Fire-fighting monitoring system for ship

Abstract

The invention provides a fire-fighting monitoring system for a ship. The fire-fighting monitoring system for the ship comprises a fire detection module and a fire-fighting monitoring module, wherein the fire detection module comprises fire monitoring and identifying cameras and sensor assemblies which are arranged at all corners of the ship; the fire monitoring module is used for constructing a fire recognition model based on the collected data of the ship and performing fire recognition warning; the fire hazard early warning module is used for constructing a fire hazard prediction model and performing prediction warning of fire hazard risks; the fire control module is used for realizing automatic fire extinguishing and comprises an automatic fire extinguishing control unit and a remote control unit; the intelligent decision-making module is used for providing escape guidance and comprises a fire source positioning unit and a route planning unit; the performance optimization module comprises fire source positioning optimization and escape route optimization. The system can comprehensively monitor the interior of the ship, accurately identify and predict the fire risk, can perform automatic fire extinguishing operation, position a fire source and plan an escape route at the first time when a fire occurs, guarantees the life and property safety of personnel, reduces the ship loss, and reduces the environmental pollution risk.

Description

Technical Field

[0001] The present invention relates to the technical field of fire monitoring, and in particular to a fire monitoring system for ships. Background Art

[0002] A ship is a man-made means of transportation that mainly operates in geographical waters. It plays an important role in human history and modern life. It is not only the main means of water transportation, but also an important carrier of national security and leisure and entertainment. With the advancement of science and technology and the development of marine resources by humans, the future development of ships will be broader and more diversified.

[0003] Due to the special structure of ships, there are many confined spaces on ships, complex structures, narrow passages and entrances and exits. Once a fire occurs, toxic smoke and hot air can easily fill the entire cabin or room, making it difficult to evacuate personnel. There are many flammable materials on board, such as ship debris, hull decoration materials, daily necessities, cargo, etc.; there are many dangerous sources that are prone to fire, such as engine room oil rags, waste oil, cables in the living area, fuel, etc. If a fire in one part cannot be controlled in time, the fire will spread quickly and even cause an explosion. In addition, ship rescue is difficult. A fire on a ship may occur while it is sailing, anchored in the river, or docked at a port. It is difficult for maritime rescue forces to arrive at the scene in the first time, and there is a great risk of fire.

[0004] Based on the above problems, it can be seen that fire monitoring on ships is particularly important. However, the existing fire monitoring system still has 1) blind spot problems: the current ship fire monitoring system cannot cover all areas, and there are blind spots in certain corners, which can easily cause fires to be ignored. 2) Manual intervention problem: Although the system can automatically detect and alarm, the crew still needs to manually perform fire extinguishing operations, and there is a lack of fully automated solutions. 3) Lag problem: The existing monitoring system can often only monitor fires that have already occurred and cannot play a preventive role, and will still cause significant losses. In the future, ship fire monitoring systems still need to be improved. Therefore, the present invention proposes a ship fire monitoring system to solve the above problems. Summary of the invention

[0005] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a ship fire monitoring system that can comprehensively monitor the interior of the ship, accurately identify and predict fire risks, and can also automatically perform fire extinguishing operations as soon as a fire occurs, locate the fire source and plan escape routes, thereby ensuring the safety of life and property of personnel, reducing ship losses, and reducing environmental pollution risks.

[0006] To achieve the above object, the present invention provides the following solution: A fire monitoring system for a ship, comprising:

[0007] Fire detection module, used to monitor and collect real-time data from various areas of the ship, including fire monitoring and identification cameras and sensor components installed in various corners of the ship;

[0008] The fire monitoring module is used to build a fire recognition model based on the collected data of the ship and to carry out fire recognition warning, including a data preprocessing unit, a data fusion unit, a feature extraction unit and a model building unit;

[0009] Fire warning module, used to build fire prediction models and provide fire risk prediction and warning;

[0010] A fire control module, used to realize automatic fire extinguishing, including an automatic fire extinguishing control unit and a remote control unit;

[0011] Intelligent decision-making module, used to provide escape guidance using data analysis and intelligent algorithms, including a fire source location unit and a route planning unit;

[0012] Performance optimization module, including fire source location optimization and escape route optimization;

[0013] Among them, the fire detection module, the fire monitoring module, the fire warning module, the fire control module, the intelligent decision-making module and the performance optimization module are interconnected.

[0014] Optionally, in the fire detection module: the sensor component includes a temperature sensor, a smoke sensor and a gas sensor, and the sensor component and the fire monitoring and identification camera transmit the collected images and data in real time to the fire monitoring module and the fire warning module for identification and prediction, wherein the collected data includes temperature, smoke, gas and flame thermal radiation.

