An intelligent auxiliary system for fire operation safety defense based on multi-dimensional data

Abstract

The present invention discloses an intelligent auxiliary system for hot work safety defense based on multi-dimensional data, which belongs to the field of data processing technology; it is used to solve the technical problems of poor autonomous identification and evaluation effect and poor autonomous control effect of hot work safety defense assistance in existing solutions; multi-directional video recording, image processing and analysis are performed on the hot work area to obtain target recognition features, and data processing and calculation are performed on the target recognition features to obtain the abnormality of the operation area; monitoring and data processing are performed from the operation protection dimension, all the abnormal operation data obtained by processing are integrated and calculated to obtain the abnormality of the operation, and data analysis is performed on the abnormality of the operation to obtain the corresponding operation identification mark and operation status instruction, by integrating and calculating the risk analysis data of different dimensions, and according to the operation risk mark obtained through analysis, the risk dynamic prompt and safety dynamic control of the hot work are performed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent auxiliary system for safety defense of hot work operations based on multi-dimensional data. Background Art

[0002] Hot work refers to non-routine work that may produce flames, sparks, or hot surfaces in a fire-free zone outside of process facilities that directly or indirectly produce open flames. Such work requires strict safety management and control measures due to the risk of fire or explosion; hot work mainly includes but is not limited to electric welding, gas welding (cutting), use of blowtorches, electric drills, grinding wheels, sandblasting machines, etc.

[0003] Although different types of hot work operations essentially need to follow the same basic safety principles and regulatory requirements, there may be differences in specific operational requirements and safety measures, mainly to adapt to the unique risks of different types of operations; when implementing existing hot work safety defense plans, they cannot carry out targeted risk assessments and proactively implement safety defenses for hot work operations of different types of operations, resulting in poor autonomous identification and assessment effects and poor autonomous control effects of hot work safety defense assistance. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent assistance system for hot work safety defense based on multi-dimensional data, which is used to solve the technical problems of poor autonomous identification and evaluation effect and poor autonomous control effect of hot work safety defense assistance in existing solutions.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] An intelligent auxiliary system for fire operation safety defense based on multi-dimensional data, comprising:

[0007] The operation area image data acquisition and processing module is used to carry out all-round monitoring point photography of the target area for hot work to obtain monitoring images of corresponding positions and sort and combine them to obtain a regional monitoring combination set, and pre-process and match and analyze several monitoring images in the regional monitoring combination set to obtain regional risk analysis data;

[0008] The operation specification image data acquisition and processing module is used to take a frontal video of the operator performing the hot work to obtain the corresponding operation image, pre-process and match the operation image to obtain the operation risk analysis data;

[0009] The operation status integration assessment management module is used to integrate and calculate the regional risk analysis data corresponding to the target area where the hot work operation is implemented and the operational risk analysis data corresponding to the operator to obtain the corresponding operation risk integration value, analyze the operation risk integration value to determine the overall operation risk corresponding to the hot work operation and implement targeted safety management and control; the operation risk integration value is a numerical value that digitally represents the overall risk of the hot work operation by integrating and calculating the risk analysis data of different dimensions.

[0010] Preferably, preprocessing and feature extraction are performed on a plurality of monitoring images sorted in the regional monitoring combination set, and all identification features obtained by processing all monitoring images are sorted and combined to obtain an identification feature set;

[0011] When analyzing the abnormal impact of the identification feature set on the operating area, the identification feature set is traversed to count the total number of identification features and analyzed. If the total number of identification features is 0, a normal instruction for the operating area is generated and the abnormal feature impact flag is set to 0.

[0012] Preferably, if the total number of identification features is not 0, an abnormal operation area instruction is generated and several identification features in the identification feature set are traversed with a preset sample feature database. If there is a sample feature identical to the identification feature in the sample feature database, the corresponding identification feature is marked as a target identification feature;

[0013] If there is no sample feature identical to the identification feature in the sample feature database, the corresponding identification feature is marked as a normal identification feature;

[0014] The total number n of target identification features is counted and analyzed. If the total number of target identification features is 0, a normal instruction for the operating area is generated and prompted.

