CN117455246A

CN117455246A - Electric fire risk dynamic early warning method and system based on edge calculation

Info

Publication number: CN117455246A
Application number: CN202311785114.7A
Authority: CN
Inventors: 李学钧; 戴相龙; 王晓鹏; 蒋勇; 何成虎
Original assignee: Jiangsu Haohan Information Technology Co ltd
Current assignee: Jiangsu Haohan Information Technology Co ltd
Priority date: 2023-12-25
Filing date: 2023-12-25
Publication date: 2024-01-26
Anticipated expiration: 2043-12-25
Also published as: CN117455246B

Abstract

The disclosure provides an electrical fire risk dynamic early warning method and system based on edge calculation, and relates to the technical field of risk early warning, wherein the method comprises the following steps: acquiring a plurality of scale sequences and a plurality of susceptibility sequences; configuring a scheme for risk monitoring of a plurality of electrical devices at a plurality of edge ends or cloud ends to obtain a configuration result sequence; constructing a plurality of risk analyzers to be configured in a plurality of edge ends and cloud ends; acquiring an edge risk parameter set sequence and a cloud risk parameter set sequence; obtaining a marginal risk parameter field sequence and a cloud risk parameter field sequence; generating an early warning scheme for operators, carrying out early warning, solving the technical problem that the efficiency of electric fire risk early warning is low because of low monitoring analysis accuracy and efficiency of electric equipment in the prior art, realizing the aim of improving the monitoring analysis accuracy and efficiency of the electric equipment and achieving the technical effect of improving the efficiency of electric fire risk early warning.

Description

Electric fire risk dynamic early warning method and system based on edge calculation

Technical Field

The disclosure relates to the technical field of risk early warning, in particular to an electrical fire risk dynamic early warning method and system based on edge calculation.

Background

As the application of intelligent electrical equipment becomes wider, the fire safety problem of the electrical equipment becomes more and more serious. At present, the existing electric fire risk early warning mainly monitors an electric circuit in real time, utilizes a big data analysis function to analyze the safety of monitoring data, and performs early warning when detecting monitoring data exceeding a safety threshold preset by a system, however, as electric equipment becomes larger and higher in complexity, the traditional big data analysis function is lower in accuracy and efficiency of analyzing the safety of the monitoring data, so that the efficiency of electric fire risk early warning is lower, and potential safety hazards are caused. Therefore, a method for dynamic early warning of electrical fire risk is needed to solve the above problems.

In summary, in the prior art, the monitoring and analyzing accuracy and efficiency of the electrical equipment are low, so that the efficiency of early warning of electrical fire risks is low.

Disclosure of Invention

The disclosure provides an electrical fire risk dynamic early warning method and system based on edge calculation, which are used for solving the technical problem that the efficiency of electrical fire risk early warning is low due to low monitoring analysis accuracy and efficiency of electrical equipment in the prior art.

According to a first aspect of the present disclosure, there is provided an electrical fire risk dynamic early warning method based on edge calculation, including: acquiring electrical characteristic parameters of a plurality of electrical devices in a target area to be subjected to electrical fire risk in a plurality of time nodes within a preset time range in the future, obtaining a plurality of electrical characteristic parameter sequences, and carrying out scale analysis and susceptibility analysis of fire occurrence of the electrical devices to obtain a plurality of scale sequences and a plurality of susceptibility sequences, wherein the electrical characteristic parameters comprise installation position temperature and electrical power; the monitoring configuration unit is used for configuring a scheme for risk monitoring of the plurality of electrical devices at the plurality of edge ends or cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences, so as to obtain a configuration result sequence; constructing a plurality of risk analyzers for analyzing electrical operation parameters of the plurality of electrical devices in a fire risk manner, and configuring the risk analyzers in the plurality of edge ends and the cloud end according to the configuration result sequence; acquiring a plurality of electrical operation parameters of the plurality of electrical devices when the plurality of time nodes are reached through a dynamic monitoring unit, and performing risk analysis based on a cloud end and a plurality of edge ends according to the configuration result sequence to obtain an edge end risk parameter set sequence and a cloud end risk parameter set sequence; performing risk parameter field rendering based on the edge-side risk parameter set sequence and the cloud risk parameter set sequence, correcting rendering parameters according to the plurality of scale sequences and the plurality of susceptibility sequences, obtaining an edge risk parameter field sequence and a cloud risk parameter field sequence, and displaying at a plurality of time nodes; and acquiring movement rule information of the operator in the target area, combining the edge risk parameter field sequence and the cloud risk parameter field sequence, and generating an early warning scheme for the operator at the plurality of time nodes to perform early warning.

According to a second aspect of the present disclosure, there is provided an electrical fire risk dynamic early warning system based on edge calculation, comprising: the system comprises a scale sequence acquisition module, a power generation module and a power generation module, wherein the scale sequence acquisition module is used for acquiring electrical characteristic parameters of a plurality of electrical devices in a target area to be subjected to electrical fire risk in a plurality of time nodes within a future preset time range, acquiring a plurality of electrical characteristic parameter sequences, and carrying out scale analysis and susceptibility analysis of the electrical devices on the occurrence of fire, so as to acquire a plurality of scale sequences and a plurality of susceptibility sequences, wherein the electrical characteristic parameters comprise installation position temperature and electrical power; the configuration result sequence obtaining module is used for obtaining a configuration result sequence by monitoring a configuration unit and respectively configuring a scheme of risk monitoring of the plurality of electrical devices at the plurality of edge ends or cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences; the risk analyzer configuration modules are used for constructing a plurality of risk analyzers for carrying out electrical operation parameter fire risk analysis on the plurality of electrical equipment and are configured in the plurality of edge ends and the cloud according to the configuration result sequence; the cloud risk parameter set sequence obtaining module is used for collecting a plurality of electrical operation parameters of the plurality of electrical devices through the dynamic monitoring unit when the plurality of time nodes are reached, and carrying out risk analysis based on a cloud end and a plurality of edge ends according to the configuration result sequence to obtain an edge end risk parameter set sequence and a cloud end risk parameter set sequence; the edge risk parameter field sequence obtaining module is used for rendering a risk parameter field based on the edge end risk parameter set sequence and the cloud risk parameter set sequence, correcting rendering parameters according to the plurality of scale sequences and the plurality of susceptibility sequences, obtaining an edge risk parameter field sequence and a cloud risk parameter field sequence, and displaying at a plurality of time nodes; the early warning scheme obtaining module is used for obtaining movement rule information of operators in the target area, combining the edge risk parameter field sequence and the cloud risk parameter field sequence, and generating early warning schemes for the operators at the plurality of time nodes to perform early warning.