[0015] Optionally, in the fire monitoring module:

[0016] The data preprocessing unit is used to perform missing value processing, outlier processing, data cleaning and data conversion on the collected data to obtain original data, and store the original data in a database;

[0017] The data fusion unit is used to fuse the temperature value, smoke value, gas value and flame thermal radiation value in the original data to obtain a data set, and then divide the data set into a recognition test set and a recognition training set;

[0018] The feature extraction unit is used to extract feature variables in the data set using an artificial intelligence algorithm, and to label and classify the feature variables;

[0019] The model building unit is used to train the feature variables based on a convolutional neural network, and then adjust the model parameters through a back propagation algorithm and an optimizer to obtain the original recognition model, input the recognition test set into the original recognition model for performance evaluation, and then optimize the original recognition model to obtain the fire recognition model;

[0020] The fire recognition model is deployed in an actual environment to perform fire recognition tasks, and flames are detected in real time in the data stream of the fire monitoring and recognition camera.

[0021] Optionally, in the fire warning module, building a fire prediction model is specifically as follows:

[0022] Collecting a comprehensive data set including fire data and non-fire data, annotating the comprehensive data set according to the fire prediction task requirements to distinguish between fire situations and non-fire situations, and dividing the comprehensive data set into a prediction training set and a prediction test set;

[0023] Based on the comprehensive data set, the fire recognition model is retrained using the transfer learning method, the model parameters are adjusted, and an initial prediction model is obtained. The initial prediction model is then evaluated using the prediction test set, the accuracy and recall rate are calculated, and the initial prediction model is optimized to obtain the fire prediction model.

[0024] Optionally, in the fire control module:

[0025] The automatic fire extinguishing control unit is used to confirm whether a fire has occurred according to the identification result of the fire identification model using preset logic and algorithm, and automatically start corresponding fire extinguishing instructions according to the fire situation, wherein the fire extinguishing instructions include automatic fire extinguishing instructions, instructions for notifying firefighters, and issuing evacuation instructions, wherein the automatic fire extinguishing instructions include automatically releasing fire extinguishing agents, starting a water spray system, and shutting down a ventilation system;

[0026] The remote control unit is used to monitor ship data and operate the fire monitoring system in real time using the remote control platform, and to send alarm information, fire emergency handling information and escape guidance information in real time using the automatic alarm function.

[0027] Optionally, in the intelligent decision-making module:

[0028] The fire source positioning unit is used to process and analyze the data collected by the sensor assembly and the fire monitoring and recognition camera, extract the characteristics of the fire, determine the location and range of the fire based on the characteristics of the fire and the recognition results of the fire recognition model, and then determine the direction and range of the fire spread based on the prediction results of the fire prediction model;

[0029] The route planning unit is used to plan an escape route using an intelligent algorithm according to the location and scope of the fire, the direction and scope of the fire spread, and the internal layout of the ship, and to verify and optimize the escape route to achieve the effectiveness of the escape route.

[0030] Optionally, in the performance optimization module:

[0031] The fire source location optimization is used to establish fire risk areas and corresponding regional risk levels based on the fire location and scope and the fire spread direction and scope, and to perform regular updates;

[0032] The escape route optimization is used to update and verify the escape route in real time according to the result of the fire source location optimization, and to establish different escape plans using different fire source locations.

[0033] The present invention discloses the following technical effects by providing a fire monitoring system for ships:

[0034] 1. The present invention can cover all areas of the ship through fire monitoring and identification cameras and sensor components, avoiding the existence of blind spots; at the same time, the collected images and data are used to establish fire identification models and fire prediction models, which can not only accurately monitor fire risks, reduce false alarms, and improve the safety and efficiency of the system, but also predict and warn of fires, take precautions against them, and play a role in preventing fires, thereby ensuring the safety of life and property of personnel to the greatest extent, reducing ship losses, and reducing environmental pollution risks.

[0035] 2. The present invention realizes automatic fire extinguishing control, can automatically start the corresponding fire extinguishing device after detecting a fire, can make emergency treatment at the first time of fire, improves the fire prevention and fire extinguishing capabilities of the ship, and provides an automated solution for the fire monitoring system.

[0036] 3. The present invention can determine the location and scope of the fire source through fire source positioning and escape route planning, and make trend predictions on the location and scope of the fire source, so as to carry out targeted escape route planning at the location of the fire source, provide the occupants with important fire information and accurate escape guidance, ensure the safe evacuation of the occupants, and further protect the safety of life and property of the personnel.

[0037] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 creative labor.

[0039] Figure 1 A system architecture diagram provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] like Figure 1 As shown, the present invention provides a fire monitoring system for ships, comprising: a fire detection module, a fire monitoring module, a fire early warning module, a fire control module, an intelligent decision module and a performance optimization module. The fire detection module, the fire monitoring module, the fire early warning module, the fire control module, the intelligent decision module and the performance optimization module are interconnected.