[0015] Preferably, if the total number of target identification features is not 0, a data processing instruction is generated, and the feature influence coefficients yi associated with different target identification features are obtained according to the data processing instruction, where i=1, 2, 3, ..., n; n is a positive integer; i is a different target identification feature, and the formula is used to obtain the feature influence coefficients yi associated with different target identification features. Calculate and obtain the abnormality Zy of the operation area corresponding to all target identification features; where NJj is the detection concentration of different combustible gases in the hot work area, NJj0 is the standard concentration of different combustible gases in the hot work area; j=1, 2, 3, ..., m; m is a positive integer; j is different combustible gases;

[0016] Analyze the abnormality of the operation area to determine the abnormal impact corresponding to the operation area and obtain an abnormal low impact instruction for the operation area or an abnormal high impact instruction for the operation area;

[0017] Normal instructions for the operating area, the degree of abnormality in the operating area, and the abnormally low-impact instructions for the operating area or the abnormally high-impact instructions for the operating area obtained through analysis constitute the regional risk analysis data.

[0018] Preferably, a standard operation feature is obtained according to the type of hot work, the operation image is preprocessed and feature recognized to obtain an operation identification feature, all the operation identification features obtained by recognition are numbered, and all the numbered operation identification features are sequentially traversed and matched with the sample operation feature set, and the sample operation feature that is the same as the operation identification feature is marked as a valid feature; and the sample operation feature that is not matched in the sample operation feature set is marked as an abnormal feature;

[0019] The total number of identification features N1 corresponding to all operation identification features and the total number of sample features N2 corresponding to all sample operation features in the sample operation feature set are counted, and data analysis is performed through the operation feature identification piecewise function to output the operation identification mark.

[0020] Preferably, the expression of the operation feature identification piecewise function is: ; In the formula, Zk is the characteristic influencing factor corresponding to different abnormal characteristics; k is different abnormal characteristics, k=1, 2, 3, ..., N2-N1; Cy is the abnormality degree of the operation, .

[0021] Preferably, when determining the operation state corresponding to the operator according to the operation identification mark, the operation identification mark is analyzed, and if the operation identification mark is 0, a normal operation instruction is generated and prompted;

[0022] If the operation identification flag is not 0, the operation identification flag is compared with the operation identification threshold value for analysis. If the operation identification flag is less than or equal to the operation identification threshold value, a slight abnormal operation instruction is generated and a prompt is given;

[0023] If the operation identification flag is greater than the operation identification threshold, a severe operation abnormality instruction is generated and a prompt is given;

[0024] The degree of abnormality of the operation, the operation identification mark, and the normal operation instructions, slightly abnormal operation instructions, or severely abnormal operation instructions obtained through analysis constitute the operation risk analysis data.

[0025] Preferably, the regional risk analysis data and operational risk analysis data corresponding to the implementation of the hot work are obtained and traversed and analyzed. If the results of the traversal statistics do not contain both normal instructions for the operating area and normal instructions for the operation, an integrated instruction is generated. According to the integrated instruction, the operating area abnormality Zy in the regional risk analysis data and the operating operation abnormality Cy in the operational risk analysis data are obtained, and the operational risk integration value Zf corresponding to the hot work is calculated by the formula Zf=α×Zy+β×Cy; wherein α and β are different weight coefficients, 0<β<α.

[0026] Preferably, when determining the overall risk of the operation corresponding to the hot work according to the operation risk integration value, the operation risk integration value is input into the operation risk identification piecewise function for data analysis and output of the operation risk identification, and the corresponding overall risk prompt of the operation is generated according to the operation risk identification, and targeted safety control is implemented for the hot work;

[0027] According to the operation risk identification with a value of 1 or 2, a corresponding overall low risk warning or an overall high risk warning for the operation is generated respectively; and according to the operation risk identification with a value of 1 or 2, the safety management personnel are controlled to perform on-site safety management or replace the operating personnel respectively.

[0028] Preferably, the expression of the piecewise function for identifying operational risk is: ; Where Y is the operation risk classification value.

[0029] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0030] The present invention obtains target identification features by multi-directional video recording, image processing and analysis of the hot fire operation area, and obtains the abnormality degree of the operation area by data processing and calculation of the target identification features. It can not only digitally represent the abnormal impact of the hot fire operation area, but also provide reliable operation area risk data support for the processing and analysis of the subsequent overall operation risks, thereby improving the automatic identification of dimensional risks in the hot fire operation area and the diversity of processing and utilization.