One or more technical solutions provided in the present disclosure have at least the following technical effects or advantages: according to the method, in a plurality of time nodes in a future preset time range, electrical characteristic parameters of a plurality of electrical devices in a target area to be subjected to electrical fire risk are acquired, a plurality of electrical characteristic parameter sequences are obtained, scale analysis and susceptibility analysis of fire occurrence of the electrical devices are carried out, and a plurality of scale sequences and a plurality of susceptibility sequences are obtained, wherein the electrical characteristic parameters comprise installation position temperature and electrical power; the monitoring configuration unit is used for configuring a scheme for risk monitoring of the plurality of electrical devices at the plurality of edge ends or cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences, so as to obtain a configuration result sequence; constructing a plurality of risk analyzers for analyzing electrical operation parameters of the plurality of electrical devices in a fire risk manner, and configuring the risk analyzers in the plurality of edge ends and the cloud end according to the configuration result sequence; acquiring a plurality of electrical operation parameters of the plurality of electrical devices when the plurality of time nodes are reached through a dynamic monitoring unit, and performing risk analysis based on a cloud end and a plurality of edge ends according to the configuration result sequence to obtain an edge end risk parameter set sequence and a cloud end risk parameter set sequence; performing risk parameter field rendering based on the edge-side risk parameter set sequence and the cloud risk parameter set sequence, correcting rendering parameters according to the plurality of scale sequences and the plurality of susceptibility sequences, obtaining an edge risk parameter field sequence and a cloud risk parameter field sequence, and displaying at a plurality of time nodes; the method comprises the steps of acquiring movement rule information of operators in a target area, combining the edge risk parameter field sequence and the cloud risk parameter field sequence, generating an early warning scheme for the operators at a plurality of time nodes, and carrying out early warning, so that the technical problem that the efficiency of electric fire risk early warning is low due to low monitoring analysis accuracy and efficiency of electric equipment in the prior art is solved, the aim of improving the monitoring analysis accuracy and efficiency of the electric equipment is fulfilled, and the technical effect of improving the efficiency of the electric fire risk early warning is achieved.

It should be understood that the description of this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

For a clearer description of the present disclosure or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described, it being obvious that the drawings in the description below are only exemplary and that other drawings may be obtained, without inventive effort, by a person skilled in the art, from the provided drawings.

Fig. 1 is a schematic flow chart of an electrical fire risk dynamic early warning method based on edge calculation according to an embodiment of the disclosure;

fig. 2 is a schematic structural diagram of an electrical fire risk dynamic early warning system based on edge calculation according to an embodiment of the disclosure.

Reference numerals illustrate: the system comprises a scale sequence obtaining module 11, a configuration result sequence obtaining module 12, a plurality of risk analyzers configuration modules 13, a cloud risk parameter set sequence obtaining module 14, a marginal risk parameter field sequence obtaining module 15 and an early warning scheme obtaining module 16.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Example 1

The embodiment of the disclosure provides an edge calculation-based dynamic early warning method for electrical fire risk, which is described with reference to fig. 1, and includes:

acquiring electrical characteristic parameters of a plurality of electrical devices in a target area to be subjected to electrical fire risk in a plurality of time nodes within a preset time range in the future, obtaining a plurality of electrical characteristic parameter sequences, and carrying out scale analysis and susceptibility analysis of fire occurrence of the electrical devices to obtain a plurality of scale sequences and a plurality of susceptibility sequences, wherein the electrical characteristic parameters comprise installation position temperature and electrical power;

specifically, the plurality of time nodes in the preset time range are a plurality of interval time nodes in the continuous time range. Further, the acquisition is performed in a plurality of time nodes within a future preset time range. For example, the plurality of time nodes within the future preset time range are a plurality of time points in a day. Further, the target area is an area to be subjected to electric fire risk early warning. For example, the target area is an office. Further, collecting electrical characteristic parameters of a plurality of electrical devices in the target area, and combining to obtain a plurality of electrical characteristic parameter sequences. For example, the plurality of electrical devices may be air conditioning in an office, lighting, a socket, a computer, a projector, or a router, among others. The electrical characteristic parameters are operation data monitoring parameters of a plurality of electrical devices, including installation position temperature and electrical power. Further, a plurality of sample electrical characteristic parameter sets, a plurality of sample scale sets and a plurality of sample susceptibility sets are collected to train a plurality of electrical characteristic analysis branches of the electrical characteristic analyzer, a plurality of electrical characteristic parameter sequences are input to the electrical characteristic analyzer, and a plurality of scale sequences and a plurality of susceptibility sequences are output and obtained.

The monitoring configuration unit is used for configuring a scheme for risk monitoring of the plurality of electrical devices at the plurality of edge ends or cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences, so as to obtain a configuration result sequence;

specifically, the electric fire risk dynamic early warning platform based on edge calculation comprises a monitoring configuration unit. The risk monitoring analysis is required to be accurate for electrical equipment with large scale, the risk monitoring analysis is configured on the cloud, and the electrical equipment with large susceptibility is required to be processed rapidly and configured on the edge. Further, in a plurality of time nodes within a preset time range in the future, in the scope of optimization constraint, a plurality of scale sequences and a plurality of susceptibility sequences in the configuration optimization function obtained by construction are adjusted, namely, a plurality of electrical devices are configured at a cloud end or an edge end at a plurality of time nodes to be optimized, and then configuration results are optimized, a plurality of configuration results with the largest configuration fitness are obtained, and a configuration result sequence is generated.

