Safety inspection method and system based on intelligent fire protection

Abstract

The invention discloses a safety inspection method and system based on intelligent fire protection, and relates to the technical field of intelligent fire protection, and the method comprises the steps of heat conduction layer monitoring, heat insulation layer monitoring, regular fire protection inspection and abnormal fire protection inspection. Analyzing to obtain a heat conduction risk index of each abnormal heat conduction monitoring point; secondly, thermal insulation layer temperature change data are collected through thermal insulation layer monitoring, and thermal insulation risk indexes of all abnormal thermal insulation monitoring points are analyzed and obtained; according to the method, the monitoring and risk assessment refinement degree of a heat conduction layer and a heat insulation layer is improved, the inspection scheme is scientifically planned in combination with an intelligent algorithm, the risk assessment precision is improved, the risk assessment precision is improved, and the risk assessment precision of the heat conduction layer and the heat insulation layer is improved. The accuracy and efficiency of fire safety inspection are effectively improved, and the fire risk is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent fire protection technology, and in particular to a safety inspection method and system based on intelligent fire protection. Background Art

[0002] With the acceleration of urbanization and the increasing complexity of industrial facilities, a large number of safety hazards have increased. In order to maintain fire safety, a safety inspection method and system based on intelligent fire protection is needed.

[0003] Existing technologies, such as the invention patent application with announcement number CN118397725B, disclose an intelligent inspection device for energy stations and parks and a method for its adaptive environment, which relates to the field of intelligent inspection technology; through infrared thermal imaging technology and analysis of appearance images, it can accurately assess the thermal effect risk and aging degree of each equipment in each area, and at the same time, by analyzing environmental information including humidity, temperature, noise amplitude and other factors, it can accurately assess the degree of interference of each regional environment on the equipment operation, providing data support for the realization of intelligent inspection planning; through comprehensive analysis of operating parameters and environmental interference values, it can dynamically adjust the inspection route and priority to ensure that the inspection work can respond to changes in equipment conditions in a timely manner, thereby improving the flexibility and adaptability of the inspection; in addition, by calculating the inspection efficiency value and call value, it can optimize the allocation of inspection personnel to ensure that inspection resources are used most effectively, thereby improving the resource allocation efficiency of the inspection.

[0004] The above scheme has the following technical problems: 1. The monitoring objects of the above scheme are very limited. It mainly monitors the thermal effects and aging risks of equipment in energy stations and parks. The monitoring objects are concentrated on the equipment itself. There is a lack of monitoring of key parts in the building structure such as thermal conductivity layer and thermal insulation layer. The performance of thermal conductivity layer and thermal insulation layer directly affects fire safety. The above scheme does not analyze the data of thermal conductivity layer and thermal insulation layer, and cannot fully consider potential fire risk factors.

[0005] 2. The risk assessment algorithm of the above scheme is not deep enough. In terms of risk assessment, although the above scheme analyzes the equipment operating status and environmental interference, the calculation process relies on a large number of set proportional coefficients and thresholds, and lacks in-depth mining of the inherent laws of the data. For example, in temperature status monitoring and aging status monitoring, risks are mainly assessed by comparison with set intervals and simple weighted calculations. A complex equipment spatial continuity analysis is not constructed, and the distribution status of thermal conductivity and insulation efficiency in space is not utilized, which reduces the accuracy of risk judgment.

[0006] 3. The above scheme lacks scientificity in dividing the inspection area. After obtaining the inspection value based on comprehensive analysis of equipment and environmental information, the above scheme only determines the inspection points by setting inspection thresholds, and does not scientifically cluster the inspection area. In the allocation of inspection points, a circle is drawn with the target inspection point as the center to select the preliminary call end, and then the call value is calculated based on multiple indicators to allocate inspection tasks. The process is complicated and does not fully consider the spatial distribution characteristics of the region. The inspection area is not divided based on spatial clustering and abnormal point density, which reduces the rationality of inspection resource allocation. Summary of the Invention

[0007] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a safety inspection method and system based on intelligent fire protection.

[0008] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a safety inspection method based on intelligent fire protection, comprising the following steps: Step 1, thermal conductivity layer monitoring: collecting thermal conductivity layer temperature change data, analyzing the thermal conductivity layer temperature change data, and obtaining the thermal conductivity risk index of each abnormal thermal conductivity monitoring point.

[0009] Step 2: Thermal insulation layer monitoring: Collect and analyze the temperature change data of the thermal insulation layer to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point.

[0010] Step 3: Regular fire inspections: Obtain the spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring point from the database, set up each inspection area, and thereby obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area, and then set up the inspection plan.

[0011] Step 4: Abnormal fire inspection: Collect inspection information, analyze the inspection information, obtain the environmental risk index, issue fire warnings, and then set up a heavy inspection plan.

[0012] Preferably, the setting of each inspection area is specifically carried out as follows: the spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring are the Euclidean distance of each abnormal thermal conductivity monitoring point and the Euclidean distance of each abnormal thermal insulation monitoring, respectively. The DBSCAN algorithm is used, and the Euclidean distance is less than the preset Euclidean reference distance as the threshold. The abnormal thermal conductivity monitoring points and the abnormal thermal insulation monitoring points are spatially clustered, and the points with the Euclidean distance less than the preset Euclidean reference distance are divided into the same area, thereby obtaining each basic inspection area.