[0031] The present invention monitors and processes data from the operation protection dimension, integrates and calculates all the acquired operation abnormality data to obtain the operation operation abnormality degree, and performs data analysis on the operation operation abnormality degree to obtain the corresponding operation identification mark and operation status instruction. It can not only monitor and digitally represent the operation protection standardization of operators, but also provide reliable operation operation standardization data support for the subsequent processing and analysis of overall operation risks, thereby improving the diversity and comprehensiveness of automatic identification and processing of risks in the operation protection dimension.

[0032] The present invention integrates and calculates risk analysis data from different dimensions to digitally represent the overall operational risk of hot fire operations, and provides dynamic risk prompts and dynamic safety management and control of hot fire operations based on the operational risk identifiers obtained through analysis, thereby improving the autonomous identification and evaluation effect and autonomous management and control effect of safety defense assistance for hot fire operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] Figure 1 This is a module block diagram of an intelligent auxiliary system for fire operation safety defense based on multi-dimensional data of the present invention.

[0035] Figure 2 The present invention is a flowchart of the operation of an intelligent auxiliary system for safety defense of hot work based on multi-dimensional data. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Example 1: Figure 1 to Figure 2 As shown, the present invention is an intelligent auxiliary system for fire operation safety defense based on multi-dimensional data, including: an operation area image data acquisition and processing module, an operation specification image data acquisition and processing module and an operation status integration assessment management module;

[0038] The operation area image data acquisition and processing module is used to carry out all-round monitoring point photography of the target area for hot work to obtain monitoring images of corresponding positions and sort and combine them to obtain a regional monitoring combination set, and pre-process and match and analyze several monitoring images in the regional monitoring combination set to obtain regional risk analysis data; including:

[0039] The target area is the area where the hot work is to be carried out. The monitoring points are a number of monitoring points set at the midpoint of the target area and at preset intervals in different directions. The different directions include but are not limited to due east, due west, due north and due south. The intervals are determined according to the required data of the existing operation area corresponding to the hot work. The purpose of setting a number of monitoring points is to obtain all environmental images around the target area when the hot work is carried out through the monitoring points. The environmental images obtained by video recording can provide reliable image data support for the automatic identification and analysis of risks in the subsequent operation area.

[0040] It should be noted that combustible materials should be removed around hot work to prevent the open flame from spreading or igniting surrounding objects;

[0041] Preprocessing and feature extraction are performed on a number of monitoring images sorted in the regional monitoring combination set, and all identification features obtained by processing all monitoring images are sorted and combined to obtain an identification feature set;

[0042] It should be noted that image preprocessing and feature extraction for a number of monitoring images are both existing conventional technical solutions, and the specific steps are not repeated here; in addition, feature extraction is the feature of foreign objects on the ground in the monitoring image;

[0043] When analyzing the abnormal impact of the operation area on the identification feature set, the identification feature set is traversed to count the total number of identification features and analyzed. If the total number of identification features is 0, a normal instruction for the operation area is generated and the abnormal feature impact flag is set to 0;

[0044] If the total number of identification features is not 0, an abnormal instruction for the operation area is generated and several identification features in the identification feature set are traversed with the preset sample feature database. If there is a sample feature identical to the identification feature in the sample feature database, the corresponding identification feature is marked as the target identification feature;

[0045] The sample feature database is pre-set with a number of sample features, and the sample features are determined according to the existing hot work environment requirement data; the sample features are specifically features corresponding to different combustibles;

[0046] If there is no sample feature identical to the identification feature in the sample feature database, the corresponding identification feature is marked as a normal identification feature;

[0047] The total number n of target identification features is counted and analyzed. If the total number of target identification features is 0, a normal instruction for the operation area is generated and prompted. It can be understood that although there are foreign objects in the target area, the foreign objects are not combustibles, so it is determined that the environmental requirements for hot work are met;

[0048] If the total number of target identification features is not 0, a data processing instruction is generated, and the feature influence coefficients yi associated with different target identification features are obtained according to the data processing instruction, where i=1, 2, 3, ..., n; n is a positive integer; i is a different target identification feature, and the formula is used Calculate and obtain the abnormality Zy of the operation area corresponding to all target identification features; where NJj is the detection concentration of different combustible gases in the hot work area, which can be detected and obtained by existing different gas detection sensors, and NJj0 is the standard concentration of different combustible gases in the hot work area, which is determined according to the existing detection standard requirements data; j=1, 2, 3, ..., m; m is a positive integer; j is a different combustible gas; specifically, combustible gases include but are not limited to methane, propane, acetylene, which can be detected and obtained according to existing detection instruments;

