Cable fireproof monitoring system, method and device

Abstract

The invention relates to the technical field of cable safety monitoring, and particularly discloses a cable fireproof monitoring system, method and device, which realize all-around and high-precision monitoring and efficient response to cable fire hazards through a series of innovative functions such as multi-element perception, intelligent analysis and linkage execution. Meanwhile, a monitoring method based on the system and a cable fireproof monitoring device with a scientific and reasonable structure are provided in a matched mode, so that safe and stable operation of the cable is guaranteed, the risk of fire disasters is reduced, and losses caused by the fire disasters are reduced. According to the invention, the intelligent analysis and decision module of the deep neural network model is adopted, the multi-source data can be efficiently analyzed, the fire hazard probability and grade can be accurately evaluated, and a powerful basis is provided for timely taking scientific and reasonable countermeasures. According to the cable fireproof monitoring device, the fireproof isolation platform is formed by splicing the fireproof units through the mortise and tenon structure, installation and maintenance are convenient, and fire disasters can be effectively isolated.

Description

Technical Field

[0001] The present invention relates to the technical field of cable safety monitoring, and in particular to a cable fire prevention monitoring system, method and device. Background Art

[0002] In modern power infrastructure, as a core component for power transmission and distribution, cables are widely distributed in various buildings, industrial sites and urban power grids. However, the problem of cable fires has always been a major challenge threatening the safe and stable operation of the power system, bringing serious risks to social economy and people's lives and property.

[0003] The occurrence of cable fires often stems from multiple factors. Firstly, cables are in a long-term high-load operation state. Their insulating layers and sheaths are mostly made of polymer organic materials such as polyvinyl chloride and cross-linked polyethylene. Under the combined action of current thermal effect, environmental temperature and mechanical stress, the insulation performance gradually deteriorates, making it extremely easy to cause short circuits and overheating phenomena, becoming potential fire sources. Secondly, the cable laying environment is complex. In some places, there are problems such as dense cable layout and poor ventilation and heat dissipation. Once a cable fails and catches fire, heat and flames will quickly accumulate and spread in a limited space, accelerating the combustion of surrounding cables. Thirdly, external factors such as electric sparks generated by electrical equipment failures, misoperations during construction, and poor management of fire hazard areas may also become the inducements for cable fires.

[0004] Existing cable fire prevention monitoring technologies have obvious deficiencies in dealing with these complex problems. Traditional temperature monitoring methods, such as using ordinary thermocouples or thermistors, have limited monitoring accuracy and slow response speed. It is difficult to capture the rapid changes in cable temperature and cannot effectively warn of early fire hazards. Some systems based on smoke detection have large interference from environmental factors on detection sensitivity and are prone to false alarms or missed alarms in complex environments such as dusty and humid environments. And simply relying on manual inspection not only has low efficiency but also is affected by subjective factors, making it difficult to achieve real-time and comprehensive monitoring of large-area cable networks. In addition, existing monitoring systems often lack the ability to comprehensively analyze multiple fire-related parameters, and cannot accurately evaluate the severity of fire hazards and take timely and effective countermeasures.

[0005] With the rapid development of materials science and information technology, quantum dot materials have shown unique advantages in the sensing field. Their high-sensitivity fluorescence characteristics for temperature provide a new way for precise temperature monitoring. At the same time, the powerful capabilities of artificial intelligence technologies such as deep neural networks in data processing and pattern recognition lay the foundation for building a more accurate fire hazard analysis model.

[0006] Therefore, it has become an urgent problem for people to develop a cable fire prevention monitoring system, method and device with functions of comprehensive monitoring of multiple parameters, intelligent analysis and decision-making, and convenient maintenance. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to provide a cable fire prevention monitoring system, which realizes comprehensive, high-precision monitoring and efficient response to cable fire hazards through a series of innovative functions such as multi-sensor perception, intelligent analysis, and linkage execution. At the same time, a monitoring method based on this system and a cable fire prevention monitoring device with a scientific and reasonable structure are provided to ensure the safe and stable operation of the cable, reduce the risk of fire, and minimize the losses caused by fire.

