leading the monitoring information to be more visual, filtering the monitoring risk to be more important, and more important to the safety and more important to the monitoring information, and the monitoring information is better perceived by the monitoring and has better visual performance, and has the safety and important safety and has the important monitoring performance, and has the safety and important performance, and is better than the monitoring and has the monitoring and is possible safety, therefore, the application provides the power supply room safety monitoring method and the device based on the multi-sensor data, which can solve the problem of lower power supply room safety monitoring efficiency.
Drawings
Fig. 1 is a flow chart of a power supply room safety monitoring method based on multi-sensor data according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a topology diagram of a generation target power supply room according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a multi-sensor data collection of a target power supply room according to an embodiment of the application;
FIG. 4 is a functional block diagram of a power supply room safety monitoring device based on multi-sensor data according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a power supply room safety monitoring method based on multi-sensor data. The execution main body of the power supply room safety monitoring method based on the multi-sensor data comprises at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the power supply room security monitoring method based on the multi-sensor data may be performed by software or hardware installed in the terminal device or the server device. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a power supply room security monitoring method based on multi-sensor data according to an embodiment of the application is shown. In this embodiment, the power supply room security monitoring method based on multi-sensor data includes:
s1, acquiring power supply room data of a target power supply room, and generating a topological graph of the target power supply room according to the power supply room data.
In the embodiment of the application, the generation of the topological graph of the target power supply room according to the power supply room data is to clearly show the structure, layout and connection mode of the power supply room, which provides a basis for subsequent monitoring, configuration and analysis.
In an embodiment of the present application, referring to fig. 2, the generating a topology map of the target power supply room according to the power supply room data includes:
s21, screening structural data of the power supply room data to obtain the structural data of the power supply room data;
s22, generating an association relation of the structural data, and generating a power supply room structure diagram of the target power supply room according to the structural data and the association relation;
s23, carrying out component identification on the power supply room structure diagram according to component data in the power supply room data to obtain a power supply room identification diagram of the power supply room structure diagram, and determining the power supply room identification diagram of the power supply room structure diagram as a topological diagram of the target power supply room.
In the embodiment of the present application, the step of performing structural data screening on the power supply room data refers to extracting data related to a power supply room structure, such as information of rooms, equipment, cables, etc., from the power supply room data; the generation of the association relationship of the structural data refers to determining the association relationship between each structural element, such as the connection relationship between equipment and a room, the connection relationship between a cable and the equipment, and the like, according to the structural data.
In detail, the power supply room structure diagram shows the layout and the connection mode of each element in the power supply room, so that the topology structure of the power supply room can be clearly shown; and identifying each component on a power supply room structure diagram according to the component data in the power supply room data so as to facilitate subsequent analysis and operation, wherein the component can be an element in a power supply room such as equipment, a cable, a switch and the like.
Further, after the components are identified, the power supply room structure diagram becomes an identification diagram of the power supply room, which shows the position and identification information of each component and the connection relationship between them.
In detail, the step of performing component identification on the power supply room structure diagram according to the component data in the power supply room data to obtain a power supply room identification diagram of the power supply room structure diagram includes:
component data screening is carried out on the power supply room data one by one according to a preset component tag, so that component data in the power supply room data are obtained;
generating a label identification of the preset component label, and carrying out data identification on the component data by utilizing the label identification to obtain identification data of the component data;
and carrying out component configuration on the power supply room structure diagram by utilizing the identification data to obtain a power supply room identification diagram of the power supply room structure diagram.
In the embodiment of the application, the preset component tags can be of equipment type, cable type, switch type and the like, and each component tag can be used for classifying and identifying component data; the screening of the component data can be performed according to the characteristics, attributes or other identifiers of the components; the data identification of the component data by using the tag identification can correlate a preset component tag with the component data, and mark or tag the component data.
In detail, the configuring the components of the power supply room structure diagram by using the identification data refers to positioning and identifying each component on the power supply room structure diagram according to the identification information of the component data, so as to ensure the correct position of each component in the diagram.