[0049] Among them, different sample features are pre-set with a corresponding feature influence coefficient, and the feature influence coefficient is used to digitize and differentiate the abnormal influence of different sample features. The specific value of the feature influence coefficient can be set by professional and technical personnel in this field according to work experience and work requirement data;

[0050] In addition, the abnormality degree of the operation area is used to integrate and calculate the different abnormal data of the image recognition and analysis of the hot work area to digitally represent its abnormal impact; the larger the abnormality degree of the operation area, the greater the abnormal impact of the corresponding operation area;

[0051] Analyze the abnormality of the operating area to determine the abnormal impact corresponding to the operating area;

[0052] If the abnormality of the operation area is less than or equal to 1, an abnormal low impact instruction of the operation area is generated and prompted;

[0053] If the abnormality of the operation area is greater than 1, an abnormal high impact instruction of the operation area is generated and prompted;

[0054] Normal instructions for the operating area, the degree of abnormality in the operating area, and the abnormally low-impact instructions for the operating area or the abnormally high-impact instructions for the operating area obtained through analysis constitute the regional risk analysis data;

[0055] Different from the prior art solutions in which the risks of hot fire operation areas are identified and determined manually, in the embodiments of the present invention, multi-directional video recording, image processing and analysis are performed on the hot fire operation area to obtain target identification features, and data processing and calculation are performed on the target identification features to obtain the abnormality of the operation area. This can not only digitally represent the abnormal impact of the hot fire operation area, but also provide reliable operation area risk data support for the processing and analysis of the subsequent overall operation risks, thereby improving the automatic identification of dimensional risks in the hot fire operation area and the diversity of processing and utilization.

[0056] The operation specification image data acquisition and processing module is used to obtain the corresponding operation image by frontally photographing the operator performing the hot work. This can be achieved based on the on-site monitoring and recording device. The monitoring and recording device is used to record the entire process of the hot work, pre-process the operation image and perform matching analysis to obtain the operation risk analysis data; including:

[0057] Obtain standard operation features according to the type of hot work, the type of hot work includes but is not limited to welding and cutting type and baking and drying type, the standard operation features refer to the protection features corresponding to different protection tools, the protection tools include but are not limited to fireproof masks, face protection glasses, fireproof clothing, fireproof gloves, fireproof boots, etc., preprocess the operation image and perform feature recognition to obtain operation identification features, mark all the operation identification features obtained by recognition with numbers, and traverse and match all the numbered operation identification features with the sample operation feature set in turn, mark the sample operation features that are the same as the operation identification features as valid features; and mark the sample operation features that are not matched in the sample operation feature set as abnormal features;

[0058] Among them, image preprocessing and feature extraction of several monitoring images are both existing conventional technical solutions, and the specific steps are not repeated here; in addition, the feature extraction here is the protection features of the face, chest, hands, and legs of the person in the monitoring image; the sample operation feature concentration is constructed by the existing protection features of fireproof masks, facial protective glasses, fireproof clothing, fireproof gloves, fireproof boots, etc.;

[0059] Count the total number of identification features N1 corresponding to all operation identification features, and the total number of sample features N2 corresponding to all sample operation features in the sample operation feature set, and perform data analysis through the operation feature identification piecewise function and output the operation identification mark;

[0060] Among them, the expression of the operation feature recognition piecewise function is: ; In the formula, Zk is the characteristic influencing factor corresponding to different abnormal characteristics; k is different abnormal characteristics, k=1, 2, 3, ..., N2-N1; Cy is the abnormality degree of the operation, ;

[0061] It should be noted that different sample operation characteristics are preset with a corresponding characteristic impact factor, which is used to digitally and differentially represent the characteristic impact corresponding to the sample operation characteristics. The specific value of the characteristic impact factor can be determined based on the total number of accidents caused by different sample operation characteristics in history, or can be determined by the staff in this field based on work experience and work requirement data;

[0062] The abnormal degree of operation is used to integrate and calculate all abnormal data of operation to digitally represent the overall impact of the operation; the operation identification mark is used to classify the abnormal degree of operation and digitally represent it;

[0063] When determining the operation status corresponding to the operator according to the operation identification mark, the operation identification mark is analyzed, and if the operation identification mark is 0, a normal operation instruction is generated and prompted;

[0064] If the operation identification flag is not 0, the operation identification flag is compared with the operation identification threshold. If the operation identification flag is less than or equal to the operation identification threshold, a minor abnormal operation instruction is generated and prompted. The operation identification threshold is determined according to the total number of abnormalities of non-standard operation in the history.