[0013] Count the abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in each basic inspection area to obtain the number of abnormal points and area of ​​each basic inspection, divide the number of abnormal points in each basic inspection area by the corresponding area to obtain the abnormal point density of each basic inspection area, divide the maximum value of the abnormal point density of adjacent basic inspection areas by the minimum value to obtain the density ratio of adjacent basic inspection areas, obtain the preset density ratio interval from the database, if the density ratio of adjacent basic inspection areas falls within the preset density ratio interval, and the area center distance of adjacent basic inspection areas is less than the preset standard reduction area, merge the adjacent basic inspection areas to obtain each inspection area.

[0014] Preferably, the inspection plan is set up, and the specific setting process is as follows: count the abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in each inspection area to obtain the number of abnormal points and the area of ​​each inspection area, divide the number of abnormal points in each inspection area by the corresponding area to obtain the abnormal point density of each inspection area, obtain the risk correction factor corresponding to each abnormal density from the database, and thereby obtain the risk correction factor of each inspection area.

[0015] The maximum thermal conductivity risk index and the maximum thermal insulation risk index of each inspection area are obtained from the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area. The maximum thermal conductivity risk index and the maximum thermal insulation risk index of each inspection area are weighted and calculated to obtain the risk base index of each inspection area. The risk base index of each inspection area is multiplied by the corresponding risk correction factor to obtain the risk index of each inspection area. Each inspection area with a risk index greater than or equal to the standard inspection risk index is recorded as a high-risk inspection area, and each inspection area with a risk index less than the standard inspection risk index is recorded as a low-risk inspection area.

[0016] The inspection plan is: all thermal conductivity monitoring points and thermal insulation monitoring points in the high-risk inspection area are recorded as inspection points, and all abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in the low-risk inspection area are recorded as inspection points. In this way, the inspection points are obtained, and the shortest path for inspecting each inspection point is obtained through genetic algorithm, and drone inspection is carried out according to the shortest path.

[0017] On the other hand, the present invention provides a safety inspection system based on intelligent fire protection, including the following modules: a thermal conductive layer monitoring module, which is used to collect the temperature change data of the thermal conductive layer, analyze the temperature change data of the thermal conductive layer, and obtain the thermal conductive risk index of each abnormal thermal conductive monitoring point.

[0018] The thermal insulation layer monitoring module is used to collect and analyze the temperature change data of the thermal insulation layer to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point.

[0019] The regular fire inspection module is used to obtain the spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring point from the database, set each inspection area, thereby obtaining the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area, and then set the inspection plan.

[0020] The abnormal fire inspection module is used to collect inspection information, analyze the inspection information, obtain the environmental risk index, issue fire warnings, and then set up heavy inspection plans.

[0021] The beneficial effects of the present invention are: 1. The present invention first collects the temperature change data of the thermal conductive layer through thermal conductive layer monitoring, and analyzes to obtain the thermal conductive risk index of each abnormal thermal conductive monitoring point; secondly, the present invention collects the temperature change data of the thermal insulation layer through thermal insulation layer monitoring, and analyzes to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point; then, through regular fire inspections, based on the inspection data of abnormal monitoring points, the inspection area is divided, and then the inspection plan is set, and finally, specific inspections are carried out through abnormal fire inspections. The present invention improves the refinement of monitoring and risk assessment of the thermal conductive layer and the thermal insulation layer, combines intelligent algorithms to scientifically plan inspection plans, effectively improves the accuracy and efficiency of fire safety inspections, and reduces fire risks.

[0022] 2. This invention monitors the thermal conductivity layer and the thermal insulation layer, two key areas in the fire protection field that are closely related to fire risk. Performance changes in these layers can directly cause fires or affect the speed of fire spread. By collecting data such as the temperature deviation and heat flux mutation rate of the thermal conductivity layer, as well as information such as the thermal resistance degradation and thermal diffusion coefficient fluctuation of the thermal insulation layer, and conducting in-depth analysis, potential fire hazards can be more accurately identified, alleviating deficiencies in building structure fire safety monitoring and effectively improving the comprehensiveness of fire hazard detection.

[0023] 3. The present invention integrates data from multiple dimensions for calculation, systematically analyzes the temperature change data of the thermal conductive layer, comprehensively evaluates the thermal conductivity risk from multiple parameter levels, and further refines the risk assessment results by calculating the thermal conductivity risk variation index and introducing a thermal conductivity correction factor. This can more scientifically and accurately assess the fire safety risk level, providing a reliable basis for subsequent decision-making.

[0024] 4. When setting up the inspection plan, the present invention divides the area into high-risk and low-risk inspection areas according to the risk index of each inspection area, adopts different inspection point setting strategies for different risk areas, and uses genetic algorithms to plan the shortest path for drone inspections, so that inspection resources are more reasonably allocated, the inspection efficiency is greatly improved, the inspection tasks can be completed more quickly and efficiently, and potential fire problems can be discovered and handled in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 The figure is a flow chart of the steps for implementing the method of the present invention.

[0027] Figure 2 This is a schematic diagram of the system structure connection of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0029] according to Figure 1 As shown, the present invention provides a safety inspection method based on intelligent fire protection, comprising the following steps: Step 1, thermal conductivity layer monitoring: collecting thermal conductivity layer temperature change data, analyzing the thermal conductivity layer temperature change data, and obtaining the thermal conductivity risk index of each abnormal thermal conductivity monitoring point.