[0008] To solve the above technical problems, the technical solution provided by the present invention is: A cable fire prevention monitoring system, comprising:

[0009] A multi-sensor perception module, including a temperature sensing component, a smoke detection component, and a gas component analysis component; the temperature sensing component collects the real-time temperature of the cable surface; the smoke detection component senses the change of smoke concentration in the cable tray; the gas component analysis component samples the air in the cable tray in real time and analyzes whether there are fire-related characteristic gases;

[0010] A data aggregation and preliminary processing unit, which aggregates the data collected by the temperature sensing component, the smoke detection component, and the gas component analysis component, and performs preliminary denoising and normalization processing;

[0011] An intelligent analysis and decision-making module, which receives the data processed by the data aggregation and preliminary processing unit, and comprehensively evaluates the cable status through a fire hazard analysis model to judge whether there are fire hazards and the hazard level;

[0012] A linkage execution module, when the intelligent analysis and decision-making module determines that there are fire hazards, triggers corresponding actions according to the hazard level, including starting the alarm device and activating the fire extinguishing device;

[0013] A remote interaction terminal, which communicates with the intelligent analysis and decision-making module through a wireless communication link, and is used to remotely view the real-time status of the cables in the cable tray, receive alarm information, and remotely configure system parameters.

[0014] Further, the temperature sensing component adopts a quantum dot temperature sensor, and uses the fluorescence characteristics of quantum dot materials sensitive to temperature to obtain the cable temperature by detecting the change of fluorescence wavelength and intensity.

[0015] Further, the smoke detection component emits ultrasonic waves and receives the echo signals scattered by the smoke particles, and accurately calculates the smoke concentration according to the change of the echo signal intensity and frequency.

[0016] Further, the fire hazard analysis model in the intelligent analysis and decision-making module is a deep neural network model, which is trained through cable fire historical data and normal operation data. The model input is multi-source data of temperature, smoke concentration, and characteristic gas concentration, and the output is the fire hazard probability and hazard level.

[0017] Further, the construction of the deep neural network model is as follows:

[0018] The input layer receives multi-source data of temperature T, smoke concentration S, and characteristic gas concentration G to form an input vector x = [T, S, G] T ;

[0019] The output h of the neurons in the hidden layer j is calculated through weighted input and activation function. The weighted sum input to the j-th neuron is net j = ∑ i w ij h i + b j , where w ij is the connection weight between the i-th input and the j-th neuron, and b j is the bias. Using the ReLU activation function f(x) = max(0, x), the output h of the hidden layer neurons j = f(net j );

[0020] The output layer obtains the final result through a linear combination of the hidden layer output. The weight matrix of the output layer is W, the bias vector is b, and the output vector Y = WH + b, where H is the hidden layer output vector, and the elements of the output vector Y correspond to the fire hazard probability and hazard level; The model training uses the backpropagation algorithm. By minimizing the loss function L(θ), the weights and biases are updated using the gradient descent method, and the gradient is calculated through the chain rule. The weight update formula is α is the learning rate.

[0021] The present invention also provides a cable fire prevention monitoring method based on the above system, including the following steps:

[0022] S1. Initialize the system, set the parameters of each sensor, the threshold of the fire hazard analysis model, and the linkage execution strategy;

[0023] S2. The multi-sensor perception module continuously collects data on temperature, smoke concentration, and gas composition in the cable tray and transmits it to the data aggregation and preliminary processing unit;

[0024] S3. After the data aggregation and preliminary processing unit aggregates, denoises, and normalizes the collected data, it sends it to the intelligent analysis and decision-making module;

[0025] S4. The intelligent analysis and decision-making module uses the fire hazard analysis model to analyze the processed data and outputs the fire hazard probability and level.

