Fire early warning control method and device, electronic equipment and memory

Abstract

The invention discloses a fire early warning control method and device, electronic equipment and a storer, and the method comprises the steps: obtaining detection data of sensors arranged in a roadway, the sensors are at least arranged on each branch of the roadway, and the branches refer to roadways without other communication except the head and tail positions of the roadway; according to the detection data, whether a fire occurs in each branch is judged, a first fire alarm signal is sent in response to the judgment that the fire occurs, and the first fire alarm signal comprises a fire occurrence position and fire occurrence time; estimating the spreading situation of the fire according to the first fire alarm signal, and adjusting the passage between the roadways according to the spreading situation. By integrating advanced sensor technology, data analysis technology, automatic control technology and the like, real-time monitoring and data analysis of the underground environment of the coal mine are realized, so that the safety production level of the coal mine is improved.

Description

Technical Field

[0001] The present application relates to a fire warning method, and in particular to an underground fire warning control method, device, electronic equipment and memory. Background Art

[0002] In coal mine scenarios, the traditional fire warning method is mainly to manually report to the dispatch room through mobile communication networks, such as mobile phones, landlines, etc. The above traditional model has many disadvantages, including:

[0003] 1. This model requires staff to have professional knowledge and skills. Once the staff is negligent or makes mistakes in judgment, it may lead to untimely or wrong warnings, thus affecting the timely detection and control of fires;

[0004] 2. Manual monitoring takes time to detect abnormal conditions, but fires develop very quickly, and manual response time may not be enough to prevent the fire from spreading rapidly;

[0005] 3. Manual operation may also cause delayed response due to various reasons (such as fatigue, lack of concentration, etc.);

[0006] 4. It is difficult to process a large amount of real-time data manually, especially in complex building environments. Single manual monitoring is difficult to cover all corners, which may lead to the omission of fire hazards.

[0007] 5. With the development of technology, the technology and standards of fire warning systems are constantly updated, requiring continuous technical updates and personnel training, which increases costs and time.

[0008] With the development of the industry, more and more intelligent devices have been developed. There are many types of intelligent monitoring sensors underground, such as wind speed sensors, wind direction sensors, smoke sensors, carbon monoxide sensors, carbon dioxide sensors, damper controllers, and wind window controllers. Through dynamic monitoring and real-time calculation of multiple devices, fire early warning control in coal mines has become possible. Summary of the invention

[0009] The embodiments of the present application provide a fire warning control method, device, electronic device and memory, which are used to solve many problems of existing fire warning methods caused by reliance on human experience.

[0010] According to one aspect of the present application, a fire early warning control method is provided, comprising:

[0011] Acquire detection data of sensors arranged in the lane, wherein the sensors are arranged at least on each branch of the lane, and the branch refers to a lane that is not connected to other lanes except the head and tail positions of the lane;

[0012] Determine whether a fire occurs in each branch according to the detection data, and send a first fire alarm signal in response to determining that a fire occurs, wherein the first fire alarm signal includes a location and a time when the fire occurs;

[0013] The spread of the fire is estimated according to the first fire alarm signal, and the passages between the lanes are adjusted according to the spread.

[0014] Furthermore, judging whether a fire occurs in each branch according to the detection data includes: if there is smoke in the detection data belonging to the same branch and the temperature is greater than or equal to 30° C., judging that a fire occurs in the branch.

[0015] Furthermore, the estimating the fire spread situation according to the first fire alarm signal includes:

[0016] Obtaining multi-dimensional data of the lane, and generating a twin lane based on the multi-dimensional data;

[0017] A ventilation model is generated by training according to the historical damper and window setting information, ventilation equipment setting information, and wind speed and direction information of the lane;

[0018] Taking the current fire location, fire time and the current ventilation model as input information, based on the constructed intelligent optimization model, output a real-time tunnel opening and closing plan;

[0019] Performing simulation verification of the real-time lane opening and closing scheme on the twin lanes;

[0020] In response to the simulation verification, the opening and closing of the dampers and windows in the lanes are adjusted through the corresponding real-time lane opening and closing scheme, and the spreading situation is estimated and updated in real time according to the lane opening and closing scheme and presented on the display terminal of the twin lanes.

