Comprehensive pipe gallery cable fire intelligent identification and prevention and control linkage system

Abstract

The invention relates to the technical field of comprehensive pipe galleries, and provides a comprehensive pipe gallery cable fire intelligent identification and prevention and control linkage system. In the system, fire simulation is carried out on a comprehensive pipe gallery cable through a cable fire simulation device; the fire behavior of the cable in the pipe gallery is monitored in real time through the image acquisition unit, and the acquired simulated fire image information is transmitted to the deployed fire identification model in real time for fire identification, so that the fire identification result of the fire identification model is judged through the deployed fire early warning model. A fire extinguishing instruction or an early warning instruction is sent out according to the judgment result; further, the fire extinguishing linkage device responds after receiving the fire extinguishing instruction, and a self-made fire resisting shutter with a flexible steel brush is firstly started to block a fire point area; and then a telescopic end of an electric push rod mounted at the top of the pipe rack quickly extends out to crush a temperature sensing glass ball of the suspension type fire extinguisher, so that quick linkage prevention and control of the pipe rack cable fire are realized.

Description

Technical Field

[0001] The present application relates to the technical field of integrated pipe corridors, and in particular to an intelligent identification and prevention and control linkage system for cable fires in integrated pipe corridors. Background Art

[0002] With the acceleration of urbanization, the construction of urban underground comprehensive pipeline corridors is increasing. As underground spaces accommodating various municipal pipelines, the comprehensive pipeline corridors face serious fire risks due to the laying of a large number of cables in the power compartments of the comprehensive pipeline corridors. Because the cables are usually laid continuously and the materials such as the cable insulation layer are mostly flammable.

[0003] The high temperature and thick smoke generated by the fire will not only cause serious damage to the cables themselves, leading to power outages and affecting the city's power supply, but may also endanger the structural safety of the entire integrated pipe gallery and threaten the normal operation of other pipelines in the pipe gallery. At the same time, the toxic gases produced by the combustion will also pose a major threat to the life safety of personnel entering the pipe gallery for maintenance and other operations. Traditional fire detection methods have limitations in the special environment of the pipe gallery. For example, smoke detectors may also be affected by the special smoke components and concentration changes produced by cable combustion in cable fires, resulting in false alarms or missed alarms. At the same time, it is impossible to warn of abnormal detection, which will pose a major threat to the lives of personnel entering the pipe gallery for maintenance and other operations.

[0004] In terms of fire extinguishing, due to the narrowness of the tunnel space, the fire extinguishing agent will spread along both ends of the tunnel under the initial kinetic energy of the fire extinguisher after being activated, thus weakening the fire extinguishing effect on the fire source. In addition, although the traditional suspended dry powder fire extinguishing system has good fire extinguishing efficiency, the glass ball embedded in the fire extinguisher reaches 68 o C before it can respond, which may easily cause fire extinguishing delays and may miss the best time for fire extinguishing.

[0005] Therefore, there is an urgent need to provide a technical solution to the above-mentioned deficiencies in the prior art. Summary of the invention

[0006] The purpose of this application is to provide an intelligent identification and prevention and control linkage system for cable fires in an integrated pipeline corridor to solve or alleviate the problems existing in the above-mentioned prior art.

[0007] In order to achieve the above objectives, this application provides the following technical solutions: The present application provides a comprehensive pipe gallery cable fire intelligent identification and prevention and control linkage system, including: a pipe gallery cable fire simulation device, which is a shell structure and is used to simulate the fire of the comprehensive pipe gallery cable; The identification device monitors the fire simulation in the cable fire simulation device in real time through the image acquisition unit, and transmits the collected simulated fire image information to the deployed fire identification model in real time for fire identification, so as to judge the fire identification result of the fire identification model through the deployed fire warning model, and issue a fire extinguishing instruction or a warning instruction according to the judgment result; A fire extinguishing linkage device is installed in the pipe gallery cable fire simulation device, and is used to respond after receiving a fire extinguishing command from the identification device, so that the fireproof roller shutter with a flexible steel brush is activated, and after the fire point area in the pipe gallery cable fire simulation device is blocked, the telescopic end of the electric push rod installed on the top of the pipe gallery cable fire simulation device is extended to smash the temperature-sensitive glass ball of the suspended fire extinguisher installed on the top of the pipe gallery cable fire simulation device, thereby realizing the fire extinguishing operation of the fire simulation carried out in the pipe gallery cable fire simulation device.

[0008] Preferably, the pipe gallery cable fire simulation device comprises: a pipe gallery platform, which is a rectangular shell structure with an opening on one side; The size adjustment unit is used to block the opening of the pipe gallery platform to form a pipe gallery cavity with the pipe gallery platform; and can move along the opening direction of the pipe gallery platform to adjust the spatial size of the pipe gallery cavity.