[0026] S5. If there is a fire hazard, the linkage execution module activates corresponding alarm and fire extinguishing measures according to the hazard level. At the same time, the remote interaction terminal receives the alarm information and can perform remote intervention operations.

[0027] Furthermore, during use, the system performs self-calibration and maintenance. By inputting standard detection signals to each sensor, comparing the actual output with the standard value, it automatically adjusts the sensor parameters. At the same time, it checks the status of the system hardware devices to promptly detect and handle potential faults.

[0028] The present invention also provides a cable fire prevention monitoring device, including a fire prevention isolation platform and a cable tray.

[0029] The cable tray is fixed on the top of the fire prevention isolation platform. A central controller and temperature sensors, smoke sensors, alarms, and fire extinguishers electrically connected thereto are fixed inside the cable tray.

[0030] The fire prevention isolation platform is formed by splicing a plurality of fire prevention units made of fire prevention materials through a mortise and tenon structure.

[0031] The advantages of the present invention compared with the prior art are as follows:

[0032] The present invention comprehensively collects data on multiple aspects such as temperature, smoke concentration, and gas composition through the multi-source perception module. Compared with the traditional single-parameter monitoring method, it can more comprehensively and accurately reflect the operating state of the cable, significantly improving the accuracy of fire hazard judgment.

[0033] The present invention adopts an intelligent analysis and decision-making module based on a deep neural network model, which is trained based on a large amount of historical data. It can efficiently analyze multi-source data, accurately evaluate the fire hazard probability and level, and provide a strong basis for timely taking scientific and reasonable countermeasures.

[0034] The linkage execution module of the present invention quickly triggers corresponding actions according to the determination result of the intelligent analysis and decision-making module, realizing the automation of operations such as alarm and fire extinguishing, and effectively reducing the losses caused by fires.

[0035] The present invention enables operators to remotely and real-time understand the cable status, receive alarm information, and configure parameters through the remote interaction terminal, greatly improving the management efficiency and convenience of the monitoring system.

[0036] In the monitoring method of the present invention, the system has a self-calibration and maintenance function, which can automatically adjust the sensor parameters, check the status of the hardware devices, and ensure the long-term stable and reliable operation of the system.

[0037] In the cable fire monitoring device of the present invention, the fireproof isolation platform is spliced by a mortise and tenon structure of fireproof units, which is convenient for installation and maintenance and can effectively isolate fires; a variety of monitoring and response devices are integrated in the cable tray to form an integrated fireproof monitoring system. Brief Description of the Drawings

[0038] Figure 1 It is a system block diagram of a cable fire monitoring system of the present invention.

[0039] Figure 2 It is a flowchart of a cable fire monitoring method of the present invention.

[0040] Figure 3 It is a schematic structural diagram of a cable fire monitoring device of the present invention.

[0041] Figure 4 It is an exploded view of the structure of a cable fire monitoring device of the present invention.

[0042] As shown in the figure: 1. Fireproof isolation platform, 2. Cable tray, 3. Temperature sensor, 4. Smoke sensor, 5. Fire extinguisher, 6. Alarm, 7. Mortise and tenon structure. Detailed Embodiments

[0043] Next, various exemplary embodiments of the present invention will be described in detail with reference to the drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps described in these embodiments do not limit the scope of the present invention.

[0044] The following description of at least one exemplary embodiment is actually only illustrative and in no way restricts the present invention and its application or use.

[0045] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods, and devices should be regarded as part of the specification.

[0046] In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0047] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", "left", "right", "inner", "outer", "vertical", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0048] In the present invention, unless otherwise clearly defined and limited, terms such as "installation", "connection", "attachment", "fixation" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] The following further elaborates on a cable fire prevention monitoring system, method and device of the present invention with reference to the accompanying drawings.

[0050] Combined with the attached Figures 1-4 , the present invention is introduced in detail.