S2, performing monitoring site configuration on the target power supply room by using the topological graph to obtain configuration sites of the target power supply room.
In the embodiment of the present application, the configuring the monitoring site for the target power supply room by using the topology map to obtain the configuration site of the target power supply room includes:
performing monitoring position analysis on the topological graph according to a preset monitoring requirement to obtain a monitoring position of the topological graph;
and configuring the monitoring sites of the target power supply room according to the monitoring positions to obtain the configuration sites of the target power supply room.
In detail, the preset monitoring requirement may be a need to monitor power equipment, cable connection points, room temperature, etc.
In detail, the analyzing the monitoring position of the topology map to obtain the monitoring position of the topology map refers to determining a position or a node suitable for monitoring by examining the topology map, for example: and the positions to be monitored are found out by analyzing the association relation of the power equipment, the connection relation between the cable connection points and the rooms and the like.
In detail, the configuring the monitoring site of the target power supply room according to the monitoring position refers to selecting a proper position or node according to an analysis result, and configuring monitoring equipment, sensors, and the like, for example: and a temperature sensor, a humidity sensor, a current sensor and the like are arranged at corresponding monitoring positions.
In detail, the configuration sites are locations or nodes where monitoring devices have been installed or configured for real-time monitoring and data acquisition, and these configuration sites can be identified and recorded according to the locations or nodes on the topology graph.
In detail, the configuration of the monitoring sites of the target power supply room by using the topological graph can ensure that proper monitoring equipment is installed at a key position or node so as to monitor the state and data of the target power supply room in real time, and the determination of the configuration sites provides convenience for subsequent data acquisition and monitoring.
S3, monitoring parameter configuration is carried out on the configuration site, and the parameter site of the configuration site is obtained.
In the embodiment of the present application, the monitoring parameter configuration is performed on the configuration site to obtain a parameter site of the configuration site, including:
determining a sensor type of the target power supply room according to the configuration site, and generating sensor parameters of the configuration site according to the sensor type;
and carrying out monitoring parameter configuration on the configuration sites one by one according to the sensor parameters to obtain the parameter sites of the configuration sites.
In detail, the determining the sensor type of the target power supply room according to the configuration site refers to selecting an appropriate sensor type according to the monitoring requirement and the characteristics of the target power supply room, for example: a temperature sensor, a humidity sensor, a current sensor, and the like; the sensor parameters comprise sampling frequency, measuring range, accuracy and the like of the sensor, and corresponding parameter values are set according to the characteristics of different sensor types.
In detail, the step of configuring the monitoring parameters of the configuration sites one by one according to the sensor parameters means that monitoring devices or sensors on the sites are configured according to the sensor parameters, so as to ensure that the monitoring devices or sensors work according to preset parameters, for example: the sampling frequency, temperature range, etc. of the sensor are configured according to the parameters of the temperature sensor.
In detail, the parameter site represents a site where the monitoring parameter has been configured, and can be identified and recorded according to the location or node.
And S4, acquiring multi-sensing data of the target power supply room according to the parameter sites to obtain the multi-sensing data of the target power supply room.
In the embodiment of the present application, referring to fig. 3, the multi-sensor data acquisition is performed on the target power supply room according to the parameter location to obtain multi-sensor data of the target power supply room, including:
s31, acquiring site data of the parameter sites one by using a preset sensor, and performing data sampling on the site data to obtain sampling data of the site data;
s32, carrying out quantization processing on the sampling data to obtain quantized data of the sampling data;
s33, carrying out data encoding on the quantized data by using a preset encoding algorithm to obtain encoded data of the quantized data, wherein the preset encoding algorithm is as follows:
wherein T is the encoded data of the quantized data, round is a rounding function for converting floating point numbers into integers, p is the sampled data, V min Is the minimum sampling value, V max Is the maximum sampling value, N is the quantization grade number of the quantized data;
s34, determining the coded data as digital signals of the site data, and collecting the digital signals as multi-sensor data of the target power supply room.