[0043] 1. Fire detection module, which is used to monitor and collect real-time data from various areas of the ship, including fire monitoring and identification cameras and sensor components installed in various corners of the ship.

[0044] The sensor component includes a temperature sensor, a smoke sensor and a gas sensor. The sensor component and the fire monitoring and identification camera transmit the collected images and data to the fire monitoring module and the fire warning module in real time for identification and prediction, wherein the collected data includes temperature, smoke, gas and flame thermal radiation.

[0045] 2. Fire monitoring module, which is used to build a fire recognition model based on the collected data of the ship and to carry out fire recognition warning, including a data preprocessing unit, a data fusion unit, a feature extraction unit and a model building unit. Among them:

[0046] The data preprocessing unit is used to perform missing value processing, outlier processing, data cleaning and data conversion on the collected data to obtain original data, and store the original data in a database;

[0047] The data fusion unit is used to fuse the temperature value, smoke value, gas value and flame thermal radiation value in the original data to obtain a data set, and then divide the data set into a recognition test set and a recognition training set;

[0048] The feature extraction unit is used to extract feature variables in the data set using an artificial intelligence algorithm, and to label and classify the feature variables;

[0049] The model building unit is used to train the feature variables based on a convolutional neural network, and then adjust the model parameters through a back propagation algorithm and an optimizer to obtain the original recognition model, input the recognition test set into the original recognition model for performance evaluation, and then optimize the original recognition model to obtain the fire recognition model;

[0050] The fire recognition model is deployed in an actual environment to perform fire recognition tasks, and flames are detected in real time in the data stream of the fire monitoring and recognition camera.

[0051] 3. Fire warning module, used to build a fire prediction model and provide prediction and warning of fire risks.

[0052] Specifically:

[0053] Collecting a comprehensive data set including fire data and non-fire data, annotating the comprehensive data set according to the fire prediction task requirements to distinguish between fire situations and non-fire situations, and dividing the comprehensive data set into a prediction training set and a prediction test set;

[0054] Based on the comprehensive data set, the fire recognition model is retrained using the transfer learning method, the model parameters are adjusted, and an initial prediction model is obtained. The initial prediction model is then evaluated using the prediction test set, the accuracy and recall rate are calculated, and the initial prediction model is optimized to obtain the fire prediction model.

[0055] 4. Fire control module, used to realize automatic fire extinguishing, including automatic fire extinguishing control unit and remote control unit.

[0056] The automatic fire extinguishing control unit is used to confirm whether a fire has occurred based on the recognition results of the fire recognition model using preset logic and algorithms, and automatically initiate corresponding fire extinguishing instructions based on the fire situation. The fire extinguishing instructions include automatic fire extinguishing instructions, instructions for notifying firefighters, and issuing evacuation instructions, wherein the automatic fire extinguishing instructions include automatically releasing fire extinguishing agents, starting a water spray system, and shutting down a ventilation system.

[0057] The remote control unit is used to monitor ship data and operate the fire monitoring system in real time using the remote control platform, and to send alarm information, fire emergency handling information and escape guidance information in real time using the automatic alarm function.

[0058] 5. Intelligent decision-making module, which is used to provide escape guidance by using data analysis and intelligent algorithms, including a fire source location unit and a route planning unit.

[0059] The fire source positioning unit is used to process and analyze the data collected by the sensor component and the fire monitoring and identification camera, extract the characteristics of the fire (for example, changes in smoke density, temperature increases, changes in gas concentration, etc. are all characteristics of the fire), determine the location and scope of the fire based on the characteristics of the fire and the recognition results of the fire identification model, and then determine the direction and scope of the fire spread based on the prediction results of the fire prediction model.

[0060] The route planning unit is used to plan an escape route using an intelligent algorithm based on the location and scope of the fire, the direction and scope of the fire spread, and the internal layout of the ship (including information such as cabins, passages, emergency exits, etc., and possible escape routes and exit locations are determined based on the layout design), and to verify and optimize the escape route to achieve the effectiveness of the escape route.

[0061] Among them, the intelligent algorithm needs to consider factors such as the width, patency, and ventilation of the escape passage to find the safest and shortest escape route.

[0062] 6. Performance optimization module, including fire source location optimization and escape route optimization.

[0063] The fire source location optimization is used to establish fire risk areas and corresponding regional risk levels based on the fire location and scope and the fire spread direction and scope, and to perform regular updates.

[0064] The escape route optimization is used to update and verify the escape route in real time according to the result of the fire source location optimization, and to establish different escape plans using different fire source locations.

[0065] Therefore, the present invention provides a ship fire monitoring system that can comprehensively monitor the interior of the ship, accurately identify and predict fire risks, and can also automatically perform fire extinguishing operations as soon as a fire occurs, locate the fire source and plan escape routes, thereby ensuring the safety of life and property of personnel, reducing ship losses, and reducing environmental pollution risks.