[0021] Furthermore, the obtaining of multi-dimensional data of the lane and generating a twin lane based on the multi-dimensional data includes:

[0022] Obtaining physical elements of the lane, wherein the physical elements include the location, size, temperature, smoke concentration, gas concentration, and the location and opening and closing conditions of the air door and air window of the lane;

[0023] The physical elements are formed into a set and used to generate the twin lane.

[0024] Furthermore, the training and generating of a ventilation model based on the historical damper and window setting information, ventilation equipment setting information, and wind speed and direction information of the lane includes:

[0025] Acquire a training data set, wherein the training data set includes the position, opening and closing status, wind speed, wind direction and ventilation equipment setting information of the damper and window;

[0026] The positions, opening and closing states of the dampers and windows and the ventilation equipment setting information in the training data set are used as input, and the wind speed and wind direction are used as output to train the ventilation model until the model converges.

[0027] Furthermore, the current fire location, fire time and the current ventilation model are used as input information, and based on the constructed intelligent optimization model, a real-time tunnel opening and closing plan is output, including:

[0028] The intelligent optimization model is a reinforcement model, which uses the current fire location, fire occurrence time and the current ventilation model as the state space, the controllable conditions of the lane as the action space, and the range of the fire location in the lane as the delayed reward. The lane opening and closing plan is output under the reinforcement learning state constructed by the state space, action space and delayed reward; wherein the controllable conditions include the opening and closing mode of the dampers and windows and the working state of the ventilation equipment.

[0029] Furthermore, the method further comprises:

[0030] Generate a corresponding real-time lane map according to the real-time lane opening and closing scheme;

[0031] Obtaining the location of underground personnel, and generating personnel route guidance according to the location of the personnel in the current real-time tunnel map and the estimated updated spread situation, wherein the personnel route guidance includes a travel route and the arrival time of at least key points on the route; wherein the travel route selects a passable route in the real-time tunnel map, and the arrival time of the key points is earlier than the time when the estimated updated spread situation covers the key points;

[0032] The route guidance is sent to a receiving device of the underground personnel.

[0033] A second aspect of the present invention provides a fire early warning control device, comprising:

[0034] A detection unit, used to obtain detection data of sensors arranged in the lane, wherein the sensors are arranged at least on each branch of the lane, and the branch refers to a lane that is not connected to other lanes except the head and tail positions of the lane;

[0035] a judgment alarm unit, configured to judge whether a fire occurs in each branch according to the detection data, and send a first fire alarm signal in response to judging whether a fire occurs, wherein the first fire alarm signal includes a fire occurrence location and a fire occurrence time;

[0036] An adjustment unit is used to estimate the spread of fire according to the first fire alarm signal, and adjust the passages between the lanes according to the spread.

[0037] The third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method described in the first aspect of the present application.

[0038] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program. When the computer program is run on a computer, the computer executes the method described in the first aspect of the present application.

[0039] In the embodiment of the present application, a fire early warning control method is adopted, including: obtaining detection data of sensors arranged in the tunnel, the sensors are arranged at least on each branch of the tunnel, and the branch refers to a tunnel that has no other connections except the head and tail positions of the tunnel section; judging whether a fire occurs in each branch according to the detection data, and sending a first fire alarm signal in response to judging that a fire occurs, the first fire alarm signal includes the location and time of the fire; estimating the spread of the fire according to the first fire alarm signal, and adjusting the passages between the tunnels according to the spread. The present invention realizes real-time monitoring and data analysis of the underground environment of coal mines by integrating advanced sensor technology, data analysis technology, automatic control technology, etc., thereby improving the safety production level of coal mines. Through this application, many problems existing in the underground fire early warning method, such as poor fire control effect caused by relying on personnel experience, are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 It is a flow chart of a fire warning control method according to an embodiment of the present application.

[0042] Figure 2 It is a structural schematic diagram of a fire warning control device according to an embodiment of the present application.

[0043] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0045] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0046] The embodiment of the present invention conceives to provide real-time feedback of underground fire conditions through intelligent sensing sensors. When a fire occurs, a multi-system linkage control solution is given according to the current situation. By changing the air doors and windows, etc., the effect of controlling the scope of the fire is achieved. Evacuation route guidance is provided based on fire prediction, which is conducive to guiding personnel evacuation and deploying firefighting work.

