A substation fire-fighting data fusion processing method and system

Abstract

The application discloses a kind of substation fire-fighting data fusion processing method and system, by obtaining the monitoring data of multiple fire-fighting monitoring subsystems in substation, the monitoring data is fused by intelligent fire-fighting acquisition board card to multiple-source heterogeneous data, and fused multiple-source heterogeneous data is obtained, and the intelligent fire-fighting acquisition board card is based on electric Honggong thing link operating system construction;The fused multiple-source heterogeneous data is input into fire risk assessment model constructed by combining machine learning algorithm with bayesian risk identification and analysis algorithm as core, and the fire risk grade and equipment maintenance suggestion are output;According to the fire risk grade and equipment maintenance suggestion, risk linkage control is executed, and the risk linkage control includes when fire detector sends alarm signal, automatically start the video monitoring system of corresponding area to confirm alarm, and according to the confirmation result, access control system and fire extinguishing equipment are linked. The fire safety management level and emergency disposal efficiency of substation are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent fire risk assessment technology, and in particular to a method and system for fusion processing of fire protection data in substations. Background Technology

[0002] As substations evolve towards full automation and unmanned operation, fire safety management faces new challenges. Existing substations typically have independent automatic fire alarm systems, video surveillance systems, environmental monitoring systems, and fire water systems. However, these systems suffer from data silos and inconsistent standards, creating severe information silos and hindering data sharing and business collaboration. When a fire alarm occurs, the fire protection system and video surveillance system cannot work together to confirm the fire, requiring personnel to go to the site for verification, which can easily lead to missed opportunities for optimal response. Furthermore, the issues of heterogeneous data fusion and intelligent linkage control between various fire protection subsystems have not been effectively resolved, resulting in a severe deficiency in intelligent fire risk assessment and early warning capabilities. Summary of the Invention

[0003] The purpose of this invention is to solve the above problems by designing a method and system for fusion processing of fire protection data in substations.

[0004] To achieve the above objectives, the technical solution of the present invention further includes the following steps in the above-mentioned substation fire protection data fusion processing method: Acquire monitoring data from multiple fire monitoring subsystems within the substation, including an automatic fire alarm system, a video surveillance system, an environmental monitoring system, a temperature measurement system, and a fire water system; The monitoring data is fused using a smart fire protection data acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection data acquisition board is built on the Elec-Link IoT operating system. The fire risk assessment model, which integrates multi-source heterogeneous data, is constructed using Bayesian risk identification and analysis algorithms combined with machine learning algorithms. The model outputs fire risk levels and equipment maintenance recommendations. Risk linkage control is implemented based on the fire risk level and equipment maintenance recommendations. The risk linkage control includes automatically activating the video surveillance system in the corresponding area to confirm the alarm when the fire detector sends an alarm signal, and linking the access control system and fire extinguishing equipment based on the confirmation result.

[0005] Furthermore, in the above-mentioned substation fire protection data fusion processing method, the monitoring data is fused using a smart fire protection acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection acquisition board is built on the Dianhong IoT operating system and includes: The intelligent fire protection data acquisition board utilizes domestically produced chip components and is compatible with multiple communication protocols and interfaces. It is used to uniformly collect data information from fire water systems, pyrolysis monitoring systems, fiber optic temperature measurement systems, and fire alarm control panels and upload it to the Internet of Things platform, thereby realizing the fusion of multi-source heterogeneous data from various fire alarm monitoring systems and hierarchical linkage control.

[0006] Furthermore, in the above-mentioned substation fire protection data fusion processing method, the monitoring data is fused using a smart fire protection acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection acquisition board is built on the Dianhong IoT operating system and includes: The monitoring data is cleaned, format converted, and normalized to integrate fire data of different modalities into a standardized unified data format, resulting in standard multi-source data. Image features are extracted from image data in standard multi-source data using convolutional neural networks; audio features are extracted from sound data using Fourier transform and Mel frequency cepstral coefficients; and text features are extracted from text data using natural language processing techniques, thus obtaining multi-source model feature data. Early fusion methods are used to fuse multi-source model feature data to obtain fused multi-source heterogeneous data.