[0009] Preferably, fixed slide rails extending toward the opening direction are arranged on the inner side walls at both ends of the pipe gallery platform; correspondingly, Both ends of the size adjustment unit are provided with fixed sliding blocks slidably mounted with the fixed sliding rails, so that the size adjustment unit can move along the opening direction of the pipe gallery platform.

[0010] Preferably, the pipe gallery cable fire simulation device also includes: an adjustable experimental oil pan, which is slidably mounted on the inner wall of the pipe gallery platform opposite to the opening and can be adjusted in position along the height direction and horizontal direction of the pipe gallery platform.

[0011] Preferably, the shell structure of the pipeline corridor cable fire simulation device is divided into multiple simulation areas in the horizontal direction; each of the simulation areas is respectively installed with the image acquisition unit and the suspended fire extinguisher.

[0012] Preferably, there are multiple fireproof roller shutters, which are respectively arranged between two adjacent simulation areas; and after receiving the fire extinguishing command issued by the identification device, the two fireproof roller shutters corresponding to the simulation area for fire simulation move to block the simulation area for fire simulation.

[0013] Preferably, one end of the fireproof roller shutter is mounted on the inner wall of the pipe gallery cable fire simulation device, and can be moved in the front-to-rear direction driven by the closing motor to block the simulation area for fire simulation.

[0014] Preferably, a plurality of through grooves are arranged in parallel along the height direction on the fireproof roller shutter, each of the through grooves corresponds to the cables arranged in the horizontal direction in the pipe gallery cable fire simulation device, and each is provided with the flexible steel brush; wherein the through grooves extend along the width direction of the pipe gallery platform.

[0015] Preferably, the fire identification model deployed in the identification device is trained based on pre-acquired fire sample images, and the convolutional layer and the fully connected layer of the fire identification model are updated based on the Adam method until the fire identification error of the fire identification model is less than or equal to a preset error threshold.

[0016] Preferably, the fire identification model deployed in the identification device is constructed through a convolutional layer according to the formula: Extract the fire features of the fire sample image; where, For the The convolutional layer extracts Fire characteristics, is the activation function of the convolutional layer of the fire recognition model, For the a fire sample image; The fire identification model In the convolutional layer Fire characteristics and The weights between the fire characteristics, The fire identification model In the convolutional layer The offset of each fire feature; All are positive integers; The fire identification model performs dimensionality reduction processing on the fire features of the extracted fire sample images through a pooling layer; The fire identification model is implemented through a fully connected layer according to the formula: Classify the fire characteristics after dimensionality reduction; where, The fire identification model nodes of the fully connected layer; The fire identification model nodes in the fully connected layer, The fire identification model The fully connected layers to The weights of the fully connected layers, For the The bias term of the fully connected layer, is the activation function of the fully connected layer of the fire identification model; The output layer of the fire identification model is processed by the Softmax function according to the formula: Calculate the probability of fire ; In the formula, is the output of the fully connected layer of the fire identification model fire feature classification labels; among them, hour, , indicating a fire has occurred, hour, , indicating that no fire occurred.

[0017] Preferably, according to the formula: Updating the convolutional layer and the fully connected layer of the fire identification model; In the formula, The fire identification model In the convolutional layer Fire characteristics and The updated weights between the fire features are The fire identification model In the convolutional layer Fire characteristics and The current weights between the fire characteristics, is the self-learning rate of the weights corresponding to the convolutional layer of the fire identification model; is the fire identification model The fully connected layers to The updated weights of the fully connected layers are The fire identification model The fully connected layers to The current weight of the fully connected layer, is the self-learning rate of the weights corresponding to the fully connected layer of the fire identification model; are vectors of the first-order moment estimate and the second-order moment estimate of the gradient initialized to 0; is the smoothing term.

[0018] Preferably, according to the formula: Determine the first Fire characteristics Input the normalized predicted fire probability obtained in the fire warning model The fire occurrence probability output by the fire identification model Error , to judge the fire identification result of the fire identification model; In the formula, is the activation function of the output layer of the fire identification model, is the weight matrix corresponding to the output layer of the fire warning model, The fire identification model extracts the first A hidden layer value obtained by inputting a fire feature into the hidden layer of the fire warning model; is the bias term of the hidden layer; is the bias term of the output layer; is the activation function of the hidden layer of the fire recognition model, The fire identification model extracts the first Fire characteristics The weight matrix of The fire identification model extracts the first A hidden layer value obtained by inputting a fire feature into the hidden layer of the fire warning model; is the hidden layer value The corresponding weight matrix.

[0019] Preferably, in response to the error Greater than the preset monitoring threshold , the identification device issues the warning instruction; in response to the error Less than or equal to the preset monitoring threshold , the identification device issues the fire extinguishing instruction.