[0047] Based on the above concept, Figure 1 FIG. 1 is a flow chart of a fire early warning control method according to an embodiment of the present invention. Figure 1 It can be seen that the fire early warning control method includes:

[0048] Step S101, acquiring detection data of sensors arranged in the lane, wherein the sensors are arranged at least on each branch of the lane, and the branch refers to a lane that has no other connections except the head and tail positions of the lane.

[0049] In order to monitor the situation in the lane through sensors, multiple different types of sensors need to be arranged in the lane. In this embodiment, sensors are arranged according to the branches of the lane to achieve refined control of the lane. The sensors include at least a temperature sensor, a smoke sensor, a carbon monoxide gas sensor, a carbon dioxide gas sensor, a wind speed sensor, and a wind direction sensor.

[0050] Step S102: determining whether a fire occurs in each branch according to the detection data, and sending a first fire alarm signal in response to determining that a fire occurs, wherein the first fire alarm signal includes a fire occurrence location and a fire occurrence time.

[0051] In certain preferred embodiments, judging whether a fire occurs in each branch based on the detection data includes: if there is smoke in the detection data belonging to the same branch and the temperature is greater than or equal to 30° C., judging that a fire occurs in the branch.

[0052] In some optional embodiments, a camera is provided in the lane and a position recognition algorithm is configured. Based on the camera's captured image, the distance recognition algorithm is used to accurately identify the location of possible fire points in the captured image. Since the roads in the lane are crisscrossed, the impact of different fire points on the fire varies greatly. Therefore, this embodiment is conducive to accurate prediction and control of the fire by accurately locating the location of the fire. The first fire alarm signal not only alarms the first fire point, but also changes dynamically in real time with the development of the fire. The first fire alarm signal constitutes the alarm content of all the locations and times of the fire spread. The above alarm content can reflect the development process from the initial occurrence of the fire to the current time, which is conducive to the use of these contents to predict and control the spread of the fire.

[0053] In some other optional embodiments, after the first fire alarm signal is sent in response to determining that a fire has occurred, the method further includes:

[0054] Continue to determine whether each branch is spread by the fire based on the detection data, specifically by detecting whether the temperature sensor, smoke sensor, carbon monoxide gas sensor, and carbon dioxide gas sensor all meet their respective alarm conditions. For example, the alarm condition of the temperature sensor is greater than or equal to 30°C, the alarm condition of the smoke sensor is smoke alarm, the alarm condition of the carbon monoxide gas sensor is carbon monoxide concentration greater than or equal to 35ppm alarm, and the alarm condition of the carbon dioxide sensor is carbon dioxide concentration greater than or equal to 3% alarm.

[0055] Step S103: predicting the spread of the fire according to the first fire alarm signal, and adjusting the passages between the lanes according to the spread.

[0056] like Figure 2The lane map shown includes 4 branches, namely F101, F102, F103 and F104, among which F101 is connected with F102, F104 is connected with F105, the starting point of F103 is located at the connection point of F101 and F102, and the end point of F103 is located at the connection point of F103 and F104, wherein the starting point of F101, the end point of F102, the starting point of F103, the end point of F103, the starting point of F104 and the end point of F105 are provided with dampers and windows. The starting position of the current fire location is located in F101, 100 meters away from the starting point. The current ventilation model is that all the dampers and windows involved in the figure are in the open state. Under the action of the ventilation equipment, the wind blows into F101 from the starting point of F101 and enters F102 and F103. Under the effect of the ventilation model, as time goes by, the fire at the starting point of the fire will spread to the branches of F102 and F103. In some embodiments, the upstream and downstream relationship between the branches is obtained according to the location of the fire, wind speed, and wind direction, and the time to spread to the connection point between the branches can be estimated. For example, the wind speed in the branch F101 is 3m / s, and the interval between F101 and F103 is 200m. Then, the estimated arrival time can be estimated to be about 66 seconds, that is, it will spread to the branch F103 after 66 seconds from the starting point of the fire. At this time, ideally, before the actual current time reaches the estimated arrival time, the damper and window D3 at the starting point of F103 should be closed to prevent the fire from spreading to F103. If the actual current time has exceeded the estimated arrival time, the current location of the fire spread can be calculated based on the actual current time and the wind speed in the branch. For example, if the actual current time is 70 seconds from the fire start time, and the wind speed in branch F101 is 3m / s and the wind speed in F103 is 2m / s, the fire spreads to a location in F103 about 8 meters away from the starting point of F103. At this time, the damper and window D3 at the starting point of F103 and the damper and window D4 at the end point of F103 should be closed to prevent the fire from spreading to F104 and F105. In this way, the above-mentioned prediction of the fire spread area and the control of the dampers and windows can be carried out simultaneously in multiple branches. With the different regulation of the dampers and windows, it will affect the subsequent ventilation model, thereby achieving the purpose of controlling the spread of the fire.