In detail, the step of acquiring the site data of the parameter sites one by using a preset sensor means that corresponding sensor data is acquired according to configured monitoring equipment or sensors, for example, temperature data is acquired by a temperature sensor, humidity data is acquired by a humidity sensor, and the like.
In detail, the purpose of the data sampling is to convert continuously changing sensor data into discrete data points, which is convenient for subsequent processing and analysis; the quantization processing of the sampled data refers to mapping a continuous data range to discrete quantization levels, which can be processed according to a preset quantization level number and data range, and common quantization methods include linear quantization, nonlinear quantization, and the like.
In detail, after the digital signals of which the coded data are the site data are determined, the digital signals of all sites are collected to form multi-sensing data of the target power supply room, the data represent monitoring values of different sites, and comprehensive understanding of the state and performance of all positions of the power supply room is provided.
And S5, carrying out data classification on the multi-sensing data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensing data.
In an embodiment of the present application, the data classification of the multi-sensor data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensor data includes:
carrying out data denoising on the multi-sensing data to obtain denoising data of the multi-sensing data;
carrying out vectorization conversion on the denoising data to obtain a data vector of the denoising data;
performing feature selection on the denoising data according to the data vector to obtain target features of the denoising data;
and carrying out feature classification on the target features by using a preset multi-target classification algorithm to obtain classification features of the target features, and generating classification data of the multi-sensor data according to the classification features.
In detail, the data denoising of the multi-sensor data refers to removing noise or abnormal values in the data to obtain denoising data, and various signal processing or statistical techniques such as filtering, smoothing and the like can be used.
In detail, the vectorizing conversion of the denoising data refers to merging a plurality of sensing data into one data vector for subsequent processing and analysis, for example: the sensing data of temperature, humidity, current and the like are combined into a multidimensional vector, and the three sensors are assumed to be used for respectively measuring the temperature, the humidity and the current. Assume that the measurement results of each sensor are T, H and I, respectively. We can combine these three values into one three-dimensional vector: v= [ T, H, I ].
In detail, the data feature selection is a process of selecting features related to a monitoring target according to a data vector, and after vectorization conversion, we obtain a vector containing a plurality of features. However, not all features have importance or relevance to the monitoring target, and thus, the purpose of data feature selection is to select features related to the monitoring target from among the features for subsequent processing and classification; feature selection may be based on importance, relevance, or other pre-set criteria of the features, such as: a statistical analysis method, such as a correlation coefficient or mutual information, may be used to measure the degree of correlation between the feature and the monitored object, and based on these indices, a feature having a higher correlation or importance may be selected as the relevant feature of the monitored object.
In detail, the preset multi-objective classification algorithm is as follows:
wherein alpha is i Is the Lagrangian multiplier of the ith target feature generated from the multi-sensor data, i and j are the feature identities of the target features, n is the feature total number of the target features, alpha j Is the Lagrangian multiplier, x of the j-th said target feature i ·x j Is the point multiplication of the ith target feature and the jth target feature, y i Feature tag, y, which is the i-th target feature j Feature tag, x, being the jth target feature i Is the ith target feature, x j Is the j-th target feature and max is the maximum function.
Further, in the multi-sensor data, the measurement result of each sensor can be regarded as a target feature, and x in the preset multi-target classification algorithm i Representing the ith target feature, e.g. temperature, humidity, current, etc., each target feature having a corresponding feature tag y j The signature describes the state or class represented by the target feature, e.g., normal and abnormal may be used as the signature of the temperature sensor.
In detail, the Lagrangian multiplier is used to represent the importance of the target featureOr the weight, the influence of different target features in classification can be adjusted by adjusting the value of the Lagrange multiplier; x is x i ·x j Is a point multiplication of the i-th target feature and the j-th target feature, where the point multiplication operation is used to calculate a correlation or similarity between different target features.
In detail, the preset multi-target classification algorithm is to adjust the value of the Lagrangian multiplier to maximize the sum of the products of the point multiplication of the target features and the feature labels, and classify the multi-sensor data and identify states or categories represented by different target features by maximizing the value.