[0020] Beneficial effects: In the integrated pipe gallery cable fire intelligent identification and prevention and control linkage system provided by the embodiment of the present application, a fire simulation is performed on the integrated pipe gallery cable through a pipe gallery cable fire simulation device with a shell structure; in the identification device, the fire simulation performed in the pipe gallery cable fire simulation device is monitored in real time through an image acquisition unit, and the collected simulated fire image information is transmitted in real time to the deployed fire identification model for fire identification, so that the fire identification result of the fire identification model is judged by the deployed fire warning model, and a fire extinguishing command or a warning command is issued according to the judgment result; the fire extinguishing linkage device installed in the pipe gallery cable fire simulation device responds after receiving the fire extinguishing command issued by the identification device, and the homemade fireproof roller shutter with a flexible steel brush is first activated to block the fire point area; then, the telescopic end of the electric push rod installed on the top of the pipe gallery is quickly extended to smash the temperature-sensitive glass ball of the suspended fire extinguisher, thereby realizing rapid linkage prevention and control of the pipe gallery cable fire.

[0021] Thus, the video (image acquisition unit) collects multiple features in the pipe gallery, and through the established dual identification and early warning model of pipe gallery cable fire (fire identification model, fire early warning model), the fire occurrence situation is effectively and comprehensively detected, thereby improving the accuracy of fire identification, reducing the false alarm rate of pipe gallery cable fire, and improving the sensitivity and accuracy of judgment; and after identifying the occurrence of a fire, the fire extinguishing linkage device located in the pipe gallery cable fire simulation device can be opened in time to achieve local blocking of the fire point in the pipe gallery and spraying of fire extinguishing agent, thereby improving the timeliness and automation level of fire extinguishing of pipe gallery cable fire. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary 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. Among them: Figure 1 A schematic diagram of the principle of an integrated pipe gallery cable fire intelligent identification and prevention and control linkage system provided according to some embodiments of the present application; Figure 2 A schematic diagram of the structure of an integrated pipe gallery cable fire intelligent identification and prevention and control linkage system provided according to some embodiments of the present application; Figure 3 A schematic diagram of the structure of a pipe gallery cable fire simulation device provided according to some embodiments of the present application; Figure 4 An exploded schematic diagram of a fixed slide rail and a fixed slide block provided according to some embodiments of the present application; Figure 5 A schematic diagram of installing an adjustable experimental oil pan according to some embodiments of the present application; Figure 6 for Figure 5 Schematic diagram of the installation explosion of the adjustable experimental oil pan shown; Figure 7 A schematic diagram of the structure of a fireproof roller shutter provided according to some embodiments of the present application; Figure 8 A schematic diagram of the installation of a closed motor according to some embodiments of the present application; Fig. 9 A schematic diagram of the working principle of a flexible steel brush provided according to some embodiments of the present application; Fig.10 It is a schematic diagram of assembling a hanging fire extinguisher according to some embodiments of the present application; Fig.11 for Fig.10 Installation diagram of dry powder fire extinguisher in; Fig.12 A schematic diagram of the principle of an identification device provided according to some embodiments of the present application; Fig.13 A schematic diagram of the structure of a dual identification warning model provided according to some embodiments of the present application.

[0023] Description of reference numerals: 1. Pipeline corridor cable fire simulation device; 101. Pipe gallery platform; 102. Size adjustment unit; 103. Adjustable experimental oil pan; 111. Fixing the slide rail; 112. Fixing the slide block; 301. Suspended fire extinguisher; 302. Fireproof roller shutter; 312. Through groove; 322. Flexible steel brush. DETAILED DESCRIPTION

[0024] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. Each example is provided by way of explanation of the present application and does not limit the present application. In fact, it will be clear to those skilled in the art that modifications and variations may be made in the present application without departing from the scope or spirit of the present application. For example, a feature shown or described as a part of an embodiment may be used in another embodiment to produce yet another embodiment. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the embodiments of the present invention should belong to the scope of protection of the embodiments of the present invention.

[0025] In the existing identification technology for judging cable fires based on composite gas characteristics, although the shortcomings of single gas fire detectors have been avoided to a certain extent, there are still problems in the identification process such as low identification accuracy and weak fire extinguishing timeliness; at the same time, this technology still detects the gas produced by the fire, and has low accuracy in identifying other fire characteristics. In addition, when extinguishing cable fires in confined spaces, traditional fire extinguishing methods still have problems such as poor fire extinguishing effect (the fire extinguishing agent spreads around the fire source) and long response time (the fire extinguisher's temperature-sensitive glass ball 68o C response) and other issues.

[0026] Based on this, the embodiment of the present application provides an intelligent identification and prevention and control linkage system for cable fire in an integrated pipe gallery, such as Figures 1 to 13 As shown, in the system, a fire simulation of the integrated pipe gallery cable is performed through a pipe gallery cable fire simulation device 1 of a shell structure. Specifically, the pipe gallery cable fire simulation device 1 comprises: a pipe gallery platform 101 and a size adjustment unit 102; wherein the pipe gallery platform 101 is a rectangular shell structure with an opening on one side, and the opening of the pipe gallery platform 101 is blocked by the size adjustment unit 102, so that the size adjustment unit 102 and the pipe gallery platform 101 form a pipe gallery cavity; and the size adjustment unit 102 can move along the opening direction of the pipe gallery platform 101 to adjust the spatial size of the pipe gallery cavity, so as to simulate integrated pipe galleries of different sizes and widths.