Constructing a plurality of risk analyzers for analyzing electrical operation parameters of the plurality of electrical devices in a fire risk manner, and configuring the risk analyzers in the plurality of edge ends and the cloud end according to the configuration result sequence;

Specifically, the risk analyzers are installed on the cloud or unloaded from the cloud to the edge according to the configuration positions of each electrical device at each time node in the configuration result sequence, so as to save the space of the cloud and the edge.

Acquiring a plurality of electrical operation parameters of the plurality of electrical devices when the plurality of time nodes are reached through a dynamic monitoring unit, and performing risk analysis based on a cloud end and a plurality of edge ends according to the configuration result sequence to obtain an edge end risk parameter set sequence and a cloud end risk parameter set sequence;

specifically, through the dynamic monitoring unit of the dynamic early warning platform for the electrical fire risk based on edge calculation, when a plurality of time nodes are reached, a plurality of electrical operation parameters of a plurality of electrical devices are collected, and according to a configuration result sequence, a plurality of electrical operation parameters are input into a plurality of risk analyzers of a cloud end and a plurality of edge ends to carry out risk analysis, so that an edge end risk parameter set sequence and a cloud end risk parameter set sequence are respectively obtained.

Performing risk parameter field rendering based on the edge-side risk parameter set sequence and the cloud risk parameter set sequence, correcting rendering parameters according to the plurality of scale sequences and the plurality of susceptibility sequences, obtaining an edge risk parameter field sequence and a cloud risk parameter field sequence, and displaying at a plurality of time nodes;

Specifically, according to the edge risk parameter set sequence and the cloud risk parameter set sequence, rendering parameters corresponding to the edge risk parameter set sequence and the cloud risk parameter set sequence are obtained. The rendering parameters are gray values, when the risk parameters are larger, the gray values are smaller, the rendering colors are darker, and otherwise, the rendering colors are lighter. Further, rendering of the risk parameter field is carried out by rendering parameters corresponding to the edge-side risk parameter set sequence and the cloud risk parameter set sequence. Wherein the risk parameter field is a gray scale image. Further, according to the multiple scale sequences and the multiple susceptibility sequences, the rendering parameters are corrected, when the scale and susceptibility corresponding to the electrical equipment are larger, the corresponding rendering parameters, namely the gray values, are reduced, so that the rendering position is darker, otherwise, the gray values are enlarged, so that the rendering position is shallower. Further, according to the corrected risk parameter field, the color of the corresponding position of the electrical equipment in the target area is obtained, so that the electrical fire risk of the corresponding position of the electrical equipment in the target area is high. When the color in the target area is darker, the electric fire risk of the corresponding electric equipment is higher, and conversely, the electric fire risk of the corresponding electric equipment is lower. The risk parameter fields are displayed for fire monitoring staff to know risk conditions.

And acquiring movement rule information of the operator in the target area, combining the edge risk parameter field sequence and the cloud risk parameter field sequence, and generating an early warning scheme for the operator at the plurality of time nodes to perform early warning.

Specifically, the moving positions of the operators in a plurality of time nodes in the target area, namely moving rule information, are obtained, and an early warning scheme for the operators is generated in the plurality of time nodes by combining the sum of risk parameters of the edge risk parameter field sequence and the cloud risk parameter field sequence to perform early warning. When the sum of the risk parameters is larger, the emergency degree of the early warning scheme is higher, and otherwise, the emergency degree is higher and lower.

The technical problem that in the prior art, the efficiency of electric fire risk early warning is low due to low monitoring and analysis accuracy and efficiency of electric equipment can be solved, the aim of improving the monitoring and analysis accuracy and efficiency of the electric equipment is achieved, and the technical effect of improving the efficiency of electric fire risk early warning is achieved.

The method provided by the embodiment of the disclosure further comprises the following steps:

acquiring a plurality of sample electrical characteristic parameter sets based on the types of the plurality of electrical devices, and acquiring a plurality of sample scale sets and a plurality of sample susceptibility sets, wherein the sample scale comprises scale information of electrical fire occurrence, and the sample susceptibility comprises probability information of the electrical fire occurrence;

Respectively adopting the plurality of sample electrical characteristic parameter sets, the plurality of sample scale sets and the plurality of sample vulnerability sets, and training to obtain an electrical characteristic analyzer comprising a plurality of electrical characteristic analysis branches;

and analyzing the plurality of electrical characteristic parameter sequences by adopting the electrical characteristic analyzer to obtain the plurality of scale sequences and the plurality of susceptibility sequences.

Specifically, the kinds of the plurality of electric devices are acquired, and for example, the plurality of electric devices are classified according to power. Further, the same kind of electrical samples of the plurality of electrical devices are acquired by kind, for example, the same kind of electrical samples have the same power. Further, collecting and acquiring electrical characteristic parameters of the same type of electrical samples to obtain an electrical characteristic parameter set. Further, the sample size includes information of the size of the electrical fire, and the sample susceptibility includes information of the probability of the electrical fire. And calculating and acquiring a plurality of sample scale sets and a plurality of sample susceptibility sets according to the plurality of sample electrical characteristic parameter sets. The higher the electrical characteristic parameters of the plurality of sample electrical characteristic parameter sets, the higher the plurality of sample scale sets and the plurality of sample susceptibility sets, and vice versa, the lower.

Further, a plurality of sample electrical characteristic parameter sets are respectively adopted as training sets, a plurality of sample scale sets and a plurality of sample susceptibility sets are adopted as verification sets, and an electrical characteristic analyzer comprising a plurality of electrical characteristic analysis branches is obtained through training. The electrical characteristic analysis branches are supervised and trained through the electrical characteristic parameter sets of the samples in the training set, when the output results of the electrical characteristic analysis branches tend to be in a convergence state, the output result accuracy of the electrical characteristic analysis branches is verified through the verification set, a preset verification accuracy index is obtained, and the preset verification accuracy index can be set by a person skilled in the art in a self-defined mode based on actual conditions, for example: 95%. When the accuracy of the output results of the plurality of electrical characteristic analysis branches is greater than or equal to a preset verification accuracy index, a plurality of electrical characteristic analysis branches are obtained, and then the electrical characteristic analyzers are obtained through combination.