[0030] In a specific embodiment, the thermal conductivity layer temperature change data is collected, and the specific collection process is as follows: the thermal conductivity layer temperature change data includes the temperature deviation of each thermal conductivity monitoring point, the heat flux mutation rate, the contact thermal resistance growth rate, and the thermal conductivity efficiency decay rate; a temperature sensor is installed at each thermal conductivity monitoring point, and the temperature of each thermal conductivity monitoring point is collected. The temperature of each thermal conductivity monitoring point is averaged and calculated to obtain the average thermal conductivity temperature; the difference between the temperature of each thermal conductivity monitoring point and the average thermal conductivity temperature is divided by the average thermal conductivity temperature to obtain the temperature deviation of each thermal conductivity monitoring point.

[0031] The heat flux of each thermal conductivity monitoring point is collected by a heat flux sensor to obtain the heat flux at each collection time point of each thermal conductivity monitoring point. The average heat flux of each thermal conductivity monitoring point is calculated by averaging. The difference between the heat flux at the current collection time point of each thermal conductivity monitoring point and the heat flux at the last collection time point in the past is subtracted and divided by the product of the corresponding average heat flux and the interval time to obtain the heat flux mutation rate of each thermal conductivity monitoring point.

[0032] The temperatures of the inner and outer layers are collected by temperature sensors, and the temperature of the outer layer is subtracted from the temperature of the inner layer to obtain the temperature difference of each thermal conductivity monitoring point. The temperature difference of each thermal conductivity monitoring point is divided by the corresponding heat flux to obtain the thermal resistance of each thermal conductivity monitoring point. The difference between the thermal resistance of each thermal conductivity monitoring point at the current collection time point and the thermal resistance at the last collection time point in the past is divided by the thermal resistance at the last collection time point in the past to obtain the contact thermal resistance growth rate of each thermal conductivity monitoring point.

[0033] The input heat and output heat of each thermal conductivity monitoring point are collected by a heat flow meter. The output heat of each thermal conductivity monitoring point is divided by the input heat to obtain the heat transfer efficiency index of each thermal conductivity monitoring point. The difference between the current heat transfer efficiency index of each thermal conductivity monitoring point and the initial heat transfer efficiency index is divided by the initial heat transfer efficiency index to obtain the thermal conductivity efficiency decay rate.

[0034] In a specific embodiment, the thermal conductivity layer temperature change data is analyzed, and the specific analysis process is as follows: the thermal conductivity layer temperature change data includes the temperature deviation, heat flux mutation rate, contact thermal resistance growth rate, and thermal conductivity efficiency decay rate of each thermal conductivity monitoring point; the temperature deviation threshold, heat flux mutation rate threshold, contact thermal resistance growth rate threshold, and thermal conductivity efficiency decay rate threshold are obtained from a database; the temperature deviation of each thermal conductivity monitoring point is divided by the temperature deviation threshold to obtain a first-category thermal conductivity risk rate of each thermal conductivity monitoring point; the heat flux mutation rate of each thermal conductivity monitoring point is divided by the heat flux mutation rate threshold to obtain a second-category thermal conductivity risk rate of each thermal conductivity monitoring point; the contact thermal resistance growth rate of each thermal conductivity monitoring point is divided by the contact thermal resistance growth rate threshold to obtain a third-category thermal conductivity risk rate of each thermal conductivity monitoring point; and the thermal conductivity efficiency decay rate of each thermal conductivity monitoring point is divided by the thermal conductivity efficiency decay rate threshold to obtain a fourth-category thermal conductivity risk rate of each thermal conductivity monitoring point.

[0035] It should be noted that the temperature deviation threshold, heat flux mutation rate threshold, contact thermal resistance growth rate threshold, and thermal conductivity efficiency attenuation rate threshold are all thresholds for temperature change data of the thermal layer in a normal thermal environment. When the collected value is greater than the threshold, it indicates that the current thermal environment is abnormal and prone to fire. The specific values ​​are set by the staff.

[0036] The maximum value is selected from the first type of thermal conductivity risk rate, the second type of thermal conductivity risk rate, the third type of thermal conductivity risk rate and the fourth type of thermal conductivity risk rate of each thermal conductivity monitoring point and recorded as the thermal conductivity risk rate of each thermal conductivity monitoring point.

[0037] In a specific embodiment, the thermal conductivity risk index of each abnormal thermal conductivity monitoring point is obtained through the following analysis process: each thermal conductivity monitoring point having a thermal conductivity risk rate greater than a benchmark thermal conductivity risk rate is recorded as an abnormal thermal conductivity monitoring point, and the thermal conductivity risk rate interval corresponding to each thermal conductivity risk basic index is obtained from a database. If the thermal conductivity risk rate of a thermal conductivity monitoring point falls within the thermal conductivity risk rate interval corresponding to a certain thermal conductivity risk basic index, it is indicated that the thermal conductivity monitoring point has the thermal conductivity risk basic index, thereby obtaining the thermal conductivity risk basic index of each thermal conductivity monitoring point.