[0007] Furthermore, in the aforementioned method for fusing and processing substation fire protection data, the step of inputting the fused multi-source heterogeneous data into a fire risk assessment model constructed using a Bayesian risk identification and analysis algorithm combined with machine learning algorithms, and outputting fire risk levels and equipment maintenance recommendations, includes: Identify fire risk points and fire risk influencing factors in substations using deductive reasoning and quantitative statistical methods; The fire simulation software FDS was used to numerically simulate fires in substations, analyze the heat release rate, temperature and smoke changes caused by different hazard sources, and determine the degree of danger of various fire hazard sources as a weighting index. The Bayesian network model is used to determine the assessment objects and key indicators, and a Bayesian network is constructed for fire risk assessment. By introducing time series analysis and data mining techniques, historical data can be deeply mined and analyzed to discover potential fire risk trends and patterns.

[0008] Furthermore, in the above-mentioned substation fire protection data fusion processing method, the risk linkage control also includes establishing an alarm handling step model. The alarm handling step model records the progress and handling time of each step of the alarm handling process. The steps include viewing, fault elimination, video inspection, and false alarm confirmation. Based on the alarm handling step model, the average alarm handling time of each station is statistically analyzed to generate alarm handling efficiency analysis data.

[0009] Furthermore, in the above-mentioned method for fusing and processing substation fire protection data, the fusion of multi-source heterogeneous data is also used to generate substation fire protection overview information. The fire protection overview information includes displaying the location distribution of each substation within the jurisdiction on an electronic map based on a regional GIS identifier logical model; and displaying the total number of fire protection equipment, the number of equipment in normal status, the number of equipment in fault status, and the number of equipment in offline status in a graphical form based on a regional fire protection equipment status table.

[0010] Furthermore, in the above-mentioned substation fire protection data fusion processing method, the monitoring data is encrypted and signed by calling the unified cryptographic service during transmission, and the monitoring data is encrypted and stored by calling the unified cryptographic service when stored. The SM4 national cryptographic symmetric algorithm and the national cryptographic signature algorithm are used to ensure the confidentiality and integrity of data storage.

[0011] Furthermore, in a substation fire protection data fusion processing system, the substation fire protection data fusion processing system includes the following modules: The monitoring data acquisition module is used to acquire monitoring data from multiple fire monitoring subsystems within the substation. These multiple fire monitoring subsystems include an automatic fire alarm system, a video surveillance system, an environmental monitoring system, a temperature measurement system, and a fire water system. The monitoring data processing module is used to perform multi-source heterogeneous data fusion on the monitoring data through the smart fire protection acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection acquisition board is built on the Elec-Link IoT operating system. The fire risk assessment module is used to input the fused multi-source heterogeneous data into a fire risk assessment model constructed with Bayesian risk identification and analysis algorithm as the core and machine learning algorithm, and output fire risk level and equipment maintenance recommendations. The risk linkage control module is used to execute risk linkage control according to the fire risk level and equipment maintenance recommendations. The risk linkage control includes automatically activating the video surveillance system of the corresponding area to confirm the alarm when the fire detector sends an alarm signal, and linking the access control system and fire extinguishing equipment according to the confirmation result.

[0012] Furthermore, in a substation fire protection data fusion processing system, the intelligent fire protection acquisition board uses domestically produced chip components, is compatible with multiple communication protocols and interfaces, and uniformly collects and uploads data information from the fire water system, pyrolysis monitoring system, fiber optic temperature measurement system, and fire alarm host to the Internet of Things platform.

[0013] Furthermore, in a substation fire protection data fusion processing system, the system also includes a substation operation support system, on which a substation smart fire protection application is deployed. The substation smart fire protection application includes a fire protection overview module, a site fire protection overview module, a fire equipment status identification module, a fire alarm module, a fire early warning module, an emergency management module, a risk linkage module, a fire safety assessment module, and a report management module, which are used to realize a digital fire protection pre-control system for substation fire protection equipment.