[0065] If the operation identification flag is greater than the operation identification threshold, a severe operation abnormality instruction is generated and a prompt is given;

[0066] The abnormality degree of the operation, the operation identification mark, and the normal operation instructions, slightly abnormal operation instructions, or severely abnormal operation instructions obtained through analysis constitute the operation risk analysis data;

[0067] In the embodiment of the present invention, by monitoring and data processing from the operation protection dimension, all the acquired operation abnormality data are integrated and calculated to obtain the operation operation abnormality degree, and the operation operation abnormality degree is analyzed to obtain the corresponding operation identification mark and operation status instruction. This can not only monitor and digitally represent the operation protection standardization of the operator, but also provide reliable operation operation standard data support for the subsequent overall operation risk processing and analysis, thereby improving the diversity and comprehensiveness of automatic identification and processing of risks in the operation protection dimension.

[0068] The operation status integrated assessment management module is used to integrate and calculate the regional risk analysis data corresponding to the target area where the hot work is carried out and the operation risk analysis data corresponding to the operator to obtain the corresponding operation risk integration value, analyze the operation risk integration value to determine the overall operation risk corresponding to the hot work and implement targeted safety management and control; including:

[0069] Obtain the regional risk analysis data and operation risk analysis data corresponding to the hot work and traverse and analyze them. If the traversal and statistical results show both normal instructions for the operation area and normal instructions for the operation, generate normal instructions.

[0070] If the result of the traversal statistics does not contain both normal instructions for the work area and normal instructions for operation, an integrated instruction is generated, and the abnormality degree Zy of the work area in the regional risk analysis data and the abnormality degree Cy of the work operation in the operation risk analysis data are obtained according to the integrated instruction, and the integrated value Zf of the work risk corresponding to the hot work is calculated by the formula Zf=α×Zy+β×Cy; in the formula, α and β are different weight coefficients, 0<β<α;

[0071] It should be noted that the operational risk integration value is a numerical value that digitally represents the overall risk of hot work by integrating and calculating risk analysis data from different dimensions;

[0072] When the overall risk of the hot work operation is determined according to the operation risk integration value, the operation risk integration value is input into the operation risk identification piecewise function for data analysis and output of the operation risk identification, and the corresponding overall risk prompt of the operation is generated according to the operation risk identification, and targeted safety control is implemented for the hot work operation;

[0073] Among them, the expression of the piecewise function of operation risk identification is: ; In the formula, Y is the operational risk classification value, and the specific value of the operational risk classification value is determined according to the median value of all operational risk integration values ​​tested in the previous period;

[0074] According to the operation risk indicator with a value of 1 or 2, a corresponding overall low risk prompt or overall high risk prompt of the operation is generated respectively;

[0075] In addition, according to the operation risk identification with a value of 1 or 2, the safety management personnel are controlled to conduct on-site safety management or replace the operating personnel.

[0076] In the embodiment of the present invention, by integrating and calculating the risk analysis data of different dimensions, it is possible to digitally represent the overall operational risk of hot fire operations, and to provide dynamic risk prompts and dynamic safety management and control of hot fire operations based on the operational risk identifiers obtained through analysis, thereby improving the autonomous identification and evaluation effect and autonomous management and control effect of safety defense assistance for hot fire operations.