[0038] The monitoring area corresponding to each abnormal thermal conductivity monitoring point is obtained from the database to obtain the basic thermal conductivity risk index of each abnormal thermal conductivity monitoring point in each abnormal thermal conductivity monitoring point area. The average of the basic thermal conductivity risk indexes of each abnormal thermal conductivity monitoring point in each abnormal thermal conductivity monitoring point area is calculated to obtain the average basic thermal conductivity risk index of each abnormal thermal conductivity monitoring point area. The average basic thermal conductivity risk index of each abnormal thermal conductivity monitoring point area is divided by the basic thermal conductivity risk index of the corresponding abnormal thermal conductivity monitoring point to obtain the thermal conductivity risk variation index of each abnormal thermal conductivity monitoring point.

[0039] The thermal conductivity correction factor corresponding to each thermal conductivity risk variation index is obtained from the database to obtain the thermal conductivity correction factor of each abnormal thermal conductivity monitoring point. The thermal conductivity risk basic index of each abnormal thermal conductivity monitoring point is multiplied by the thermal conductivity correction factor to obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point.

[0040] Step 2: Thermal insulation layer monitoring: Collect and analyze the temperature change data of the thermal insulation layer to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point.

[0041] In a specific embodiment, the insulation layer temperature change data is collected, and the specific collection process is as follows: the insulation layer temperature change data includes the thermal resistance degradation degree, thermal diffusion coefficient fluctuation degree, hot spot defect depth and hot spot defect range of each insulation monitoring point, and the current thermal resistance of each insulation monitoring point is obtained by Fourier's law. The factory thermal resistance in the database is subtracted from the current thermal resistance of each insulation monitoring point and divided by the factory thermal resistance to obtain the thermal resistance degradation degree of each insulation monitoring point.

[0042] The thermal diffusivity of each depth region of the insulation layer at each insulation monitoring point is obtained by one-dimensional unsteady-state heat conduction equation. The average thermal diffusivity of each insulation monitoring point is obtained by mean calculation. The difference between the maximum thermal diffusivity and the minimum thermal diffusivity of the insulation layer at each insulation monitoring point is divided by the average thermal diffusivity to obtain the thermal diffusivity fluctuation of each insulation monitoring point.

[0043] Based on the principle of thermal wave imaging inversion, the propagation time of the thermal wave in the insulation layer of each insulation monitoring point is measured, and the insulation defect depth corresponding to each propagation time is obtained from the database, thereby obtaining the insulation defect depth of each insulation monitoring point.

[0044] An infrared thermal imager is used to obtain thermal images of the insulation layer surface. The hotspot area is identified through image processing technology, and its area is calculated as the hotspot defect range. The threshold segmentation algorithm is used to separate the hotspot area from the background according to the temperature difference. The area is then calculated through pixel statistics to obtain the hotspot defect range of each insulation monitoring point.

[0045] In a specific embodiment, the temperature change data of the thermal insulation layer is analyzed, and the specific analysis process is as follows: the temperature change data of the thermal insulation layer includes the thermal resistance degradation degree, thermal diffusion coefficient fluctuation degree, hot spot defect depth and hot spot defect range of each thermal insulation monitoring point, and the thermal resistance degradation degree threshold, thermal diffusion coefficient fluctuation degree threshold, hot spot defect depth threshold and hot spot defect range threshold are obtained from the database. The thermal resistance degradation degree of each thermal insulation monitoring point is divided by the thermal resistance degradation degree threshold to obtain the first type of thermal insulation risk rate of each thermal insulation monitoring point, the thermal diffusion coefficient fluctuation degree of each thermal insulation monitoring point is divided by the thermal diffusion coefficient fluctuation threshold to obtain the second type of thermal insulation risk rate of each thermal insulation monitoring point, the hot spot defect depth of each thermal insulation monitoring point is divided by the hot spot defect depth threshold to obtain the third type of thermal insulation risk rate of each thermal insulation monitoring point, and the hot spot defect range of each thermal insulation monitoring point is divided by the hot spot defect range threshold to obtain the fourth type of thermal insulation risk rate of each thermal insulation monitoring point.

[0046] It should be noted that the thermal resistance degradation threshold, thermal diffusion coefficient fluctuation threshold, hot spot defect depth threshold and hot spot defect range threshold are all thresholds for temperature change data of the insulation layer under normal insulation conditions. When the collected value is greater than the threshold, it indicates that the insulation material is abnormal and prone to fire. The specific values ​​are set by the staff.

[0047] The maximum value is selected from the first type of thermal insulation risk rate, the second type of thermal insulation risk rate, the third type of thermal insulation risk rate and the fourth type of thermal insulation risk rate of each thermal insulation monitoring point and recorded as the thermal insulation risk rate of each thermal insulation monitoring point.

[0048] In a specific embodiment, the insulation risk index of each abnormal insulation monitoring point is obtained, and the analysis process is as follows: each insulation monitoring point whose insulation risk rate is greater than the benchmark insulation risk rate is recorded as an abnormal insulation monitoring point, and the insulation risk rate interval corresponding to each insulation risk basic index is obtained from the database. If the insulation risk rate of a certain insulation monitoring point belongs to the insulation risk rate interval corresponding to a certain insulation risk basic index, it indicates that the insulation monitoring point is the insulation risk basic index, thereby obtaining the insulation risk basic index of each insulation monitoring point.