[0014] Its beneficial effects lie in the fact that, through the smart fire protection data acquisition board based on the Dianhong IoT operating system, it unifies and integrates data from various heterogeneous systems such as fire water systems, pyrolysis monitoring systems, fiber optic temperature measurement systems, and fire alarm control panels, breaking down data silos between different fire protection subsystems within the substation and achieving unified access, management, and security monitoring of fire protection sensing terminals; through multimodal data fusion technology, it extracts and deeply fuses features from fire protection data of different modalities such as images, sound, and text, and uses deep learning algorithms such as convolutional neural networks and YOLO object detection to achieve flame recognition, smoke recognition, and channel detection. Occupancy identification effectively improves the accuracy and reliability of fire detection; a substation fire risk assessment model based on Bayesian networks and machine learning algorithms has been constructed, with an assessment accuracy rate of over 95%, realizing a shift from passive post-event handling to proactive pre-event early warning; intelligent linkage between fire protection systems, video surveillance systems, and access control systems has been realized, automatically initiating video confirmation and automatic door opening for evacuation when a fire alarm occurs, significantly shortening fire response time, improving the fire safety management level and emergency response efficiency of substations, and avoiding duplication of construction and waste of resources through effective integration of existing fire protection facilities. Attached Figure Description

[0015] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention.

[0016] Figure 1 This is a schematic diagram of the first embodiment of a substation fire protection data fusion processing method according to the present invention; Figure 2 This is a schematic diagram of the first embodiment of a substation fire protection data fusion processing system according to the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms "one," "an," and "this" used herein may also include the plural forms. It should be further understood that the terminology used in this specification includes the presence of features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0019] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 As shown, a method for fusion processing of substation fire protection data includes the following steps: Step 101: Obtain monitoring data from multiple fire monitoring subsystems within the substation. These subsystems include an automatic fire alarm system, a video surveillance system, an environmental monitoring system, a temperature measurement system, and a fire water system. Specifically, in this embodiment, the automatic fire alarm system uses a fire alarm controller deployed in the control room to collect fire alarm signals and control system operating status in real time from areas such as transformer rooms, switch rooms, and cable trays. The detection system consists of smoke detectors, heat detectors, smoke-temperature combination detectors, combustible gas detectors, infrared beam detectors, heat-sensing cables, signal input modules, and manual alarm buttons. Monitoring data includes: the online status of the fire alarm controller, indicator light status, alarm status, alarm time, alarm description, and real-time detection data and fault information from various detectors.

[0020] The video surveillance system provides 24 / 7 video monitoring of the substation by deploying cameras at key electrical equipment locations, installation sites, and the substation perimeter. Monitoring data includes: camera online status, real-time video streams, and intelligent analysis results (flame detection, smoke detection, fire lane obstruction detection, etc.).

[0021] The environmental monitoring system uses sensors deployed in various areas of the substation to collect real-time environmental parameters such as indoor temperature and humidity, SF6 gas concentration, O2 concentration, and water immersion status. Monitoring data includes: temperature and humidity values, SF6 concentration values, O2 concentration values, water immersion alarm status, and alarm time.

[0022] The temperature monitoring system employs a distributed fiber optic temperature measurement system (DTS) to conduct long-distance online temperature monitoring of equipment such as high-voltage cables, cable tunnels, cable interlayers, and transformers within the substation. Monitoring data includes: temperature values ​​at each measuring point, constant temperature alarms, temperature rise alarms, area temperature difference alarms, fault alarms, and alarm area location information.

[0023] The fire protection water system uses sensors deployed in areas such as fire water storage tanks and fire pump rooms to collect key parameters in real time, including water level, flow rate, pressure, and temperature. Monitoring data includes: water level values ​​(monitored level, actual level, and warning level), flow rate, pressure, operating status of fire pumps and pressure-stabilizing pumps (pressure and flow rate), alarm status, and alarm time. Step 102: The monitoring data is fused using the smart fire protection acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection acquisition board is built on the Elec-Tech IoT operating system. Specifically, in this embodiment, the smart fire protection data acquisition board utilizes domestically produced chip components and is compatible with multiple communication protocols and interfaces. It is used to uniformly collect data information from the fire water system, pyrolysis monitoring system, fiber optic temperature measurement system, and fire alarm host and upload it to the Internet of Things platform, thereby realizing the fusion of multi-source heterogeneous data from various fire alarm monitoring systems and hierarchical linkage control.