[0077] Embodiment 2: Based on Embodiment 1, further comprising:

[0078] The gas monitoring module is used to monitor the leakage of flammable and explosive gases in work stations or closed work spaces in real time. It monitors the leakage of acetylene gas, oxygen gas, argon gas, and carbon dioxide gas at welding points and welding sites with a central radius of 5 meters, eliminating the explosion caused by excessive flammable gas at welding stations and the suffocation hazard caused by the leakage concentration of carbon dioxide and argon gas reaching a certain level. Several gas monitoring devices are arranged around the welding points, and a gas alarm threshold is set. Once the on-site gas concentration is detected to exceed the threshold, the intelligent monitoring device will alarm in various ways such as sound and light, reminding on-site personnel to stop working immediately, turn off the power and gas source, start ventilation equipment or open windows for ventilation; and immediately start the solenoid valves of the acetylene and oxygen cylinder valves through 5G communication to cut off the gas supply valve; or cut off the power supply of the welding machine to force and automatically stop the operation;

[0079] The smoke monitoring module is used to monitor and warn the smoke concentration in the work station or confined space. The smoke concentration is monitored at the welding point and the welding site with a central radius of 5 meters to eliminate the hidden danger of suffocation caused by harmful smoke in the welding station to personnel; a number of smoke monitoring devices are arranged around the welding point to monitor the concentration of harmful smoke in real time and set the smoke alarm threshold. Once the smoke concentration on site exceeds the threshold, the intelligent monitoring device will alarm in various ways such as sound and light, reminding the on-site personnel to stop the operation immediately, turn off the power and evacuate to fresh air immediately, and manually start the ventilation equipment or open the window for ventilation;

[0080] The welding machine monitoring module is used to monitor the safety status of the welding machine and display it in real time. When the welding machine is in an abnormal operating state, such as the grounding clamp falling off, abnormally high current, operating parameters exceeding the safety threshold, etc., the welding machine will automatically power off and give a voice prompt to stop the operation, and the supervisor will intervene to handle the problem.

[0081] In addition, the system monitors whether the welding machine is online and the unsafe state of leakage and displays it in real time; configures leakage monitoring equipment on site to monitor the unsafe state of electrical equipment or lines such as welding machines, welding fume purifiers, and electric tools in real time due to leakage, automatically turns on leakage protection, and cuts off the power supply; and alarms are given through various means such as sound and light;

[0082] The workstation personnel monitoring module is used to monitor the online and offline status of personnel and provide prompts through the traffic light bar. When there are people in the working area, the red light will be on; when there are no people in the working area, the green light will be on. The infrared human body sensor will sense and provide prompts, so that the assessor knows whether there is someone working on the equipment, eliminating the safety hazards without assessor monitoring.