[0049] The monitoring areas corresponding to the abnormal thermal insulation monitoring points are obtained from the database to obtain the basic thermal insulation risk index of each abnormal thermal insulation monitoring point in the abnormal thermal insulation monitoring point area. The average of the basic thermal insulation risk indexes of each abnormal thermal insulation monitoring point in the abnormal thermal insulation monitoring point area is calculated to obtain the average basic thermal insulation risk index of each abnormal thermal insulation monitoring point area. The average basic thermal insulation risk index of each abnormal thermal insulation monitoring point area is divided by the basic thermal insulation risk index of the corresponding abnormal thermal insulation monitoring point to obtain the thermal insulation risk variation index of each abnormal thermal insulation monitoring point.

[0050] The insulation correction factor corresponding to each insulation risk variation index is obtained from the database to obtain the insulation correction factor of each abnormal insulation monitoring point. The insulation risk basic index of each abnormal insulation monitoring point is multiplied by the insulation correction factor to obtain the insulation risk index of each abnormal insulation monitoring point.

[0051] Step 3: Regular fire inspections: Obtain spatial data of each abnormal thermal conductivity monitoring point and each abnormal thermal insulation monitoring point from the database, set up inspection areas, and thereby obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area, and then set up inspection plans;

[0052] In a specific embodiment, the setting of each inspection area is specifically carried out as follows: the spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring are the Euclidean distance of each abnormal thermal conductivity monitoring point and the Euclidean distance of each abnormal thermal insulation monitoring, respectively. The DBSCAN algorithm is used, and the Euclidean distance is less than the preset Euclidean reference distance as the threshold. The abnormal thermal conductivity monitoring points and the abnormal thermal insulation monitoring points are spatially clustered, and the points with the Euclidean distance less than the preset Euclidean reference distance are divided into the same area, thereby obtaining each basic inspection area.

[0053] Count the abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in each basic inspection area to obtain the number of abnormal points and area of ​​each basic inspection, divide the number of abnormal points in each basic inspection area by the corresponding area to obtain the abnormal point density of each basic inspection area, divide the maximum value of the abnormal point density of adjacent basic inspection areas by the minimum value to obtain the density ratio of adjacent basic inspection areas, obtain the preset density ratio interval from the database, if the density ratio of adjacent basic inspection areas falls within the preset density ratio interval, and the area center distance of adjacent basic inspection areas is less than the preset standard reduction area, merge the adjacent basic inspection areas to obtain each inspection area.

[0054] In a specific embodiment, the inspection plan is set up, and the specific setting process is as follows: count the abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in each inspection area to obtain the number of abnormal points and the area of ​​each inspection area, divide the number of abnormal points in each inspection area by the corresponding area to obtain the abnormal point density of each inspection area, obtain the risk correction factor corresponding to each abnormal density from the database, and thereby obtain the risk correction factor of each inspection area.

[0055] The maximum thermal conductivity risk index and the maximum thermal insulation risk index of each inspection area are obtained from the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area. The maximum thermal conductivity risk index and the maximum thermal insulation risk index of each inspection area are weighted and calculated to obtain the risk base index of each inspection area. The risk base index of each inspection area is multiplied by the corresponding risk correction factor to obtain the risk index of each inspection area. Each inspection area with a risk index greater than or equal to the standard inspection risk index is recorded as a high-risk inspection area, and each inspection area with a risk index less than the standard inspection risk index is recorded as a low-risk inspection area.

[0056] The inspection plan is: all thermal conductivity monitoring points and thermal insulation monitoring points in the high-risk inspection area are recorded as inspection points, and all abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in the low-risk inspection area are recorded as inspection points. In this way, the inspection points are obtained, and the shortest path for inspecting each inspection point is obtained through genetic algorithm, and drone inspection is carried out according to the shortest path.

[0057] Step 4: Abnormal fire inspection: Collect inspection information, analyze the inspection information, obtain the environmental risk index, issue fire warnings, and then set up a heavy inspection plan.

[0058] In a specific embodiment, the inspection information is collected, and the specific collection process is as follows: the inspection information includes the ambient temperature, ambient wind speed, regional environmental flammability index and regional risk index of each monitoring point, the ambient temperature and ambient wind speed of each monitoring point are collected by the temperature sensor and eddy current sensor of the drone, the corresponding area picture of each monitoring point is collected by the drone camera, the flammable material space volume and the regional space volume are obtained by image recognition, the flammable material space volume is divided by the regional space volume to obtain the regional environmental flammability index, the thermal conductivity risk index of each monitoring point is obtained by the process of obtaining the thermal conductivity risk index of the thermal conductivity monitoring point, the thermal insulation risk index of each monitoring point is obtained by the process of obtaining the thermal insulation risk index of the thermal insulation monitoring point, the thermal conductivity risk index and the thermal insulation risk index of each monitoring point are weighted and calculated to obtain the regional risk index of each monitoring point.

[0059] In a specific embodiment, the inspection information is analyzed, and the specific analysis process is as follows: the inspection information includes the ambient temperature, ambient wind speed, regional environmental flammability index and regional risk index of each monitoring point, and the ambient temperature threshold, ambient wind speed threshold, regional environmental flammability index threshold and regional risk index threshold are obtained from the database. When the ambient temperature of a monitoring point exceeds the threshold, the ambient wind speed exceeds the threshold, the regional environmental flammability index exceeds the threshold or the regional risk index exceeds the threshold, the monitoring area corresponding to the monitoring point is recorded as an inspection warning area, and a warning is issued.