[0057] Through the method of the above-mentioned embodiment, combined with sensors and artificial intelligence means, the underground tunnels are connected and disconnected, the ventilation status is quickly adjusted, and the further expansion of the fire is effectively curbed, making the fire control in the tunnels and the evacuation of underground personnel more intelligent, ensuring the timeliness and efficiency of safety prevention and control, and helping to reduce disaster losses.

[0058] In some preferred embodiments, the estimating the fire spread situation according to the first fire alarm signal includes:

[0059] Step S1031, obtaining multi-dimensional data of the lane, and generating a twin lane based on the multi-dimensional data. By collecting the multi-dimensional data, a data basis is provided for the subsequent generation of accurate twin lanes.

[0060] Step S1032: training and generating a ventilation model based on the historical damper and window setting information, ventilation equipment setting information, and wind speed and direction information of the lane.

[0061] Step S1033: taking the current fire location, fire time and the current ventilation model as input information, and outputting a real-time tunnel opening and closing plan based on the constructed intelligent optimization model.

[0062] Step S1034: perform simulation verification of the real-time lane opening and closing scheme on the twin lanes.

[0063] Step S1035, in response to the simulation verification, adjusting the opening and closing of the dampers and windows in the lanes through the corresponding real-time lane opening and closing scheme, and estimating and updating the spreading situation in real time according to the lane opening and closing scheme and presenting it on the display terminal of the twin lanes.

[0064] The above-mentioned embodiment collects the on-site factors that affect the development of the fire and identifies the tunnel on-off scheme through an intelligent optimization model, wherein the current fire location, the time of the fire and the current ventilation model are the main factors affecting the next development trend of the fire. Through the above-mentioned method, the tunnel on-off scheme can be output in real time and the damper and window control based on the real-time on-off scheme can be immediately deployed in place, so that the control of the fire in the tunnel is fast and accurate. And through the visual display of the twin tunnels, the fire situation in the tunnel and the on-off scheme in the tunnel can be intuitively presented to the control personnel and the people to be evacuated in the tunnel, which is conducive to guiding personnel to quickly and efficiently achieve safe evacuation.

[0065] In some preferred embodiments, the physical data of the lanes is obtained by collecting multi-dimensional actual data of the lanes, thereby achieving the technical goal of providing a comprehensive and accurate data basis for the subsequent construction of twin lanes using digital twin technology. Therefore, the multi-dimensional data of the lanes is obtained, and the twin lanes are generated based on the multi-dimensional data, including:

[0066] Step S10311, obtaining physical elements of the lane, wherein the physical elements include the location, size, temperature, smoke concentration, gas concentration, and the position and opening and closing status of the air door and window of the lane;

[0067] Step S10312: Form a set of the physical elements and use them to generate the twin lanes.

[0068] In some preferred embodiments, the ventilation model is an important factor affecting the spread of fire and the evacuation of personnel. Therefore, real-time control and regulation of the ventilation model is the core of implementing dynamic fire control and evacuation of personnel. In order to fully grasp the ventilation conditions under various damper and window setting conditions and ventilation equipment setting conditions in the lane, the ventilation model is generated by training based on the historical damper and window setting information, ventilation equipment setting information and wind speed and direction information of the lane, including:

[0069] Step S10321, obtaining a training data set, wherein the training data set includes the position, opening and closing status, wind speed, wind direction and ventilation equipment setting information of the damper and window.

[0070] Step S10322: using the positions, opening and closing states of the dampers and windows and the ventilation equipment setting information in the training data set as input, and using the wind speed and wind direction as output to train the ventilation model until the model converges.