[0027] In a specific example, the pipe gallery platform 101 mainly includes: a platform roof, a platform side wall, a platform rear wall, a platform support structure and a cable module. Among them, the platform roof, the platform side wall, the platform rear wall and the platform support structure are all made of steel structure, and the platform roof, the platform side wall and the platform rear wall are welded to each other and together with the platform bottom plate form a rectangular shell structure with a lateral opening; the platform support structure is located at the bottom of the rectangular shell structure and is used to support the rectangular shell structure; a cable module is arranged on the inner side of the platform rear wall (located in the rectangular shell structure) along the length direction of the pipe gallery platform 101. Specifically, the cable support component in the cable module is fixedly connected to the platform rear wall along the length direction of the pipe gallery platform 101, and the cable line in the cable module is arranged on the cable support device. Here, multiple cable modules can be arranged at the same time, and multiple cable modules are evenly distributed on the platform rear wall in parallel along the height direction of the pipe gallery platform 101 to simulate the cable pipe gallery scene more realistically.

[0028] On the rear wall of the tunnel facing the opening side of the tunnel platform 101, an oil pan chute is also provided along the length direction of the tunnel platform 101, that is, an oil pan chute is provided in the horizontal direction on the inner wall opposite to the lateral opening of the tunnel, and an oil pan support plate is installed in the oil pan chute. Among them, a slider with a dovetail cross-section that slides with the oil pan chute is provided on the oil pan support plate. In other words, the oil pan chute is a chute that extends in the horizontal direction of the tunnel platform 101 and has a dovetail cross-section, and the cross-section of the slider on the oil pan support plate that matches the oil pan chute is also dovetail, thereby realizing the movement of the oil pan support plate along the horizontal direction (length direction) of the tunnel platform 101, so as to adjust the position of the adjustable experimental oil pan 103 placed on the oil pan support plate along the length direction of the tunnel platform 101.

[0029] At the same time, an oil pan platform is slidably installed on the oil pan support plate, and the oil pan platform can adjust its position along the height direction of the pipe gallery platform 101, thereby realizing the height adjustment of the adjustable experimental oil pan 103 placed on the oil pan platform. Specifically, a vertical slide groove extending along the height direction of the pipe gallery platform 101 is provided on the oil pan support plate, and the oil pan platform is slidably mounted in the vertical slide groove, thereby realizing the movement of the oil pan platform along the height direction on the oil pan support plate. It should be noted that the vertical slide groove adopts a T-shaped section or a dovetail section; a threaded hole perpendicular to the bottom surface of the vertical slide groove is also provided on the oil pan platform, and a locking stud or locking screw is installed in the threaded hole. When the oil pan platform is adjusted to the set height, the locking stud or locking screw is tightened so that the end face of the locking stud or locking screw is pressed against the bottom surface of the vertical slide groove, thereby locking the oil pan platform on the oil pan support plate.

[0030] A size adjustment unit 102 is slidably installed on the opening side of the pipe gallery platform 101, and the size of the space of the pipe gallery cavity is adjusted by moving the size adjustment unit 102 along the width direction of the pipe gallery platform 101. Specifically, fixed slide rails 111 extending toward the opening direction are provided on the inner side walls at both ends of the pipe gallery platform 101, and fixed sliders 112 slidably installed with the fixed slide rails 111 are provided at both ends of the size adjustment unit 102. The size adjustment unit 102 can move along the opening direction of the pipe gallery platform 101 through the cooperation of the fixed slider 112 and the fixed slide rail 111.

[0031] In a specific example, steel card slots are provided at both ends of the removable fireproof glass of the size adjustment unit 102, and fixed sliders 112 matched with the fixed slide rails 111 are provided on the steel card slots. The fixed sliders 112 are slidably inserted into the fixed sliders 112, so that the removable fireproof glass can be moved along the width direction of the pipe gallery platform 101. Here, it should be noted that the removable fireproof glass is matched with the lateral opening of the pipe gallery platform 101 to achieve the closure of the lateral opening of the rectangular shell structure of the pipe gallery platform 101 to form a pipe gallery cavity. Thus, by moving the removable fireproof glass along the width direction of the pipe gallery platform 101, the size of the pipe gallery cavity is adjusted to achieve the simulation of cable pipe galleries of different sizes.

[0032] A ventilation adjustment module is also arranged in the shell structure of the pipe gallery cable fire simulation device 1, and the air volume and wind speed in the pipe gallery cavity are simulated by the ventilation adjustment module to further simulate different types of cable gallery scenes. Among them, the air inlet and air outlet of the ventilation adjustment module are respectively installed on the platform ceiling near the platform side wall.