[0024] The monitoring data undergoes data cleaning, format conversion, and normalization to integrate fire data from different modalities into a standardized, unified data format, resulting in standard multi-source data. Image features are extracted from image data using convolutional neural networks, audio features are extracted from sound data using Fourier transform and Mel-frequency cepstral coefficients, and text features are extracted from text data using natural language processing techniques, resulting in multi-source model feature data. Finally, an early fusion method is used to fuse the multi-source model feature data, yielding fused multi-source heterogeneous data.

[0025] The merged data is also used to generate substation fire protection overview information, which includes: displaying the location distribution of each substation within the jurisdiction on an electronic map based on the regional GIS identification logic model; displaying the total number of fire protection equipment, the number in normal condition, the number in fault condition, and the number in offline condition in a graphical form based on the regional fire protection equipment status table; displaying the fire safety index of each station in a graphical form based on the regional fire safety index evaluation model; and displaying the total number of hidden dangers and the number of unrectified hidden dangers in a graphical form based on the regional hidden danger analysis model.

[0026] Step 103: Input multi-source heterogeneous data into the fire risk assessment model constructed with Bayesian risk identification and analysis algorithm as the core and machine learning algorithm, and output fire risk level and equipment maintenance recommendations. Specifically, in this embodiment, deductive reasoning and quantitative statistical methods are used to identify fire risk points and fire-fighting risk influencing factors in substations; the fire simulation software FDS is used to numerically simulate fires in substations, analyze the heat release rate, temperature, and smoke changes caused by different hazard sources, and determine the degree of danger of various fire hazard sources as weight indicators; a Bayesian network model is used to determine the assessment objects and key indicators, and a Bayesian network is constructed for fire risk assessment; time series analysis and data mining techniques are introduced to deeply mine and analyze historical data to discover potential fire risk trends and patterns.

[0027] The data processing of the video surveillance system includes: marking fire areas using clustering image segmentation methods, determining whether an area is a fire area and triggering an alarm using sample entropy thresholding; training and classifying the extracted features using deep learning algorithms based on convolutional neural networks, and using YOLO or Faster R-CNN object detection models for object localization and classification to achieve flame recognition, smoke recognition, and fire lane occupancy recognition.

[0028] Step 104: Implement risk linkage control based on fire risk level and equipment maintenance recommendations. Risk linkage control includes automatically activating the video surveillance system in the corresponding area to confirm the alarm when the fire detector sends an alarm signal, and linking the access control system and fire extinguishing equipment based on the confirmation result.

[0029] Specifically, in this embodiment, risk linkage control also includes: establishing an alarm handling step model, which records the progress and handling time of each step in alarm handling, including viewing, fault elimination, video inspection and false alarm confirmation; and statistically analyzing the average alarm handling time of each site or a single site based on the alarm handling step model to generate alarm handling efficiency analysis data.

[0030] During transmission, monitoring data is encrypted and signed by calling the unified cryptographic service, using the SM3 national cryptographic signature algorithm, the SM2 asymmetric algorithm, and the SM4 symmetric algorithm to ensure the confidentiality and integrity of data transmission. When storing monitoring data, the unified cryptographic service is called to encrypt the data before it is entered into the database, using the SM4 national cryptographic symmetric algorithm and the national cryptographic signature algorithm to ensure the confidentiality and integrity of data storage. When sharing data externally, sensitive fields are anonymized through the data anonymization service before being sent.