S6, performing interface visualization processing on the classified data to obtain visualized data of the classified data, and performing safety monitoring on the target power supply room according to a preset alarm threshold and the visualized data.
In the embodiment of the application, the interface visualization processing is performed on the classified data, so that monitoring personnel can intuitively know the change condition of the classified data. This helps to discover anomalies or trends in time and supports security monitoring and decision making of the power house.
In an embodiment of the present application, the performing interface visualization processing on the classification data to obtain visualized data of the classification data includes:
according to the time labels of the classified data, carrying out data sorting on the classified data to obtain a data sequence table of the classified data;
generating a data line graph of the classified data according to the data sequence table;
and carrying out visual display on the data line graph to obtain visual data of the classified data.
In detail, the sorting of the classified data according to the time tag of the classified data can ensure that the data are presented according to time sequence during visual display, so that monitoring and analysis are convenient; the data sequence list organizes the classified data into a list structure according to time sequence, and each data item comprises a time tag and corresponding monitoring data.
In detail, the data line graph is a common visualization mode, and by taking time as an abscissa and monitoring data as an ordinate, each data point is connected by a broken line, and the trend of the monitoring data changing along with time is reflected.
In detail, the visual display of the data line graph may use a chart library or visual tool to present the data line graph on an interface in an intuitive manner, and the visual display may include horizontal coordinates, vertical coordinates, data point display, broken line patterns, etc., so that a user can clearly observe and analyze trends and changes of classified data.
In an embodiment of the present application, the performing security monitoring on the target power supply room according to a preset alarm threshold and the visual data includes:
setting a threshold line of a preset alarm threshold value on a visual interface of the visual data;
and generating a safety value of the target power supply room according to the threshold line and the data point of the visual data, and carrying out safety analysis on the target power supply room according to the safety value.
In detail, the threshold line is a horizontal line, and is used for representing the limit of a preset alarm threshold, the threshold may be the upper limit or the lower limit of a certain monitoring parameter, and when the threshold is exceeded, the potential safety risk or abnormal situation exists.
In detail, the generating the safety value of the target power supply room according to the threshold line and the data point of the visual data refers to comparing the threshold line with the data point of the visual data, judging whether each data point exceeds or is lower than a preset alarm threshold, and generating the safety value of the target power supply room according to a judging result, wherein the safety value can be a binary value (for example, 0 represents normal, 1 represents abnormal) or a numerical safety score or grade, and reflects the safety state of the target power supply room.
In detail, the safety analysis of the target power supply room according to the safety value means that corresponding measures can be taken for different safety value conditions, such as triggering an alarm, generating a safety report or providing a real-time safety suggestion.
The embodiment of the application can clearly show the arrangement and interconnection relation of the devices in the power supply room by acquiring the power supply room data of the target power supply room and generating the topological graph according to the data, thus helping monitoring personnel to comprehensively understand the structure of the power supply room, leading the monitoring arrangement to be more reasonable and efficient, reducing the monitoring blind area, improving the monitoring efficiency, utilizing the generated topological graph, carrying out monitoring site configuration on the target power supply room, namely determining the proper position to install the monitoring device, covering a wider area by reasonably configuring the monitoring site, improving the comprehensiveness and accuracy of monitoring, reducing the situation of missing report and misinformation, carrying out monitoring parameter configuration on the configuration site, namely setting proper monitoring parameters, adjusting the accuracy and sensitivity of monitoring to the optimal state, leading different devices and monitoring requirements to possibly needing different parameter configuration, leading the configuration module to meet different monitoring requirements, acquiring multiple sensing data to provide more information and indexes, providing more reliable basis for subsequent judgment and analysis, carrying out automatic acquisition of multiple sensing data according to preset multiple target algorithms, leading the multiple sensing data and automatic acquisition data to be more efficient, leading the power supply information to be more visual, leading the monitoring risk to be more important to the safety of the monitoring information, filtering the monitoring information, leading the monitoring information to be more visual, filtering the monitoring risk to be more important, and more important to the safety and more important to the monitoring information, and the monitoring information is better perceived by the monitoring and has better visual performance, and has the safety and important safety and has the important monitoring performance, and has the safety and important performance, and is better than the monitoring and has the monitoring and is possible safety, therefore, the application provides the power supply room safety monitoring method based on the multi-sensor data, which can solve the problem of lower power supply room safety monitoring efficiency.