[0060] It should be noted that the ambient temperature threshold, ambient wind speed threshold, regional environmental flammability index threshold and regional risk index threshold are all inspection environment data thresholds for normal environments. When the collected value is greater than the threshold, it means that there is a risk of fire in the environment. The specific settings are set by the staff.

[0061] In a specific embodiment, the re-inspection plan is set up, and the specific setting process is as follows: after the warning, the inspection warning area is inspected at preset intervals, and the regional risk index is collected to obtain the regional risk index of each collection time point in the inspection warning area, and a regional risk index change graph that changes with time is established. The regional risk index change trend slope is obtained through image recognition technology, and the risk index threshold and the regional risk index change trend slope threshold are obtained from the database. When the regional risk index of the inspection warning area is greater than the risk index threshold or the regional risk index change trend slope is greater than the regional risk index change trend slope threshold, a building abnormality warning is issued.

[0062] It should be noted that the risk index threshold and the regional risk index change trend slope threshold are both thresholds for regional building risk data after normal warning. When the collected value is greater than the threshold, it indicates that the building's thermal insulation effect is poor and cannot effectively prevent fires. The specific value is set by the staff.

[0063] according to Figure 2 As shown, the present invention provides a safety inspection system based on intelligent fire protection, which includes the following modules: a thermal conductive layer monitoring module, a thermal insulation layer monitoring module, a regular fire inspection module, an abnormal fire inspection module and a database.

[0064] The thermal insulation layer monitoring module is respectively connected to the thermal conductive layer monitoring module and the regular fire inspection module, the abnormal fire inspection module is connected to the regular fire inspection module, and the thermal conductive layer monitoring module, the thermal insulation layer monitoring module, the regular fire inspection module, and the abnormal fire inspection are all connected to the database.

[0065] The thermal conductivity layer monitoring module is used to collect the temperature change data of the thermal conductivity layer, analyze the temperature change data of the thermal conductivity layer, and obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point.

[0066] The thermal insulation layer monitoring module is used to collect and analyze the temperature change data of the thermal insulation layer to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point.

[0067] The regular fire inspection module is used to obtain the spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring point from the database, set each inspection area, thereby obtaining the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area, and then set the inspection plan.

[0068] The abnormal fire inspection module is used to collect inspection information, analyze the inspection information, obtain the environmental risk index, issue fire warnings, and then set up heavy inspection plans.

[0069] A database is used to store temperature deviation thresholds, heat flux mutation rate thresholds, contact thermal resistance growth rate thresholds, thermal conductivity efficiency attenuation rate thresholds, thermal conductivity risk rate intervals corresponding to each thermal conductivity risk basic index, monitoring areas corresponding to each abnormal thermal conductivity monitoring point, thermal conductivity correction factors corresponding to each thermal conductivity risk variation index, factory thermal resistance, insulation defect depth corresponding to each propagation time, thermal resistance degradation thresholds, thermal diffusion coefficient fluctuation thresholds, hot spot defect depth thresholds, hot spot defect range thresholds, insulation risk rate intervals corresponding to each thermal insulation risk basic index, monitoring areas corresponding to each abnormal thermal insulation monitoring point, insulation correction factors corresponding to each thermal insulation risk variation index, inspection data of each abnormal thermal conductivity monitoring point and each abnormal thermal insulation monitoring, preset density ratio intervals, risk correction factors corresponding to each abnormal density, ambient temperature thresholds, ambient wind speed thresholds, regional ambient flammability index thresholds, regional risk index thresholds, risk index thresholds, and regional risk index change trend slope thresholds.

[0070] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the scope of protection of the present invention.

Claims

1. A safety inspection method based on intelligent fire protection, characterized in that: The steps include: Step 1: Thermal Conductive Layer Monitoring: Collect and analyze the temperature change data of the thermal conductive layer to obtain the thermal conductive risk index of each abnormal thermal conductive monitoring point; Step 2: Thermal insulation layer monitoring: Collect and analyze the temperature change data of the thermal insulation layer to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point; Step 3: Regular fire inspections: Obtain spatial data of each abnormal thermal conductivity monitoring point and each abnormal thermal insulation monitoring point from the database, set up inspection areas, and thereby obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area, and then set up inspection plans; Step 4: Abnormal fire inspection: Collect inspection information, analyze the inspection information, obtain the environmental risk index, issue fire warnings, and then set up a heavy inspection plan.

2. A safety inspection method based on intelligent fire protection according to claim 1, characterized in that: The specific analysis process of analyzing the temperature change data of the heat conducting layer is as follows: The temperature change data of the thermal conductivity layer includes the temperature deviation, heat flux mutation rate, contact thermal resistance growth rate, and thermal conductivity efficiency decay rate of each thermal conductivity monitoring point. The temperature deviation threshold, heat flux mutation rate threshold, contact thermal resistance growth rate threshold, and thermal conductivity efficiency decay rate threshold are obtained from the database. The temperature deviation of each thermal conductivity monitoring point is divided by the temperature deviation threshold to obtain the first type of thermal conductivity risk rate of each thermal conductivity monitoring point. The heat flux mutation rate of each thermal conductivity monitoring point is divided by the heat flux mutation rate threshold to obtain the second type of thermal conductivity risk rate of each thermal conductivity monitoring point. The contact thermal resistance growth rate of each thermal conductivity monitoring point is divided by the contact thermal resistance growth rate threshold to obtain the third type of thermal conductivity risk rate of each thermal conductivity monitoring point. The thermal conductivity efficiency decay rate of each thermal conductivity monitoring point is divided by the thermal conductivity efficiency decay rate threshold to obtain the fourth type of thermal conductivity risk rate of each thermal conductivity monitoring point. The maximum value is selected from the first type of thermal conductivity risk rate, the second type of thermal conductivity risk rate, the third type of thermal conductivity risk rate and the fourth type of thermal conductivity risk rate of each thermal conductivity monitoring point and recorded as the thermal conductivity risk rate of each thermal conductivity monitoring point.