Further, an electrical characteristic analyzer is adopted to input a plurality of electrical characteristic parameter sequences to a plurality of electrical characteristic analysis branches respectively for analysis, and a plurality of scale sequences and a plurality of susceptibility sequences are obtained.

The scale analysis and the susceptibility analysis of the fire disaster of the electrical equipment are carried out, a plurality of scale sequences and a plurality of susceptibility sequences are obtained, and the accuracy of subsequent risk analysis and early warning can be improved.

constructing a configuration optimization function for optimizing electrical fire risk monitoring configurations of the plurality of electrical devices, wherein the configuration optimization function comprises the following formula:

；

wherein des is the configuration fitness, M is the number of electrical devices configured at the cloud for electrical fire risk monitoring, N is the number of electrical devices configured at the edge for electrical fire risk monitoring,for the size of the ith electrical equipment configured in the cloud, < >>For the susceptibility of the jth electrical device arranged at the edge side,/for example>Calculation effort required for monitoring electrical fire risk for the ith electrical equipment configured in the cloud,/-electrical equipment configured in the cloud>、/>And->Is the weight;

taking the total calculation force for monitoring the electrical fire risk by using the electrical equipment configured on the cloud for monitoring the electrical fire risk as an optimization constraint, wherein the total calculation force for monitoring the electrical fire risk is not more than the cloud calculation force;

and optimizing configuration results in the plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences based on the configuration optimization function and the optimization constraint, obtaining a plurality of configuration results with the maximum configuration fitness, and generating the configuration result sequence.

Specifically, a configuration optimization function for optimizing electrical fire risk monitoring configurations of a plurality of electrical devices is constructed, as follows:

；

Further, des is the configuration fitness, M is the number of electrical devices configured to monitor the electrical fire risk at the cloud, N is the number of electrical devices configured to monitor the electrical fire risk at the edge,for the size of the ith electrical equipment configured in the cloud, < >>For the susceptibility of the jth electrical device arranged at the edge side,/for example>Calculation effort required for monitoring electrical fire risk for the ith electrical equipment configured in the cloud,/-electrical equipment configured in the cloud>、/>And->Is the weight. Wherein the weight->、And->The sum is 1, p->、/>And->The ratio of the weight allocation is custom set by the person skilled in the art according to the actual situation, e.g./or->：/>：/>Is 3:3:4. the higher the configuration fitness, the higher the accuracy of electrical fire risk monitoring.

Further, the electrical equipment configured at the cloud end for electrical fire risk monitoring is extracted, and the total calculation force of the electrical equipment is obtained as optimization constraint when the total calculation force of the electrical equipment for electrical fire risk monitoring at the cloud end is not more than the calculation force of the cloud end, namely is less than or equal to the total calculation force of the electrical equipment. The cloud computing power is the cloud of the dynamic early warning platform for the electrical fire risk based on edge computing and is used for electrical fire risk analysis.

Further, in a plurality of time nodes within a preset time range in the future, optimizing configuration results, particularly optimizing configuration results of a plurality of time nodes, based on a configuration optimizing function, a plurality of scale sequences and a plurality of susceptibility sequences, in the range of optimizing constraint, wherein the configuration results comprise configuring electrical fire risk monitoring of which electrical devices at a cloud end, configuring electrical fire risk monitoring of which electrical devices at an edge end, calculating configuration fitness of the configuration results based on a plurality of scales and a plurality of susceptibility of the plurality of electrical devices corresponding to the time nodes, randomly adjusting the electrical devices configured at the cloud end and the edge end for electrical fire risk monitoring based on any optimizing algorithm in the prior art, optimizing to obtain a plurality of configuration results with the maximum configuration fitness, and generating a configuration result sequence.

Accordingly, another embodiment is to obtain a sample scale set and a sample susceptibility set, and obtain a sample configuration scheme set, where each sample configuration scheme includes configuring electrical fire risk monitoring of an electrical device at an edge or cloud. Further, a sample scale set, a sample susceptibility set and a sample configuration scheme set are adopted, and a configuration decision maker is constructed by taking the scale and the susceptibility as decision classification data based on a decision tree. And combining and decision classifying the scales and the easily-transmitted degrees in the scale sequences and the easily-transmitted degrees in the time nodes by adopting a configuration decision device to obtain a plurality of configuration scheme sequences and generate a configuration result sequence.

Wherein, obtaining the configuration result sequence can improve the accuracy and efficiency of the electrical fire risk analysis.

collecting a plurality of sample electrical operation parameter sets based on the electrical equipment types of the plurality of electrical equipment, and analyzing to obtain a plurality of sample risk parameter sets;

respectively adopting the plurality of sample electric operation parameter sets and the plurality of sample risk parameter sets, and training to obtain a plurality of risk analyzers for carrying out electric operation parameter fire risk analysis on the plurality of electric devices;

and installing the risk analyzers on the cloud sides of the electrical fire risk monitoring configuration of the corresponding electrical equipment or unloading the risk analyzers to the edge sides of the electrical fire risk monitoring configuration of the corresponding electrical equipment at the plurality of time nodes based on the configuration result sequences.

Specifically, a plurality of sample electrical operating parameter sets of a plurality of electrical samples corresponding to a plurality of categories are collected based on the electrical device categories of the plurality of electrical devices. And performing risk analysis according to the plurality of sample electrical operation parameter sets to obtain a plurality of sample risk parameter sets. The risk of the plurality of sample electrical operation parameter sets is higher, the corresponding plurality of sample risk parameter sets are larger, and conversely, the risk of the plurality of sample electrical operation parameter sets are smaller.