[0031] Its beneficial effects lie in the fact that, through the smart fire protection data acquisition board based on the Dianhong IoT operating system, it unifies and integrates data from various heterogeneous systems such as fire water systems, pyrolysis monitoring systems, fiber optic temperature measurement systems, and fire alarm control panels, breaking down data silos between different fire protection subsystems within the substation and achieving unified access, management, and security monitoring of fire protection sensing terminals; through multimodal data fusion technology, it extracts and deeply fuses features from fire protection data of different modalities such as images, sound, and text, and uses deep learning algorithms such as convolutional neural networks and YOLO object detection to achieve flame recognition, smoke recognition, and channel detection. Occupancy identification effectively improves the accuracy and reliability of fire detection; a substation fire risk assessment model based on Bayesian networks and machine learning algorithms has been constructed, with an assessment accuracy rate of over 95%, realizing a shift from passive post-event handling to proactive pre-event early warning; intelligent linkage between fire protection systems, video surveillance systems, and access control systems has been realized, automatically initiating video confirmation and automatic door opening for evacuation when a fire alarm occurs, significantly shortening fire response time, improving the fire safety management level and emergency response efficiency of substations, and avoiding duplication of construction and waste of resources through effective integration of existing fire protection facilities.

[0032] The above describes an embodiment of the substation fire protection data fusion processing method of the present invention. Please refer to [link / reference]. Figure 2 In a substation fire protection data fusion processing system, the substation fire protection data fusion processing system includes the following modules: The monitoring data acquisition module is used to acquire monitoring data from multiple fire monitoring subsystems within the substation. These subsystems include an automatic fire alarm system, a video surveillance system, an environmental monitoring system, a temperature measurement system, and a fire water system. The monitoring data processing module is used to perform multi-source heterogeneous data fusion on the monitoring data through the smart fire protection acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection acquisition board is built on the Elec-Link IoT operating system. The fire risk assessment module is used to input multi-source heterogeneous data into a fire risk assessment model that combines Bayesian risk identification and analysis algorithms with machine learning algorithms, and outputs fire risk level and equipment maintenance recommendations. The risk linkage control module is used to execute risk linkage control based on the fire risk level and equipment maintenance recommendations. Risk linkage control includes automatically activating the video surveillance system in the corresponding area to confirm the alarm when the fire detector sends an alarm signal, and linking the access control system and fire extinguishing equipment based on the confirmation result.

[0033] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended technical solutions and equivalents.

Claims

1. A method for fusing and processing fire protection data in substations, characterized in that, The substation fire protection data fusion processing method includes the following steps: Acquire monitoring data from multiple fire monitoring subsystems within the substation, including an automatic fire alarm system, a video surveillance system, an environmental monitoring system, a temperature measurement system, and a fire water system; The monitoring data is fused using a smart fire protection data acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection data acquisition board is built on the Elec-Link IoT operating system. The fire risk assessment model, which integrates multi-source heterogeneous data, is constructed using Bayesian risk identification and analysis algorithms combined with machine learning algorithms. The model outputs fire risk levels and equipment maintenance recommendations. Risk linkage control is implemented based on the fire risk level and equipment maintenance recommendations. The risk linkage control includes automatically activating the video surveillance system in the corresponding area to confirm the alarm when the fire detector sends an alarm signal, and linking the access control system and fire extinguishing equipment based on the confirmation result.

2. The substation fire protection data fusion processing method as described in claim 1, characterized in that, The monitoring data is fused using a smart fire protection data acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection data acquisition board is built on the Dianhong IoT operating system and includes: The intelligent fire protection data acquisition board utilizes domestically produced chip components and is compatible with multiple communication protocols and interfaces. It is used to uniformly collect data information from fire water systems, pyrolysis monitoring systems, fiber optic temperature measurement systems, and fire alarm control panels and upload it to the Internet of Things platform, thereby realizing the fusion of multi-source heterogeneous data from various fire alarm monitoring systems and hierarchical linkage control.

3. The substation fire protection data fusion processing method as described in claim 1, characterized in that, The monitoring data is fused using a smart fire protection data acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection data acquisition board is built on the Dianhong IoT operating system and includes: The monitoring data is cleaned, format converted, and normalized to integrate fire data of different modalities into a standardized unified data format, resulting in standard multi-source data. Image features are extracted from image data in standard multi-source data using convolutional neural networks; audio features are extracted from sound data using Fourier transform and Mel frequency cepstral coefficients; and text features are extracted from text data using natural language processing techniques, thus obtaining multi-source model feature data. Early fusion methods are used to fuse multi-source model feature data to obtain fused multi-source heterogeneous data.