Fig. 4 is a functional block diagram of a power supply room safety monitoring device based on multi-sensor data according to an embodiment of the present application.
The power supply room safety monitoring device 100 based on the multi-sensor data can be installed in electronic equipment. Depending on the functions implemented, the power supply room safety monitoring device 100 based on the multi-sensor data may include a topology map generation module 101, a monitoring site configuration module 102, a monitoring parameter configuration module 103, a multi-sensor data acquisition module 104, a multi-sensor data classification module 105, and a visual monitoring module 106. The module of the application, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the topological graph generation module 101 is configured to obtain power supply room data of a target power supply room, and generate a topological graph of the target power supply room according to the power supply room data;
the monitoring site configuration module 102 is configured to perform monitoring site configuration on the target power supply room by using the topological graph to obtain a configuration site of the target power supply room;
the monitoring parameter configuration module 103 is configured to perform monitoring parameter configuration on the configuration site to obtain a parameter site of the configuration site;
the multi-sensing data acquisition module 104 is configured to acquire multi-sensing data of the target power supply room according to the parameter location, so as to obtain multi-sensing data of the target power supply room;
the multi-sensing data classification module 105 is configured to perform data classification on the multi-sensing data according to a preset multi-target classification algorithm, so as to obtain classification data of the multi-sensing data, where the preset multi-target classification algorithm is:
wherein alpha is i Is the Lagrangian multiplier of the ith target feature generated from the multi-sensor data, i and j are the feature identities of the target features, n is the feature total number of the target features, alpha j Is the j thLagrangian multiplier, x of the target feature i ·x j Is the point multiplication of the ith target feature and the jth target feature, y i Feature tag, y, which is the i-th target feature j Feature tag, x, being the jth target feature i Is the ith target feature, x j Is the jth target feature, max is the maximum function;
the visual monitoring module 106 is configured to perform interface visual processing on the classified data to obtain visual data of the classified data, and perform security monitoring on the target power supply room according to a preset alarm threshold and the visual data.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Claims (10)
1. A power supply room safety monitoring method based on multi-sensor data, the method comprising:
acquiring power supply room data of a target power supply room, and generating a topological graph of the target power supply room according to the power supply room data;
performing monitoring site configuration on the target power supply room by using the topological graph to obtain configuration sites of the target power supply room;
monitoring parameter configuration is carried out on the configuration site to obtain a parameter site of the configuration site;
acquiring multi-sensing data of the target power supply room according to the parameter locus to obtain multi-sensing data of the target power supply room;
performing data classification on the multi-sensing data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensing data, wherein the preset multi-target classification algorithm is as follows:
wherein alpha is i Is the Lagrangian multiplier of the ith target feature generated from the multi-sensor data, i and j are the feature identities of the target features, n is the feature total number of the target features, alpha j Is the Lagrangian multiplier, x of the j-th said target feature i ·x j Is the point multiplication of the ith target feature and the jth target feature, y i Feature tag, y, which is the i-th target feature j Feature tag, x, being the jth target feature i Is the ith target feature, x j Is the jth target feature, max is the maximum function;
and performing interface visualization processing on the classified data to obtain visualized data of the classified data, and performing safety monitoring on the target power supply room according to a preset alarm threshold and the visualized data.
2. The power supply room safety monitoring method based on multi-sensor data according to claim 1, wherein the generating the topology map of the target power supply room according to the power supply room data comprises:
carrying out structural data screening on the power supply room data to obtain structural data of the power supply room data;
generating an association relation of the structural data, and generating a power supply room structure diagram of the target power supply room according to the structural data and the association relation;
and carrying out component identification on the power supply room structure diagram according to the component data in the power supply room data to obtain a power supply room identification diagram of the power supply room structure diagram, and determining the power supply room identification diagram of the power supply room structure diagram as the topological diagram of the target power supply room.