Further, the plurality of sample electrical operation parameter sets are used as training data, the plurality of sample risk parameter sets are used as verification data, and a plurality of risk analyzers corresponding to the plurality of electrical devices are trained. When the output results of the risk analyzers tend to be in a convergence state, verifying the accuracy of the output results of the risk analyzers through verification data to obtain a preset verification accuracy threshold, wherein the preset verification accuracy refers to the fact that a person skilled in the art can customize the threshold based on actual conditions, for example: 85%. And when the accuracy of the output results of the risk analyzers is greater than or equal to a preset verification accuracy threshold, obtaining the risk analyzers.

Further, based on the scheme in the configuration result sequence, at a plurality of time nodes, a plurality of risk analyzers are installed on the cloud end of the electrical fire risk monitoring configuration of the corresponding electrical equipment, or are unloaded to the edge end of the electrical fire risk monitoring configuration of the corresponding electrical equipment. The risk analyzers are installed on the cloud or unloaded to the edge end from the cloud according to the configuration positions of each electrical device of each time node, so that the space of the cloud and the edge end is saved.

mapping and obtaining corresponding rendering gray values in a rendering gray range as rendering parameters according to the size of each risk parameter based on the edge risk parameter set sequence to obtain an edge rendering parameter set sequence;

mapping and acquiring a cloud rendering parameter set sequence based on the cloud risk parameter set sequence;

correcting and calculating rendering parameters in the edge end rendering parameter set sequence and the cloud end rendering parameter set sequence according to the plurality of scale sequences and the plurality of susceptibility sequences to obtain a corrected edge end rendering parameter set sequence and a corrected cloud end rendering parameter set sequence;

and according to the corrected edge end rendering parameter set sequence and the corrected cloud rendering parameter set sequence, performing risk parameter field rendering at a plurality of time nodes to obtain the edge risk parameter field sequence and the cloud risk parameter field sequence.

Specifically, according to the size of each risk parameter, mapping the edge-side risk parameter set sequence in a rendering gray range to obtain a corresponding rendering gray value as a rendering parameter, and obtaining an edge-side rendering parameter set sequence. The rendering gray scale range is a gray scale value range, namely, pixel values from 0 to 255. When the risk parameter of the edge end is larger, the rendered gray value is smaller, and conversely, the rendered gray value is larger.

Further, according to the size of each risk parameter, mapping the cloud risk parameter set sequence in a rendering gray scale range to obtain a corresponding rendering gray scale value as a rendering parameter, and obtaining a rendered cloud rendering parameter set sequence. The rendering gray scale range is a gray scale value range, namely, pixel values from 0 to 255. When the risk parameter of the edge end is larger, the gray value of the rendering is smaller, the color is darker and more striking, otherwise, the color is lighter and less striking.

Further, according to the size of the scale in the plurality of scale sequences and the size of the vulnerability in the plurality of vulnerability sequences, correcting and calculating rendering parameters in the edge-end rendering parameter set sequence and the cloud-end rendering parameter set sequence, namely gray values of corresponding electrical equipment, so as to obtain a corrected edge-end rendering parameter set sequence and a corrected cloud-end rendering parameter set sequence.

Further, according to the corrected edge rendering parameter set sequence and the corrected cloud rendering parameter set sequence, performing risk parameter field rendering at a plurality of time nodes, when the scale and the probability corresponding to the electrical equipment are larger, reducing the corresponding rendering parameters, namely the gray values, so that the rendering positions are deeper, otherwise, amplifying the gray values so that the rendering positions are shallower, and further obtaining the edge risk parameter field sequence and the cloud risk parameter field sequence. The method comprises the steps of correcting rendering parameters to obtain a marginal risk parameter field sequence and a cloud risk parameter field sequence, and obtaining an intuitive electric fire risk representation method, so that the electric fire risk early warning efficiency is improved.

calculating the reciprocal of the ratio of the scale of the plurality of electrical equipment configured at the plurality of edge ends to the average scale of the electrical fire risk monitoring in each time node according to the configuration result sequence, and obtaining an edge scale correction coefficient set sequence;

calculating the reciprocal of the ratio of the susceptibility to the average susceptibility of a plurality of electrical devices configured at a plurality of edge ends for monitoring the electrical fire risk in each time node according to the configuration result sequence, obtaining an edge susceptibility correction coefficient set sequence, and calculating to obtain an edge correction coefficient set sequence by combining the edge scale correction coefficient set sequence;

performing corresponding correction calculation on rendering parameters in the edge end rendering parameter set sequence by adopting the edge correction coefficient set sequence to obtain the corrected edge end rendering parameter set sequence;

and correcting and calculating the rendering parameters in the cloud rendering parameter set sequence according to the plurality of scale sequences and the plurality of susceptibility sequences to obtain the corrected cloud rendering parameter set sequence.

Specifically, according to the configuration result sequence, calculating the reciprocal of the ratio of the scale of the plurality of electrical devices configured at the plurality of edge ends to the average scale of the electrical fire risk monitoring in each time node, and obtaining an edge scale correction coefficient set sequence, namely calculating the reciprocal of the ratio of the scale of each electrical device to the scale average of the plurality of electrical devices in the plurality of edge ends, wherein the plurality of time nodes correspond to the plurality of edge scale correction coefficient sets to form an edge scale correction coefficient set sequence for correcting rendering parameters, so that the rendering parameters of the electrical devices with large scale and high probability are smaller, and the color is darker and more striking.

Further, calculating the reciprocal of the ratio of the susceptibility to the average susceptibility of a plurality of electrical devices configured at a plurality of edge terminals for monitoring the electrical fire risk in each time node according to the configuration result sequence, obtaining an edge susceptibility correction coefficient set sequence, and calculating to obtain the edge correction coefficient set sequence by combining the edge scale correction coefficient set sequence. For example, the edge correction coefficient set sequence is obtained by performing weighted calculation or calculation on the two correction coefficients corresponding to the edge susceptible correction coefficient set sequence and the edge scale correction coefficient set sequence.