[0051] A cable fire prevention monitoring system includes:

[0052] Multi-sensor module: Composed of a temperature sensing component, a smoke detection component and a gas composition analysis component. The temperature sensing component is responsible for collecting the real-time temperature of the cable surface, the smoke detection component is used to sense the change of the smoke concentration in the cable tray, and the gas composition analysis component samples the air in the cable tray in real time and analyzes whether there are characteristic gases related to fire. Specifically, the temperature sensing component adopts a quantum dot temperature sensor, and uses the fluorescence characteristics of quantum dot materials sensitive to temperature to obtain the cable temperature by detecting the change of fluorescence wavelength and intensity. The smoke detection component emits ultrasonic waves and receives the echo signals scattered by the smoke particles, and accurately calculates the smoke concentration according to the change of the echo signal intensity and frequency.

[0053] Data aggregation and preliminary processing unit: This unit aggregates the data collected by the temperature sensing component, the smoke detection component and the gas composition analysis component, and conducts preliminary denoising and normalization processing so that the subsequent intelligent analysis and decision-making module can analyze more efficiently.

[0054] Intelligent analysis and decision-making module: Receives the data processed by the data aggregation and preliminary processing unit, and comprehensively evaluates the operating state of the cable with the help of a fire hazard analysis model to judge whether there is a fire hazard and the level of the hazard. Among them, the fire hazard analysis model is a deep neural network model, which is trained by cable fire historical data and normal operation data. The input of the model is multi-source data such as temperature, smoke concentration, and characteristic gas concentration, and the output is the fire hazard probability and the hazard level. The construction method of the deep neural network model is as follows:

[0055] Input layer: Receives multi-source data of temperature T, smoke concentration S, and characteristic gas concentration G, and forms an input vector X = [T, S, G] T ;

[0056] Hidden layer: The output h of the neuron j is calculated through weighted inputs and activation functions. The weighted sum input to the j-th neuron is net j = ∑ i w ij h i + b j , where w ij is the connection weight between the i-th input and the j-th neuron, and b j is the bias. Using the ReLU activation function f(x) = max(0, x), the output h of the hidden layer neuron is j = f(net j );

[0057] Output layer: The final result is obtained through a linear combination of the hidden layer outputs. The output layer weight matrix is W, the bias vector is b, and the output vector Y = WH + b, where H is the hidden layer output vector, and the elements of the output vector Y correspond to the fire hazard probability and hazard level; The model training uses the backpropagation algorithm. By minimizing the loss function L(θ), the weights and biases are updated using the gradient descent method. The gradient is calculated through the chain rule, and the weight update formula is α is the learning rate.

[0058] Linkage execution module: When the intelligent analysis and decision-making module determines that there is a fire hazard, corresponding actions are triggered according to the hazard level, including activating the alarm device, turning on the fire extinguishing device, etc.

[0059] Remote interaction terminal: Communicates with the intelligent analysis and decision-making module through a wireless communication link, and is used to remotely view the real-time status of the cables in the cable tray, receive alarm information, and remotely configure the system parameters.

[0060] A monitoring method based on a cable fire prevention monitoring system includes the following steps:

[0061] S1: Initialize the system, set the parameters of each sensor, the threshold of the fire hazard analysis model, and the linkage execution strategy.

[0062] S2: The multi-sensor module continuously collects the temperature, smoke concentration, and gas composition data in the cable tray and transmits it to the data aggregation and preliminary processing unit.

[0063] S3: After aggregating, denoising, and normalizing the collected data, the data aggregation and preliminary processing unit sends it to the intelligent analysis and decision-making module.

[0064] S4: The intelligent analysis and decision-making module uses the fire hazard analysis model to analyze the processed data and outputs the fire hazard probability and level.

[0065] S5: If there are fire hazards, the linkage execution module activates corresponding alarm and fire extinguishing measures according to the hazard level. Meanwhile, the remote interaction terminal receives the alarm information and can perform remote intervention operations. During use, the system performs self-calibration and maintenance. By inputting standard detection signals to each sensor, comparing the actual output with the standard value, it automatically adjusts the sensor parameters. At the same time, it checks the status of the system hardware devices to promptly detect and handle potential faults.