3. The method for monitoring the safety of the power supply room based on the multi-sensor data according to claim 2, wherein the step of performing component identification on the power supply room structure diagram according to the component data in the power supply room data to obtain a power supply room identification diagram of the power supply room structure diagram comprises the following steps:
component data screening is carried out on the power supply room data one by one according to a preset component tag, so that component data in the power supply room data are obtained;
generating a label identification of the preset component label, and carrying out data identification on the component data by utilizing the label identification to obtain identification data of the component data;
and carrying out component configuration on the power supply room structure diagram by utilizing the identification data to obtain a power supply room identification diagram of the power supply room structure diagram.
4. The power supply room safety monitoring method based on multi-sensor data according to claim 1, wherein the performing monitoring site configuration on the target power supply room by using the topological graph to obtain the configuration site of the target power supply room comprises:
performing monitoring position analysis on the topological graph according to a preset monitoring requirement to obtain a monitoring position of the topological graph;
and configuring the monitoring sites of the target power supply room according to the monitoring positions to obtain the configuration sites of the target power supply room.
5. The power supply room safety monitoring method based on multi-sensor data according to claim 1, wherein the monitoring parameter configuration is performed on the configuration site to obtain a parameter site of the configuration site, and the method comprises the following steps:
determining a sensor type of the target power supply room according to the configuration site, and generating sensor parameters of the configuration site according to the sensor type;
and carrying out monitoring parameter configuration on the configuration sites one by one according to the sensor parameters to obtain the parameter sites of the configuration sites.
6. The power supply room safety monitoring method based on multi-sensor data according to claim 1, wherein the multi-sensor data acquisition is performed on the target power supply room according to the parameter site to obtain the multi-sensor data of the target power supply room, and the method comprises the following steps:
acquiring site data of the parameter sites one by using a preset sensor, and performing data sampling on the site data to obtain sampling data of the site data;
carrying out quantization processing on the sampling data to obtain quantized data of the sampling data;
and carrying out data encoding on the quantized data by using a preset encoding algorithm to obtain encoded data of the quantized data, wherein the preset encoding algorithm is as follows:
wherein T is the encoded data of the quantized data, round is a rounding function for converting floating point numbers into integers, p is the sampled data, V min Is the minimum sampling value, V max Is the maximum sampling value, N is the quantization grade number of the quantized data;
and determining the coded data as digital signals of the site data, and collecting the digital signals as multi-sensing data of the target power supply room.
7. The power supply room safety monitoring method based on multi-sensor data according to claim 1, wherein the data classification of the multi-sensor data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensor data comprises:
carrying out data denoising on the multi-sensing data to obtain denoising data of the multi-sensing data;
carrying out vectorization conversion on the denoising data to obtain a data vector of the denoising data;
performing feature selection on the denoising data according to the data vector to obtain target features of the denoising data;
and carrying out feature classification on the target features by using a preset multi-target classification algorithm to obtain classification features of the target features, and generating classification data of the multi-sensor data according to the classification features.
8. The power supply room safety monitoring method based on multi-sensor data according to claim 1, wherein the performing interface visualization processing on the classification data to obtain visualized data of the classification data comprises:
according to the time labels of the classified data, carrying out data sorting on the classified data to obtain a data sequence table of the classified data;
generating a data line graph of the classified data according to the data sequence table;
and carrying out visual display on the data line graph to obtain visual data of the classified data.
9. The multi-sensor data based power house security monitoring method according to any one of claims 1 to 8, wherein the security monitoring of the target power house according to a preset alarm threshold and the visualized data comprises:
setting a threshold line of a preset alarm threshold value on a visual interface of the visual data;
and generating a safety value of the target power supply room according to the threshold line and the data point of the visual data, and carrying out safety analysis on the target power supply room according to the safety value.