[0033] In the present application, a plurality of simulation areas are divided horizontally in the shell structure of the pipe gallery cable fire simulation device 1, and an adjustable experimental oil pan 103, an image acquisition unit and a suspended fire extinguisher 301 are arranged in each simulation area, and two adjacent simulation areas are isolated or connected by a fireproof roller curtain 302. It should be noted that the oil pan slideway for installing the adjustable experimental oil pan 103 is discontinuous at the fireproof roller curtain 302 installed in two adjacent simulation areas, thereby realizing independent adjustment of the adjustable experimental oil pan 103 in each simulation area, simulating different ignition positions of the cable by changing the position of the adjustable experimental oil pan 103 in the simulation area, and independently performing fire simulation at different positions in each simulation area, effectively simulating the uncertain ignition position of the cable in the pipe gallery cable.

[0034] When a fire simulation is performed in the simulation area of ​​the pipe gallery cable fire simulation device 1, the real-time state of the fire simulation is monitored in real time by the image acquisition unit installed on the platform ceiling, and the collected simulated fire image information is transmitted in real time to the deployed fire identification model for fire identification; the fire identification result of the fire identification model is judged by the deployed fire warning model, and a fire extinguishing instruction or a warning instruction is issued according to the judgment result. Thus, the fire identification model identifies whether a fire has occurred by using the real-time simulated fire image information collected by the image acquisition unit, and the fire warning model judges the identification result; if the error between the identification result of the fire identification model and the judgment result of the fire warning model is greater than the preset monitoring threshold, the identification device issues a warning instruction to notify the staff to conduct on-site inspection and processing; if the error between the identification result of the fire identification model and the judgment result of the fire warning model is less than or equal to the preset monitoring threshold, the identification device issues a fire extinguishing instruction and opens the fire extinguishing linkage device to extinguish the fire. Furthermore, through dual identification and early warning of fire, the untimely fire extinguishing caused by abnormal situations caused by single model prediction errors can be effectively avoided, and the losses can be reduced. Through dual identification and early warning, the fire situation in the cable corridor can be identified and monitored in a timely and accurate manner.

[0035] In a specific example, by establishing a fire recognition model for pipe gallery cables, deep features of real-time monitoring images are automatically extracted, including but not limited to extracting flame shape features, flame color features, smoke color features, flame motion features, smoke motion features, etc. The fire recognition model deployed in the recognition device is trained based on the pre-acquired fire sample images, and the convolutional layer and the fully connected layer of the fire recognition model are updated based on the Adam method until the fire recognition error of the fire recognition model is less than or equal to the preset error threshold.

[0036] In this embodiment, the collected fire sample images are manually annotated with the flames and smoke therein, and then input into the fire recognition model to train the fire recognition model. The hidden layer of the fire recognition model includes several convolutional layers, pooling layers and fully connected layers, wherein the convolutional layer of the fire recognition model is according to the formula: Extract the fire features of the fire sample image; where, For the The convolutional layer extracts Fire characteristics, is the activation function of the convolutional layer of the fire recognition model, For the fire sample images; The fire identification model In the convolutional layer Fire characteristics and The weights between the fire characteristics, The fire identification model In the convolutional layer The offset of each fire feature; All are positive integers.

[0037] The fire feature image obtained by the convolution layer of the fire recognition model is too long. The fire recognition model uses the pooling layer to reduce the dimension of the fire features of the extracted fire sample image. The image features after dimensionality reduction effectively improve the operation speed and effectively extract important features such as flame, smoke shape, color, and movement in the fire. Specifically, when the convolution layer of the fire recognition model extracts the feature matrix of the fire feature, the fire uses the maximum pooling method to reduce the dimension of the fire feature and extract the maximum data feature in each sub-matrix. Among them, the flame shape features mainly include the edge features of the flame shape and the flame height; the flame color features mainly include the red, white, and yellow pixel distribution in the flame; the smoke color features include the black and gray pixel distribution in the smoke; the flame motion features include the speed, range, and direction of flame spread; the smoke motion features include the speed, range, and direction of smoke spread.

[0038] Then, the feature image obtained by the pooling layer is converted into a one-dimensional vector through the fully connected layer of the fire identification model, and the classifier is used to classify the fire features. For example, the continuous flame and intermittent flame in the edge features of the flame shape are classified. Specifically, the fully connected layer of the fire identification model is based on the formula: Classify the fire characteristics after dimensionality reduction; where, The fire identification model nodes of the fully connected layer; The fire identification model nodes in the fully connected layer, The fire identification model The fully connected layers to The weights of the fully connected layers, For the The bias term of the fully connected layer, is the activation function of the fully connected layer of the fire recognition model.