[0066] A cable fire prevention monitoring device: It includes a fire prevention isolation platform 1 and a cable tray 2. The cable tray 2 is fixed on the top of the fire prevention isolation platform 1. Inside the cable tray 2, a central controller and temperature sensors 3, smoke sensors 4, alarms 6, and fire extinguishers 5 electrically connected to it are fixed. The fire prevention isolation platform 1 is composed of several fire prevention units made of fireproof materials spliced through a mortise and tenon structure 7. This fire prevention isolation platform 1 can be replaced with a cable trench fire wall.

[0067] The specific implementation process of a cable fire prevention monitoring system, method, and device of the present invention is as follows:

[0068] Embodiment 1: Cable fire prevention monitoring system

[0069] Installation of the multi-sensor perception module and data acquisition: The quantum dot temperature sensors 3 are installed on the cable surface at a certain interval to ensure accurate acquisition of the real-time temperature of different parts of the cable. The smoke detection component is installed at a suitable position inside the cable tray 2 so that the ultrasonic waves it emits can effectively cover the tray space to accurately receive the echo signals scattered by smoke particles and calculate the smoke concentration. The gas component analysis component is connected to the air sampling pipeline inside the tray to sample and analyze the air regularly to obtain data on characteristic gases related to fire.

[0070] Operation of the data aggregation and preliminary processing unit: The data aggregation and preliminary processing unit is connected to each component of the multi-sensor perception module through a data transmission line and receives temperature, smoke concentration, and gas component data in real time. A filtering algorithm is used to denoise the collected data, removing the interference noise in the data and improving the data quality. Then, according to the characteristic range of the data, the denoised data is normalized so that it is in a unified numerical interval, facilitating subsequent analysis by the intelligent analysis and decision-making module.

[0071] Training and application of the intelligent analysis and decision-making module: A large amount of historical data on cable fires and data on the temperature, smoke concentration, and characteristic gas concentration during normal operation of the cable are collected to train the deep neural network model. During the training process, the weights and biases of the model are continuously adjusted through the backpropagation algorithm so that the model can accurately output the fire hazard probability and hazard level according to the input multi-source data. After training, the intelligent analysis and decision-making module receives the data processed by the data aggregation and preliminary processing unit in real time and uses the trained model to comprehensively evaluate the cable status.

[0072] Linkage Execution Module Action Trigger: When the intelligent analysis and decision-making module determines that there is a fire hazard, it sends an instruction to the linkage execution module according to the hazard level. If it is a low-level hazard, the linkage execution module activates the alarm device to alert relevant personnel; if it is a high-level hazard, the fire extinguishing device is immediately activated to extinguish the fire.

[0073] Remote Interaction Terminal Operation: The operator communicates with the intelligent analysis and decision-making module through the remote interaction terminal using a wireless communication link. The operator can view the real-time status information such as the temperature, smoke concentration, and fire hazard probability of the cables in the cable tray 2 in real time. When receiving an alarm message, the operator can timely understand the fire hazard situation and remotely configure the system parameters according to actual needs, such as adjusting the threshold of the fire hazard analysis model and modifying the linkage execution strategy.

[0074] Embodiment 2: Cable Fire Prevention Monitoring Method

[0075] System Initialization: The system adopts the cable fire prevention monitoring system of Embodiment 1; before the system is put into use, the parameters of each sensor are set, including the measurement range and accuracy of the temperature sensor 3, the sensitivity of the smoke sensor 4, etc. The threshold of the fire hazard analysis model is set, and the judgment criteria corresponding to different fire hazard probabilities and levels are determined. A linkage execution strategy is formulated to clarify the startup methods and operation procedures of devices such as the alarm device and the fire extinguishing device under different hazard levels.