10. A power house safety monitoring device based on multi-sensor data, the device comprising:
the topological graph generation module is used for acquiring power supply room data of a target power supply room and generating a topological graph of the target power supply room according to the power supply room data;
the monitoring site configuration module is used for configuring the monitoring site of the target power supply room by utilizing the topological graph to obtain the configuration site of the target power supply room;
the monitoring parameter configuration module is used for carrying out monitoring parameter configuration on the configuration site to obtain a parameter site of the configuration site;
the multi-sensing data acquisition module is used for acquiring multi-sensing data of the target power supply room according to the parameter sites to obtain multi-sensing data of the target power supply room;
the multi-sensing data classification module is used for carrying out data classification on the multi-sensing data according to a preset multi-target classification algorithm to obtain classification data of the multi-sensing data, wherein the preset multi-target classification algorithm is as follows:
wherein alpha is i Is the Lagrangian multiplier of the ith target feature generated from the multi-sensor data, i and j are the feature identities of the target features, n is the feature total number of the target features, alpha j Is the Lagrangian multiplier, x of the j-th said target feature i ·x j Is the point multiplication of the ith target feature and the jth target feature, y i Feature tag, y, which is the i-th target feature j Feature tag, x, being the jth target feature i Is the ith target feature, x j Is the jth target feature, max is the maximum function;
and the visual monitoring module is used for carrying out interface visual processing on the classified data to obtain visual data of the classified data, and carrying out safety monitoring on the target power supply room according to a preset alarm threshold and the visual data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897620.9A CN116702045A (en) | 2023-07-20 | 2023-07-20 | Power supply room safety monitoring method and device based on multi-sensor data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897620.9A CN116702045A (en) | 2023-07-20 | 2023-07-20 | Power supply room safety monitoring method and device based on multi-sensor data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116702045A true CN116702045A (en) | 2023-09-05 |
Family
ID=87845336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310897620.9A Pending CN116702045A (en) | 2023-07-20 | 2023-07-20 | Power supply room safety monitoring method and device based on multi-sensor data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702045A (en) |
-
2023
- 2023-07-20 CN CN202310897620.9A patent/CN116702045A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111768082A (en) | Power equipment state evaluation method based on big data analysis | |
| CN115170000B (en) | Remote monitoring method and system based on electric energy meter communication module | |
| CN109034400B (en) | Transformer substation abnormal measurement data prediction platform system | |
| JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
| CN115578015A (en) | Sewage treatment overall process supervision method and system based on Internet of things and storage medium | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN115640860B (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
| CN112464439A (en) | Three-layer data mining-based power system fault type analysis method and device | |
| CN111999591B (en) | Method for identifying abnormal state of primary equipment of power distribution network | |
| CN117041029A (en) | Network equipment fault processing method and device, electronic equipment and storage medium | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN117277566B (en) | Power grid data analysis power dispatching system and method based on big data | |
| CN117110794A (en) | Intelligent diagnosis system and method for cable faults | |
| CN117421994A (en) | Edge application health monitoring method and system | |
| CN117194171A (en) | Heterogeneous cloud resource panoramic anomaly detection system | |
| CN117235617A (en) | ML-RFKNN-based photovoltaic array fault diagnosis method in sand and dust weather | |
| CN116881661A (en) | Performance automatic analysis method and system based on low-voltage power capacitor | |
| CN116845863A (en) | Terminal power grid abnormal equipment access alarm method and device based on space-time track | |
| CN112016739A (en) | Fault detection method and device, electronic equipment and storage medium | |
| CN116702045A (en) | Power supply room safety monitoring method and device based on multi-sensor data | |
| Jingyu et al. | Statistical analysis of distribution network fault information based on multi-source heterogeneous data mining | |
| CN117171176B (en) | Electricity consumption big data self-upgrading supervision platform based on artificial intelligence | |
| CN114743089B (en) | Image recognition GIS fault diagnosis device and method based on SSA-SVM | |
| CN117973697B (en) | Efficient data processing method for electric power layout device | |
| CN109257206A (en) | A kind of method of data inputting and evaluation diagnostic message feedback |
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 |