[0071] The trained ventilation model will respond in real time to the position, opening and closing status of doors and windows, and ventilation equipment setting information, and can respond to and output corresponding combinations of wind speed and wind direction. These combinations of wind speed and wind direction will be used as part of the input of subsequent intelligent models, providing a basis for the operation of the intelligent model, thereby facilitating the intelligent model to obtain the best real-time alley opening and closing plan.

[0072] In some preferred embodiments, the current fire location, fire time and the current ventilation model are used as input information, and a real-time tunnel opening and closing scheme is output based on the constructed intelligent optimization model, including:

[0073] The intelligent optimization model is a reinforcement model, which uses the current fire location, fire occurrence time and the current ventilation model as the state space, the controllable conditions of the lane as the action space, and the range of the fire location in the lane as the delayed reward. The lane opening and closing plan is output under the reinforcement learning state constructed by the state space, action space and delayed reward; wherein the controllable conditions include the opening and closing mode of the dampers and windows and the working state of the ventilation equipment.

[0074] Because the reinforcement model uses the range of the location of the fire in the lane as a delayed reward, the lane opening and closing scheme output by the trained reinforcement model can control the spread of the fire to the maximum extent. The opening and closing mode of the dampers and windows includes the opening and closing combination of specific dampers and windows, and the working state of the ventilation equipment includes the start and stop of the ventilation equipment at a specific location and the control of the air volume. The above variables together lead to different ventilation states in the lane, which will affect the spread of the fire. Therefore, the reinforcement learning model can provide efficient guidance for fire control in the lane.

[0075] Since the opening and closing of the lane is very important for the evacuation of people in the lane, in some preferred embodiments, the method further includes:

[0076] Step S104: Generate a corresponding real-time lane map according to the real-time lane on-off scheme.

[0077] Step S105, obtaining the location of underground personnel, and generating personnel route guidance according to the location of the personnel in the current real-time tunnel map and the estimated updated spread situation, wherein the personnel route guidance includes a travel route and the arrival time of at least key points on the route; wherein the travel route selects a passable route in the real-time tunnel map, and the arrival time of the key points is earlier than the time when the estimated updated spread situation covers the key points.

[0078] Step S106: Send the route guidance to the receiving device of the underground personnel.

[0079] Through the above methods, accurate and effective guidance can be provided to personnel in different locations to help them evacuate from the fire scene.

[0080] Based on the same inventive concept as the above method embodiment, a fire early warning control device comprises:

[0081] A detection unit, used to obtain detection data of sensors arranged in the lane, wherein the sensors are arranged at least on each branch of the lane, and the branch refers to a lane that is not connected to other lanes except the head and tail positions of the lane;

[0082] a judgment alarm unit, configured to judge whether a fire occurs in each branch according to the detection data, and send a first fire alarm signal in response to judging whether a fire occurs, wherein the first fire alarm signal includes a fire occurrence location and a fire occurrence time;

[0083] An adjustment unit is used to estimate the spread of fire according to the first fire alarm signal, and adjust the passages between the lanes according to the spread.

[0084] In some preferred embodiments, the alarm determination unit is used to determine whether a fire occurs in each branch according to the detection data, including:

[0085] The smoke and temperature recognition unit is used to determine that a fire has occurred in a branch if smoke exists in the detection data belonging to the same branch and the temperature is greater than or equal to 30°C.

[0086] In some preferred embodiments, the adjusting unit estimates the spread of the fire according to the first fire alarm signal, including:

[0087] A twin lane generation unit, used to obtain multi-dimensional data of the lane, and generate a twin lane based on the multi-dimensional data;

[0088] A ventilation model generating unit, used for training and generating a ventilation model according to the historical damper and window setting information, ventilation equipment setting information and wind speed and direction information of the lane;

[0089] A tunnel opening and closing scheme generating unit is used to take the current fire location, fire occurrence time and the current ventilation model as input information, and output a real-time tunnel opening and closing scheme based on the constructed intelligent optimization model;

[0090] A simulation unit, used for simulating and verifying the real-time lane opening and closing scheme for the twin lanes;

[0091] An adjustment unit is used to adjust the opening and closing of the dampers and windows in the lanes in response to the simulation verification through the corresponding real-time lane opening and closing scheme, and to estimate and update the spreading situation in real time according to the lane opening and closing scheme and present it on the display terminal of the twin lanes.