[0076] Data Acquisition and Transmission: The multi-sensor perception module continuously acquires the temperature, smoke concentration, and gas composition data in the cable tray 2 at a set time interval, and transmits the acquired data to the data aggregation and preliminary processing unit in real time through the data transmission line.

[0077] Data Processing and Analysis: The data aggregation and preliminary processing unit aggregates the received data, uses a denoising algorithm to remove the noise interference in the data, and unifies the data to a suitable numerical range through a normalization algorithm. The processed data is sent to the intelligent analysis and decision-making module, and the intelligent analysis and decision-making module uses the trained fire hazard analysis model to analyze the data and outputs the fire hazard probability and level.

[0078] Linkage Execution and Remote Intervention: If the intelligent analysis and decision-making module determines that there is a fire hazard, the linkage execution module initiates corresponding measures according to the hazard level. At the same time, the remote interaction terminal receives the alarm message, and the operator can perform remote intervention operations on the system through the remote interaction terminal, such as manually starting or stopping certain devices to further optimize the system operation status.

[0079] System Self-Calibration and Maintenance: Regularly input standard detection signals to each sensor. The sensor compares the actual output with the standard value, and the system automatically adjusts the sensor parameters to ensure the accuracy of sensor measurement. Check the status of the system hardware devices, including data transmission lines, controllers, and various monitoring components, etc., detect and handle potential faults in a timely manner, and ensure the normal operation of the system.

[0080] Embodiment 3: Cable Fire Prevention Monitoring Device

[0081] Installation of the Fireproof Isolation Platform 1: According to the cable laying requirements, select an appropriate number of fireproof units made of fireproof materials, and splice each fireproof unit into the fireproof isolation platform 1 through the mortise and tenon structure 7 of the dovetail joint. Ensure firm splicing, and the size and load-bearing capacity of the fireproof isolation platform 1 meet the installation requirements of the cable tray 2.

[0082] Place the cable tray 2 inside the fireproof isolation platform 1; install a central controller in the cable tray 2. The central controller is equipped with the system in Embodiment 1, and electrically connect devices such as the temperature sensor 3, the smoke sensor 4, the alarm 6, and the fire extinguisher 5 to the central controller. The temperature sensor 3 is installed close to the cable to accurately measure the cable temperature; the smoke sensor 4 is installed in the internal space of the cable tray to effectively detect the smoke concentration; the alarm 6 and the fire extinguisher 5 are installed in positions that are easy to operate and play a role.

[0083] After the device is put into use, the central controller receives the data of the temperature sensor 3 and the smoke sensor 4 in real time. When an abnormal situation is detected, it controls the alarm 6 to sound an alarm according to the preset program and activates the fire extinguisher 5 to extinguish the fire. Regularly maintain the device, check whether the splicing structure of the fireproof isolation platform 1 is firm, whether each device is operating normally, and replace aging or damaged device components in a timely manner to ensure the long-term effective operation of the device. The fireproof isolation platform 1 in this embodiment can be replaced with a cable trench fireproof wall.

[0084] The above describes the present invention and its implementation manners. This description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments to this technical solution without creative work without departing from the gist of the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A cable fire prevention monitoring system, characterized in that, Comprising: A multi-sensor module, including a temperature sensing component, a smoke detection component, and a gas composition analysis component; the temperature sensing component collects the real-time temperature of the cable surface; The smoke detection component senses the change in smoke concentration in the cable tray; the gas composition analysis component samples the air in the cable tray in real time to analyze whether there are fire-related characteristic gases; A data aggregation and preliminary processing unit that aggregates the data collected by the temperature sensing component, the smoke detection component, and the gas composition analysis component, and performs preliminary denoising and normalization processing; An intelligent analysis and decision-making module that receives the data processed by the data aggregation and preliminary processing unit, and comprehensively evaluates the cable status through a fire hazard analysis model to determine whether there is a fire hazard and the hazard level; A linkage execution module that triggers corresponding actions according to the hazard level when the intelligent analysis and decision-making module determines that there is a fire hazard, including activating the alarm device and turning on the fire extinguishing device; A remote interaction terminal that communicates with the intelligent analysis and decision-making module through a wireless communication link, and is used to remotely view the real-time status of the cables in the cable tray, receive alarm information, and remotely configure system parameters.