[0039] The fully connected layer of the fire identification model realizes the classification of fire features, dividing the fire features into two categories: fire and no fire. Then, the image classification labels of the fully connected layer are output through the output layer of the fire identification model. Specifically, the output layer of the fire identification model uses the Softmax function according to the formula: Calculate the probability of fire ; In the formula, is the output of the fully connected layer of the fire recognition model fire feature classification labels; among them, hour, , indicating a fire has occurred, hour, , indicating that no fire occurred.

[0040] In the training process of the fire identification model, the output value of the fire identification model is compared with the true value, and the error between the output value of the fire identification model and the true value (the fire identification error of the fire identification model) is reflected by the loss function value. According to the formula: In the formula, For the The true value corresponding to the fire sample image, that is, whether a fire occurs, or ; For the The output value of the fire identification model corresponding to the fire sample image, that is, the probability of fire occurrence ,and 1; Flame sample image input for fire recognition model, The fire identification model In the convolutional layer Fire characteristics and The current weights between the fire characteristics, The fire identification model The fully connected layers to In this application, the weights between the convolutional layer and the fire features of the fully connected layer of the fire identification model are updated by the Adam method to make the prediction error of the fire identification model smaller. Specifically, according to the formula: The convolutional layer and the fully connected layer of the fire identification model are updated. Where, The fire identification model In the convolutional layer Fire characteristics and The updated weights between the fire features are The fire identification model In the convolutional layer Fire characteristics and The current weights between the fire characteristics, is the self-learning rate of the weights corresponding to the convolutional layer of the fire identification model; The fire identification model The fully connected layers to The updated weights of the fully connected layers are The fire identification model The fully connected layers to The current weight of the fully connected layer, is the self-learning rate of the weights corresponding to the fully connected layer of the fire identification model; are vectors of the first-order moment estimate and the second-order moment estimate of the gradient initialized to 0; is the smoothing term.

[0041] In the present application, the image acquisition unit collects images in the pipeline corridor cable fire simulation device 1 and analyzes the probability of fire occurrence through the fire identification model. A single judgment on whether a fire occurs through the fire identification model may also lead to false alarms or missed alarms of fire. In this regard, in the present application, a fire warning model is simultaneously deployed to judge the identification results of the fire identification model to further improve the prediction accuracy of pipeline corridor cable fires.

[0042] Specifically, the fire warning model is based on the formula: Determine the first Fire characteristics Normalized predicted fire probability obtained by inputting the fire warning model The fire occurrence probability output by the fire identification model Error , in order to judge the fire identification results of the fire identification model.

[0043] In the formula, is the activation function of the output layer of the fire identification model, is the weight matrix corresponding to the output layer of the fire warning model, The fire identification model extracts the first The hidden layer value obtained by inputting the fire characteristics into the hidden layer of the fire warning model; is the bias term of the hidden layer; is the bias term of the output layer; is the activation function of the hidden layer of the fire recognition model, The fire identification model extracts the first Fire characteristics The weight matrix of The fire identification model extracts the first The hidden layer value obtained by inputting the fire characteristics into the hidden layer of the fire warning model; is the hidden layer value The corresponding weight matrix.

[0044] In the fire warning model, when the fire recognition model extracts the first Fire characteristics Normalized predicted fire probability obtained by inputting the fire warning model The fire occurrence probability output by the fire identification model Error Greater than the preset monitoring threshold When the fire identification model extracts the first Fire characteristics Normalized predicted fire probability obtained by inputting the fire warning model The fire occurrence probability output by the fire identification model Error Less than or equal to the preset monitoring threshold When the fire extinguishing instruction is issued by the identification device, the fire extinguishing linkage device installed in the pipe gallery cable fire simulation device 1 performs a fire extinguishing operation on the fire simulation in the pipe gallery cable fire simulation device 1. Specifically, the fire extinguishing linkage device is activated after receiving the fire extinguishing instruction issued by the identification device, and the fire extinguishing operation is performed on the fire simulation in the pipe gallery cable fire simulation device 1 through the suspended fire extinguisher 301 installed in the pipe gallery cable fire simulation device 1.

[0045] Two adjacent simulation areas in the tunnel cavity are isolated or connected by fireproof roller shutters 302. On the one hand, simulation of tunnels of different sizes can be realized, and on the other hand, fire isolation of different areas can be realized to reduce losses. After receiving the fire extinguishing command issued by the identification device, the two fireproof roller shutters 302 corresponding to the simulation area for fire simulation move to block the simulation area for fire simulation, thereby realizing the closed fire extinguishing operation of the simulation area for fire simulation.