3. A safety inspection method based on intelligent fire protection according to claim 2, characterized in that: The thermal conductivity risk index of each abnormal thermal conductivity monitoring point is obtained, and the analysis process is as follows: Each thermal conductivity monitoring point with a thermal conductivity risk rate greater than the benchmark thermal conductivity risk rate is recorded as an abnormal thermal conductivity monitoring point. The thermal conductivity risk rate interval corresponding to each thermal conductivity risk basic index is obtained from the database. If the thermal conductivity risk rate of a thermal conductivity monitoring point falls within the thermal conductivity risk rate interval corresponding to a certain thermal conductivity risk basic index, it indicates that the thermal conductivity monitoring point has the thermal conductivity risk basic index. In this way, the thermal conductivity risk basic index of each thermal conductivity monitoring point is obtained. Obtaining the monitoring area corresponding to each abnormal thermal conductivity monitoring point from the database, thereby obtaining the thermal conductivity risk basic index of each abnormal thermal conductivity monitoring point in each abnormal thermal conductivity monitoring point area, calculating the average of the thermal conductivity risk basic index of each abnormal thermal conductivity monitoring point in each abnormal thermal conductivity monitoring point area, and dividing the average thermal conductivity risk basic index of each abnormal thermal conductivity monitoring point area by the thermal conductivity risk basic index of the corresponding abnormal thermal conductivity monitoring point to obtain the thermal conductivity risk variation index of each abnormal thermal conductivity monitoring point; The thermal conductivity correction factor corresponding to each thermal conductivity risk variation index is obtained from the database to obtain the thermal conductivity correction factor of each abnormal thermal conductivity monitoring point. The thermal conductivity risk basic index of each abnormal thermal conductivity monitoring point is multiplied by the thermal conductivity correction factor to obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point.

4. A safety inspection method based on intelligent fire protection according to claim 2, characterized in that: The specific analysis process of analyzing the temperature change data of the thermal insulation layer is as follows: The temperature change data of the thermal insulation layer includes the thermal resistance degradation degree, thermal diffusion coefficient fluctuation degree, hot spot defect depth, and hot spot defect range of each thermal insulation monitoring point. The thermal resistance degradation degree threshold, thermal diffusion coefficient fluctuation degree threshold, hot spot defect depth threshold, and hot spot defect range threshold are obtained from the database. The thermal resistance degradation degree of each thermal insulation monitoring point is divided by the thermal resistance degradation degree threshold to obtain the first type of thermal insulation risk rate of each thermal insulation monitoring point. The thermal diffusion coefficient fluctuation of each thermal insulation monitoring point is divided by the thermal diffusion coefficient fluctuation threshold to obtain the second type of thermal insulation risk rate of each thermal insulation monitoring point. The hot spot defect depth of each thermal insulation monitoring point is divided by the hot spot defect depth threshold to obtain the third type of thermal insulation risk rate of each thermal insulation monitoring point. The hot spot defect range of each thermal insulation monitoring point is divided by the hot spot defect range threshold to obtain the fourth type of thermal insulation risk rate of each thermal insulation monitoring point. The maximum value is selected from the first type of thermal insulation risk rate, the second type of thermal insulation risk rate, the third type of thermal insulation risk rate and the fourth type of thermal insulation risk rate of each thermal insulation monitoring point and recorded as the thermal insulation risk rate of each thermal insulation monitoring point.

5. A safety inspection method based on intelligent fire protection according to claim 4, characterized in that: The thermal insulation risk index of each abnormal thermal insulation monitoring point is obtained, and the analysis process is as follows: Each insulation monitoring point whose insulation risk rate is greater than the benchmark insulation risk rate is recorded as an abnormal insulation monitoring point. The insulation risk rate interval corresponding to each insulation risk basic index is obtained from the database. If the insulation risk rate of a certain insulation monitoring point belongs to the insulation risk rate interval corresponding to a certain insulation risk basic index, it indicates that the insulation monitoring point has the insulation risk basic index. In this way, the insulation risk basic index of each insulation monitoring point is obtained. Obtaining the monitoring area corresponding to each abnormal thermal insulation monitoring point from the database, thereby obtaining the thermal insulation risk basic index of each abnormal thermal insulation monitoring point in each abnormal thermal insulation monitoring point area, calculating the average thermal insulation risk basic index of each abnormal thermal insulation monitoring point in each abnormal thermal insulation monitoring point area, and dividing the average thermal insulation risk basic index of each abnormal thermal insulation monitoring point area by the thermal insulation risk basic index of the corresponding abnormal thermal insulation monitoring point to obtain the thermal insulation risk variation index of each abnormal thermal insulation monitoring point; The insulation correction factor corresponding to each insulation risk variation index is obtained from the database to obtain the insulation correction factor of each abnormal insulation monitoring point. The insulation risk basic index of each abnormal insulation monitoring point is multiplied by the insulation correction factor to obtain the insulation risk index of each abnormal insulation monitoring point.