Further, an edge correction coefficient set sequence is adopted to carry out corresponding correction calculation on the rendering parameters in the edge end rendering parameter set sequence, namely, the rendering parameters are corrected according to the scale and the magnitude of the easy occurrence, so that the rendering parameters obtained by corresponding analysis of electrical equipment with larger scale and easy occurrence are smaller, namely, the gray level is smaller, the color is darker and more striking, and the corrected edge end rendering parameter set sequence is obtained.

Further, based on the same method, according to a plurality of scale sequences and a plurality of susceptibility sequences, correcting and calculating the rendering parameters in the cloud rendering parameter set sequence, namely correcting the rendering parameters according to the scale and the susceptibility, reducing the rendering parameters corresponding to the electrical equipment with large scale and susceptibility, namely the gray value, so that the color of the rendering position is darker, otherwise, amplifying the gray value, so that the rendering position is shallower, and further obtaining the corrected cloud rendering parameter set sequence. The visual electric fire risk representation method is obtained by correcting and calculating rendering parameters in the edge rendering parameter set sequence and the cloud rendering parameter set sequence, and therefore the electric fire risk early warning efficiency is improved.

acquiring the moving positions of operators in the target area in the plurality of time nodes, and acquiring a moving position sequence as moving rule information;

according to the moving position sequence, in the edge risk parameter field sequence and the cloud risk parameter field sequence, calculating the sum of rendering parameters of K nearest electrical equipment positions of each moving position in a statistical mode to obtain a personnel rendering parameter sequence, wherein K is an integer larger than 1;

acquiring a sample personnel rendering parameter set and a sample early warning scheme set;

adopting the sample personnel rendering parameter set and the sample early warning scheme set to construct an early warning analyzer based on a decision tree;

and analyzing according to the personnel rendering parameter sequence by adopting an early warning analyzer to obtain a plurality of early warning schemes, and carrying out early warning at the plurality of time nodes.

Specifically, the moving positions of the operator in the target area in a plurality of time nodes are obtained, and a moving position sequence is obtained as moving rule information. And taking the target area as a square grid for frame selection, and obtaining the transverse displacement step length and the longitudinal displacement step length of an operator in the square grid as a moving position sequence.

Further, according to the moving position sequence, in the edge risk parameter field sequence and the cloud risk parameter field sequence, calculating the sum of rendering parameters of K nearest electric equipment positions of each moving position in a statistical mode, namely obtaining the electric fire risks of K nearest electric equipment positions of each moving position in a statistical mode, and further obtaining a personnel rendering parameter sequence. Wherein, at least the rendering parameters of the two nearest electrical device positions are acquired, so K is an integer greater than 1. Further, the higher the sum of rendering parameters, the higher the electrical fire risk, and vice versa, the lower.

Further, a sample personnel rendering parameter set and a sample early warning scheme set are obtained. The sample personnel rendering parameter set is a sample personnel rendering parameter set of a plurality of sample electrical devices which are the same as the personnel rendering parameter sequence. Further, according to the sample moving position sequence of the operator, in the sample edge risk parameter field sequence and the sample cloud risk parameter field sequence, calculating the sum of rendering parameters of K nearest sample electrical equipment positions of each moving position in a statistical mode, and obtaining a sample operator rendering parameter set. Further, the sample early warning scheme set is a corresponding early warning scheme generated according to the sample personnel rendering parameter set. For example, a power outage early warning scheme may be performed for areas where the sample person rendering parameter set is higher.

Further, a sample personnel rendering parameter set and a sample early warning scheme set are adopted, and based on a decision tree, the sample personnel rendering parameter set and the sample early warning scheme set are used as decision classification data to construct an early warning analyzer. And rendering the parameter set by the input sample personnel, and obtaining different sample early warning scheme sets in decision classification.

Further, the personnel rendering parameter sequence is input into an early warning analyzer, and a plurality of early warning schemes are obtained according to the size of the personnel rendering parameter sequence. When the personnel rendering parameter sequence is smaller, the risk parameters of the electrical equipment nearby the personnel are higher, the color in the risk parameter field is darker, the emergency degree of the early warning scheme is higher, and otherwise, the emergency degree is lower. Further, early warning is carried out at a plurality of time nodes according to the corresponding early warning scheme. The method comprises the steps of acquiring movement rule information of an operator in a target area, combining an edge risk parameter field sequence and a cloud risk parameter field sequence, and generating an early warning scheme for the operator at a plurality of time nodes, so that accuracy and efficiency of early warning in the target area can be improved.

Example two

Based on the same inventive concept as the electrical fire risk dynamic early warning method based on edge calculation in the foregoing embodiment, as shown in fig. 2, the present disclosure further provides an electrical fire risk dynamic early warning system based on edge calculation, where the system includes:

The scale sequence obtaining module 11 is configured to collect electrical characteristic parameters of a plurality of electrical devices in a target area where electrical fire risks are to be performed in a plurality of time nodes within a future preset time range, obtain a plurality of electrical characteristic parameter sequences, and perform scale analysis and susceptibility analysis of fire occurrence of the electrical devices to obtain a plurality of scale sequences and a plurality of susceptibility sequences, where the electrical characteristic parameters include installation position temperature and electrical power;

the configuration result sequence obtaining module 12 is configured to configure a risk monitoring scheme of the plurality of electrical devices at the plurality of edge ends or the cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences by monitoring a configuration unit, so as to obtain a configuration result sequence;

a plurality of risk analyzer configuration modules 13, wherein the plurality of risk analyzer configuration modules 13 are used for constructing a plurality of risk analyzers for performing electrical operation parameter fire risk analysis on the plurality of electrical devices, and are configured in the plurality of edge ends and the cloud according to the configuration result sequence;

The cloud risk parameter set sequence obtaining module 14 is configured to collect, by using a dynamic monitoring unit, a plurality of electrical operation parameters of the plurality of electrical devices when reaching the plurality of time nodes, and perform risk analysis based on a cloud and a plurality of edge ends according to the configuration result sequence, to obtain an edge end risk parameter set sequence and a cloud risk parameter set sequence;

the edge risk parameter field sequence obtaining module 15 is configured to perform risk parameter field rendering based on the edge risk parameter set sequence and the cloud risk parameter set sequence, correct rendering parameters according to the multiple scale sequences and the multiple susceptibility sequences, obtain an edge risk parameter field sequence and a cloud risk parameter field sequence, and display at multiple time nodes;

the early warning scheme obtaining module 16 is configured to obtain movement rule information of an operator in the target area, and generate early warning schemes for the operator at the plurality of time nodes by combining the edge risk parameter field sequence and the cloud risk parameter field sequence, so as to perform early warning.