2. The cable fire prevention monitoring system according to claim 1, characterized in that: The temperature sensing component uses a quantum dot temperature sensor, and utilizes the fluorescence characteristics of quantum dot materials that are sensitive to temperature to obtain the cable temperature by detecting the changes in fluorescence wavelength and intensity.

3. The cable fire prevention monitoring system according to claim 2, characterized in that: The smoke detection component emits ultrasonic waves and receives the echo signals scattered by the smoke particles, and accurately calculates the smoke concentration according to the changes in the intensity and frequency of the echo signals.

4. A cable fire prevention monitoring system according to claim 3, characterized in that: The fire hazard analysis model in the intelligent analysis and decision-making module is a deep neural network model, which is trained through cable fire historical data and normal operation data. The model input is multi-source data of temperature, smoke concentration, and characteristic gas concentration, and the output is the fire hazard probability and the hazard level.

5. A cable fire prevention monitoring system according to claim 4, characterized in that: The construction of the deep neural network model is as follows: The input layer receives multi-source data of temperature T, smoke concentration S, and characteristic gas concentration G to form an input vector X = [T, S, G] T ; The output h of the neurons in the hidden layer j Calculated through the weighted input and the activation function, the weighted sum input to the j-th neuron is net j = ∑ i w ij h i + b j , where w ij is the connection weight between the i-th input and the j-th neuron, b j is the bias. Using the ReLU activation function f(x) = max(0, x), the output h of the hidden layer neurons j = f(net j ); The output layer obtains the final result through a linear combination of the hidden layer outputs. The weight matrix of the output layer is W, the bias vector is b, and the output vector Y = WH + b, where H is the output vector of the hidden layer. The elements of the output vector Y correspond to the fire hazard probability and the hazard level. The model is trained using the backpropagation algorithm. By minimizing the loss function L(θ), the weights and biases are updated using the gradient descent method. The gradient is calculated using the chain rule, and the weight update formula is α is the learning rate.

6. A monitoring method for a cable fire prevention monitoring system according to any one of claims 1-5, characterized in that, Including the following steps: S1. Initialize the system, set the parameters of each sensor, the threshold of the fire hazard analysis model, and the linkage execution strategy; S2. The multi-sensor module continuously collects the temperature, smoke concentration, and gas composition data in the cable tray and transmits them to the data aggregation and preliminary processing unit; S3. The data aggregation and preliminary processing unit summarizes, denoises, and normalizes the collected data, and then sends it to the intelligent analysis and decision-making module; S4. The intelligent analysis and decision-making module uses the fire hazard analysis model to analyze the processed data and outputs the fire hazard probability and level; S5. If there is a fire hazard, the linkage execution module activates corresponding alarm and fire extinguishing measures according to the hazard level. At the same time, the remote interaction terminal receives the alarm information and can perform remote intervention operations.

7. A cable fire prevention monitoring method according to claim 6, characterized in that: During use, the system performs self-calibration and maintenance. By inputting standard detection signals to each sensor, comparing the actual output with the standard value, the sensor parameters are automatically adjusted; at the same time, the status of the system hardware equipment is checked to detect and handle potential faults in a timely manner.

8. A cable fire prevention monitoring device, characterized in that: Including a fireproof isolation platform and a cable tray; The cable tray is fixed on the top of the fireproof isolation platform, and a central controller and temperature sensors, smoke sensors, alarms, and fire extinguishers electrically connected thereto are fixed in the cable tray; The fireproof isolation platform is formed by splicing a number of fireproof units made of fireproof materials through a mortise and tenon structure.

Images