[0066] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0067] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A fire monitoring system for a ship, characterized in that: include: Fire detection module, used to monitor and collect real-time data from various areas of the ship, including fire monitoring and identification cameras and sensor components installed in various corners of the ship; The fire monitoring module is used to build a fire recognition model based on the collected data of the ship and to carry out fire recognition warning, including a data preprocessing unit, a data fusion unit, a feature extraction unit and a model building unit; Fire warning module, used to build fire prediction models and provide fire risk prediction and warning; A fire control module, used to realize automatic fire extinguishing, including an automatic fire extinguishing control unit and a remote control unit; Intelligent decision-making module, used to provide escape guidance using data analysis and intelligent algorithms, including a fire source location unit and a route planning unit; Performance optimization module, including fire source location optimization and escape route optimization; Among them, the fire detection module, the fire monitoring module, the fire warning module, the fire control module, the intelligent decision-making module and the performance optimization module are interconnected.

2. A ship fire monitoring system according to claim 1, characterized in that: In the fire detection module: the sensor component includes a temperature sensor, a smoke sensor and a gas sensor. The sensor component and the fire monitoring and identification camera transmit the collected images and data to the fire monitoring module and the fire warning module in real time for identification and prediction, wherein the collected data includes temperature, smoke, gas and flame thermal radiation.

3. A fire monitoring system for ships according to claim 2, characterized in that: In the fire monitoring module: The data preprocessing unit is used to perform missing value processing, outlier processing, data cleaning and data conversion on the collected data to obtain original data, and store the original data in a database; The data fusion unit is used to fuse the temperature value, smoke value, gas value and flame thermal radiation value in the original data to obtain a data set, and then divide the data set into a recognition test set and a recognition training set; The feature extraction unit is used to extract feature variables in the data set using an artificial intelligence algorithm, and to label and classify the feature variables; The model building unit is used to train the feature variables based on a convolutional neural network, and then adjust the model parameters through a back propagation algorithm and an optimizer to obtain the original recognition model, input the recognition test set into the original recognition model for performance evaluation, and then optimize the original recognition model to obtain the fire recognition model; The fire recognition model is deployed in an actual environment to perform fire recognition tasks, and flames are detected in real time in the data stream of the fire monitoring and recognition camera.

4. A fire monitoring system for ships according to claim 3, characterized in that: In the fire warning module, the fire prediction model is constructed as follows: Collecting a comprehensive data set including fire data and non-fire data, annotating the comprehensive data set according to the fire prediction task requirements to distinguish between fire situations and non-fire situations, and dividing the comprehensive data set into a prediction training set and a prediction test set; Based on the comprehensive data set, the fire recognition model is retrained using the transfer learning method, the model parameters are adjusted, and an initial prediction model is obtained. The initial prediction model is then evaluated using the prediction test set, the accuracy and recall rate are calculated, and the initial prediction model is optimized to obtain the fire prediction model.

5. A fire monitoring system for ships according to claim 4, characterized in that: In the fire control module: The automatic fire extinguishing control unit is used to confirm whether a fire has occurred according to the identification result of the fire identification model using preset logic and algorithm, and automatically start corresponding fire extinguishing instructions according to the fire situation, wherein the fire extinguishing instructions include automatic fire extinguishing instructions, instructions for notifying firefighters, and issuing evacuation instructions, wherein the automatic fire extinguishing instructions include automatically releasing fire extinguishing agents, starting a water spray system, and shutting down a ventilation system; The remote control unit is used to monitor ship data and operate the fire monitoring system in real time using the remote control platform, and to send alarm information, fire emergency handling information and escape guidance information in real time using the automatic alarm function.

6. A fire monitoring system for ships according to claim 5, characterized in that: In the intelligent decision-making module: The fire source positioning unit is used to process and analyze the data collected by the sensor assembly and the fire monitoring and recognition camera, extract the characteristics of the fire, determine the location and range of the fire based on the characteristics of the fire and the recognition results of the fire recognition model, and then determine the direction and range of the fire spread based on the prediction results of the fire prediction model; The route planning unit is used to plan an escape route using an intelligent algorithm according to the location and scope of the fire, the direction and scope of the fire spread, and the internal layout of the ship, and to verify and optimize the escape route to achieve the effectiveness of the escape route.

7. A fire monitoring system for ships according to claim 6, characterized in that: In the performance optimization module: The fire source location optimization is used to establish fire risk areas and corresponding regional risk levels based on the fire location and scope and the fire spread direction and scope, and to perform regular updates; The escape route optimization is used to update and verify the escape route in real time according to the result of the fire source location optimization, and to establish different escape plans using different fire source locations.

Images