Further, the system further comprises:

the system comprises a plurality of sample susceptibility sets acquisition modules, a plurality of sample susceptibility sets acquisition modules and a plurality of control modules, wherein the plurality of sample susceptibility sets acquisition modules are used for acquiring a plurality of sample electrical characteristic parameter sets based on the types of the plurality of electrical devices and acquiring a plurality of sample scale sets and a plurality of sample susceptibility sets, wherein the sample scale comprises scale information of electrical fire occurrence and the sample susceptibility comprises probability information of the occurrence of the electrical fire;

the electrical characteristic analyzer obtaining module is used for training and obtaining an electrical characteristic analyzer comprising a plurality of electrical characteristic analysis branches by respectively adopting the plurality of sample electrical characteristic parameter sets, the plurality of sample scale sets and the plurality of sample vulnerability sets;

and the plurality of susceptibility sequences acquisition modules are used for analyzing the plurality of electrical characteristic parameter sequences by adopting the electrical characteristic analyzer to acquire the plurality of scale sequences and the plurality of susceptibility sequences.

Further, the system further comprises:

the configuration optimization function construction module is used for constructing a configuration optimization function for optimizing the electrical fire risk monitoring configuration of the plurality of electrical devices, and the configuration optimization function construction module is used for constructing a configuration optimization function for optimizing the electrical fire risk monitoring configuration of the plurality of electrical devices according to the following formula:

；

A configuration optimization function processing module, wherein des is configuration fitness, M is the number of electrical devices configured to monitor electrical fire risk at the cloud, N is the number of electrical devices configured to monitor electrical fire risk at the edge,for the size of the ith electrical equipment configured in the cloud, < >>For the susceptibility of the jth electrical device arranged at the edge side,/for example>Calculation effort required for monitoring electrical fire risk for the ith electrical equipment configured in the cloud,/-electrical equipment configured in the cloud>、/>And->Is the weight;

the optimization constraint obtaining module is used for taking the total calculation force for monitoring the electrical fire risk of the electrical equipment configured on the cloud for monitoring the electrical fire risk as an optimization constraint, wherein the total calculation force is not more than the cloud calculation force;

and the configuration result optimization module is used for optimizing the configuration result according to the plurality of scale sequences and the plurality of susceptibility sequences in the plurality of time nodes based on the configuration optimization function and the optimization constraint, obtaining a plurality of configuration results with the maximum configuration fitness, and generating the configuration result sequence.

Further, the system further comprises:

A plurality of sample risk parameter set obtaining modules, which are used for collecting a plurality of sample electrical operation parameter sets based on the electrical equipment types of the plurality of electrical equipment and analyzing to obtain a plurality of sample risk parameter sets;

the risk analyzer training modules are used for training and acquiring a plurality of risk analyzers for carrying out electrical operation parameter fire risk analysis on the plurality of electrical equipment by adopting the plurality of sample electrical operation parameter sets and the plurality of sample risk parameter sets respectively;

and the electrical fire risk monitoring configuration module is used for installing the plurality of risk analyzers on the cloud sides of the electrical fire risk monitoring configuration of the corresponding electrical equipment or unloading the cloud sides to the edge ends of the electrical fire risk monitoring configuration of the corresponding electrical equipment at the plurality of time nodes based on the configuration result sequence.

Further, the system further comprises:

the edge end rendering parameter set sequence obtaining module is used for obtaining a corresponding rendering gray value as a rendering parameter in a rendering gray range in a mapping manner based on the edge end risk parameter set sequence to obtain an edge end rendering parameter set sequence;

The cloud rendering parameter set sequence obtaining module is used for mapping and obtaining a cloud rendering parameter set sequence based on the cloud risk parameter set sequence;

the corrected edge end rendering parameter set sequence obtaining module is used for correcting and calculating rendering parameters in the edge end rendering parameter set sequence and the cloud end rendering parameter set sequence according to the plurality of scale sequences and the plurality of susceptibility sequences to obtain a corrected edge end rendering parameter set sequence and a corrected cloud end rendering parameter set sequence;

the cloud risk parameter field sequence obtaining module is used for carrying out risk parameter field rendering at a plurality of time nodes according to the corrected edge end rendering parameter set sequence and the corrected cloud rendering parameter set sequence to obtain the edge risk parameter field sequence and the cloud risk parameter field sequence.

Further, the system further comprises:

the edge scale correction coefficient set sequence obtaining module is used for calculating the reciprocal of the ratio of the scale of the plurality of electrical devices configured at the plurality of edge ends to the average scale of the electrical fire risk monitoring in each time node according to the configuration result sequence to obtain an edge scale correction coefficient set sequence;

The edge correction coefficient set sequence obtaining module is used for calculating the reciprocal of the ratio of the susceptibility to the average susceptibility of a plurality of electrical devices configured at a plurality of edge ends for monitoring the electrical fire risk in each time node according to the configuration result sequence to obtain an edge susceptibility correction coefficient set sequence, and calculating to obtain an edge correction coefficient set sequence by combining the edge scale correction coefficient set sequence;

the corrected edge end rendering parameter set sequence obtaining module is used for carrying out corresponding correction calculation on rendering parameters in the edge end rendering parameter set sequence by adopting the edge correction coefficient set sequence to obtain the corrected edge end rendering parameter set sequence;

the corrected cloud rendering parameter set sequence obtaining module is used for carrying out correction calculation on rendering parameters in the cloud rendering parameter set sequence according to the plurality of scale sequences and the plurality of susceptibility sequences to obtain the corrected cloud rendering parameter set sequence.