6. A safety inspection method based on intelligent fire protection according to claim 5, characterized in that: The specific setting process for setting each inspection area is as follows: The spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring point are the Euclidean distance of each abnormal thermal conductivity monitoring point and the Euclidean distance of each abnormal thermal insulation monitoring point, respectively. The DBSCAN algorithm is used to perform spatial clustering on the abnormal thermal conductivity monitoring points and the abnormal thermal insulation monitoring points, with the Euclidean distance being less than the preset Euclidean benchmark distance as the threshold. Points with Euclidean distances less than the preset Euclidean benchmark distance are divided into the same area, thereby obtaining each basic inspection area; Count the abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in each basic inspection area to obtain the number of abnormal points and area of ​​each basic inspection, divide the number of abnormal points in each basic inspection area by the corresponding area to obtain the abnormal point density of each basic inspection area, divide the maximum value of the abnormal point density of adjacent basic inspection areas by the minimum value to obtain the density ratio of adjacent basic inspection areas, obtain the preset density ratio interval from the database, if the density ratio of adjacent basic inspection areas falls within the preset density ratio interval, and the area center distance of adjacent basic inspection areas is less than the preset standard reduction area, merge the adjacent basic inspection areas to obtain each inspection area.

7. A safety inspection method based on intelligent fire protection according to claim 6, characterized in that: The specific setting process of setting the inspection plan is as follows: Count the abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in each inspection area to obtain the number of abnormal points and the area of ​​each inspection area. Divide the number of abnormal points in each inspection area by the corresponding area to obtain the abnormal point density of each inspection area. Obtain the risk correction factor corresponding to each abnormal density from the database to obtain the risk correction factor of each inspection area. The maximum thermal conductivity risk index and the maximum thermal insulation risk index of each inspection area are obtained from the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area. The maximum thermal conductivity risk index and the maximum thermal insulation risk index of each inspection area are weighted to obtain the risk base index of each inspection area. The risk base index of each inspection area is multiplied by the corresponding risk correction factor to obtain the risk index of each inspection area. Each inspection area with a risk index greater than or equal to the standard inspection risk index is recorded as a high-risk inspection area, and each inspection area with a risk index less than the standard inspection risk index is recorded as a low-risk inspection area. The inspection plan is: all thermal conductivity monitoring points and thermal insulation monitoring points in the high-risk inspection area are recorded as inspection points, and all abnormal thermal conductivity monitoring points and abnormal thermal insulation monitoring points in the low-risk inspection area are recorded as inspection points. In this way, the inspection points are obtained, and the shortest path for inspecting each inspection point is obtained through genetic algorithm, and drone inspection is carried out according to the shortest path.

8. The safety inspection method based on intelligent fire protection according to claim 1 is characterized in that: The inspection information is analyzed, and the specific analysis process is as follows: The inspection information includes the ambient temperature, ambient wind speed, regional environmental flammability index and regional risk index of each monitoring point. The ambient temperature threshold, ambient wind speed threshold, regional environmental flammability index threshold and regional risk index threshold are obtained from the database. When the ambient temperature of a monitoring point exceeds the threshold, the ambient wind speed exceeds the threshold, the regional environmental flammability index exceeds the threshold or the regional risk index exceeds the threshold, the monitoring area corresponding to the monitoring point is recorded as an inspection warning area and an early warning is issued.

9. A safety inspection method based on intelligent fire protection according to claim 8, characterized in that: The specific setting process of setting the heavy inspection plan is as follows: After the warning, the inspection warning area is inspected at preset intervals and the regional risk index is collected to obtain the regional risk index at each collection time point in the inspection warning area. A regional risk index change graph that changes with time is established, and the slope of the regional risk index change trend is obtained through image recognition technology. The risk index threshold and the regional risk index change trend slope threshold are obtained from the database. When the regional risk index of the inspection warning area is greater than the risk index threshold or the regional risk index change trend slope is greater than the regional risk index change trend slope threshold, a building abnormality warning is issued.

10. A safety inspection system using the safety inspection method based on intelligent fire protection according to any one of claims 1 to 9, characterized in that: Includes the following modules: The thermal conductivity layer monitoring module is used to collect and analyze the temperature change data of the thermal conductivity layer to obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point; The thermal insulation layer monitoring module is used to collect and analyze the temperature change data of the thermal insulation layer to obtain the thermal insulation risk index of each abnormal thermal insulation monitoring point; The regular fire inspection module is used to obtain the spatial data of each abnormal thermal conductivity monitoring point and the spatial data of each abnormal thermal insulation monitoring point from the database, set each inspection area, and thereby obtain the thermal conductivity risk index of each abnormal thermal conductivity monitoring point and the thermal insulation risk index of each abnormal thermal insulation monitoring point in each inspection area, and then set the inspection plan; The abnormal fire inspection module is used to collect inspection information, analyze the inspection information, obtain the environmental risk index, issue fire warnings, and then set up heavy inspection plans.

Images