[0083] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0084] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0085] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0087] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent auxiliary system for fire operation safety defense based on multi-dimensional data, It is characterized in that include: The operation area image data acquisition and processing module is used to carry out all-round monitoring point photography of the target area for hot work to obtain monitoring images of corresponding positions and sort and combine them to obtain a regional monitoring combination set, and pre-process and match and analyze several monitoring images in the regional monitoring combination set to obtain regional risk analysis data; Among them, a number of monitoring images sorted in the regional monitoring combination set are preprocessed and feature extracted, and all identification features obtained by processing all monitoring images are sorted and combined to obtain an identification feature set; When analyzing the abnormal impact of the operation area on the identification feature set, the total number of identification features is traversed and analyzed. If the total number of identification features is 0, a normal instruction for the operation area is generated and the abnormal feature impact flag is set to 0; If the total number of identification features is not 0, an abnormal instruction for the operation area is generated and several identification features in the identification feature set are traversed with the preset sample feature database. If there is a sample feature identical to the identification feature in the sample feature database, the corresponding identification feature is marked as the target identification feature; If there is no sample feature identical to the identification feature in the sample feature database, the corresponding identification feature is marked as a normal identification feature; The total number n of target identification features is counted and analyzed. If the total number of target identification features is 0, a normal instruction for the operation area is generated and prompted; If the total number of target identification features is not 0, a data processing instruction is generated, and according to the data processing instruction, the characteristic influence coefficients yi associated with different target identification features are obtained, where i=1, 2, 3, ..., n; n is a positive integer; i is a different target identification feature, and the detection concentrations of different combustible gases in the hot work area and the corresponding standard concentrations are calculated to obtain the abnormality of the operation area corresponding to all target identification features; Analyze the abnormality of the operation area to determine the abnormal impact corresponding to the operation area and obtain an abnormal low impact instruction for the operation area or an abnormal high impact instruction for the operation area; Normal instructions for the operating area, the degree of abnormality in the operating area, and the abnormally low-impact instructions for the operating area or the abnormally high-impact instructions for the operating area obtained through analysis constitute the regional risk analysis data; The operation specification image data acquisition and processing module is used to take a frontal video of the operator performing the hot work to obtain the corresponding operation image, pre-process and match the operation image to obtain the operation risk analysis data; Among them, the standard operation features are obtained according to the type of hot work, the operation images are preprocessed and feature recognized to obtain the operation identification features, all the operation identification features obtained by recognition are numbered and marked, and all the numbered operation identification features are traversed and matched with the sample operation feature set in turn, and the sample operation features that are the same as the operation identification features are marked as valid features; and the sample operation features that are not matched in the sample operation feature set are marked as abnormal features; Count the total number of identification features N1 corresponding to all operation identification features, and the total number of sample features N2 corresponding to all sample operation features in the sample operation feature set, and perform data analysis through the operation feature identification piecewise function and output the operation identification mark; the operation identification mark is used to classify the abnormality of the operation and digitally represent it; When determining the operation status corresponding to the operator according to the operation identification mark, the operation identification mark is analyzed, and if the operation identification mark is 0, a normal operation instruction is generated and prompted; If the operation identification flag is not 0, the operation identification flag is compared with the operation identification threshold value for analysis. If the operation identification flag is less than or equal to the operation identification threshold value, a slight abnormal operation instruction is generated and a prompt is given; If the operation identification flag is greater than the operation identification threshold, a severe operation abnormality instruction is generated and a prompt is given; The abnormality degree of the operation, the operation identification mark, and the normal operation instructions, slightly abnormal operation instructions, or severely abnormal operation instructions obtained through analysis constitute the operation risk analysis data; The operation status integration assessment management module is used to integrate and calculate the regional risk analysis data corresponding to the target area where the hot work is to be carried out and the operation risk analysis data corresponding to the operator to obtain the corresponding operation risk integration value, analyze the operation risk integration value to determine the overall operation risk corresponding to the hot work and implement targeted safety management and control; the operation risk integration value is a numerical value that digitally represents the overall risk of the hot work by integrating and calculating the risk analysis data of different dimensions; Among them, the regional risk analysis data and operational risk analysis data corresponding to the implementation of hot work are obtained and traversed and analyzed. If the results of the traversal statistics do not contain both normal instructions for the operating area and normal instructions for the operation, an integrated instruction is generated. According to the integrated instruction, the operating area abnormality Zy in the regional risk analysis data and the operating operation abnormality Cy in the operational risk analysis data are obtained, and the operational risk integration value Zf corresponding to the hot work is calculated through the formula Zf=α×Zy+β×Cy; wherein α and β are different weight coefficients, 0<β<α.

2. According to claim 1, a fire operation safety defense intelligent auxiliary system based on multidimensional data, It is characterized in that By formula Calculate and obtain the abnormality degree Zy of the operation area corresponding to all target identification features; where NJj is the detection concentration of different combustible gases in the hot work area, NJj0 is the standard concentration of different combustible gases in the hot work area; j=1, 2, 3,..., m; m is a positive integer; j is a different combustible gas.

3. According to claim 1, a fire operation safety defense intelligent auxiliary system based on multidimensional data, It is characterized in that The expression of the piecewise function for operating feature recognition is: ; In the formula, Zk is the characteristic influencing factor corresponding to different abnormal characteristics; k is different abnormal characteristics, k=1, 2, 3, ..., N2-N1; Cy is the abnormality degree of the operation, .

4. According to claim 1, a fire operation safety defense intelligent auxiliary system based on multidimensional data, It is characterized in that When the overall risk of the hot work operation is determined according to the operation risk integration value, the operation risk integration value is input into the operation risk identification piecewise function for data analysis and output of the operation risk identification, and the corresponding overall risk prompt of the operation is generated according to the operation risk identification, and targeted safety control is implemented for the hot work operation; According to the operation risk indicator with a value of 1 or 2, a corresponding overall low risk prompt or overall high risk prompt of the operation is generated respectively; In addition, according to the operation risk identification with a value of 1 or 2, the safety management personnel are controlled to conduct on-site safety management or replace the operating personnel.

5. According to claim 4, a fire operation safety defense intelligent auxiliary system based on multidimensional data, It is characterized in that The expression of the piecewise function for job risk identification is: ; Where Y is the operation risk classification value.

Images