[0046] In a specific application scenario, one end of the fireproof rolling curtain 302 is installed on the inner wall of the pipe gallery cable fire simulation device 1, and the closing motor is installed on the platform ceiling, and is driven by gear transmission to move along the width direction (i.e., the front-to-back direction) of the pipe gallery platform 101 to block the simulation area for fire simulation. A plurality of through grooves 312 are arranged in parallel along the height direction on the fireproof rolling curtain 302, each of which extends along the width direction of the pipe gallery platform 101 and corresponds to the cables arranged in the horizontal direction in the pipe gallery cable fire simulation device 1, and each of which is provided with a flexible steel brush 322.

[0047] The fireproof rolling curtain 302 is a steel structure, and a flexible steel brush 322 is installed at the position of the through groove 312, so that when the fireproof rolling curtain 302 moves under the drive of the closed motor, the cable is located in the through groove 312 and is not affected by the movement of the fireproof rolling curtain 302. Here, the flexible steel brush 322 is connected (for example, welded) to the fireproof rolling curtain 302 through a steel brush connecting plate. When the flexible steel brush 322 contacts the cable during the movement of the fireproof rolling curtain 302, the resistance of the cable causes the flexible steel brush 322 to automatically lift up, thereby not only enabling the fireproof rolling curtain 302 to isolate and prevent the spread of fire, but also not destroying the integrity of the cable.

[0048] The closing motor drives the fireproof roller shutter 302 to move along the width direction of the tunnel platform 101 through gear transmission. When a fire is detected, the closing motor starts, driving the fireproof roller shutter 302 to move along the roller door slide rails set on the platform ceiling and the platform floor and automatically close, isolating the fire area separately, thereby isolating and preventing the fire from spreading in time.

[0049] In a specific application scenario, when a fire is identified, the temperature-sensitive glass ball of the dry powder fire extinguisher is broken by the electric push rod installed on the platform ceiling of the pipe gallery platform 101, so that the dry powder fire extinguishing agent in the dry powder fire extinguisher extinguishes the fire (simulation) in the corresponding simulation area of ​​the pipe gallery cable fire simulation device 1. Among them, the dry powder fire extinguisher and the electric push rod are both installed on the platform ceiling, and the telescopic end of the electric push rod is facing the temperature-sensitive glass ball of the dry powder fire extinguisher, so that when a fire is identified, the telescopic end of the electric push rod is quickly extended to hit the temperature-sensitive glass ball, so that the temperature-sensitive glass ball is broken, and the dry powder fire extinguisher is sprayed to extinguish the fire (simulation) in the corresponding simulation area.

[0050] Thus, multiple fire features in the pipe gallery are collected by video (image acquisition unit), and the fire occurrence situation is effectively and comprehensively detected through the established cable fire identification and warning model (fire identification model, fire warning model), thereby improving the accuracy of fire identification, reducing the false alarm rate of pipe gallery cable fire, and improving the sensitivity and accuracy of judgment; and after identifying the occurrence of a fire, the fire extinguishing linkage device located in the pipe gallery cable fire simulation device 1 can be opened in time to realize the rapid start of the integrated pipe gallery fire extinguisher, and the fire in the fire occurrence area can be dealt with in a timely and effective manner, thereby improving the timeliness and automation of fire extinguishing and reducing the passivity of manual fire extinguishing.

[0051] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0052] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection, an electrical connection, or communication with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0055] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0056] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent identification and prevention and control linkage system for cable fire in an integrated pipe gallery, characterized in that: include: The pipe gallery cable fire simulation device is a shell structure, used for simulating the fire of the integrated pipe gallery cable; The identification device monitors the fire simulation in the cable fire simulation device in real time through the image acquisition unit, and transmits the collected simulated fire image information to the deployed fire identification model in real time for fire identification, so as to judge the fire identification result of the fire identification model through the deployed fire warning model, and issue a fire extinguishing instruction or a warning instruction according to the judgment result; A fire extinguishing linkage device is installed in the pipe gallery cable fire simulation device, and is used to respond after receiving a fire extinguishing command from the identification device, so that the fireproof roller shutter with a flexible steel brush is activated, and after the fire point area in the pipe gallery cable fire simulation device is blocked, the telescopic end of the electric push rod installed on the top of the pipe gallery cable fire simulation device is extended to smash the temperature-sensitive glass ball of the suspended fire extinguisher installed on the top of the pipe gallery cable fire simulation device, thereby realizing the fire extinguishing operation of the fire simulation carried out in the pipe gallery cable fire simulation device.

2. The integrated pipe gallery cable fire intelligent identification and prevention and control linkage system according to claim 1 is characterized in that: The pipe gallery cable fire simulation device comprises: The pipe gallery platform is a rectangular shell structure with an opening on one side, and fixed slide rails extending toward the opening are arranged on the inner side walls at both ends; A size adjustment unit is used to block the opening of the pipe gallery platform to form a pipe gallery cavity with the pipe gallery platform; and fixed sliders slidably mounted with the fixed slide rails are provided at both ends, so that the size adjustment unit can move along the opening direction of the pipe gallery platform to adjust the spatial size of the pipe gallery cavity; The adjustable experimental oil pan is slidably mounted on the inner wall of the pipe gallery platform opposite to the opening, and can be adjusted in position along the height direction and the horizontal direction of the pipe gallery platform.