[0092] In some preferred embodiments, the twin lane generation unit is used to obtain multi-dimensional data of the lane, and generate the twin lane based on the multi-dimensional data, including:

[0093] A physical element acquisition unit, used to acquire the physical elements of the lane, wherein the physical elements include the location, size, temperature, smoke concentration, gas concentration, and the position and opening and closing status of the air door and window of the lane;

[0094] A set generation unit is used to form the physical elements into a set and use it to generate the twin lane.

[0095] In some preferred embodiments, the ventilation model generation unit is used to train and generate a ventilation model based on the historical damper and window setting information, ventilation equipment setting information, and wind speed and direction information of the lane, including:

[0096] A training data acquisition unit, used to acquire a training data set, wherein the training data set includes the position, opening and closing state, wind speed, wind direction of the damper and window, and ventilation equipment setting information;

[0097] The training unit is used to use the positions, opening and closing states of the dampers and windows in the training data set and the ventilation equipment setting information as input, and use the wind speed and wind direction as output to train the ventilation model until the model converges.

[0098] In some preferred embodiments, the tunnel opening and closing scheme generating unit is used to take the current fire location, fire occurrence time and the current ventilation model as input information, and output a real-time tunnel opening and closing scheme based on the constructed intelligent optimization model, including:

[0099] The intelligent optimization model is a reinforcement model, which uses the current fire location, fire occurrence time and the current ventilation model as the state space, the controllable conditions of the lane as the action space, and the range of the fire location in the lane as the delayed reward. The lane opening and closing plan is output under the reinforcement learning state constructed by the state space, action space and delayed reward; wherein the controllable conditions include the opening and closing mode of the dampers and windows and the working state of the ventilation equipment.

[0100] In some preferred embodiments, the fire warning control device further includes:

[0101] A map generating unit, used for generating a corresponding real-time lane map according to the real-time lane opening and closing scheme;

[0102] A guidance generating unit is used to obtain the location of underground personnel, and generate personnel route guidance according to the location of the personnel in the current real-time tunnel map and the estimated updated spreading situation, wherein the personnel route guidance includes a travel route and an arrival time of at least a key point on the route; wherein the travel route selects a passable route in the real-time tunnel map, and the arrival time of the key point is earlier than the time when the estimated updated spreading situation covers the key point;

[0103] A sending unit is used to send the route guidance to a receiving device of the underground personnel.

[0104] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0105] Based on the same inventive concept as the above-mentioned method embodiment, an electronic device is also provided in an embodiment of the present application, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the electronic device implements the control method in the above-mentioned embodiment.

[0106] In one embodiment, the electronic device may be a server. In this embodiment, the structure of the electronic device may be as follows: Figure 3 As shown, it includes a memory 2001 , a communication module 2003 and one or more processors 2002 .

[0107] The memory 2001 is used to store computer programs executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and programs required for running the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0108] The memory 2001 may be a volatile memory, such as a random-access memory (RAM); the memory 2001 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 2001 may be any other medium that can be used to carry or store a desired computer program in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2001 may be a combination of the above memories.

[0109] The processor 2002 may include one or more central processing units (CPU) or a digital processing unit, etc. The processor 2002 is used to implement the above-mentioned audio data processing method when calling the computer program stored in the memory 2001 .

[0110] The communication module 2003 is used to communicate with terminal devices and other servers.

[0111] The specific connection medium between the memory 2001, the communication module 2003 and the processor 2002 is not limited in the embodiment of the present application. Figure 3 In the embodiment, the memory 2001 and the processor 2002 are connected via a bus 2004. The bus 2004 is Figure 3 The arrows in the figure are used to describe the connection between other components, which is only for illustrative purposes and is not intended to be limiting. Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 3 The diagram only uses one arrow, but does not describe only one bus or one type of bus.