4. The substation fire protection data fusion processing method as described in claim 1, characterized in that, The fire risk assessment model, constructed by integrating multi-source heterogeneous data and using Bayesian risk identification and analysis algorithms combined with machine learning algorithms, outputs fire risk levels and equipment maintenance recommendations, including: Identify fire risk points and fire risk influencing factors in substations using deductive reasoning and quantitative statistical methods; The fire simulation software FDS was used to numerically simulate fires in substations, analyze the heat release rate, temperature and smoke changes caused by different hazard sources, and determine the degree of danger of various fire hazard sources as a weighting index. The Bayesian network model is used to determine the assessment objects and key indicators, and a Bayesian network is constructed for fire risk assessment. By introducing time series analysis and data mining techniques, historical data can be deeply mined and analyzed to discover potential fire risk trends and patterns.

5. The substation fire protection data fusion processing method as described in claim 1, characterized in that, The risk linkage control also includes establishing an alarm handling step model, which records the progress and handling time of each step in the alarm handling process. The steps include viewing, fault elimination, video inspection, and false alarm confirmation. Based on the alarm handling step model, the average alarm handling time of each site is statistically analyzed to generate alarm handling efficiency analysis data.

6. The substation fire protection data fusion processing method as described in claim 1, characterized in that, The fusion of multi-source heterogeneous data is also used to generate substation fire protection overview information, which includes displaying the location distribution of each substation within the jurisdiction on an electronic map based on a regional GIS identifier logical model; and displaying the total number of fire protection equipment, the number of equipment in normal condition, the number of equipment in fault condition, and the number of equipment in offline condition in a graphical form based on a regional fire protection equipment status table.

7. The substation fire protection data fusion processing method as described in claim 1, characterized in that, The monitoring data is encrypted and signed by calling the unified cryptographic service during transmission. When the monitoring data is stored, the unified cryptographic service is called to encrypt the data before it is stored in the database. The SM4 national cryptographic symmetric algorithm and the national cryptographic signature algorithm are used to ensure the confidentiality and integrity of the data storage.

8. A substation fire protection data fusion processing system, characterized in that, The substation fire protection data fusion processing system includes the following modules: The monitoring data acquisition module is used to acquire monitoring data from multiple fire monitoring subsystems within the substation. These multiple fire monitoring subsystems include an automatic fire alarm system, a video surveillance system, an environmental monitoring system, a temperature measurement system, and a fire water system. The monitoring data processing module is used to perform multi-source heterogeneous data fusion on the monitoring data through the smart fire protection acquisition board to obtain fused multi-source heterogeneous data. The smart fire protection acquisition board is built on the Elec-Link IoT operating system. The fire risk assessment module is used to input the fused multi-source heterogeneous data into a fire risk assessment model constructed with Bayesian risk identification and analysis algorithm as the core and machine learning algorithm, and output fire risk level and equipment maintenance recommendations. The risk linkage control module is used to execute risk linkage control according to the fire risk level and equipment maintenance recommendations. The risk linkage control includes automatically activating the video surveillance system of the corresponding area to confirm the alarm when the fire detector sends an alarm signal, and linking the access control system and fire extinguishing equipment according to the confirmation result.

9. The substation fire protection data fusion processing system as described in claim 8, characterized in that, The intelligent fire protection data acquisition board uses domestically produced chips and components, is compatible with multiple communication protocols and interfaces, and collects and uploads data from the fire water system, pyrolysis monitoring system, fiber optic temperature measurement system, and fire alarm host to the Internet of Things platform.

10. The substation fire protection data fusion processing system as described in claim 8, characterized in that, The system also includes a substation operation support system, on which a substation smart fire protection application is deployed. The substation smart fire protection application includes a fire protection overview module, a site fire protection overview module, a fire equipment status identification module, a fire alarm module, a fire early warning module, an emergency management module, a risk linkage module, a fire safety assessment module, and a report management module, which are used to realize a digital fire protection pre-control system for substation fire protection equipment.

Images