3. The integrated pipe gallery cable fire intelligent identification and prevention and control linkage system according to claim 1 is characterized in that: The shell structure of the pipe gallery cable fire simulation device is divided into a plurality of simulation areas in the horizontal direction; The image acquisition unit and the suspended fire extinguisher are respectively installed in each simulation area.

4. The integrated pipe gallery cable fire intelligent identification and prevention and control linkage system according to claim 3 is characterized in that: There are multiple fireproof roller shutters, which are respectively arranged between two adjacent simulation areas; and after receiving the fire extinguishing command issued by the identification device, the two fireproof roller shutters corresponding to the simulation area for fire simulation move to block the simulation area for fire simulation.

5. The integrated pipe gallery cable fire intelligent identification and prevention and control linkage system according to claim 4 is characterized in that: A plurality of through grooves are arranged in parallel along the height direction on the fireproof roller shutter, each of the through grooves corresponds to the cables arranged in the horizontal direction in the pipe gallery cable fire simulation device, and each of the through grooves is provided with the flexible steel brush; wherein the through grooves extend along the width direction of the pipe gallery platform.

6. The integrated pipe gallery cable fire intelligent identification and prevention linkage system according to claim 1 is characterized in that: The fire identification model deployed in the identification device is trained based on the pre-acquired fire sample image, and the convolution layer and the fully connected layer of the fire identification model are updated based on the Adam method until the fire identification error of the fire identification model is less than or equal to a preset error threshold.

7. The integrated pipe gallery cable fire intelligent identification and prevention and control linkage system according to claim 6 is characterized in that: The fire identification model deployed in the identification device is constructed through a convolutional layer according to the formula: Extract the fire features of the fire sample image; where, For the The convolutional layer extracts Fire characteristics, is the activation function of the convolutional layer of the fire recognition model, For the a fire sample image; The fire identification model In the convolutional layer Fire characteristics and The weights between the fire characteristics, The fire identification model In the convolutional layer The offset of each fire feature; All are positive integers; The fire identification model performs dimensionality reduction processing on the fire features of the extracted fire sample images through a pooling layer; The fire identification model is implemented through a fully connected layer according to the formula: Classify the fire characteristics after dimensionality reduction; where, The fire identification model nodes of the fully connected layer; The fire identification model nodes in the fully connected layer, The fire identification model The fully connected layers to The weights of the fully connected layers, For the The bias term of the fully connected layer, is the activation function of the fully connected layer of the fire identification model; The output layer of the fire identification model is processed by the Softmax function according to the formula: Calculate the probability of fire ; In the formula, is the output of the fully connected layer of the fire identification model fire feature classification labels; among them, hour, , indicating a fire has occurred, hour, , indicating that no fire occurred.

8. The integrated pipe gallery cable fire intelligent identification and prevention and control linkage system according to claim 7 is characterized in that: According to the formula: Updating the convolutional layer and the fully connected layer of the fire identification model; In the formula, The fire identification model In the convolutional layer Fire characteristics and The updated weights between the fire features are The fire identification model In the convolutional layer Fire characteristics and The current weights between the fire characteristics, is the self-learning rate of the weights corresponding to the convolutional layer of the fire identification model; is the fire identification model The fully connected layers to The updated weights of the fully connected layers are The fire identification model The fully connected layers to The current weight of the fully connected layer, is the self-learning rate of the weights corresponding to the fully connected layer of the fire identification model; are vectors of the first-order moment estimate and the second-order moment estimate of the gradient initialized to 0; is the smoothing term.

9. The integrated pipe gallery cable fire intelligent identification and prevention linkage system according to claim 6 is characterized in that: According to the formula: Determine the first Fire characteristics Input the normalized predicted fire probability obtained in the fire warning model The fire occurrence probability output by the fire identification model Error , to judge the fire identification result of the fire identification model; In the formula, is the activation function of the output layer of the fire identification model, is the weight matrix corresponding to the output layer of the fire warning model, The fire identification model extracts the first A hidden layer value obtained by inputting a fire feature into the hidden layer of the fire warning model; is the bias term of the hidden layer; is the bias term of the output layer; is the activation function of the hidden layer of the fire recognition model, The fire identification model extracts the first Fire characteristics The weight matrix of The fire identification model extracts the first A hidden layer value obtained by inputting a fire feature into the hidden layer of the fire warning model; is the hidden layer value The corresponding weight matrix.

10. The integrated pipe gallery cable fire intelligent identification and prevention linkage system according to claim 9 is characterized in that: Responding to Error Greater than the preset monitoring threshold , the identification device issues the warning instruction; Responding to Error Less than or equal to the preset monitoring threshold , the identification device issues the fire extinguishing instruction.

Images