[0112] Based on the same inventive concept as the above method embodiment, an embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium is used to store a computer program, when the computer program is run on a computer, the electronic device implements the control method in the above embodiment. The computer-readable storage medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0113] Based on the same inventive concept as the above-mentioned method embodiment, an embodiment of the present invention further provides a computer program product, the computer program product including a computer program. When the program product is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the control method according to various exemplary embodiments of the present application described above in this specification. The program product may adopt any combination of one or more readable media. These computer program commands may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the commands executed by the processor of the computer or other programmable data processing device generate commands for implementing the steps in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

Claims

1. A fire early warning control method, characterized in that: Acquire detection data of sensors arranged in the lane, wherein the sensors are arranged at least on each branch of the lane, and the branch refers to a lane that is not connected to other lanes except the head and tail positions of the lane; Determine whether a fire occurs in each branch according to the detection data, and send a first fire alarm signal in response to determining that a fire occurs, wherein the first fire alarm signal includes a location and a time when the fire occurs; The spread of the fire is estimated according to the first fire alarm signal, and the passages between the lanes are adjusted according to the spread.

2. The method according to claim 1, characterized in that: The determining whether a fire occurs in each branch according to the detection data includes: if there is smoke in the detection data belonging to the same branch and the temperature is greater than or equal to 30° C., determining that a fire occurs in the branch.

3. The method according to claim 2, characterized in that The estimating the spread of fire according to the first fire alarm signal comprises: Obtaining multi-dimensional data of the lane, and generating a twin lane based on the multi-dimensional data; A ventilation model is generated by training according to the historical damper and window setting information, ventilation equipment setting information, and wind speed and direction information of the lane; Taking the current fire location, fire time and the current ventilation model as input information, based on the constructed intelligent optimization model, output a real-time tunnel opening and closing plan; Performing simulation verification of the real-time lane opening and closing scheme on the twin lanes; In response to the simulation verification, the opening and closing of the dampers and windows in the lanes are adjusted through the corresponding real-time lane opening and closing scheme, and the spreading situation is estimated and updated in real time according to the lane opening and closing scheme and presented on the display terminal of the twin lanes.

4. The method according to claim 2, characterized in that The step of obtaining the multi-dimensional data of the lane and generating a twin lane based on the multi-dimensional data includes: Obtaining physical elements of the lane, wherein the physical elements include the location, size, temperature, smoke concentration, gas concentration, and the location and opening and closing conditions of the air door and air window of the lane; The physical elements are formed into a set and used to generate the twin lane.

5. The method according to claim 2, characterized in that The training and generating of a ventilation model according to the historical damper and window setting information, ventilation equipment setting information and wind speed and direction information of the lane includes: Acquire a training data set, wherein the training data set includes the position, opening and closing status, wind speed, wind direction and ventilation equipment setting information of the damper and window; The positions, opening and closing states of the dampers and windows and the ventilation equipment setting information in the training data set are used as input, and the wind speed and wind direction are used as output to train the ventilation model until the model converges.

6. The method according to claim 2, characterized in that The current fire location, fire time and the current ventilation model are used as input information, and based on the constructed intelligent optimization model, a real-time tunnel opening and closing plan is output, including: The intelligent optimization model is a reinforcement model, which uses the current fire location, fire occurrence time and the current ventilation model as the state space, the controllable conditions of the lane as the action space, and the range of the fire location in the lane as the delayed reward. The lane opening and closing plan is output under the reinforcement learning state constructed by the state space, action space and delayed reward; wherein the controllable conditions include the opening and closing mode of the dampers and windows and the working state of the ventilation equipment.

7. The method according to claim 3, characterized in that The method further comprises: Generate a corresponding real-time lane map according to the real-time lane opening and closing scheme; Obtaining the location of underground personnel, and generating personnel route guidance according to the location of the personnel in the current real-time tunnel map and the estimated updated spread situation, wherein the personnel route guidance includes a travel route and the arrival time of at least key points on the route; wherein the travel route selects a passable route in the real-time tunnel map, and the arrival time of the key points is earlier than the time when the estimated updated spread situation covers the key points; The route guidance is sent to a receiving device of the underground personnel.

8. A fire early warning control device, characterized in that: include: A detection unit, used to obtain detection data of sensors arranged in the lane, wherein the sensors are arranged at least on each branch of the lane, and the branch refers to a lane that has no other connections except the head and tail positions of the lane; a judgment alarm unit, configured to judge whether a fire occurs in each branch according to the detection data, and send a first fire alarm signal in response to judging whether a fire occurs, wherein the first fire alarm signal includes a fire occurrence location and a fire occurrence time; An adjustment unit is used to estimate the spread of fire according to the first fire alarm signal, and adjust the passages between the lanes according to the spread.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images