Further, the system further comprises:

the mobile position sequence obtaining module is used for obtaining the mobile positions of the operators in the plurality of time nodes and in the target area, and obtaining a mobile position sequence as mobile rule information;

the personnel rendering parameter sequence obtaining module is used for obtaining a personnel rendering parameter sequence by calculating the sum of rendering parameters of K nearest electrical equipment positions of each moving position in the edge risk parameter field sequence and the cloud risk parameter field sequence according to the moving position sequence, wherein K is an integer larger than 1;

the sample personnel rendering parameter set obtaining module is used for obtaining a sample personnel rendering parameter set and a sample early warning scheme set;

the early warning analyzer construction module is used for constructing an early warning analyzer based on a decision tree by adopting the sample personnel rendering parameter set and the sample early warning scheme set;

the early warning scheme obtaining modules are used for obtaining a plurality of early warning schemes by adopting an early warning analyzer and analyzing according to the personnel rendering parameter sequences, and early warning is carried out at the plurality of time nodes.

The specific example of the electrical fire risk dynamic early warning method based on edge calculation in the first embodiment is also applicable to the electrical fire risk dynamic early warning system based on edge calculation in this embodiment, and those skilled in the art can clearly know the electrical fire risk dynamic early warning system based on edge calculation in this embodiment through the foregoing detailed description of the electrical fire risk dynamic early warning method based on edge calculation, so that details are not described herein for brevity of description. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simpler, and the relevant points refer to the description of the method.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. The utility model provides an electric fire risk dynamic early warning method based on edge calculation, which is characterized in that the method is applied to an electric fire risk dynamic early warning platform based on edge calculation, the platform includes with a plurality of edge ends, high in the clouds, still includes monitoring configuration unit, dynamic monitoring unit and early warning processing unit, the method includes:

2. The method of claim 1, wherein performing a scale analysis and a susceptibility analysis of the electrical device to fire to obtain a plurality of scale sequences and a plurality of susceptibility sequences comprises:

3. The method of claim 1, wherein configuring the risk monitoring schemes of the plurality of electrical devices at the plurality of edge ends or cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences, respectively, to obtain a configuration result sequence, includes:

；

wherein des is the configuration fitness, M is the number of electrical devices configured at the cloud for electrical fire risk monitoring, N is the number of electrical devices configured at the edge for electrical fire risk monitoring,for the size of the ith electrical equipment configured in the cloud, < >>For the susceptibility of the jth electrical device arranged at the edge side,/for example >Calculation effort required for monitoring electrical fire risk for the ith electrical equipment configured in the cloud,/-electrical equipment configured in the cloud>、/>And->Is the weight;

4. The method of claim 1, wherein constructing a plurality of risk analyzers for electrical operating parameter fire risk analyses of the plurality of electrical devices, configured in the plurality of edge and cloud ends according to the configuration result sequence, comprises:

5. The method of claim 1, wherein performing risk parameter field rendering based on the edge risk parameter set sequence and cloud risk parameter set sequence, and correcting rendering parameters according to the plurality of scale sequences and the plurality of susceptibility sequences to obtain an edge risk parameter field sequence and a cloud risk parameter field sequence, comprises:

6. The method of claim 5, wherein performing correction calculation on rendering parameters in the edge rendering parameter set sequence and the cloud rendering parameter set sequence according to the plurality of scale sequences and the plurality of susceptibility sequences comprises:

7. The method of claim 1, wherein obtaining movement law information of the operator in the target area, combining the edge risk parameter field sequence and the cloud risk parameter field sequence, and generating an early warning scheme for the operator at the plurality of time nodes, comprises:

8. An electrical fire risk dynamic early warning system based on edge calculation, which is used for implementing the electrical fire risk dynamic early warning method based on edge calculation as claimed in any one of claims 1 to 7, wherein the system comprises:

the system comprises a scale sequence acquisition module, a power generation module and a power generation module, wherein the scale sequence acquisition module is used for acquiring electrical characteristic parameters of a plurality of electrical devices in a target area to be subjected to electrical fire risk in a plurality of time nodes within a future preset time range, acquiring a plurality of electrical characteristic parameter sequences, and carrying out scale analysis and susceptibility analysis of the electrical devices on the occurrence of fire, so as to acquire a plurality of scale sequences and a plurality of susceptibility sequences, wherein the electrical characteristic parameters comprise installation position temperature and electrical power;

the configuration result sequence obtaining module is used for obtaining a configuration result sequence by monitoring a configuration unit and respectively configuring a scheme of risk monitoring of the plurality of electrical devices at the plurality of edge ends or cloud ends in a plurality of time nodes according to the plurality of scale sequences and the plurality of susceptibility sequences;

The risk analyzer configuration modules are used for constructing a plurality of risk analyzers for carrying out electrical operation parameter fire risk analysis on the plurality of electrical equipment and are configured in the plurality of edge ends and the cloud according to the configuration result sequence;

the cloud risk parameter set sequence obtaining module is used for collecting a plurality of electrical operation parameters of the plurality of electrical devices through the dynamic monitoring unit when the plurality of time nodes are reached, and carrying out risk analysis based on a cloud end and a plurality of edge ends according to the configuration result sequence to obtain an edge end risk parameter set sequence and a cloud end risk parameter set sequence;

the edge risk parameter field sequence obtaining module is used for rendering a risk parameter field based on the edge end risk parameter set sequence and the cloud risk parameter set sequence, correcting rendering parameters according to the plurality of scale sequences and the plurality of susceptibility sequences, obtaining an edge risk parameter field sequence and a cloud risk parameter field sequence, and displaying at a plurality of time nodes;

The early warning scheme obtaining module is used for obtaining movement rule information of operators in the target area, combining the edge risk parameter field sequence and the cloud risk parameter field sequence, and generating early warning schemes for the operators at the plurality of time nodes to perform early warning.